diff options
| author | Nilay Vaish <nilay@cs.wisc.edu> | 2012-02-10 09:51:37 -0600 |
|---|---|---|
| committer | Nilay Vaish <nilay@cs.wisc.edu> | 2012-02-10 09:51:37 -0600 |
| commit | 26ca8b87470912d5e593a21fc968dd2ddf0e20b2 (patch) | |
| tree | bf97df45e65f08107321f58d83688b08bbd3f675 /tests/long/se | |
| parent | 6a7a6263e16cd3a16b4d7738f7df06f6e7a97ed6 (diff) | |
| download | gem5-26ca8b87470912d5e593a21fc968dd2ddf0e20b2.tar.xz | |
Regressions: Update stats due to O3 CPU changes
Diffstat (limited to 'tests/long/se')
36 files changed, 4575 insertions, 4171 deletions
diff --git a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/config.ini b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/config.ini index 9f24d0367..2c3feadf1 100644 --- a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=gzip input.log 1 -cwd=build/ARM_SE/tests/opt/long/00.gzip/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/00.gzip/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/gzip +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/gzip gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/simout b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/simout index d3786fda6..316fa1ee5 100755 --- a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/00.gzip/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/00.gzip/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 08:31:06 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/00.gzip/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/00.gzip/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:23 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/00.gzip/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/00.gzip/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... spec_init @@ -38,4 +40,4 @@ Uncompressing Data Uncompressed data 1048576 bytes in length Uncompressed data compared correctly Tested 1MB buffer: OK! -Exiting @ tick 177098873000 because target called exit() +Exiting @ tick 177116942500 because target called exit() diff --git a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/stats.txt index 5022d17a1..e05b6f985 100644 --- a/tests/long/se/00.gzip/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/00.gzip/ref/arm/linux/o3-timing/stats.txt @@ -1,24 +1,24 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.177099 # Number of seconds simulated -sim_ticks 177098873000 # Number of ticks simulated -final_tick 177098873000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.177117 # Number of seconds simulated +sim_ticks 177116942500 # Number of ticks simulated +final_tick 177116942500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 154897 # Simulator instruction rate (inst/s) -host_tick_rate 45541130 # Simulator tick rate (ticks/s) -host_mem_usage 220436 # Number of bytes of host memory used -host_seconds 3888.77 # Real time elapsed on the host -sim_insts 602359805 # Number of instructions simulated -system.physmem.bytes_read 5833856 # Number of bytes read from this memory +host_inst_rate 89657 # Simulator instruction rate (inst/s) +host_tick_rate 26362655 # Simulator tick rate (ticks/s) +host_mem_usage 256136 # Number of bytes of host memory used +host_seconds 6718.48 # Real time elapsed on the host +sim_insts 602359810 # Number of instructions simulated +system.physmem.bytes_read 5833792 # Number of bytes read from this memory system.physmem.bytes_inst_read 46976 # Number of instructions bytes read from this memory -system.physmem.bytes_written 3720192 # Number of bytes written to this memory -system.physmem.num_reads 91154 # Number of read requests responded to by this memory -system.physmem.num_writes 58128 # Number of write requests responded to by this memory +system.physmem.bytes_written 3720320 # Number of bytes written to this memory +system.physmem.num_reads 91153 # Number of read requests responded to by this memory +system.physmem.num_writes 58130 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 32941237 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 265253 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 21006300 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 53947537 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 32937515 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 265226 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 21004879 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 53942395 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,141 +62,141 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 48 # Number of system calls -system.cpu.numCycles 354197747 # number of cpu cycles simulated +system.cpu.numCycles 354233886 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 91137531 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 84224367 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 4001637 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 86284566 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 80014553 # Number of BTB hits +system.cpu.BPredUnit.lookups 91144697 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 84232652 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 4003225 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 86347481 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 80064419 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 1704311 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 1605 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 76786839 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 703787736 # Number of instructions fetch has processed -system.cpu.fetch.Branches 91137531 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 81718864 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 159146597 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 18455506 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 103039518 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 28 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 620 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 74412736 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 1337820 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 353350911 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.128080 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 2.980798 # Number of instructions fetched each cycle (Total) +system.cpu.BPredUnit.usedRAS 1704141 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 1603 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 76798037 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 703840817 # Number of instructions fetch has processed +system.cpu.fetch.Branches 91144697 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 81768560 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 159197395 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 18458844 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 103018501 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 27 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 596 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 74422546 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 1338162 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 353393528 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.127927 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 2.980484 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 194204457 54.96% 54.96% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 25620928 7.25% 62.21% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 19248235 5.45% 67.66% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 24404617 6.91% 74.57% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 11778472 3.33% 77.90% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 13409998 3.80% 81.69% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 4602257 1.30% 83.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 7805373 2.21% 85.21% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 52276574 14.79% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 194196282 54.95% 54.95% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 25625707 7.25% 62.20% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 19294200 5.46% 67.66% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 24432014 6.91% 74.58% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 11774546 3.33% 77.91% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 13391437 3.79% 81.70% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 4604134 1.30% 83.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 7796226 2.21% 85.21% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 52278982 14.79% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 353350911 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.257307 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.986991 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 98877750 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 83515155 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 137076269 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 19506954 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 14374783 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 6301291 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 2551 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 740114896 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 7230 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 14374783 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 111843103 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 9537973 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 119731 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 143514381 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 73960940 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 727174418 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 286 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 59845789 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 10289393 # Number of times rename has blocked due to LSQ full -system.cpu.rename.FullRegisterEvents 334 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 752889395 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 3380302991 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 3380302863 # Number of integer rename lookups +system.cpu.fetch.rateDist::total 353393528 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.257301 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.986938 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 98941962 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 83442113 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 137180071 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 19452898 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 14376484 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 6300700 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 2518 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 740147617 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 7037 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 14376484 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 111904204 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 9631562 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 118839 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 143566748 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 73795691 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 727217623 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 278 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 59684680 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 10267337 # Number of times rename has blocked due to LSQ full +system.cpu.rename.FullRegisterEvents 352 # Number of times there has been no free registers +system.cpu.rename.RenamedOperands 752950298 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 3380504235 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 3380504107 # Number of integer rename lookups system.cpu.rename.fp_rename_lookups 128 # Number of floating rename lookups -system.cpu.rename.CommittedMaps 627417394 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 125472001 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 13297 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 13294 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 132095966 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 179744866 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 82855502 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 19180586 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 24795671 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 702443112 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 9504 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 663038146 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 743101 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 99536301 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 237037166 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 3158 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 353350911 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.876430 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.733239 # Number of insts issued each cycle +system.cpu.rename.CommittedMaps 627417402 # Number of HB maps that are committed +system.cpu.rename.UndoneMaps 125532896 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 13135 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 13128 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 131736703 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 179759563 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 82851365 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 19142240 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 24648771 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 702464419 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 9443 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 663065354 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 737309 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 99563138 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 237077273 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 3096 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 353393528 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.876280 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.733355 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 85428360 24.18% 24.18% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 90441308 25.60% 49.77% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 76153703 21.55% 71.32% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 42544702 12.04% 83.36% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 25577763 7.24% 90.60% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 18033700 5.10% 95.71% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 7283699 2.06% 97.77% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 6627828 1.88% 99.64% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 1259848 0.36% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 85420653 24.17% 24.17% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 90592891 25.64% 49.81% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 76061550 21.52% 71.33% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 42517322 12.03% 83.36% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 25489615 7.21% 90.57% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 18140901 5.13% 95.71% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 7279964 2.06% 97.77% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 6670408 1.89% 99.65% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 1220224 0.35% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 353350911 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 353393528 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 202982 4.88% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 4.88% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 2990868 71.85% 76.73% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 968637 23.27% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 202199 4.87% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 4.87% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 2984693 71.84% 76.71% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 967527 23.29% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 412586864 62.23% 62.23% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 6565 0.00% 62.23% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 412589272 62.22% 62.22% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 6572 0.00% 62.23% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 62.23% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 62.23% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 62.23% # Type of FU issued @@ -224,137 +224,137 @@ system.cpu.iq.FU_type_0::SimdFloatMisc 3 0.00% 62.23% # Ty system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 62.23% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 62.23% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 62.23% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 172485012 26.01% 88.24% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 77959702 11.76% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 172499638 26.02% 88.24% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 77969869 11.76% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 663038146 # Type of FU issued -system.cpu.iq.rate 1.871943 # Inst issue rate -system.cpu.iq.fu_busy_cnt 4162487 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.006278 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 1684332755 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 802000478 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 650204091 # Number of integer instruction queue wakeup accesses +system.cpu.iq.FU_type_0::total 663065354 # Type of FU issued +system.cpu.iq.rate 1.871829 # Inst issue rate +system.cpu.iq.fu_busy_cnt 4154419 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.006265 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 1684415928 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 802048612 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 650214601 # Number of integer instruction queue wakeup accesses system.cpu.iq.fp_inst_queue_reads 36 # Number of floating instruction queue reads system.cpu.iq.fp_inst_queue_writes 16 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 16 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 667200613 # Number of integer alu accesses +system.cpu.iq.int_alu_accesses 667219753 # Number of integer alu accesses system.cpu.iq.fp_alu_accesses 20 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 29662170 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread0.forwLoads 29667951 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 30792271 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 224606 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 11800 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 12634488 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 30806967 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 225012 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 11842 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 12630350 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 13695 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 12640 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.rescheduledLoads 13680 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.cacheBlocked 12577 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 14374783 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 826341 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 58736 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 702522112 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 1853549 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 179744866 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 82855502 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 8175 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 13020 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 5275 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 11800 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 4156328 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 497844 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 4654172 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 656067860 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 169121282 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 6970286 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 14376484 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 831826 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 58719 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 702543187 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 1852399 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 179759563 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 82851365 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 8113 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 13094 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 5271 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 11842 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 4161334 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 494337 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 4655671 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 656082264 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 169130146 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 6983090 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 69496 # number of nop insts executed -system.cpu.iew.exec_refs 245806937 # number of memory reference insts executed -system.cpu.iew.exec_branches 76463124 # Number of branches executed -system.cpu.iew.exec_stores 76685655 # Number of stores executed -system.cpu.iew.exec_rate 1.852264 # Inst execution rate -system.cpu.iew.wb_sent 652210228 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 650204107 # cumulative count of insts written-back -system.cpu.iew.wb_producers 423315850 # num instructions producing a value -system.cpu.iew.wb_consumers 657380921 # num instructions consuming a value +system.cpu.iew.exec_nop 69325 # number of nop insts executed +system.cpu.iew.exec_refs 245820033 # number of memory reference insts executed +system.cpu.iew.exec_branches 76462484 # Number of branches executed +system.cpu.iew.exec_stores 76689887 # Number of stores executed +system.cpu.iew.exec_rate 1.852116 # Inst execution rate +system.cpu.iew.wb_sent 652222843 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 650214617 # cumulative count of insts written-back +system.cpu.iew.wb_producers 423345319 # num instructions producing a value +system.cpu.iew.wb_consumers 657402766 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.835709 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.643943 # average fanout of values written-back +system.cpu.iew.wb_rate 1.835552 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.643966 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.commit.commitCommittedInsts 602359856 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 100172226 # The number of squashed insts skipped by commit -system.cpu.commit.commitNonSpecStalls 6346 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 4060978 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 338976129 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.776998 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.152747 # Number of insts commited each cycle +system.cpu.commit.commitCommittedInsts 602359861 # The number of committed instructions +system.cpu.commit.commitSquashedInsts 100193357 # The number of squashed insts skipped by commit +system.cpu.commit.commitNonSpecStalls 6347 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.branchMispredicts 4062580 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 339017045 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.776783 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.152670 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 108154848 31.91% 31.91% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 106518775 31.42% 63.33% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 49308103 14.55% 77.88% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 9862304 2.91% 80.79% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 23329668 6.88% 87.67% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 14306268 4.22% 91.89% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 7919036 2.34% 94.22% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 1343281 0.40% 94.62% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 18233846 5.38% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 108187576 31.91% 31.91% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 106522126 31.42% 63.33% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 49316522 14.55% 77.88% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 9859363 2.91% 80.79% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 23336266 6.88% 87.67% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 14305882 4.22% 91.89% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 7916477 2.34% 94.23% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 1329398 0.39% 94.62% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 18243435 5.38% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 338976129 # Number of insts commited each cycle -system.cpu.commit.count 602359856 # Number of instructions committed +system.cpu.commit.committed_per_cycle::total 339017045 # Number of insts commited each cycle +system.cpu.commit.count 602359861 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.refs 219173609 # Number of memory references committed -system.cpu.commit.loads 148952595 # Number of loads committed +system.cpu.commit.refs 219173611 # Number of memory references committed +system.cpu.commit.loads 148952596 # Number of loads committed system.cpu.commit.membars 1328 # Number of memory barriers committed -system.cpu.commit.branches 70828602 # Number of branches committed +system.cpu.commit.branches 70828603 # Number of branches committed system.cpu.commit.fp_insts 16 # Number of committed floating point instructions. -system.cpu.commit.int_insts 533522643 # Number of committed integer instructions. +system.cpu.commit.int_insts 533522647 # Number of committed integer instructions. system.cpu.commit.function_calls 997573 # Number of function calls committed. -system.cpu.commit.bw_lim_events 18233846 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 18243435 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 1023273753 # The number of ROB reads -system.cpu.rob.rob_writes 1419480895 # The number of ROB writes -system.cpu.timesIdled 37084 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 846836 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.committedInsts 602359805 # Number of Instructions Simulated -system.cpu.committedInsts_total 602359805 # Number of Instructions Simulated -system.cpu.cpi 0.588017 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.588017 # CPI: Total CPI of All Threads -system.cpu.ipc 1.700631 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.700631 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 3275893571 # number of integer regfile reads -system.cpu.int_regfile_writes 675997918 # number of integer regfile writes +system.cpu.rob.rob_reads 1023326216 # The number of ROB reads +system.cpu.rob.rob_writes 1419524916 # The number of ROB writes +system.cpu.timesIdled 37353 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 840358 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.committedInsts 602359810 # Number of Instructions Simulated +system.cpu.committedInsts_total 602359810 # Number of Instructions Simulated +system.cpu.cpi 0.588077 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.588077 # CPI: Total CPI of All Threads +system.cpu.ipc 1.700458 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.700458 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 3275977261 # number of integer regfile reads +system.cpu.int_regfile_writes 676006750 # number of integer regfile writes system.cpu.fp_regfile_reads 16 # number of floating regfile reads -system.cpu.misc_regfile_reads 943643021 # number of misc regfile reads -system.cpu.misc_regfile_writes 2658 # number of misc regfile writes +system.cpu.misc_regfile_reads 943708295 # number of misc regfile reads +system.cpu.misc_regfile_writes 2660 # number of misc regfile writes system.cpu.icache.replacements 41 # number of replacements -system.cpu.icache.tagsinuse 657.503073 # Cycle average of tags in use -system.cpu.icache.total_refs 74411745 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 766 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 97143.270235 # Average number of references to valid blocks. +system.cpu.icache.tagsinuse 657.275674 # Cycle average of tags in use +system.cpu.icache.total_refs 74421550 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 765 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 97283.071895 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 657.503073 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.321046 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 74411745 # number of ReadReq hits -system.cpu.icache.demand_hits 74411745 # number of demand (read+write) hits -system.cpu.icache.overall_hits 74411745 # number of overall hits -system.cpu.icache.ReadReq_misses 991 # number of ReadReq misses -system.cpu.icache.demand_misses 991 # number of demand (read+write) misses -system.cpu.icache.overall_misses 991 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 34848500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 34848500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 34848500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 74412736 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 74412736 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 74412736 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 657.275674 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.320935 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 74421550 # number of ReadReq hits +system.cpu.icache.demand_hits 74421550 # number of demand (read+write) hits +system.cpu.icache.overall_hits 74421550 # number of overall hits +system.cpu.icache.ReadReq_misses 996 # number of ReadReq misses +system.cpu.icache.demand_misses 996 # number of demand (read+write) misses +system.cpu.icache.overall_misses 996 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 34937500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 34937500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 34937500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 74422546 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 74422546 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 74422546 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000013 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000013 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000013 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 35164.984864 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 35164.984864 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 35164.984864 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 35077.811245 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 35077.811245 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 35077.811245 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -364,67 +364,67 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 225 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 225 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 225 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 766 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 766 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 766 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 231 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 231 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 231 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 765 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 765 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 765 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 26233500 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 26233500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 26233500 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 26235000 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 26235000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 26235000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000010 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000010 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000010 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 34247.389034 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 34247.389034 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 34247.389034 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 34294.117647 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 34294.117647 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 34294.117647 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 441233 # number of replacements -system.cpu.dcache.tagsinuse 4094.750739 # Cycle average of tags in use -system.cpu.dcache.total_refs 205781738 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 445329 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 462.089237 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 87973000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4094.750739 # Average occupied blocks per context +system.cpu.dcache.replacements 441200 # number of replacements +system.cpu.dcache.tagsinuse 4094.750887 # Cycle average of tags in use +system.cpu.dcache.total_refs 205785268 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 445296 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 462.131409 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 87972000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4094.750887 # Average occupied blocks per context system.cpu.dcache.occ_percent::0 0.999695 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 137926945 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 67852137 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 1328 # number of LoadLockedReq hits -system.cpu.dcache.StoreCondReq_hits 1328 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 205779082 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 205779082 # number of overall hits -system.cpu.dcache.ReadReq_misses 249074 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 1565394 # number of WriteReq misses -system.cpu.dcache.LoadLockedReq_misses 11 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 1814468 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 1814468 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 3282849000 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 27038418025 # number of WriteReq miss cycles -system.cpu.dcache.LoadLockedReq_miss_latency 203000 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 30321267025 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 30321267025 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 138176019 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_hits 137930344 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 67852261 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 1334 # number of LoadLockedReq hits +system.cpu.dcache.StoreCondReq_hits 1329 # number of StoreCondReq hits +system.cpu.dcache.demand_hits 205782605 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 205782605 # number of overall hits +system.cpu.dcache.ReadReq_misses 248964 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 1565270 # number of WriteReq misses +system.cpu.dcache.LoadLockedReq_misses 9 # number of LoadLockedReq misses +system.cpu.dcache.demand_misses 1814234 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 1814234 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 3282822000 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 27026336525 # number of WriteReq miss cycles +system.cpu.dcache.LoadLockedReq_miss_latency 201000 # number of LoadLockedReq miss cycles +system.cpu.dcache.demand_miss_latency 30309158525 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 30309158525 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 138179308 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 69417531 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 1339 # number of LoadLockedReq accesses(hits+misses) -system.cpu.dcache.StoreCondReq_accesses 1328 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 207593550 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 207593550 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.001803 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.022550 # miss rate for WriteReq accesses -system.cpu.dcache.LoadLockedReq_miss_rate 0.008215 # miss rate for LoadLockedReq accesses -system.cpu.dcache.demand_miss_rate 0.008740 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.008740 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 13180.215518 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 17272.595925 # average WriteReq miss latency -system.cpu.dcache.LoadLockedReq_avg_miss_latency 18454.545455 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 16710.830406 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 16710.830406 # average overall miss latency +system.cpu.dcache.LoadLockedReq_accesses 1343 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.StoreCondReq_accesses 1329 # number of StoreCondReq accesses(hits+misses) +system.cpu.dcache.demand_accesses 207596839 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 207596839 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.001802 # miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.022549 # miss rate for WriteReq accesses +system.cpu.dcache.LoadLockedReq_miss_rate 0.006701 # miss rate for LoadLockedReq accesses +system.cpu.dcache.demand_miss_rate 0.008739 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.008739 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 13185.930496 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 17266.245775 # average WriteReq miss latency +system.cpu.dcache.LoadLockedReq_avg_miss_latency 22333.333333 # average LoadLockedReq miss latency +system.cpu.dcache.demand_avg_miss_latency 16706.311603 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 16706.311603 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 9583027 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 2185 # number of cycles access was blocked @@ -433,70 +433,70 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs 4385.824714 system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 395275 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 51126 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 1318013 # number of WriteReq MSHR hits -system.cpu.dcache.LoadLockedReq_mshr_hits 11 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 1369139 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 1369139 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 197948 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 247381 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 445329 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 445329 # number of overall MSHR misses +system.cpu.dcache.writebacks 395250 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 51046 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 1317892 # number of WriteReq MSHR hits +system.cpu.dcache.LoadLockedReq_mshr_hits 9 # number of LoadLockedReq MSHR hits +system.cpu.dcache.demand_mshr_hits 1368938 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 1368938 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 197918 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 247378 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 445296 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 445296 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 1625134500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 2544872027 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 4170006527 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 4170006527 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 1625205500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 2544318027 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 4169523527 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 4169523527 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.001433 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate 0.001432 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.003564 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.002145 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.002145 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 8209.906137 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 10287.257417 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 9363.878227 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 9363.878227 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 8211.509312 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 10285.142684 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 9363.487494 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 9363.487494 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 72960 # number of replacements -system.cpu.l2cache.tagsinuse 17805.724339 # Cycle average of tags in use -system.cpu.l2cache.total_refs 422235 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 88493 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 4.771394 # Average number of references to valid blocks. +system.cpu.l2cache.replacements 72965 # number of replacements +system.cpu.l2cache.tagsinuse 17807.300199 # Cycle average of tags in use +system.cpu.l2cache.total_refs 421253 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 88492 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 4.760351 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 1879.670498 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 15926.053841 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.057363 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.486025 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 165899 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 395275 # number of Writeback hits -system.cpu.l2cache.ReadExReq_hits 189031 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 354930 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 354930 # number of overall hits -system.cpu.l2cache.ReadReq_misses 32812 # number of ReadReq misses -system.cpu.l2cache.ReadExReq_misses 58353 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 91165 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 91165 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 1126662000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 2003366500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 3130028500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 3130028500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 198711 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 395275 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 247384 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 446095 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 446095 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.165124 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.235880 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.204362 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.204362 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34336.888943 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34331.850976 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34333.664235 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34333.664235 # average overall miss latency +system.cpu.l2cache.occ_blocks::0 1881.136315 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 15926.163884 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.057408 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.486028 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 165871 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 395250 # number of Writeback hits +system.cpu.l2cache.ReadExReq_hits 189027 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 354898 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 354898 # number of overall hits +system.cpu.l2cache.ReadReq_misses 32808 # number of ReadReq misses +system.cpu.l2cache.ReadExReq_misses 58355 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 91163 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 91163 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 1126263500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 2003081500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 3129345000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 3129345000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 198679 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 395250 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 247382 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 446061 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 446061 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.165131 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.235890 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.204373 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.204373 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34328.928920 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34325.790421 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34326.919913 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34326.919913 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 2057500 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 352 # number of cycles access was blocked @@ -505,28 +505,28 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs 5845.170455 system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 58128 # number of writebacks -system.cpu.l2cache.ReadReq_mshr_hits 11 # number of ReadReq MSHR hits -system.cpu.l2cache.demand_mshr_hits 11 # number of demand (read+write) MSHR hits -system.cpu.l2cache.overall_mshr_hits 11 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 32801 # number of ReadReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 58353 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 91154 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 91154 # number of overall MSHR misses +system.cpu.l2cache.writebacks 58130 # number of writebacks +system.cpu.l2cache.ReadReq_mshr_hits 10 # number of ReadReq MSHR hits +system.cpu.l2cache.demand_mshr_hits 10 # number of demand (read+write) MSHR hits +system.cpu.l2cache.overall_mshr_hits 10 # number of overall MSHR hits +system.cpu.l2cache.ReadReq_mshr_misses 32798 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 58355 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 91153 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 91153 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 1019608000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 1822407000 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 2842015000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 2842015000 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 1019340000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 1822214500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 2841554500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 2841554500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.165069 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.235880 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.204338 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.204338 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31084.662053 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31230.733638 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31178.171007 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31178.171007 # average overall mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.165080 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.235890 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.204351 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.204351 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31079.334106 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31226.364493 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31173.461104 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31173.461104 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/config.ini b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/config.ini index 6e971ebcf..3b035cefe 100644 --- a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/config.ini +++ b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -89,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -149,7 +159,14 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=X86TLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -446,9 +463,25 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=X86LocalApic +int_latency=1000 +pio_addr=2305843009213693952 +pio_latency=1000 +system=system +int_port=system.membus.port[4] +pio=system.membus.port[3] + [system.cpu.itb] type=X86TLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -479,7 +512,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -490,7 +523,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -498,7 +531,7 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=gzip input.log 1 -cwd=build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing +cwd=build/X86/tests/opt/long/se/00.gzip/x86/linux/o3-timing egid=100 env= errout=cerr @@ -522,7 +555,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side +port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side system.cpu.interrupts.pio system.cpu.interrupts.int_port [system.physmem] type=PhysicalMemory diff --git a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/simout b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/simout index bff73f5f1..774f2864e 100755 --- a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/simout +++ b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/simout @@ -1,12 +1,12 @@ -Redirecting stdout to build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing/simout -Redirecting stderr to build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing/simerr +Redirecting stdout to build/X86/tests/opt/long/se/00.gzip/x86/linux/o3-timing/simout +Redirecting stderr to build/X86/tests/opt/long/se/00.gzip/x86/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 28 2012 12:11:40 -gem5 started Jan 28 2012 12:12:43 +gem5 compiled Feb 9 2012 12:45:55 +gem5 started Feb 9 2012 12:46:40 gem5 executing on ribera.cs.wisc.edu -command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/00.gzip/x86/linux/o3-timing +command line: build/X86/gem5.opt -d build/X86/tests/opt/long/se/00.gzip/x86/linux/o3-timing -re tests/run.py build/X86/tests/opt/long/se/00.gzip/x86/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... spec_init @@ -42,4 +42,4 @@ Uncompressing Data Uncompressed data 1048576 bytes in length Uncompressed data compared correctly Tested 1MB buffer: OK! -Exiting @ tick 588785308000 because target called exit() +Exiting @ tick 586834596000 because target called exit() diff --git a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/stats.txt b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/stats.txt index f7c59f027..1e4919244 100644 --- a/tests/long/se/00.gzip/ref/x86/linux/o3-timing/stats.txt +++ b/tests/long/se/00.gzip/ref/x86/linux/o3-timing/stats.txt @@ -1,262 +1,262 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.588785 # Number of seconds simulated -sim_ticks 588785308000 # Number of ticks simulated -final_tick 588785308000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.586835 # Number of seconds simulated +sim_ticks 586834596000 # Number of ticks simulated +final_tick 586834596000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 112730 # Simulator instruction rate (inst/s) -host_tick_rate 40933847 # Simulator tick rate (ticks/s) -host_mem_usage 244824 # Number of bytes of host memory used -host_seconds 14383.83 # Real time elapsed on the host +host_inst_rate 99458 # Simulator instruction rate (inst/s) +host_tick_rate 35994653 # Simulator tick rate (ticks/s) +host_mem_usage 253740 # Number of bytes of host memory used +host_seconds 16303.38 # Real time elapsed on the host sim_insts 1621493982 # Number of instructions simulated -system.physmem.bytes_read 5878272 # Number of bytes read from this memory -system.physmem.bytes_inst_read 57216 # Number of instructions bytes read from this memory -system.physmem.bytes_written 3742528 # Number of bytes written to this memory -system.physmem.num_reads 91848 # Number of read requests responded to by this memory -system.physmem.num_writes 58477 # Number of write requests responded to by this memory +system.physmem.bytes_read 5879616 # Number of bytes read from this memory +system.physmem.bytes_inst_read 57024 # Number of instructions bytes read from this memory +system.physmem.bytes_written 3743488 # Number of bytes written to this memory +system.physmem.num_reads 91869 # Number of read requests responded to by this memory +system.physmem.num_writes 58492 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 9983727 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 97176 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 6356354 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 16340082 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 10019205 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 97172 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 6379119 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 16398324 # Total bandwidth to/from this memory (bytes/s) system.cpu.workload.num_syscalls 48 # Number of system calls -system.cpu.numCycles 1177570617 # number of cpu cycles simulated +system.cpu.numCycles 1173669193 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 141882222 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 141882222 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 7459322 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 135523268 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 134664780 # Number of BTB hits +system.cpu.BPredUnit.lookups 140536614 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 140536614 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 7896314 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 133769291 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 132901689 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 141519405 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 1135188232 # Number of instructions fetch has processed -system.cpu.fetch.Branches 141882222 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 134664780 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 328423216 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 56273795 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 658902879 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 48 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 302 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 135738609 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 998788 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 1177479353 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 1.766783 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.096310 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.icacheStallCycles 138231227 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 1143529036 # Number of instructions fetch has processed +system.cpu.fetch.Branches 140536614 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 132901689 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 330118681 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 56348337 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 656952944 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 60 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 378 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 136534174 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 2392311 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 1173574785 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.778199 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.100517 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 852058955 72.36% 72.36% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 15948065 1.35% 73.72% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 17931063 1.52% 75.24% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 17495755 1.49% 76.73% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 23352779 1.98% 78.71% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 16626553 1.41% 80.12% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 22402886 1.90% 82.02% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 28214099 2.40% 84.42% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 183449198 15.58% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 846464435 72.13% 72.13% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 17271965 1.47% 73.60% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 15892053 1.35% 74.95% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 19142892 1.63% 76.58% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 23218397 1.98% 78.56% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 16689415 1.42% 79.98% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 22145456 1.89% 81.87% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 30830267 2.63% 84.50% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 181919905 15.50% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 1177479353 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.120487 # Number of branch fetches per cycle -system.cpu.fetch.rate 0.964009 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 241266448 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 565597424 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 225300633 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 96681345 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 48633503 # Number of cycles decode is squashing -system.cpu.decode.DecodedInsts 2058834896 # Number of instructions handled by decode -system.cpu.rename.SquashCycles 48633503 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 289994325 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 136667782 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 3607 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 255841310 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 446338826 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 2031094400 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 199 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 278357951 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 133112570 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RenamedOperands 2019296537 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 4928551600 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 4928548640 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 2960 # Number of floating rename lookups +system.cpu.fetch.rateDist::total 1173574785 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.119741 # Number of branch fetches per cycle +system.cpu.fetch.rate 0.974320 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 240018155 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 564065687 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 224667967 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 96551481 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 48271495 # Number of cycles decode is squashing +system.cpu.decode.DecodedInsts 2053347825 # Number of instructions handled by decode +system.cpu.rename.SquashCycles 48271495 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 288250921 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 136396250 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 3594 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 255481832 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 445170693 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 2022383034 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 772 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 278054588 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 132157059 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RenamedOperands 2011799289 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 4917261318 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 4917257566 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 3752 # Number of floating rename lookups system.cpu.rename.CommittedMaps 1617994650 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 401301887 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 93 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 93 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 797995614 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 517349896 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 226176362 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 355062669 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 148977960 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 1979799927 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 215 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 1779311117 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 175082 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 358154503 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 654941515 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 165 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 1177479353 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.511119 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.319645 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 393804639 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 92 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 92 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 795963127 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 515675644 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 225280197 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 353360778 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 147850226 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 1972232230 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 190 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 1776284004 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 173989 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 350598274 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 640215855 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 140 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 1173574785 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.513567 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.313751 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 271443176 23.05% 23.05% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 420511572 35.71% 58.77% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 239784716 20.36% 79.13% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 159545639 13.55% 92.68% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 48751983 4.14% 96.82% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 21481111 1.82% 98.64% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 13897994 1.18% 99.82% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 1713551 0.15% 99.97% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 349611 0.03% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 268099715 22.84% 22.84% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 420406461 35.82% 58.67% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 239398162 20.40% 79.07% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 159391711 13.58% 92.65% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 48358537 4.12% 96.77% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 24330955 2.07% 98.84% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 11625243 0.99% 99.83% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 1646303 0.14% 99.97% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 317698 0.03% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 1177479353 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 1173574785 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 183781 6.86% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 6.86% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 2344413 87.49% 94.35% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 151333 5.65% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 185497 7.34% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 7.34% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 2190114 86.61% 93.95% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 153108 6.05% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available -system.cpu.iq.FU_type_0::No_OpClass 26390474 1.48% 1.48% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 1101178190 61.89% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::IntDiv 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatMult 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMult 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShift 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 63.37% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 457060255 25.69% 89.06% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 194682198 10.94% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::No_OpClass 26819156 1.51% 1.51% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 1098315644 61.83% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::IntDiv 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatMult 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMult 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShift 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 63.34% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 456429787 25.70% 89.04% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 194719417 10.96% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 1779311117 # Type of FU issued -system.cpu.iq.rate 1.511002 # Inst issue rate -system.cpu.iq.fu_busy_cnt 2679527 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.001506 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 4738956161 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 2338163322 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 1758678242 # Number of integer instruction queue wakeup accesses +system.cpu.iq.FU_type_0::total 1776284004 # Type of FU issued +system.cpu.iq.rate 1.513445 # Inst issue rate +system.cpu.iq.fu_busy_cnt 2528719 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.001424 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 4728845466 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 2323038766 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 1755173186 # Number of integer instruction queue wakeup accesses system.cpu.iq.fp_inst_queue_reads 35 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 458 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_writes 448 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 12 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 1755600151 # Number of integer alu accesses +system.cpu.iq.int_alu_accesses 1751993548 # Number of integer alu accesses system.cpu.iq.fp_alu_accesses 19 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 207757708 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread0.forwLoads 207962564 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 98307771 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 75876 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 215687 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 37990305 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 96633519 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 76725 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 215178 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 37094140 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 1126 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.rescheduledLoads 1306 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 48633503 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 1923683 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 157688 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 1979800142 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 665872 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 517349896 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 226176362 # Number of dispatched store instructions +system.cpu.iew.iewSquashCycles 48271495 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 1965747 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 154206 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 1972232420 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 7113535 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 515675644 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 225280197 # Number of dispatched store instructions system.cpu.iew.iewDispNonSpecInsts 85 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 70768 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 44 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 215687 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 4604749 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 3040457 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 7645206 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 1766024784 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 451208749 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 13286333 # Number of squashed instructions skipped in execute +system.cpu.iew.iewIQFullEvents 69568 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 118 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 215178 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 4620478 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 3457907 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 8078385 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 1762068190 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 450602678 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 14215814 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 0 # number of nop insts executed -system.cpu.iew.exec_refs 645051015 # number of memory reference insts executed -system.cpu.iew.exec_branches 112022135 # Number of branches executed -system.cpu.iew.exec_stores 193842266 # Number of stores executed -system.cpu.iew.exec_rate 1.499719 # Inst execution rate -system.cpu.iew.wb_sent 1764443624 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 1758678254 # cumulative count of insts written-back -system.cpu.iew.wb_producers 1332033031 # num instructions producing a value -system.cpu.iew.wb_consumers 1982428848 # num instructions consuming a value +system.cpu.iew.exec_refs 644481818 # number of memory reference insts executed +system.cpu.iew.exec_branches 111935144 # Number of branches executed +system.cpu.iew.exec_stores 193879140 # Number of stores executed +system.cpu.iew.exec_rate 1.501333 # Inst execution rate +system.cpu.iew.wb_sent 1756702193 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 1755173198 # cumulative count of insts written-back +system.cpu.iew.wb_producers 1327558450 # num instructions producing a value +system.cpu.iew.wb_consumers 1975144997 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.493480 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.671920 # average fanout of values written-back +system.cpu.iew.wb_rate 1.495458 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.672132 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 1621493982 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 358308768 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 350742946 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 50 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 7459361 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 1128845850 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.436418 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.651874 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 7896364 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 1125303290 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.440940 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.651939 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 347283519 30.76% 30.76% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 441725058 39.13% 69.90% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 99623372 8.83% 78.72% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 136537223 12.10% 90.82% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 31770740 2.81% 93.63% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 26056867 2.31% 95.94% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 22501724 1.99% 97.93% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 8245904 0.73% 98.66% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 15101443 1.34% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 343524257 30.53% 30.53% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 441933791 39.27% 69.80% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 99674686 8.86% 78.66% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 136523006 12.13% 90.79% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 31731928 2.82% 93.61% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 26136643 2.32% 95.93% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 22505633 2.00% 97.93% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 8189692 0.73% 98.66% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 15083654 1.34% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 1128845850 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 1125303290 # Number of insts commited each cycle system.cpu.commit.count 1621493982 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 607228182 # Number of memory references committed @@ -266,48 +266,48 @@ system.cpu.commit.branches 107161579 # Nu system.cpu.commit.fp_insts 0 # Number of committed floating point instructions. system.cpu.commit.int_insts 1621354492 # Number of committed integer instructions. system.cpu.commit.function_calls 0 # Number of function calls committed. -system.cpu.commit.bw_lim_events 15101443 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 15083654 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 3093547157 # The number of ROB reads -system.cpu.rob.rob_writes 4008258633 # The number of ROB writes -system.cpu.timesIdled 21053 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 91264 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 3082456564 # The number of ROB reads +system.cpu.rob.rob_writes 3992764754 # The number of ROB writes +system.cpu.timesIdled 21723 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 94408 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 1621493982 # Number of Instructions Simulated system.cpu.committedInsts_total 1621493982 # Number of Instructions Simulated -system.cpu.cpi 0.726226 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.726226 # CPI: Total CPI of All Threads -system.cpu.ipc 1.376982 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.376982 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 3270153545 # number of integer regfile reads -system.cpu.int_regfile_writes 1754693299 # number of integer regfile writes +system.cpu.cpi 0.723820 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.723820 # CPI: Total CPI of All Threads +system.cpu.ipc 1.381560 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.381560 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 3268959976 # number of integer regfile reads +system.cpu.int_regfile_writes 1746565098 # number of integer regfile writes system.cpu.fp_regfile_reads 12 # number of floating regfile reads -system.cpu.misc_regfile_reads 907833056 # number of misc regfile reads +system.cpu.misc_regfile_reads 905288155 # number of misc regfile reads system.cpu.icache.replacements 12 # number of replacements -system.cpu.icache.tagsinuse 808.459907 # Cycle average of tags in use -system.cpu.icache.total_refs 135737385 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 897 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 151323.729097 # Average number of references to valid blocks. +system.cpu.icache.tagsinuse 807.278486 # Cycle average of tags in use +system.cpu.icache.total_refs 136532946 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 894 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 152721.416107 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 808.459907 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.394756 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 135737385 # number of ReadReq hits -system.cpu.icache.demand_hits 135737385 # number of demand (read+write) hits -system.cpu.icache.overall_hits 135737385 # number of overall hits -system.cpu.icache.ReadReq_misses 1224 # number of ReadReq misses -system.cpu.icache.demand_misses 1224 # number of demand (read+write) misses -system.cpu.icache.overall_misses 1224 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 43199000 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 43199000 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 43199000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 135738609 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 135738609 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 135738609 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 807.278486 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.394179 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 136532946 # number of ReadReq hits +system.cpu.icache.demand_hits 136532946 # number of demand (read+write) hits +system.cpu.icache.overall_hits 136532946 # number of overall hits +system.cpu.icache.ReadReq_misses 1228 # number of ReadReq misses +system.cpu.icache.demand_misses 1228 # number of demand (read+write) misses +system.cpu.icache.overall_misses 1228 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 43195500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 43195500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 43195500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 136534174 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 136534174 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 136534174 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000009 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000009 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000009 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 35293.300654 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 35293.300654 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 35293.300654 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 35175.488599 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 35175.488599 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 35175.488599 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -317,59 +317,59 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 327 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 327 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 327 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 897 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 897 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 897 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 334 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 334 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 334 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 894 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 894 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 894 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 31683500 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 31683500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 31683500 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 31569000 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 31569000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 31569000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000007 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000007 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000007 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 35321.627648 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 35321.627648 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 35321.627648 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 35312.080537 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 35312.080537 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 35312.080537 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 459032 # number of replacements -system.cpu.dcache.tagsinuse 4094.268658 # Cycle average of tags in use -system.cpu.dcache.total_refs 431168175 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 463128 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 930.991378 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 416529000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4094.268658 # Average occupied blocks per context +system.cpu.dcache.replacements 459037 # number of replacements +system.cpu.dcache.tagsinuse 4094.269422 # Cycle average of tags in use +system.cpu.dcache.total_refs 430357004 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 463133 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 929.229841 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 414463000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4094.269422 # Average occupied blocks per context system.cpu.dcache.occ_percent::0 0.999577 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 243231636 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 187936539 # number of WriteReq hits -system.cpu.dcache.demand_hits 431168175 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 431168175 # number of overall hits -system.cpu.dcache.ReadReq_misses 217117 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 249518 # number of WriteReq misses -system.cpu.dcache.demand_misses 466635 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 466635 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 2193700500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 3216393000 # number of WriteReq miss cycles -system.cpu.dcache.demand_miss_latency 5410093500 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 5410093500 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 243448753 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_hits 242420503 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 187936501 # number of WriteReq hits +system.cpu.dcache.demand_hits 430357004 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 430357004 # number of overall hits +system.cpu.dcache.ReadReq_misses 217102 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 249556 # number of WriteReq misses +system.cpu.dcache.demand_misses 466658 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 466658 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 2192767500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 3219007000 # number of WriteReq miss cycles +system.cpu.dcache.demand_miss_latency 5411774500 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 5411774500 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 242637605 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 188186057 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 431634810 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 431634810 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.000892 # miss rate for ReadReq accesses +system.cpu.dcache.demand_accesses 430823662 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 430823662 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.000895 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.001326 # miss rate for WriteReq accesses -system.cpu.dcache.demand_miss_rate 0.001081 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.001081 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 10103.771239 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 12890.424739 # average WriteReq miss latency -system.cpu.dcache.demand_avg_miss_latency 11593.844225 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 11593.844225 # average overall miss latency +system.cpu.dcache.demand_miss_rate 0.001083 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.001083 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 10100.171809 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 12898.936511 # average WriteReq miss latency +system.cpu.dcache.demand_avg_miss_latency 11596.875013 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 11596.875013 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -378,69 +378,69 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 409997 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 3467 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 38 # number of WriteReq MSHR hits -system.cpu.dcache.demand_mshr_hits 3505 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 3505 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 213650 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 249480 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 463130 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 463130 # number of overall MSHR misses +system.cpu.dcache.writebacks 409999 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 3488 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 35 # number of WriteReq MSHR hits +system.cpu.dcache.demand_mshr_hits 3523 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 3523 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 213614 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 249521 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 463135 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 463135 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 1524751500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 2467190000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 3991941500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 3991941500 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 1523998500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 2469759000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 3993757500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 3993757500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.000878 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000880 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.001326 # mshr miss rate for WriteReq accesses -system.cpu.dcache.demand_mshr_miss_rate 0.001073 # mshr miss rate for demand accesses -system.cpu.dcache.overall_mshr_miss_rate 0.001073 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 7136.679148 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 9889.329806 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 8619.483730 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 8619.483730 # average overall mshr miss latency +system.cpu.dcache.demand_mshr_miss_rate 0.001075 # mshr miss rate for demand accesses +system.cpu.dcache.overall_mshr_miss_rate 0.001075 # mshr miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 7134.356831 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 9898.000569 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 8623.311777 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 8623.311777 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 73588 # number of replacements -system.cpu.l2cache.tagsinuse 17962.176251 # Cycle average of tags in use -system.cpu.l2cache.total_refs 452941 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 89203 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 5.077643 # Average number of references to valid blocks. +system.cpu.l2cache.replacements 73601 # number of replacements +system.cpu.l2cache.tagsinuse 17971.586292 # Cycle average of tags in use +system.cpu.l2cache.total_refs 452847 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 89223 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 5.075451 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 1977.761332 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 15984.414919 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.060356 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.487806 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 181391 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 409997 # number of Writeback hits -system.cpu.l2cache.ReadExReq_hits 190788 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 372179 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 372179 # number of overall hits -system.cpu.l2cache.ReadReq_misses 33152 # number of ReadReq misses -system.cpu.l2cache.ReadExReq_misses 58696 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 91848 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 91848 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 1130561500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 2008268500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 3138830000 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 3138830000 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 214543 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 409997 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 249484 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 464027 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 464027 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.154524 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.235270 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.197937 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.197937 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34102.361848 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34214.742061 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34174.179078 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34174.179078 # average overall miss latency +system.cpu.l2cache.occ_blocks::0 1981.498209 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 15990.088083 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.060471 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.487979 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 181345 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 409999 # number of Writeback hits +system.cpu.l2cache.ReadExReq_hits 190815 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 372160 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 372160 # number of overall hits +system.cpu.l2cache.ReadReq_misses 33162 # number of ReadReq misses +system.cpu.l2cache.ReadExReq_misses 58707 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 91869 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 91869 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 1129684500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 2008512000 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 3138196500 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 3138196500 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 214507 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 409999 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 249522 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 464029 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 464029 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.154596 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.235278 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.197981 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.197981 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34065.632350 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34212.478921 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34159.471639 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34159.471639 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -449,27 +449,27 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 58477 # number of writebacks +system.cpu.l2cache.writebacks 58492 # number of writebacks system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 33152 # number of ReadReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 58696 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 91848 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 91848 # number of overall MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 33162 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 58707 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 91869 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 91869 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 1027873500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 1819617000 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 2847490500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 2847490500 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 1028173500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 1819949000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 2848122500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 2848122500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.154524 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.235270 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.197937 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.197937 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31004.871501 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.698514 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31002.204730 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31002.204730 # average overall mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.154596 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.235278 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.197981 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.197981 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31004.568482 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.545080 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31001.997409 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31001.997409 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/config.ini b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/config.ini index bec9490f3..cbe079647 100644 --- a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,14 +529,14 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=mcf mcf.in -cwd=build/ARM_SE/tests/opt/long/10.mcf/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/10.mcf/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/mcf +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/mcf gid=100 -input=/dist/m5/cpu2000/data/mcf/smred/input/mcf.in +input=/scratch/nilay/GEM5/dist/m5/cpu2000/data/mcf/smred/input/mcf.in max_stack_size=67108864 output=cout pid=100 diff --git a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/simout b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/simout index db74d3d24..3ae44ae93 100755 --- a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/10.mcf/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/10.mcf/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 08:43:41 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/10.mcf/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/10.mcf/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:22 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/10.mcf/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/10.mcf/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -23,4 +25,4 @@ simplex iterations : 2663 flow value : 3080014995 checksum : 68389 optimal -Exiting @ tick 33080569000 because target called exit() +Exiting @ tick 33080570000 because target called exit() diff --git a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/stats.txt index 190781128..833e2ce53 100644 --- a/tests/long/se/10.mcf/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/10.mcf/ref/arm/linux/o3-timing/stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- sim_seconds 0.033081 # Number of seconds simulated -sim_ticks 33080569000 # Number of ticks simulated -final_tick 33080569000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_ticks 33080570000 # Number of ticks simulated +final_tick 33080570000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 140676 # Simulator instruction rate (inst/s) -host_tick_rate 50998874 # Simulator tick rate (ticks/s) -host_mem_usage 353196 # Number of bytes of host memory used -host_seconds 648.65 # Real time elapsed on the host +host_inst_rate 45520 # Simulator instruction rate (inst/s) +host_tick_rate 16502276 # Simulator tick rate (ticks/s) +host_mem_usage 388968 # Number of bytes of host memory used +host_seconds 2004.61 # Real time elapsed on the host sim_insts 91249885 # Number of instructions simulated system.physmem.bytes_read 997440 # Number of bytes read from this memory system.physmem.bytes_inst_read 44864 # Number of instructions bytes read from this memory @@ -15,10 +15,10 @@ system.physmem.bytes_written 2048 # Nu system.physmem.num_reads 15585 # Number of read requests responded to by this memory system.physmem.num_writes 32 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 30151839 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_read 30151838 # Total read bandwidth from this memory (bytes/s) system.physmem.bw_inst_read 1356204 # Instruction read bandwidth from this memory (bytes/s) system.physmem.bw_write 61909 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 30213749 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_total 30213748 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,7 +62,7 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 442 # Number of system calls -system.cpu.numCycles 66161139 # number of cpu cycles simulated +system.cpu.numCycles 66161141 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed system.cpu.BPredUnit.lookups 27503856 # Number of BP lookups @@ -73,95 +73,95 @@ system.cpu.BPredUnit.BTBHits 23511296 # Nu system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. system.cpu.BPredUnit.usedRAS 109835 # Number of times the RAS was used to get a target. system.cpu.BPredUnit.RASInCorrect 10070 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 15373276 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 131330352 # Number of instructions fetch has processed +system.cpu.fetch.icacheStallCycles 15373267 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 131330347 # Number of instructions fetch has processed system.cpu.fetch.Branches 27503856 # Number of branches that fetch encountered system.cpu.fetch.predictedBranches 23621131 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 32575580 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 5466802 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 14146451 # Number of cycles fetch has spent blocked +system.cpu.fetch.Cycles 32575588 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 5466804 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 14146452 # Number of cycles fetch has spent blocked system.cpu.fetch.MiscStallCycles 1 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs system.cpu.fetch.PendingTrapStallCycles 14 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 14744728 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 369535 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 66131343 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.CacheLines 14744727 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 369536 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 66131345 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::mean 2.004854 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::stdev 2.741973 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 33609066 50.82% 50.82% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 6636464 10.04% 60.86% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 33609060 50.82% 50.82% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 6636469 10.04% 60.86% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::2 5762437 8.71% 69.57% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 4857984 7.35% 76.92% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 2814891 4.26% 81.17% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 4857985 7.35% 76.92% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 2814890 4.26% 81.17% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::5 1640731 2.48% 83.65% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 1559267 2.36% 86.01% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 2974436 4.50% 90.51% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 6276067 9.49% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 1559273 2.36% 86.01% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 2974432 4.50% 90.51% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 6276068 9.49% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 66131343 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::total 66131345 # Number of instructions fetched each cycle (Total) system.cpu.fetch.branchRate 0.415710 # Number of branch fetches per cycle system.cpu.fetch.rate 1.985007 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 17946396 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 12652276 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 30529024 # Number of cycles decode is running +system.cpu.decode.IdleCycles 17946387 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 12652277 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 30529032 # Number of cycles decode is running system.cpu.decode.UnblockCycles 996648 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 4006999 # Number of cycles decode is squashing +system.cpu.decode.SquashCycles 4007001 # Number of cycles decode is squashing system.cpu.decode.BranchResolved 4433202 # Number of times decode resolved a branch system.cpu.decode.BranchMispred 29411 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 129091755 # Number of instructions handled by decode +system.cpu.decode.DecodedInsts 129091783 # Number of instructions handled by decode system.cpu.decode.SquashedInsts 32642 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 4006999 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 19654600 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 1107804 # Number of cycles rename is blocking +system.cpu.rename.SquashCycles 4007001 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 19654593 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 1107803 # Number of cycles rename is blocking system.cpu.rename.serializeStallCycles 8424491 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 29777332 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 3160117 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 124853414 # Number of instructions processed by rename +system.cpu.rename.RunCycles 29777338 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 3160119 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 124853428 # Number of instructions processed by rename system.cpu.rename.ROBFullEvents 19 # Number of times rename has blocked due to ROB full system.cpu.rename.IQFullEvents 254616 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 1879605 # Number of times rename has blocked due to LSQ full +system.cpu.rename.LSQFullEvents 1879607 # Number of times rename has blocked due to LSQ full system.cpu.rename.FullRegisterEvents 6 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 145685583 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 543523067 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 543516086 # Number of integer rename lookups +system.cpu.rename.RenamedOperands 145685596 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 543523130 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 543516149 # Number of integer rename lookups system.cpu.rename.fp_rename_lookups 6981 # Number of floating rename lookups system.cpu.rename.CommittedMaps 107429439 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 38256144 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 662187 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 664355 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 7619533 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 29336350 # Number of loads inserted to the mem dependence unit. +system.cpu.rename.UndoneMaps 38256157 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 662188 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 664356 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 7619540 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 29336358 # Number of loads inserted to the mem dependence unit. system.cpu.memDep0.insertedStores 5741000 # Number of stores inserted to the mem dependence unit. system.cpu.memDep0.conflictingLoads 1194254 # Number of conflicting loads. system.cpu.memDep0.conflictingStores 692979 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 117270516 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsAdded 117270526 # Number of instructions added to the IQ (excludes non-spec) system.cpu.iq.iqNonSpecInstsAdded 648807 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 106162042 # Number of instructions issued +system.cpu.iq.iqInstsIssued 106162051 # Number of instructions issued system.cpu.iq.iqSquashedInstsIssued 30561 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 26211084 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 62748223 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedInstsExamined 26211100 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 62748267 # Number of squashed operands that are examined and possibly removed from graph system.cpu.iq.iqSquashedNonSpecRemoved 93963 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 66131343 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::samples 66131345 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::mean 1.605321 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::stdev 1.761707 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 24322507 36.78% 36.78% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 14238727 21.53% 58.31% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 9857796 14.91% 73.22% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 8080873 12.22% 85.44% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 4216462 6.38% 91.81% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 2267133 3.43% 95.24% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 2478028 3.75% 98.99% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 24322505 36.78% 36.78% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 14238731 21.53% 58.31% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 9857797 14.91% 73.22% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 8080871 12.22% 85.44% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 4216459 6.38% 91.81% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 2267136 3.43% 95.24% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 2478029 3.75% 98.99% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::7 463113 0.70% 99.69% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::8 206704 0.31% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 66131343 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 66131345 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 52363 10.31% 10.31% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 52363 10.30% 10.30% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 27 0.01% 10.31% # attempts to use FU when none available system.cpu.iq.fu_full::IntDiv 0 0.00% 10.31% # attempts to use FU when none available system.cpu.iq.fu_full::FloatAdd 0 0.00% 10.31% # attempts to use FU when none available @@ -190,12 +190,12 @@ system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 10.31% # at system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 10.31% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 10.31% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 10.31% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 192834 37.95% 48.26% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 192835 37.95% 48.26% # attempts to use FU when none available system.cpu.iq.fu_full::MemWrite 262907 51.74% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 74696384 70.36% 70.36% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 74696385 70.36% 70.36% # Type of FU issued system.cpu.iq.FU_type_0::IntMult 11141 0.01% 70.37% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 70.37% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 70.37% # Type of FU issued @@ -224,26 +224,26 @@ system.cpu.iq.FU_type_0::SimdFloatMisc 260 0.00% 70.37% # Ty system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 70.37% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 2 0.00% 70.37% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 70.37% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 26155378 24.64% 95.01% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 26155386 24.64% 95.01% # Type of FU issued system.cpu.iq.FU_type_0::MemWrite 5298717 4.99% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 106162042 # Type of FU issued +system.cpu.iq.FU_type_0::total 106162051 # Type of FU issued system.cpu.iq.rate 1.604598 # Inst issue rate -system.cpu.iq.fu_busy_cnt 508131 # FU busy when requested +system.cpu.iq.fu_busy_cnt 508132 # FU busy when requested system.cpu.iq.fu_busy_rate 0.004786 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 278993219 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 144129610 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 102521129 # Number of integer instruction queue wakeup accesses +system.cpu.iq.int_inst_queue_reads 278993240 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 144129636 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 102521130 # Number of integer instruction queue wakeup accesses system.cpu.iq.fp_inst_queue_reads 900 # Number of floating instruction queue reads system.cpu.iq.fp_inst_queue_writes 1354 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 412 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 106669721 # Number of integer alu accesses +system.cpu.iq.int_alu_accesses 106669731 # Number of integer alu accesses system.cpu.iq.fp_alu_accesses 452 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 366276 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread0.forwLoads 366279 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 6760478 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 42465 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.squashedLoads 6760486 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 42468 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread0.memOrderViolation 731 # Number of memory ordering violations system.cpu.iew.lsq.thread0.squashedStores 994251 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address @@ -251,12 +251,12 @@ system.cpu.iew.lsq.thread0.blockedLoads 0 # Nu system.cpu.iew.lsq.thread0.rescheduledLoads 2 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 30282 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 4006999 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 4007001 # Number of cycles IEW is squashing system.cpu.iew.iewBlockCycles 182542 # Number of cycles IEW is blocking system.cpu.iew.iewUnblockCycles 28701 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 117958129 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispatchedInsts 117958139 # Number of instructions dispatched to IQ system.cpu.iew.iewDispSquashedInsts 810273 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 29336350 # Number of dispatched load instructions +system.cpu.iew.iewDispLoadInsts 29336358 # Number of dispatched load instructions system.cpu.iew.iewDispStoreInsts 5741000 # Number of dispatched store instructions system.cpu.iew.iewDispNonSpecInsts 643936 # Number of dispatched non-speculative instructions system.cpu.iew.iewIQFullEvents 9429 # Number of times the IQ has become full, causing a stall @@ -265,17 +265,17 @@ system.cpu.iew.memOrderViolationEvents 731 # Nu system.cpu.iew.predictedTakenIncorrect 1288873 # Number of branches that were predicted taken incorrectly system.cpu.iew.predictedNotTakenIncorrect 210071 # Number of branches that were predicted not taken incorrectly system.cpu.iew.branchMispredicts 1498944 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 104530426 # Number of executed instructions +system.cpu.iew.iewExecutedInsts 104530427 # Number of executed instructions system.cpu.iew.iewExecLoadInsts 25743276 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 1631616 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecSquashedInsts 1631624 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 38806 # number of nop insts executed system.cpu.iew.exec_refs 30946109 # number of memory reference insts executed system.cpu.iew.exec_branches 21214083 # Number of branches executed system.cpu.iew.exec_stores 5202833 # Number of stores executed system.cpu.iew.exec_rate 1.579937 # Inst execution rate -system.cpu.iew.wb_sent 102941811 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 102521541 # cumulative count of insts written-back +system.cpu.iew.wb_sent 102941812 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 102521542 # cumulative count of insts written-back system.cpu.iew.wb_producers 60312663 # num instructions producing a value system.cpu.iew.wb_consumers 96996327 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ @@ -283,7 +283,7 @@ system.cpu.iew.wb_rate 1.549573 # in system.cpu.iew.wb_fanout 0.621804 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 91262494 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 26696986 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 26696996 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 554844 # The number of times commit has been forced to stall to communicate backwards system.cpu.commit.branchMispredicts 1392644 # The number of times a branch was mispredicted system.cpu.commit.committed_per_cycle::samples 62124345 # Number of insts commited each cycle @@ -314,42 +314,42 @@ system.cpu.commit.int_insts 72533302 # Nu system.cpu.commit.function_calls 56148 # Number of function calls committed. system.cpu.commit.bw_lim_events 4531141 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 175546950 # The number of ROB reads -system.cpu.rob.rob_writes 239939834 # The number of ROB writes +system.cpu.rob.rob_reads 175546960 # The number of ROB reads +system.cpu.rob.rob_writes 239939856 # The number of ROB writes system.cpu.timesIdled 1543 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.idleCycles 29796 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 91249885 # Number of Instructions Simulated system.cpu.committedInsts_total 91249885 # Number of Instructions Simulated -system.cpu.cpi 0.725054 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.725054 # CPI: Total CPI of All Threads +system.cpu.cpi 0.725055 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.725055 # CPI: Total CPI of All Threads system.cpu.ipc 1.379207 # IPC: Instructions Per Cycle system.cpu.ipc_total 1.379207 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 496902731 # number of integer regfile reads -system.cpu.int_regfile_writes 120936097 # number of integer regfile writes +system.cpu.int_regfile_reads 496902735 # number of integer regfile reads +system.cpu.int_regfile_writes 120936098 # number of integer regfile writes system.cpu.fp_regfile_reads 197 # number of floating regfile reads system.cpu.fp_regfile_writes 534 # number of floating regfile writes -system.cpu.misc_regfile_reads 184886725 # number of misc regfile reads +system.cpu.misc_regfile_reads 184886717 # number of misc regfile reads system.cpu.misc_regfile_writes 11594 # number of misc regfile writes system.cpu.icache.replacements 2 # number of replacements -system.cpu.icache.tagsinuse 611.587678 # Cycle average of tags in use -system.cpu.icache.total_refs 14743812 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 611.587679 # Cycle average of tags in use +system.cpu.icache.total_refs 14743811 # Total number of references to valid blocks. system.cpu.icache.sampled_refs 722 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 20420.792244 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 20420.790859 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 611.587678 # Average occupied blocks per context +system.cpu.icache.occ_blocks::0 611.587679 # Average occupied blocks per context system.cpu.icache.occ_percent::0 0.298627 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 14743812 # number of ReadReq hits -system.cpu.icache.demand_hits 14743812 # number of demand (read+write) hits -system.cpu.icache.overall_hits 14743812 # number of overall hits +system.cpu.icache.ReadReq_hits 14743811 # number of ReadReq hits +system.cpu.icache.demand_hits 14743811 # number of demand (read+write) hits +system.cpu.icache.overall_hits 14743811 # number of overall hits system.cpu.icache.ReadReq_misses 916 # number of ReadReq misses system.cpu.icache.demand_misses 916 # number of demand (read+write) misses system.cpu.icache.overall_misses 916 # number of overall misses system.cpu.icache.ReadReq_miss_latency 32376000 # number of ReadReq miss cycles system.cpu.icache.demand_miss_latency 32376000 # number of demand (read+write) miss cycles system.cpu.icache.overall_miss_latency 32376000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 14744728 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 14744728 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 14744728 # number of overall (read+write) accesses +system.cpu.icache.ReadReq_accesses 14744727 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 14744727 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 14744727 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000062 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000062 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000062 # miss rate for overall accesses @@ -387,45 +387,45 @@ system.cpu.icache.mshr_cap_events 0 # nu system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.dcache.replacements 943456 # number of replacements -system.cpu.dcache.tagsinuse 3558.808717 # Cycle average of tags in use -system.cpu.dcache.total_refs 28819274 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 3558.808733 # Cycle average of tags in use +system.cpu.dcache.total_refs 28819271 # Total number of references to valid blocks. system.cpu.dcache.sampled_refs 947552 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 30.414451 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 30.414448 # Average number of references to valid blocks. system.cpu.dcache.warmup_cycle 12353041000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 3558.808717 # Average occupied blocks per context +system.cpu.dcache.occ_blocks::0 3558.808733 # Average occupied blocks per context system.cpu.dcache.occ_percent::0 0.868850 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 24247443 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits 24247440 # number of ReadReq hits system.cpu.dcache.WriteReq_hits 4559242 # number of WriteReq hits system.cpu.dcache.LoadLockedReq_hits 6797 # number of LoadLockedReq hits system.cpu.dcache.StoreCondReq_hits 5792 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 28806685 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 28806685 # number of overall hits +system.cpu.dcache.demand_hits 28806682 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 28806682 # number of overall hits system.cpu.dcache.ReadReq_misses 989267 # number of ReadReq misses system.cpu.dcache.WriteReq_misses 175739 # number of WriteReq misses system.cpu.dcache.LoadLockedReq_misses 7 # number of LoadLockedReq misses system.cpu.dcache.demand_misses 1165006 # number of demand (read+write) misses system.cpu.dcache.overall_misses 1165006 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 5475542500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 4498706928 # number of WriteReq miss cycles +system.cpu.dcache.ReadReq_miss_latency 5475545000 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 4498707428 # number of WriteReq miss cycles system.cpu.dcache.LoadLockedReq_miss_latency 124500 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 9974249428 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 9974249428 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 25236710 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.demand_miss_latency 9974252428 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 9974252428 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 25236707 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 4734981 # number of WriteReq accesses(hits+misses) system.cpu.dcache.LoadLockedReq_accesses 6804 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.StoreCondReq_accesses 5792 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 29971691 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 29971691 # number of overall (read+write) accesses +system.cpu.dcache.demand_accesses 29971688 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 29971688 # number of overall (read+write) accesses system.cpu.dcache.ReadReq_miss_rate 0.039200 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.037115 # miss rate for WriteReq accesses system.cpu.dcache.LoadLockedReq_miss_rate 0.001029 # miss rate for LoadLockedReq accesses system.cpu.dcache.demand_miss_rate 0.038870 # miss rate for demand accesses system.cpu.dcache.overall_miss_rate 0.038870 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 5534.949109 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 25598.796670 # average WriteReq miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 5534.951636 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 25598.799515 # average WriteReq miss latency system.cpu.dcache.LoadLockedReq_avg_miss_latency 17785.714286 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 8561.543398 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 8561.543398 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency 8561.545973 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 8561.545973 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 23239503 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 8123 # number of cycles access was blocked @@ -445,31 +445,31 @@ system.cpu.dcache.WriteReq_mshr_misses 44526 # nu system.cpu.dcache.demand_mshr_misses 947553 # number of demand (read+write) MSHR misses system.cpu.dcache.overall_mshr_misses 947553 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 2253075000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 1081062556 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 3334137556 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 3334137556 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 2253076500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 1081063056 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 3334139556 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 3334139556 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.035782 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.009404 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.031615 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.031615 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2495.025066 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 24279.354894 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 3518.681864 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 3518.681864 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2495.026727 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 24279.366123 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 3518.683974 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 3518.683974 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.l2cache.replacements 744 # number of replacements -system.cpu.l2cache.tagsinuse 9229.669539 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 9229.669691 # Cycle average of tags in use system.cpu.l2cache.total_refs 1596774 # Total number of references to valid blocks. system.cpu.l2cache.sampled_refs 15569 # Sample count of references to valid blocks. system.cpu.l2cache.avg_refs 102.561115 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 392.792284 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 8836.877255 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::0 392.792276 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 8836.877415 # Average occupied blocks per context system.cpu.l2cache.occ_percent::0 0.011987 # Average percentage of cache occupancy system.cpu.l2cache.occ_percent::1 0.269680 # Average percentage of cache occupancy system.cpu.l2cache.ReadReq_hits 901413 # number of ReadReq hits diff --git a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/config.ini b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/config.ini index c0a21768c..546611c4c 100644 --- a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/config.ini +++ b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -89,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -149,7 +159,14 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=X86TLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -446,9 +463,25 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=X86LocalApic +int_latency=1000 +pio_addr=2305843009213693952 +pio_latency=1000 +system=system +int_port=system.membus.port[4] +pio=system.membus.port[3] + [system.cpu.itb] type=X86TLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -479,7 +512,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -490,7 +523,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -498,7 +531,7 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=mcf mcf.in -cwd=build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing +cwd=build/X86/tests/opt/long/se/10.mcf/x86/linux/o3-timing egid=100 env= errout=cerr @@ -522,7 +555,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side +port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side system.cpu.interrupts.pio system.cpu.interrupts.int_port [system.physmem] type=PhysicalMemory diff --git a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/simout b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/simout index 7ce56ed7f..1c8484fc7 100755 --- a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/simout +++ b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/simout @@ -1,12 +1,12 @@ -Redirecting stdout to build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing/simout -Redirecting stderr to build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing/simerr +Redirecting stdout to build/X86/tests/opt/long/se/10.mcf/x86/linux/o3-timing/simout +Redirecting stderr to build/X86/tests/opt/long/se/10.mcf/x86/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 28 2012 12:11:40 -gem5 started Jan 28 2012 12:12:43 +gem5 compiled Feb 9 2012 12:45:55 +gem5 started Feb 9 2012 12:46:40 gem5 executing on ribera.cs.wisc.edu -command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing +command line: build/X86/gem5.opt -d build/X86/tests/opt/long/se/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86/tests/opt/long/se/10.mcf/x86/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -25,4 +25,4 @@ simplex iterations : 2663 flow value : 3080014995 checksum : 68389 optimal -Exiting @ tick 70097938500 because target called exit() +Exiting @ tick 70046988500 because target called exit() diff --git a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/stats.txt b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/stats.txt index 741105f40..0040f922c 100644 --- a/tests/long/se/10.mcf/ref/x86/linux/o3-timing/stats.txt +++ b/tests/long/se/10.mcf/ref/x86/linux/o3-timing/stats.txt @@ -1,262 +1,262 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.070098 # Number of seconds simulated -sim_ticks 70097938500 # Number of ticks simulated -final_tick 70097938500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.070047 # Number of seconds simulated +sim_ticks 70046988500 # Number of ticks simulated +final_tick 70046988500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 110386 # Simulator instruction rate (inst/s) -host_tick_rate 27814669 # Simulator tick rate (ticks/s) -host_mem_usage 379416 # Number of bytes of host memory used -host_seconds 2520.18 # Real time elapsed on the host +host_inst_rate 78701 # Simulator instruction rate (inst/s) +host_tick_rate 19816485 # Simulator tick rate (ticks/s) +host_mem_usage 388420 # Number of bytes of host memory used +host_seconds 3534.78 # Real time elapsed on the host sim_insts 278192519 # Number of instructions simulated -system.physmem.bytes_read 3896128 # Number of bytes read from this memory -system.physmem.bytes_inst_read 65152 # Number of instructions bytes read from this memory -system.physmem.bytes_written 892416 # Number of bytes written to this memory -system.physmem.num_reads 60877 # Number of read requests responded to by this memory -system.physmem.num_writes 13944 # Number of write requests responded to by this memory +system.physmem.bytes_read 3895936 # Number of bytes read from this memory +system.physmem.bytes_inst_read 65216 # Number of instructions bytes read from this memory +system.physmem.bytes_written 892288 # Number of bytes written to this memory +system.physmem.num_reads 60874 # Number of read requests responded to by this memory +system.physmem.num_writes 13942 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 55581207 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 929442 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 12730988 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 68312194 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 55618894 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 931032 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 12738421 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 68357314 # Total bandwidth to/from this memory (bytes/s) system.cpu.workload.num_syscalls 444 # Number of system calls -system.cpu.numCycles 140195878 # number of cpu cycles simulated +system.cpu.numCycles 140093978 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 37928407 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 37928407 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 1334678 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 33548417 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 33040245 # Number of BTB hits +system.cpu.BPredUnit.lookups 37937752 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 37937752 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 1331995 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 33815417 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 33320649 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 29060209 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 203598338 # Number of instructions fetch has processed -system.cpu.fetch.Branches 37928407 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 33040245 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 63274026 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 10249926 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 38189577 # Number of cycles fetch has spent blocked +system.cpu.fetch.icacheStallCycles 29024363 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 203514307 # Number of instructions fetch has processed +system.cpu.fetch.Branches 37937752 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 33320649 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 63466806 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 10233892 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 37945043 # Number of cycles fetch has spent blocked system.cpu.fetch.MiscStallCycles 18 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 77 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 28245503 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 214193 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 139407654 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.577879 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.292775 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.PendingTrapStallCycles 68 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 28213885 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 212642 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 139306492 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.579216 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.290579 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 78584615 56.37% 56.37% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 3556242 2.55% 58.92% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 2802198 2.01% 60.93% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 4529245 3.25% 64.18% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 6913485 4.96% 69.14% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 5169478 3.71% 72.85% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 7697084 5.52% 78.37% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 4298531 3.08% 81.45% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 25856776 18.55% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 78286088 56.20% 56.20% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 3759512 2.70% 58.90% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 2809249 2.02% 60.91% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 4511465 3.24% 64.15% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 7046412 5.06% 69.21% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 5071327 3.64% 72.85% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 7671850 5.51% 78.36% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 4389018 3.15% 81.51% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 25761571 18.49% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 139407654 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.270539 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.452242 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 41988791 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 28417024 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 52030953 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 8087139 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 8883747 # Number of cycles decode is squashing -system.cpu.decode.DecodedInsts 355040007 # Number of instructions handled by decode -system.cpu.rename.SquashCycles 8883747 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 48483810 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 4810408 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 9079 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 52929871 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 24290739 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 350051728 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 20 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 103496 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 20366187 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RenamedOperands 314282471 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 860902327 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 860897388 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 4939 # Number of floating rename lookups +system.cpu.fetch.rateDist::total 139306492 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.270802 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.452698 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 41961886 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 28163540 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 52299140 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 8011732 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 8870194 # Number of cycles decode is squashing +system.cpu.decode.DecodedInsts 354926885 # Number of instructions handled by decode +system.cpu.rename.SquashCycles 8870194 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 48488899 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 4721769 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 9082 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 53110553 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 24105995 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 349921643 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 18 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 105361 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 20166032 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RenamedOperands 314159745 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 860584858 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 860581891 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 2967 # Number of floating rename lookups system.cpu.rename.CommittedMaps 248344192 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 65938279 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 478 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 472 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 57634584 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 112617334 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 37601195 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 47838969 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 8379867 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 343415839 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 2328 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 316096096 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 78808 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 65029362 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 92942153 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 1882 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 139407654 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 2.267423 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.745481 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 65815553 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 479 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 473 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 57293063 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 112603571 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 37556545 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 47800126 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 8208845 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 343290045 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 2336 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 316029105 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 76885 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 64917017 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 92716043 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 1890 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 139306492 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 2.268588 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.744230 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 32098361 23.02% 23.02% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 17868067 12.82% 35.84% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 24417482 17.52% 53.36% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 32093883 23.02% 76.38% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 18421218 13.21% 89.59% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 9527374 6.83% 96.43% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 3128162 2.24% 98.67% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 1804154 1.29% 99.96% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 48953 0.04% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 32068137 23.02% 23.02% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 17712067 12.71% 35.73% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 24423194 17.53% 53.27% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 32289069 23.18% 76.44% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 18335734 13.16% 89.61% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 9491103 6.81% 96.42% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 3154604 2.26% 98.68% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 1783304 1.28% 99.96% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 49280 0.04% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 139407654 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 139306492 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 25731 1.31% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 1.31% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 1863505 95.00% 96.31% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 72393 3.69% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 25569 1.30% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 1.30% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 1859415 94.86% 96.17% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 75095 3.83% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 16711 0.01% 0.01% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 180196286 57.01% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::IntDiv 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 342 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatMult 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMult 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShift 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 57.01% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 101438567 32.09% 89.10% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 34444190 10.90% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 180131547 57.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::IntDiv 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 149 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatMult 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMult 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShift 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 57.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 101432595 32.10% 89.10% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 34448103 10.90% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 316096096 # Type of FU issued -system.cpu.iq.rate 2.254675 # Inst issue rate -system.cpu.iq.fu_busy_cnt 1961629 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.006206 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 773638738 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 408477370 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 312370165 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 1545 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 3169 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 656 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 318040246 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 768 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 52318776 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 316029105 # Type of FU issued +system.cpu.iq.rate 2.255836 # Inst issue rate +system.cpu.iq.fu_busy_cnt 1960079 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.006202 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 773400844 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 408240794 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 312293905 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 822 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 1922 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 316 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 317972066 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 407 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 52311971 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 21837946 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 139826 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 33737 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 6161444 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 21824183 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 143830 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 34021 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 6116794 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 3258 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 3821 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.rescheduledLoads 3244 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.cacheBlocked 3822 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 8883747 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 984872 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 88741 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 343418167 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 39651 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 112617334 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 37601195 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 465 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 1341 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 42673 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 33737 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 1237180 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 215729 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 1452909 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 313907375 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 100815222 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 2188721 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 8870194 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 981730 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 88786 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 343292381 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 39929 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 112603571 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 37556545 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 466 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 1316 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 42406 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 34021 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 1234482 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 211725 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 1446207 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 313835720 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 100810143 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2193385 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 0 # number of nop insts executed -system.cpu.iew.exec_refs 134855811 # number of memory reference insts executed -system.cpu.iew.exec_branches 31730666 # Number of branches executed -system.cpu.iew.exec_stores 34040589 # Number of stores executed -system.cpu.iew.exec_rate 2.239063 # Inst execution rate -system.cpu.iew.wb_sent 313087219 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 312370821 # cumulative count of insts written-back -system.cpu.iew.wb_producers 231825034 # num instructions producing a value -system.cpu.iew.wb_consumers 317282535 # num instructions consuming a value +system.cpu.iew.exec_refs 134854161 # number of memory reference insts executed +system.cpu.iew.exec_branches 31726163 # Number of branches executed +system.cpu.iew.exec_stores 34044018 # Number of stores executed +system.cpu.iew.exec_rate 2.240180 # Inst execution rate +system.cpu.iew.wb_sent 313006075 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 312294221 # cumulative count of insts written-back +system.cpu.iew.wb_producers 231754622 # num instructions producing a value +system.cpu.iew.wb_consumers 317218208 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 2.228103 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.730658 # average fanout of values written-back +system.cpu.iew.wb_rate 2.229177 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.730584 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 278192519 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 65229233 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 65103374 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 446 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 1334689 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 130523907 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 2.131353 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.650695 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 1332005 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 130436298 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 2.132785 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.651894 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 49374885 37.83% 37.83% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 24990571 19.15% 56.97% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 17165469 13.15% 70.13% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 12454302 9.54% 79.67% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 3472302 2.66% 82.33% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 3453203 2.65% 84.97% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 2713996 2.08% 87.05% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 1124527 0.86% 87.91% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 15774652 12.09% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 49351461 37.84% 37.84% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 24978168 19.15% 56.99% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 17073618 13.09% 70.08% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 12436945 9.53% 79.61% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 3526211 2.70% 82.31% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 3453253 2.65% 84.96% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 2711146 2.08% 87.04% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 1125673 0.86% 87.90% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 15779823 12.10% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 130523907 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 130436298 # Number of insts commited each cycle system.cpu.commit.count 278192519 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 122219139 # Number of memory references committed @@ -266,49 +266,49 @@ system.cpu.commit.branches 29309710 # Nu system.cpu.commit.fp_insts 40 # Number of committed floating point instructions. system.cpu.commit.int_insts 278186227 # Number of committed integer instructions. system.cpu.commit.function_calls 0 # Number of function calls committed. -system.cpu.commit.bw_lim_events 15774652 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 15779823 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 458171007 # The number of ROB reads -system.cpu.rob.rob_writes 695745355 # The number of ROB writes -system.cpu.timesIdled 23904 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 788224 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 457952368 # The number of ROB reads +system.cpu.rob.rob_writes 695479183 # The number of ROB writes +system.cpu.timesIdled 23894 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 787486 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 278192519 # Number of Instructions Simulated system.cpu.committedInsts_total 278192519 # Number of Instructions Simulated -system.cpu.cpi 0.503953 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.503953 # CPI: Total CPI of All Threads -system.cpu.ipc 1.984313 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.984313 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 554439426 # number of integer regfile reads -system.cpu.int_regfile_writes 279882097 # number of integer regfile writes -system.cpu.fp_regfile_reads 791 # number of floating regfile reads -system.cpu.fp_regfile_writes 562 # number of floating regfile writes -system.cpu.misc_regfile_reads 200975844 # number of misc regfile reads -system.cpu.icache.replacements 62 # number of replacements -system.cpu.icache.tagsinuse 823.089414 # Cycle average of tags in use -system.cpu.icache.total_refs 28244206 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 1023 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 27609.194526 # Average number of references to valid blocks. +system.cpu.cpi 0.503586 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.503586 # CPI: Total CPI of All Threads +system.cpu.ipc 1.985756 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.985756 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 554395898 # number of integer regfile reads +system.cpu.int_regfile_writes 279799467 # number of integer regfile writes +system.cpu.fp_regfile_reads 352 # number of floating regfile reads +system.cpu.fp_regfile_writes 262 # number of floating regfile writes +system.cpu.misc_regfile_reads 200946158 # number of misc regfile reads +system.cpu.icache.replacements 64 # number of replacements +system.cpu.icache.tagsinuse 822.534021 # Cycle average of tags in use +system.cpu.icache.total_refs 28212585 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 1024 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 27551.352539 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 823.089414 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.401899 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 28244206 # number of ReadReq hits -system.cpu.icache.demand_hits 28244206 # number of demand (read+write) hits -system.cpu.icache.overall_hits 28244206 # number of overall hits -system.cpu.icache.ReadReq_misses 1297 # number of ReadReq misses -system.cpu.icache.demand_misses 1297 # number of demand (read+write) misses -system.cpu.icache.overall_misses 1297 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 46884000 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 46884000 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 46884000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 28245503 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 28245503 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 28245503 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 822.534021 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.401628 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 28212585 # number of ReadReq hits +system.cpu.icache.demand_hits 28212585 # number of demand (read+write) hits +system.cpu.icache.overall_hits 28212585 # number of overall hits +system.cpu.icache.ReadReq_misses 1300 # number of ReadReq misses +system.cpu.icache.demand_misses 1300 # number of demand (read+write) misses +system.cpu.icache.overall_misses 1300 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 46952500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 46952500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 46952500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 28213885 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 28213885 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 28213885 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000046 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000046 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000046 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 36148.033924 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 36148.033924 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 36148.033924 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 36117.307692 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 36117.307692 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 36117.307692 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -318,59 +318,59 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 273 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 273 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 273 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 1024 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 1024 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 1024 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 275 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 275 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 275 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 1025 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 1025 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 1025 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 36044000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 36044000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 36044000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 36071500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 36071500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 36071500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000036 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000036 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000036 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 35199.218750 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 35199.218750 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 35199.218750 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 35191.707317 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 35191.707317 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 35191.707317 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 2072801 # number of replacements -system.cpu.dcache.tagsinuse 4073.016957 # Cycle average of tags in use -system.cpu.dcache.total_refs 77487718 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 2076897 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 37.309370 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 23652058000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4073.016957 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.994389 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 46133976 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 31353733 # number of WriteReq hits -system.cpu.dcache.demand_hits 77487709 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 77487709 # number of overall hits -system.cpu.dcache.ReadReq_misses 2288597 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 86018 # number of WriteReq misses -system.cpu.dcache.demand_misses 2374615 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 2374615 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 13760644500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 1501321288 # number of WriteReq miss cycles -system.cpu.dcache.demand_miss_latency 15261965788 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 15261965788 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 48422573 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.replacements 2072906 # number of replacements +system.cpu.dcache.tagsinuse 4073.029614 # Cycle average of tags in use +system.cpu.dcache.total_refs 77489413 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 2077002 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 37.308300 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 23588256000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4073.029614 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.994392 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 46135653 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 31353751 # number of WriteReq hits +system.cpu.dcache.demand_hits 77489404 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 77489404 # number of overall hits +system.cpu.dcache.ReadReq_misses 2289012 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 86000 # number of WriteReq misses +system.cpu.dcache.demand_misses 2375012 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 2375012 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 13766771000 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 1501245288 # number of WriteReq miss cycles +system.cpu.dcache.demand_miss_latency 15268016288 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 15268016288 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 48424665 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 31439751 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 79862324 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 79862324 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.047263 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.002736 # miss rate for WriteReq accesses -system.cpu.dcache.demand_miss_rate 0.029734 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.029734 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 6012.698828 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 17453.571206 # average WriteReq miss latency -system.cpu.dcache.demand_avg_miss_latency 6427.132730 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 6427.132730 # average overall miss latency +system.cpu.dcache.demand_accesses 79864416 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 79864416 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.047270 # miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.002735 # miss rate for WriteReq accesses +system.cpu.dcache.demand_miss_rate 0.029738 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.029738 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 6014.285203 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 17456.340558 # average WriteReq miss latency +system.cpu.dcache.demand_avg_miss_latency 6428.605956 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 6428.605956 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -379,72 +379,72 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 1880524 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 293812 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 3902 # number of WriteReq MSHR hits -system.cpu.dcache.demand_mshr_hits 297714 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 297714 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 1994785 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 82116 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 2076901 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 2076901 # number of overall MSHR misses +system.cpu.dcache.writebacks 1880780 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 294089 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 3918 # number of WriteReq MSHR hits +system.cpu.dcache.demand_mshr_hits 298007 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 298007 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 1994923 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 82082 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 2077005 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 2077005 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 5560782500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 1157739288 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 6718521788 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 6718521788 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 5565133500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 1157645788 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 6722779288 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 6722779288 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.041195 # mshr miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_mshr_miss_rate 0.002612 # mshr miss rate for WriteReq accesses -system.cpu.dcache.demand_mshr_miss_rate 0.026006 # mshr miss rate for demand accesses -system.cpu.dcache.overall_mshr_miss_rate 0.026006 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2787.660074 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 14098.827123 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 3234.878209 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 3234.878209 # average overall mshr miss latency +system.cpu.dcache.ReadReq_mshr_miss_rate 0.041196 # mshr miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.002611 # mshr miss rate for WriteReq accesses +system.cpu.dcache.demand_mshr_miss_rate 0.026007 # mshr miss rate for demand accesses +system.cpu.dcache.overall_mshr_miss_rate 0.026007 # mshr miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2789.648272 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 14103.528033 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 3236.766059 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 3236.766059 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 33248 # number of replacements -system.cpu.l2cache.tagsinuse 18948.902283 # Cycle average of tags in use -system.cpu.l2cache.total_refs 3764067 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 61254 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 61.450142 # Average number of references to valid blocks. +system.cpu.l2cache.replacements 33246 # number of replacements +system.cpu.l2cache.tagsinuse 18964.988080 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3764517 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 61253 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 61.458492 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 6031.150094 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 12917.752189 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.184056 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.394219 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 1964318 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 1880524 # number of Writeback hits -system.cpu.l2cache.ReadExReq_hits 52728 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 2017046 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 2017046 # number of overall hits -system.cpu.l2cache.ReadReq_misses 31362 # number of ReadReq misses +system.cpu.l2cache.occ_blocks::0 6037.038666 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 12927.949414 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.184236 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.394530 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 1964445 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 1880780 # number of Writeback hits +system.cpu.l2cache.ReadExReq_hits 52709 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 2017154 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 2017154 # number of overall hits +system.cpu.l2cache.ReadReq_misses 31361 # number of ReadReq misses system.cpu.l2cache.UpgradeReq_misses 1 # number of UpgradeReq misses -system.cpu.l2cache.ReadExReq_misses 29515 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 60877 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 60877 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 1071112000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 1006258500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 2077370500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 2077370500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 1995680 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 1880524 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.ReadExReq_misses 29513 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 60874 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 60874 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 1071202500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 1006190000 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 2077392500 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 2077392500 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 1995806 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 1880780 # number of Writeback accesses(hits+misses) system.cpu.l2cache.UpgradeReq_accesses 1 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 82243 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 2077923 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 2077923 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.015715 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_accesses 82222 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 2078028 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 2078028 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.015713 # miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.358876 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.029297 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.029297 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34153.179006 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34093.122141 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34124.061632 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34124.061632 # average overall miss latency +system.cpu.l2cache.ReadExReq_miss_rate 0.358943 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.029294 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.029294 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34157.153790 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34093.111510 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34126.104741 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34126.104741 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -453,31 +453,31 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 13944 # number of writebacks +system.cpu.l2cache.writebacks 13942 # number of writebacks system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 31362 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 31361 # number of ReadReq MSHR misses system.cpu.l2cache.UpgradeReq_mshr_misses 1 # number of UpgradeReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 29515 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 60877 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 60877 # number of overall MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 29513 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 60874 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 60874 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 972890000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 972854000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.UpgradeReq_mshr_miss_latency 31000 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 914988000 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 1887878000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 1887878000 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 914925500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 1887779500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 1887779500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.015715 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.015713 # mshr miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.358876 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.029297 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.029297 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31021.299662 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.358943 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.029294 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.029294 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31021.140907 # average ReadReq mshr miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000 # average UpgradeReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.779265 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31011.350756 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31011.350756 # average overall mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.762376 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31011.260965 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31011.260965 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/20.parser/ref/arm/linux/o3-timing/config.ini b/tests/long/se/20.parser/ref/arm/linux/o3-timing/config.ini index e2c071016..0436eab53 100644 --- a/tests/long/se/20.parser/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/20.parser/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,14 +529,14 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=parser 2.1.dict -batch -cwd=build/ARM_SE/tests/opt/long/20.parser/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/20.parser/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/parser +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/parser gid=100 -input=/dist/m5/cpu2000/data/parser/mdred/input/parser.in +input=/scratch/nilay/GEM5/dist/m5/cpu2000/data/parser/mdred/input/parser.in max_stack_size=67108864 output=cout pid=100 diff --git a/tests/long/se/20.parser/ref/arm/linux/o3-timing/simout b/tests/long/se/20.parser/ref/arm/linux/o3-timing/simout index c61c0591a..cc61bb6b6 100755 --- a/tests/long/se/20.parser/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/20.parser/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/20.parser/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/20.parser/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 08:49:36 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/20.parser/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/20.parser/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:20 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/20.parser/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/20.parser/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -67,4 +69,4 @@ info: Increasing stack size by one page. about 2 million people attended the five best costumes got prizes No errors! -Exiting @ tick 274198757500 because target called exit() +Exiting @ tick 274128411000 because target called exit() diff --git a/tests/long/se/20.parser/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/20.parser/ref/arm/linux/o3-timing/stats.txt index 0cc2b2b8d..c0ee61c5b 100644 --- a/tests/long/se/20.parser/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/20.parser/ref/arm/linux/o3-timing/stats.txt @@ -1,24 +1,24 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.274199 # Number of seconds simulated -sim_ticks 274198757500 # Number of ticks simulated -final_tick 274198757500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.274128 # Number of seconds simulated +sim_ticks 274128411000 # Number of ticks simulated +final_tick 274128411000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 114096 # Simulator instruction rate (inst/s) -host_tick_rate 54566255 # Simulator tick rate (ticks/s) -host_mem_usage 225172 # Number of bytes of host memory used -host_seconds 5025.06 # Real time elapsed on the host -sim_insts 573341162 # Number of instructions simulated -system.physmem.bytes_read 15248640 # Number of bytes read from this memory -system.physmem.bytes_inst_read 230400 # Number of instructions bytes read from this memory -system.physmem.bytes_written 10960192 # Number of bytes written to this memory -system.physmem.num_reads 238260 # Number of read requests responded to by this memory -system.physmem.num_writes 171253 # Number of write requests responded to by this memory +host_inst_rate 67477 # Simulator instruction rate (inst/s) +host_tick_rate 32262353 # Simulator tick rate (ticks/s) +host_mem_usage 260864 # Number of bytes of host memory used +host_seconds 8496.85 # Real time elapsed on the host +sim_insts 573341187 # Number of instructions simulated +system.physmem.bytes_read 15240192 # Number of bytes read from this memory +system.physmem.bytes_inst_read 229568 # Number of instructions bytes read from this memory +system.physmem.bytes_written 10959680 # Number of bytes written to this memory +system.physmem.num_reads 238128 # Number of read requests responded to by this memory +system.physmem.num_writes 171245 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 55611631 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 840266 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 39971706 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 95583336 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 55595084 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 837447 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 39980095 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 95575179 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,106 +62,106 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 548 # Number of system calls -system.cpu.numCycles 548397516 # number of cpu cycles simulated +system.cpu.numCycles 548256823 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 225101784 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 179007547 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 18307036 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 189868979 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 156087931 # Number of BTB hits +system.cpu.BPredUnit.lookups 224897268 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 178814817 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 18282790 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 189563731 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 156236753 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 11743928 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 2589266 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 154237973 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 996342059 # Number of instructions fetch has processed -system.cpu.fetch.Branches 225101784 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 167831859 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 251951083 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 70115496 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 88916227 # Number of cycles fetch has spent blocked +system.cpu.BPredUnit.usedRAS 11742995 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 2591276 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 154191878 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 995397299 # Number of instructions fetch has processed +system.cpu.fetch.Branches 224897268 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 167979748 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 252064252 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 69921430 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 88879876 # Number of cycles fetch has spent blocked system.cpu.fetch.MiscStallCycles 76 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 27190 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 141601056 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 4591339 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 544609039 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.120756 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 2.818747 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.PendingTrapStallCycles 27589 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 141619226 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 4743130 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 544471710 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.119468 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 2.816244 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 292670234 53.74% 53.74% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 22602609 4.15% 57.89% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 39324759 7.22% 65.11% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 38673680 7.10% 72.21% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 44132407 8.10% 80.32% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 15219761 2.79% 83.11% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 18468380 3.39% 86.50% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 13866800 2.55% 89.05% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 59650409 10.95% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 292419737 53.71% 53.71% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 22605861 4.15% 57.86% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 39604588 7.27% 65.13% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 38612877 7.09% 72.22% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 44079940 8.10% 80.32% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 15590470 2.86% 83.18% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 18445012 3.39% 86.57% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 13511392 2.48% 89.05% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 59601833 10.95% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 544609039 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.410472 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.816825 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 173360184 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 84631968 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 232819510 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 4407510 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 49389867 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 33096702 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 88546 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 1070717063 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 220828 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 49389867 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 189439670 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 6246457 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 67211324 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 221002512 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 11319209 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 984442373 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 1013 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 2966416 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 5236155 # Number of times rename has blocked due to LSQ full -system.cpu.rename.FullRegisterEvents 73 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 1176369692 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 4273292331 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 4273289228 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 3103 # Number of floating rename lookups -system.cpu.rename.CommittedMaps 672199296 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 504170396 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 6164964 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 6164681 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 63358237 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 196378247 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 77986326 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 17967729 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 12612066 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 870602735 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 7830625 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 735457773 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 1536942 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 302215535 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 751654986 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 3952431 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 544609039 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.350433 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.595771 # Number of insts issued each cycle +system.cpu.fetch.rateDist::total 544471710 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.410204 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.815568 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 173466263 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 84575198 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 232805016 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 4404092 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 49221141 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 33081437 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 88923 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 1069021878 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 219487 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 49221141 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 189418333 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 6243189 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 67194010 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 221110320 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 11284717 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 983280870 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 1088 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 2966299 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 5203884 # Number of times rename has blocked due to LSQ full +system.cpu.rename.FullRegisterEvents 24 # Number of times there has been no free registers +system.cpu.rename.RenamedOperands 1174814245 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 4267939396 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 4267936218 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 3178 # Number of floating rename lookups +system.cpu.rename.CommittedMaps 672199336 # Number of HB maps that are committed +system.cpu.rename.UndoneMaps 502614909 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 6158838 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 6158596 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 63324865 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 196341124 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 77971699 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 17887364 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 12637820 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 869953710 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 7817073 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 735125256 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 1650830 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 301557809 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 749773525 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 3938874 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 544471710 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.350162 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.594792 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 241479375 44.34% 44.34% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 95418106 17.52% 61.86% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 86231703 15.83% 77.69% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 59231990 10.88% 88.57% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 36938301 6.78% 95.35% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 14710122 2.70% 98.05% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 6373652 1.17% 99.22% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 3471755 0.64% 99.86% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 754035 0.14% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 241490713 44.35% 44.35% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 95232425 17.49% 61.84% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 86360231 15.86% 77.71% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 58954468 10.83% 88.53% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 37235413 6.84% 95.37% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 14676941 2.70% 98.07% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 6419263 1.18% 99.25% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 3351018 0.62% 99.86% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 751238 0.14% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 544609039 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 544471710 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 133367 1.38% 1.38% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 133047 1.38% 1.38% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 0 0.00% 1.38% # attempts to use FU when none available system.cpu.iq.fu_full::IntDiv 0 0.00% 1.38% # attempts to use FU when none available system.cpu.iq.fu_full::FloatAdd 0 0.00% 1.38% # attempts to use FU when none available @@ -190,15 +190,15 @@ system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 1.38% # at system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 1.38% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 1.38% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 1.38% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 6658147 68.82% 70.20% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 2883419 29.80% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 6635057 68.81% 70.19% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 2874860 29.81% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 497367446 67.63% 67.63% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 380524 0.05% 67.68% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 497160573 67.63% 67.63% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 379945 0.05% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 67.68% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 142 0.00% 67.68% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 138 0.00% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::FloatMult 0 0.00% 67.68% # Type of FU issued @@ -224,137 +224,137 @@ system.cpu.iq.FU_type_0::SimdFloatMisc 3 0.00% 67.68% # Ty system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 67.68% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 67.68% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 170820646 23.23% 90.91% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 66889012 9.09% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 170682566 23.22% 90.90% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 66902031 9.10% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 735457773 # Type of FU issued -system.cpu.iq.rate 1.341103 # Inst issue rate -system.cpu.iq.fu_busy_cnt 9674933 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.013155 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 2026736140 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 1180706061 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 693772826 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 320 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 454 # Number of floating instruction queue writes +system.cpu.iq.FU_type_0::total 735125256 # Type of FU issued +system.cpu.iq.rate 1.340841 # Inst issue rate +system.cpu.iq.fu_busy_cnt 9642964 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.013117 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 2026015704 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 1179385447 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 693708754 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 312 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 466 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 16 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 745132544 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 162 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 8466293 # Number of loads that had data forwarded from stores +system.cpu.iq.int_alu_accesses 744768062 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 158 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 8478103 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 69605317 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 50613 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 61790 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 20382475 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 69568189 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 50872 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 61447 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 20367843 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 28472 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 334 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.rescheduledLoads 28247 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.cacheBlocked 358 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 49389867 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 2700739 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 121924 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 887765924 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 12225511 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 196378247 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 77986326 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 6083275 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 46564 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 7422 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 61790 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 18530018 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 5460534 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 23990552 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 711163338 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 161856987 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 24294435 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 49221141 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 2690580 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 121747 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 887104350 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 12434546 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 196341124 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 77971699 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 6076746 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 46013 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 7579 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 61447 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 18517236 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 5450893 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 23968129 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 710591708 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 161345852 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 24533548 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 9332564 # number of nop insts executed -system.cpu.iew.exec_refs 226770071 # number of memory reference insts executed -system.cpu.iew.exec_branches 147519559 # Number of branches executed -system.cpu.iew.exec_stores 64913084 # Number of stores executed -system.cpu.iew.exec_rate 1.296803 # Inst execution rate -system.cpu.iew.wb_sent 699318417 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 693772842 # cumulative count of insts written-back -system.cpu.iew.wb_producers 395045304 # num instructions producing a value -system.cpu.iew.wb_consumers 663504976 # num instructions consuming a value +system.cpu.iew.exec_nop 9333567 # number of nop insts executed +system.cpu.iew.exec_refs 226275553 # number of memory reference insts executed +system.cpu.iew.exec_branches 147479421 # Number of branches executed +system.cpu.iew.exec_stores 64929701 # Number of stores executed +system.cpu.iew.exec_rate 1.296093 # Inst execution rate +system.cpu.iew.wb_sent 699249012 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 693708770 # cumulative count of insts written-back +system.cpu.iew.wb_producers 395011112 # num instructions producing a value +system.cpu.iew.wb_consumers 663436791 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.265091 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.595392 # average fanout of values written-back +system.cpu.iew.wb_rate 1.265299 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.595401 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.commit.commitCommittedInsts 574685046 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 313100037 # The number of squashed insts skipped by commit -system.cpu.commit.commitNonSpecStalls 3878194 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 20503761 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 495219173 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.160466 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.863525 # Number of insts commited each cycle +system.cpu.commit.commitCommittedInsts 574685071 # The number of committed instructions +system.cpu.commit.commitSquashedInsts 312438031 # The number of squashed insts skipped by commit +system.cpu.commit.commitNonSpecStalls 3878199 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.branchMispredicts 20478103 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 495250570 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.160393 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.863970 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 259975062 52.50% 52.50% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 116222276 23.47% 75.97% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 44533135 8.99% 84.96% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 21295357 4.30% 89.26% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 19840150 4.01% 93.26% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 7283820 1.47% 94.74% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 7518006 1.52% 96.25% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 3788243 0.76% 97.02% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 14763124 2.98% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 259977309 52.49% 52.49% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 116342120 23.49% 75.99% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 44473265 8.98% 84.97% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 21252753 4.29% 89.26% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 19820819 4.00% 93.26% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 7387112 1.49% 94.75% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 7391590 1.49% 96.24% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 3775030 0.76% 97.01% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 14830572 2.99% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 495219173 # Number of insts commited each cycle -system.cpu.commit.count 574685046 # Number of instructions committed +system.cpu.commit.committed_per_cycle::total 495250570 # Number of insts commited each cycle +system.cpu.commit.count 574685071 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.refs 184376781 # Number of memory references committed -system.cpu.commit.loads 126772930 # Number of loads committed +system.cpu.commit.refs 184376791 # Number of memory references committed +system.cpu.commit.loads 126772935 # Number of loads committed system.cpu.commit.membars 1488542 # Number of memory barriers committed -system.cpu.commit.branches 120192115 # Number of branches committed +system.cpu.commit.branches 120192120 # Number of branches committed system.cpu.commit.fp_insts 16 # Number of committed floating point instructions. -system.cpu.commit.int_insts 473701197 # Number of committed integer instructions. +system.cpu.commit.int_insts 473701217 # Number of committed integer instructions. system.cpu.commit.function_calls 9757362 # Number of function calls committed. -system.cpu.commit.bw_lim_events 14763124 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 14830572 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 1368233994 # The number of ROB reads -system.cpu.rob.rob_writes 1825140894 # The number of ROB writes -system.cpu.timesIdled 96084 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 3788477 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.committedInsts 573341162 # Number of Instructions Simulated -system.cpu.committedInsts_total 573341162 # Number of Instructions Simulated -system.cpu.cpi 0.956494 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.956494 # CPI: Total CPI of All Threads -system.cpu.ipc 1.045485 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.045485 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 3291621496 # number of integer regfile reads -system.cpu.int_regfile_writes 815258640 # number of integer regfile writes +system.cpu.rob.rob_reads 1367535962 # The number of ROB reads +system.cpu.rob.rob_writes 1823647630 # The number of ROB writes +system.cpu.timesIdled 94158 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 3785113 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.committedInsts 573341187 # Number of Instructions Simulated +system.cpu.committedInsts_total 573341187 # Number of Instructions Simulated +system.cpu.cpi 0.956249 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.956249 # CPI: Total CPI of All Threads +system.cpu.ipc 1.045753 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.045753 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 3289345591 # number of integer regfile reads +system.cpu.int_regfile_writes 815117578 # number of integer regfile writes system.cpu.fp_regfile_reads 16 # number of floating regfile reads -system.cpu.misc_regfile_reads 1231509968 # number of misc regfile reads -system.cpu.misc_regfile_writes 4463832 # number of misc regfile writes -system.cpu.icache.replacements 12844 # number of replacements -system.cpu.icache.tagsinuse 1060.855578 # Cycle average of tags in use -system.cpu.icache.total_refs 141584558 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 14688 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 9639.471541 # Average number of references to valid blocks. +system.cpu.misc_regfile_reads 1230585750 # number of misc regfile reads +system.cpu.misc_regfile_writes 4463842 # number of misc regfile writes +system.cpu.icache.replacements 12883 # number of replacements +system.cpu.icache.tagsinuse 1062.179544 # Cycle average of tags in use +system.cpu.icache.total_refs 141602716 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 14723 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 9617.789581 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1060.855578 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.517996 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 141584561 # number of ReadReq hits -system.cpu.icache.demand_hits 141584561 # number of demand (read+write) hits -system.cpu.icache.overall_hits 141584561 # number of overall hits -system.cpu.icache.ReadReq_misses 16495 # number of ReadReq misses -system.cpu.icache.demand_misses 16495 # number of demand (read+write) misses -system.cpu.icache.overall_misses 16495 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 235861500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 235861500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 235861500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 141601056 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 141601056 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 141601056 # number of overall (read+write) accesses -system.cpu.icache.ReadReq_miss_rate 0.000116 # miss rate for ReadReq accesses -system.cpu.icache.demand_miss_rate 0.000116 # miss rate for demand accesses -system.cpu.icache.overall_miss_rate 0.000116 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 14298.969385 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 14298.969385 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 14298.969385 # average overall miss latency +system.cpu.icache.occ_blocks::0 1062.179544 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.518642 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 141602717 # number of ReadReq hits +system.cpu.icache.demand_hits 141602717 # number of demand (read+write) hits +system.cpu.icache.overall_hits 141602717 # number of overall hits +system.cpu.icache.ReadReq_misses 16509 # number of ReadReq misses +system.cpu.icache.demand_misses 16509 # number of demand (read+write) misses +system.cpu.icache.overall_misses 16509 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 235489500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 235489500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 235489500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 141619226 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 141619226 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 141619226 # number of overall (read+write) accesses +system.cpu.icache.ReadReq_miss_rate 0.000117 # miss rate for ReadReq accesses +system.cpu.icache.demand_miss_rate 0.000117 # miss rate for demand accesses +system.cpu.icache.overall_miss_rate 0.000117 # miss rate for overall accesses +system.cpu.icache.ReadReq_avg_miss_latency 14264.310376 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 14264.310376 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 14264.310376 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -364,145 +364,145 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 1 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 1651 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 1651 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 1651 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 14844 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 14844 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 14844 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 1646 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 1646 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 1646 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 14863 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 14863 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 14863 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 154845500 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 154845500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 154845500 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 154537000 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 154537000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 154537000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000105 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000105 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000105 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 10431.521153 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 10431.521153 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 10431.521153 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 10397.429859 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 10397.429859 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 10397.429859 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 1212341 # number of replacements -system.cpu.dcache.tagsinuse 4058.230538 # Cycle average of tags in use -system.cpu.dcache.total_refs 204314278 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 1216437 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 167.961249 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 5623770000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4058.230538 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.990779 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 146820758 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 52766592 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 2494784 # number of LoadLockedReq hits -system.cpu.dcache.StoreCondReq_hits 2231915 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 199587350 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 199587350 # number of overall hits -system.cpu.dcache.ReadReq_misses 1243424 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 1472714 # number of WriteReq misses -system.cpu.dcache.LoadLockedReq_misses 59 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 2716138 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 2716138 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 14347379500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 25015184497 # number of WriteReq miss cycles -system.cpu.dcache.LoadLockedReq_miss_latency 557000 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 39362563997 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 39362563997 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 148064182 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.replacements 1212291 # number of replacements +system.cpu.dcache.tagsinuse 4058.220860 # Cycle average of tags in use +system.cpu.dcache.total_refs 203801196 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 1216387 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 167.546345 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 5623769000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4058.220860 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.990777 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 146308743 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 52772298 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 2488014 # number of LoadLockedReq hits +system.cpu.dcache.StoreCondReq_hits 2231920 # number of StoreCondReq hits +system.cpu.dcache.demand_hits 199081041 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 199081041 # number of overall hits +system.cpu.dcache.ReadReq_misses 1241922 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 1467008 # number of WriteReq misses +system.cpu.dcache.LoadLockedReq_misses 55 # number of LoadLockedReq misses +system.cpu.dcache.demand_misses 2708930 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 2708930 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 14257023500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 24962643993 # number of WriteReq miss cycles +system.cpu.dcache.LoadLockedReq_miss_latency 523000 # number of LoadLockedReq miss cycles +system.cpu.dcache.demand_miss_latency 39219667493 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 39219667493 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 147550665 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 54239306 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 2494843 # number of LoadLockedReq accesses(hits+misses) -system.cpu.dcache.StoreCondReq_accesses 2231915 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 202303488 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 202303488 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.008398 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.027152 # miss rate for WriteReq accesses -system.cpu.dcache.LoadLockedReq_miss_rate 0.000024 # miss rate for LoadLockedReq accesses -system.cpu.dcache.demand_miss_rate 0.013426 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.013426 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 11538.605898 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 16985.772185 # average WriteReq miss latency -system.cpu.dcache.LoadLockedReq_avg_miss_latency 9440.677966 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 14492.107543 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 14492.107543 # average overall miss latency +system.cpu.dcache.LoadLockedReq_accesses 2488069 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.StoreCondReq_accesses 2231920 # number of StoreCondReq accesses(hits+misses) +system.cpu.dcache.demand_accesses 201789971 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 201789971 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.008417 # miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.027047 # miss rate for WriteReq accesses +system.cpu.dcache.LoadLockedReq_miss_rate 0.000022 # miss rate for LoadLockedReq accesses +system.cpu.dcache.demand_miss_rate 0.013425 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.013425 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 11479.805898 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 17016.024448 # average WriteReq miss latency +system.cpu.dcache.LoadLockedReq_avg_miss_latency 9509.090909 # average LoadLockedReq miss latency +system.cpu.dcache.demand_avg_miss_latency 14477.918401 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 14477.918401 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles::no_targets 502000 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles::no_targets 484000 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked -system.cpu.dcache.blocked::no_targets 64 # number of cycles access was blocked +system.cpu.dcache.blocked::no_targets 61 # number of cycles access was blocked system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles::no_targets 7843.750000 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles::no_targets 7934.426230 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 1079461 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 367349 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 1132203 # number of WriteReq MSHR hits -system.cpu.dcache.LoadLockedReq_mshr_hits 59 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 1499552 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 1499552 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 876075 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 340511 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 1216586 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 1216586 # number of overall MSHR misses +system.cpu.dcache.writebacks 1079423 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 365990 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 1126420 # number of WriteReq MSHR hits +system.cpu.dcache.LoadLockedReq_mshr_hits 55 # number of LoadLockedReq MSHR hits +system.cpu.dcache.demand_mshr_hits 1492410 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 1492410 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 875932 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 340588 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 1216520 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 1216520 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 6316165000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 4359865500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 10676030500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 10676030500 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 6305474000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 4364186500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 10669660500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 10669660500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.005917 # mshr miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_mshr_miss_rate 0.006278 # mshr miss rate for WriteReq accesses -system.cpu.dcache.demand_mshr_miss_rate 0.006014 # mshr miss rate for demand accesses -system.cpu.dcache.overall_mshr_miss_rate 0.006014 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 7209.616757 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 12803.890330 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 8775.401410 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 8775.401410 # average overall mshr miss latency +system.cpu.dcache.ReadReq_mshr_miss_rate 0.005936 # mshr miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.006279 # mshr miss rate for WriteReq accesses +system.cpu.dcache.demand_mshr_miss_rate 0.006029 # mshr miss rate for demand accesses +system.cpu.dcache.overall_mshr_miss_rate 0.006029 # mshr miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 7198.588475 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 12813.682514 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 8770.641255 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 8770.641255 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 219133 # number of replacements -system.cpu.l2cache.tagsinuse 21061.116186 # Cycle average of tags in use -system.cpu.l2cache.total_refs 1567440 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 239478 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 6.545236 # Average number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 204357736000 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 7517.812526 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 13543.303660 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.229425 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.413309 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 760340 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 1079462 # number of Writeback hits -system.cpu.l2cache.UpgradeReq_hits 116 # number of UpgradeReq hits -system.cpu.l2cache.ReadExReq_hits 232507 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 992847 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 992847 # number of overall hits -system.cpu.l2cache.ReadReq_misses 130056 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 33 # number of UpgradeReq misses -system.cpu.l2cache.ReadExReq_misses 108226 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 238282 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 238282 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 4448635000 # number of ReadReq miss cycles -system.cpu.l2cache.UpgradeReq_miss_latency 68000 # number of UpgradeReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 3706374500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 8155009500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 8155009500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 890396 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 1079462 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 149 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 340733 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 1231129 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 1231129 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.146065 # miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_miss_rate 0.221477 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.317627 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.193548 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.193548 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34205.534539 # average ReadReq miss latency -system.cpu.l2cache.UpgradeReq_avg_miss_latency 2060.606061 # average UpgradeReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34246.618188 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34224.194442 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34224.194442 # average overall miss latency +system.cpu.l2cache.replacements 218982 # number of replacements +system.cpu.l2cache.tagsinuse 21063.326998 # Cycle average of tags in use +system.cpu.l2cache.total_refs 1568375 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 239342 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 6.552862 # Average number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 204310095000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.occ_blocks::0 7519.880092 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 13543.446906 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.229489 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.413313 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 760536 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 1079424 # number of Writeback hits +system.cpu.l2cache.UpgradeReq_hits 96 # number of UpgradeReq hits +system.cpu.l2cache.ReadExReq_hits 232415 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 992951 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 992951 # number of overall hits +system.cpu.l2cache.ReadReq_misses 129729 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 35 # number of UpgradeReq misses +system.cpu.l2cache.ReadExReq_misses 108423 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 238152 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 238152 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 4437312000 # number of ReadReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_latency 171500 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 3713377000 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 8150689000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 8150689000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 890265 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 1079424 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 131 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 340838 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 1231103 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 1231103 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.145720 # miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_miss_rate 0.267176 # miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.318107 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.193446 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.193446 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34204.472400 # average ReadReq miss latency +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4900 # average UpgradeReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34248.978538 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34224.734623 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34224.734623 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -511,32 +511,32 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 171253 # number of writebacks -system.cpu.l2cache.ReadReq_mshr_hits 19 # number of ReadReq MSHR hits -system.cpu.l2cache.demand_mshr_hits 19 # number of demand (read+write) MSHR hits -system.cpu.l2cache.overall_mshr_hits 19 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 130037 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 33 # number of UpgradeReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 108226 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 238263 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 238263 # number of overall MSHR misses +system.cpu.l2cache.writebacks 171245 # number of writebacks +system.cpu.l2cache.ReadReq_mshr_hits 22 # number of ReadReq MSHR hits +system.cpu.l2cache.demand_mshr_hits 22 # number of demand (read+write) MSHR hits +system.cpu.l2cache.overall_mshr_hits 22 # number of overall MSHR hits +system.cpu.l2cache.ReadReq_mshr_misses 129707 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 35 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 108423 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 238130 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 238130 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4037689500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 1023000 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 3355622000 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 7393311500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 7393311500 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 4027357500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 1085000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 3362010000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 7389367500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 7389367500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.146044 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.221477 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.317627 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.193532 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.193532 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31050.312603 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.145695 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.267176 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.318107 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.193428 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.193428 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31049.654221 # average ReadReq mshr miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000 # average UpgradeReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31005.691793 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31030.044531 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31030.044531 # average overall mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31008.273152 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31030.813001 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31030.813001 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/20.parser/ref/x86/linux/o3-timing/config.ini b/tests/long/se/20.parser/ref/x86/linux/o3-timing/config.ini index 50d3ef009..8f133335a 100644 --- a/tests/long/se/20.parser/ref/x86/linux/o3-timing/config.ini +++ b/tests/long/se/20.parser/ref/x86/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -89,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -149,7 +159,14 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=X86TLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -446,9 +463,25 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=X86LocalApic +int_latency=1000 +pio_addr=2305843009213693952 +pio_latency=1000 +system=system +int_port=system.membus.port[4] +pio=system.membus.port[3] + [system.cpu.itb] type=X86TLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -479,7 +512,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -490,7 +523,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -498,7 +531,7 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=parser 2.1.dict -batch -cwd=build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing +cwd=build/X86/tests/opt/long/se/20.parser/x86/linux/o3-timing egid=100 env= errout=cerr @@ -522,7 +555,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side +port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side system.cpu.interrupts.pio system.cpu.interrupts.int_port [system.physmem] type=PhysicalMemory diff --git a/tests/long/se/20.parser/ref/x86/linux/o3-timing/simout b/tests/long/se/20.parser/ref/x86/linux/o3-timing/simout index b3bd7cb12..1d5281a91 100755 --- a/tests/long/se/20.parser/ref/x86/linux/o3-timing/simout +++ b/tests/long/se/20.parser/ref/x86/linux/o3-timing/simout @@ -1,12 +1,12 @@ -Redirecting stdout to build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing/simout -Redirecting stderr to build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing/simerr +Redirecting stdout to build/X86/tests/opt/long/se/20.parser/x86/linux/o3-timing/simout +Redirecting stderr to build/X86/tests/opt/long/se/20.parser/x86/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 28 2012 12:11:40 -gem5 started Jan 28 2012 12:12:44 +gem5 compiled Feb 9 2012 12:45:55 +gem5 started Feb 9 2012 12:46:40 gem5 executing on ribera.cs.wisc.edu -command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing +command line: build/X86/gem5.opt -d build/X86/tests/opt/long/se/20.parser/x86/linux/o3-timing -re tests/run.py build/X86/tests/opt/long/se/20.parser/x86/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -71,4 +71,4 @@ info: Increasing stack size by one page. about 2 million people attended the five best costumes got prizes No errors! -Exiting @ tick 488997764000 because target called exit() +Exiting @ tick 488026375000 because target called exit() diff --git a/tests/long/se/20.parser/ref/x86/linux/o3-timing/stats.txt b/tests/long/se/20.parser/ref/x86/linux/o3-timing/stats.txt index f99849c12..6f075b675 100644 --- a/tests/long/se/20.parser/ref/x86/linux/o3-timing/stats.txt +++ b/tests/long/se/20.parser/ref/x86/linux/o3-timing/stats.txt @@ -1,263 +1,264 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.488998 # Number of seconds simulated -sim_ticks 488997764000 # Number of ticks simulated -final_tick 488997764000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.488026 # Number of seconds simulated +sim_ticks 488026375000 # Number of ticks simulated +final_tick 488026375000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 107684 # Simulator instruction rate (inst/s) -host_tick_rate 34439407 # Simulator tick rate (ticks/s) -host_mem_usage 280760 # Number of bytes of host memory used -host_seconds 14198.79 # Real time elapsed on the host +host_inst_rate 87795 # Simulator instruction rate (inst/s) +host_tick_rate 28022613 # Simulator tick rate (ticks/s) +host_mem_usage 289796 # Number of bytes of host memory used +host_seconds 17415.45 # Real time elapsed on the host sim_insts 1528988756 # Number of instructions simulated -system.physmem.bytes_read 37533312 # Number of bytes read from this memory -system.physmem.bytes_inst_read 347328 # Number of instructions bytes read from this memory -system.physmem.bytes_written 26337408 # Number of bytes written to this memory -system.physmem.num_reads 586458 # Number of read requests responded to by this memory -system.physmem.num_writes 411522 # Number of write requests responded to by this memory +system.physmem.bytes_read 37539712 # Number of bytes read from this memory +system.physmem.bytes_inst_read 347136 # Number of instructions bytes read from this memory +system.physmem.bytes_written 26338560 # Number of bytes written to this memory +system.physmem.num_reads 586558 # Number of read requests responded to by this memory +system.physmem.num_writes 411540 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 76755590 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 710285 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 53859976 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 130615567 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 76921482 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 711306 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 53969542 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 130891024 # Total bandwidth to/from this memory (bytes/s) system.cpu.workload.num_syscalls 551 # Number of system calls -system.cpu.numCycles 977995529 # number of cpu cycles simulated +system.cpu.numCycles 976052751 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 244993586 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 244993586 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 16602389 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 235528185 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 217667296 # Number of BTB hits +system.cpu.BPredUnit.lookups 244909233 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 244909233 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 16551670 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 235577670 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 217623896 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 204934624 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 1339258211 # Number of instructions fetch has processed -system.cpu.fetch.Branches 244993586 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 217667296 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 435322465 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 118846275 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 217468055 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 30116 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 232804 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 194158401 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 4161421 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 959969834 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.603022 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.318234 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.icacheStallCycles 203635164 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 1335786629 # Number of instructions fetch has processed +system.cpu.fetch.Branches 244909233 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 217623896 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 434745893 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 118311552 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 217882141 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 29891 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 232496 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 193900404 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 4295951 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 958022628 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.604337 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.317097 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 528643490 55.07% 55.07% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 32333608 3.37% 58.44% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 38757249 4.04% 62.47% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 32421466 3.38% 65.85% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 21788164 2.27% 68.12% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 36314533 3.78% 71.90% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 48923013 5.10% 77.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 36860126 3.84% 80.84% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 183928185 19.16% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 527271952 55.04% 55.04% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 32005205 3.34% 58.38% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 38652146 4.03% 62.41% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 32799855 3.42% 65.84% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 21637734 2.26% 68.10% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 36320351 3.79% 71.89% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 49291435 5.15% 77.03% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 36948107 3.86% 80.89% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 183095843 19.11% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 959969834 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.250506 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.369391 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 264672814 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 172740484 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 371802947 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 48771819 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 101981770 # Number of cycles decode is squashing -system.cpu.decode.DecodedInsts 2436948242 # Number of instructions handled by decode -system.cpu.rename.SquashCycles 101981770 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 302199214 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 38454889 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 15108 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 381795429 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 135523424 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 2384665027 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 2593 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 22692453 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 94335239 # Number of times rename has blocked due to LSQ full -system.cpu.rename.FullRegisterEvents 23 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 2218279276 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 5608704737 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 5608168752 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 535985 # Number of floating rename lookups +system.cpu.fetch.rateDist::total 958022628 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.250918 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.368560 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 263275556 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 173167084 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 371540300 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 48542645 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 101497043 # Number of cycles decode is squashing +system.cpu.decode.DecodedInsts 2434504159 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 2 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 101497043 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 300930740 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 38821666 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 14830 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 381234584 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 135523765 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 2382098494 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 2610 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 23187923 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 93850518 # Number of times rename has blocked due to LSQ full +system.cpu.rename.FullRegisterEvents 43 # Number of times there has been no free registers +system.cpu.rename.RenamedOperands 2215803805 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 5602953970 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 5602704256 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 249714 # Number of floating rename lookups system.cpu.rename.CommittedMaps 1427299027 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 790980249 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 1421 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 1399 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 314817660 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 575520947 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 225733737 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 224565693 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 66120103 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 2277627469 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 14301 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 1920324328 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 1300872 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 746152360 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 1169098860 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 13748 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 959969834 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 2.000401 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.810923 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 788504778 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 1440 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 1415 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 315035024 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 575221657 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 225407627 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 224840659 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 66447324 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 2274732306 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 12754 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 1918512611 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 1302000 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 743201845 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 1165991477 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 12201 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 958022628 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 2.002575 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.809760 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 279838383 29.15% 29.15% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 159390008 16.60% 45.75% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 161109543 16.78% 62.54% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 151059392 15.74% 78.27% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 108561364 11.31% 89.58% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 60361287 6.29% 95.87% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 29161241 3.04% 98.91% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 9391207 0.98% 99.89% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 1097409 0.11% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 277706841 28.99% 28.99% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 160285139 16.73% 45.72% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 161386173 16.85% 62.56% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 150309706 15.69% 78.25% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 108022954 11.28% 89.53% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 60994203 6.37% 95.90% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 28856033 3.01% 98.91% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 9365653 0.98% 99.89% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 1095926 0.11% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 959969834 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 958022628 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 2254063 14.63% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 14.63% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 10153281 65.89% 80.52% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 3001149 19.48% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 2261253 14.71% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 14.71% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 10108961 65.75% 80.46% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 3003496 19.54% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available -system.cpu.iq.FU_type_0::No_OpClass 2493580 0.13% 0.13% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 1273165358 66.30% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::IntDiv 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatMult 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMult 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShift 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 66.43% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 463198530 24.12% 90.55% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 181466860 9.45% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::No_OpClass 2434143 0.13% 0.13% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 1271908482 66.30% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::IntDiv 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatMult 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMult 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShift 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 66.42% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 462991606 24.13% 90.56% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 181178380 9.44% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 1920324328 # Type of FU issued -system.cpu.iq.rate 1.963531 # Inst issue rate -system.cpu.iq.fu_busy_cnt 15408493 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.008024 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 4817321768 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 3023912415 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 1872800388 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 6087 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 152738 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 154 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 1933237228 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 2013 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 171308750 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 1918512611 # Type of FU issued +system.cpu.iq.rate 1.965583 # Inst issue rate +system.cpu.iq.fu_busy_cnt 15373710 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.008013 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 4811718392 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 3018136915 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 1871298739 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 5168 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 82228 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 119 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 1931450456 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 1722 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 171083363 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 191418787 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 428547 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 281164 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 76573878 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 191119497 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 436651 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 282394 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 76247769 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 6486 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 8 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.rescheduledLoads 6215 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.cacheBlocked 5 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 101981770 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 7663639 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 1191899 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 2277641770 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 1232812 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 575520947 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 225734063 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 6109 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 836752 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 17253 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 281164 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 15662112 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 2402353 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 18064465 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 1886684972 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 454230068 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 33639356 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 101497043 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 7669372 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 1230820 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 2274745060 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 1222472 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 575221657 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 225407954 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 6105 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 878634 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 17249 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 282394 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 15676996 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 2334571 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 18011567 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 1885150488 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 454035777 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 33362123 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 0 # number of nop insts executed -system.cpu.iew.exec_refs 628354292 # number of memory reference insts executed -system.cpu.iew.exec_branches 176563619 # Number of branches executed -system.cpu.iew.exec_stores 174124224 # Number of stores executed -system.cpu.iew.exec_rate 1.929135 # Inst execution rate -system.cpu.iew.wb_sent 1880378728 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 1872800542 # cumulative count of insts written-back -system.cpu.iew.wb_producers 1438142804 # num instructions producing a value -system.cpu.iew.wb_consumers 2128029574 # num instructions consuming a value +system.cpu.iew.exec_refs 627868559 # number of memory reference insts executed +system.cpu.iew.exec_branches 176458351 # Number of branches executed +system.cpu.iew.exec_stores 173832782 # Number of stores executed +system.cpu.iew.exec_rate 1.931402 # Inst execution rate +system.cpu.iew.wb_sent 1879040223 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 1871298858 # cumulative count of insts written-back +system.cpu.iew.wb_producers 1436941600 # num instructions producing a value +system.cpu.iew.wb_consumers 2126368380 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.914938 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.675810 # average fanout of values written-back +system.cpu.iew.wb_rate 1.917211 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.675773 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 1528988756 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 748676946 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 745779287 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 553 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 16628282 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 857988064 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.782063 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.285478 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 16577287 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 856525585 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.785106 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.285139 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 333514129 38.87% 38.87% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 211603589 24.66% 63.53% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 76333139 8.90% 72.43% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 92892872 10.83% 83.26% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 33741100 3.93% 87.19% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 28402540 3.31% 90.50% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 15787299 1.84% 92.34% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 11367789 1.32% 93.67% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 54345607 6.33% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 331592690 38.71% 38.71% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 211839945 24.73% 63.45% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 76804588 8.97% 72.41% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 92775414 10.83% 83.24% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 33678704 3.93% 87.18% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 28505123 3.33% 90.50% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 15688691 1.83% 92.34% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 11282624 1.32% 93.65% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 54357806 6.35% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 857988064 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 856525585 # Number of insts commited each cycle system.cpu.commit.count 1528988756 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 533262345 # Number of memory references committed @@ -267,48 +268,48 @@ system.cpu.commit.branches 149758588 # Nu system.cpu.commit.fp_insts 0 # Number of committed floating point instructions. system.cpu.commit.int_insts 1528317614 # Number of committed integer instructions. system.cpu.commit.function_calls 0 # Number of function calls committed. -system.cpu.commit.bw_lim_events 54345607 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 54357806 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 3081308159 # The number of ROB reads -system.cpu.rob.rob_writes 4657476889 # The number of ROB writes -system.cpu.timesIdled 418960 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 18025695 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 3076935822 # The number of ROB reads +system.cpu.rob.rob_writes 4651204201 # The number of ROB writes +system.cpu.timesIdled 418807 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 18030123 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 1528988756 # Number of Instructions Simulated system.cpu.committedInsts_total 1528988756 # Number of Instructions Simulated -system.cpu.cpi 0.639636 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.639636 # CPI: Total CPI of All Threads -system.cpu.ipc 1.563390 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.563390 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 3178059548 # number of integer regfile reads -system.cpu.int_regfile_writes 1743141344 # number of integer regfile writes -system.cpu.fp_regfile_reads 155 # number of floating regfile reads -system.cpu.misc_regfile_reads 1037170422 # number of misc regfile reads -system.cpu.icache.replacements 10067 # number of replacements -system.cpu.icache.tagsinuse 971.911936 # Cycle average of tags in use -system.cpu.icache.total_refs 193916703 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 11565 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 16767.548898 # Average number of references to valid blocks. +system.cpu.cpi 0.638365 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.638365 # CPI: Total CPI of All Threads +system.cpu.ipc 1.566502 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.566502 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 3175693593 # number of integer regfile reads +system.cpu.int_regfile_writes 1742205758 # number of integer regfile writes +system.cpu.fp_regfile_reads 120 # number of floating regfile reads +system.cpu.misc_regfile_reads 1036377940 # number of misc regfile reads +system.cpu.icache.replacements 10111 # number of replacements +system.cpu.icache.tagsinuse 973.820201 # Cycle average of tags in use +system.cpu.icache.total_refs 193659156 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 11601 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 16693.315749 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 971.911936 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.474566 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 193923334 # number of ReadReq hits -system.cpu.icache.demand_hits 193923334 # number of demand (read+write) hits -system.cpu.icache.overall_hits 193923334 # number of overall hits -system.cpu.icache.ReadReq_misses 235067 # number of ReadReq misses -system.cpu.icache.demand_misses 235067 # number of demand (read+write) misses -system.cpu.icache.overall_misses 235067 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 1701123000 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 1701123000 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 1701123000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 194158401 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 194158401 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 194158401 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 973.820201 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.475498 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 193665655 # number of ReadReq hits +system.cpu.icache.demand_hits 193665655 # number of demand (read+write) hits +system.cpu.icache.overall_hits 193665655 # number of overall hits +system.cpu.icache.ReadReq_misses 234749 # number of ReadReq misses +system.cpu.icache.demand_misses 234749 # number of demand (read+write) misses +system.cpu.icache.overall_misses 234749 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 1699920500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 1699920500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 1699920500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 193900404 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 193900404 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 193900404 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.001211 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.001211 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.001211 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 7236.758031 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 7236.758031 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 7236.758031 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 7241.438728 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 7241.438728 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 7241.438728 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -317,60 +318,60 @@ system.cpu.icache.avg_blocked_cycles::no_mshrs no_value system.cpu.icache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.writebacks 8 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 2036 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 2036 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 2036 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 233031 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 233031 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 233031 # number of overall MSHR misses +system.cpu.icache.writebacks 4 # number of writebacks +system.cpu.icache.ReadReq_mshr_hits 2040 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 2040 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 2040 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 232709 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 232709 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 232709 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 952412000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 952412000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 952412000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 952455000 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 952455000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 952455000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.001200 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.001200 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.001200 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4087.061378 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4087.061378 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4087.061378 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4092.901435 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4092.901435 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4092.901435 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 2529213 # number of replacements -system.cpu.dcache.tagsinuse 4087.436678 # Cycle average of tags in use -system.cpu.dcache.total_refs 427576950 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 2533309 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 168.781996 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 2167021000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4087.436678 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.997909 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 278854362 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 148163093 # number of WriteReq hits -system.cpu.dcache.demand_hits 427017455 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 427017455 # number of overall hits -system.cpu.dcache.ReadReq_misses 2666620 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 997108 # number of WriteReq misses -system.cpu.dcache.demand_misses 3663728 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 3663728 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 39487606500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 20600704500 # number of WriteReq miss cycles -system.cpu.dcache.demand_miss_latency 60088311000 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 60088311000 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 281520982 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.replacements 2529316 # number of replacements +system.cpu.dcache.tagsinuse 4087.520068 # Cycle average of tags in use +system.cpu.dcache.total_refs 427611101 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 2533412 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 168.788614 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 2115074000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4087.520068 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.997930 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 278887188 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 148162157 # number of WriteReq hits +system.cpu.dcache.demand_hits 427049345 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 427049345 # number of overall hits +system.cpu.dcache.ReadReq_misses 2665882 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 998044 # number of WriteReq misses +system.cpu.dcache.demand_misses 3663926 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 3663926 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 39487902000 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 20586128000 # number of WriteReq miss cycles +system.cpu.dcache.demand_miss_latency 60074030000 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 60074030000 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 281553070 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 149160201 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 430681183 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 430681183 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.009472 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.006685 # miss rate for WriteReq accesses +system.cpu.dcache.demand_accesses 430713271 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 430713271 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.009468 # miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.006691 # miss rate for WriteReq accesses system.cpu.dcache.demand_miss_rate 0.008507 # miss rate for demand accesses system.cpu.dcache.overall_miss_rate 0.008507 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 14808.111579 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 20660.454535 # average WriteReq miss latency -system.cpu.dcache.demand_avg_miss_latency 16400.865730 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 16400.865730 # average overall miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 14812.321776 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 20626.473382 # average WriteReq miss latency +system.cpu.dcache.demand_avg_miss_latency 16396.081689 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 16396.081689 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -379,75 +380,75 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 2229973 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 903774 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 5204 # number of WriteReq MSHR hits -system.cpu.dcache.demand_mshr_hits 908978 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 908978 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 1762846 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 991904 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 2754750 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 2754750 # number of overall MSHR misses +system.cpu.dcache.writebacks 2229932 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 902993 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 6453 # number of WriteReq MSHR hits +system.cpu.dcache.demand_mshr_hits 909446 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 909446 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 1762889 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 991591 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 2754480 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 2754480 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 14963544500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 17553990000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 32517534500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 32517534500 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 14966916500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 17535799000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 32502715500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 32502715500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.006262 # mshr miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_mshr_miss_rate 0.006650 # mshr miss rate for WriteReq accesses -system.cpu.dcache.demand_mshr_miss_rate 0.006396 # mshr miss rate for demand accesses -system.cpu.dcache.overall_mshr_miss_rate 0.006396 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 8488.287973 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17697.267074 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 11804.168981 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 11804.168981 # average overall mshr miss latency +system.cpu.dcache.ReadReq_mshr_miss_rate 0.006261 # mshr miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.006648 # mshr miss rate for WriteReq accesses +system.cpu.dcache.demand_mshr_miss_rate 0.006395 # mshr miss rate for demand accesses +system.cpu.dcache.overall_mshr_miss_rate 0.006395 # mshr miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 8489.993698 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 17684.508028 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 11799.946088 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 11799.946088 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 575697 # number of replacements -system.cpu.l2cache.tagsinuse 21610.714484 # Cycle average of tags in use -system.cpu.l2cache.total_refs 3195541 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 594856 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 5.371957 # Average number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 269628029000 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 7828.943593 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 13781.770891 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.238920 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.420586 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 1434292 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 2229981 # number of Writeback hits -system.cpu.l2cache.UpgradeReq_hits 1300 # number of UpgradeReq hits -system.cpu.l2cache.ReadExReq_hits 523974 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 1958266 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 1958266 # number of overall hits -system.cpu.l2cache.ReadReq_misses 339366 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 220134 # number of UpgradeReq misses -system.cpu.l2cache.ReadExReq_misses 247116 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 586482 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 586482 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 11591670000 # number of ReadReq miss cycles -system.cpu.l2cache.UpgradeReq_miss_latency 9750500 # number of UpgradeReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 8467686500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 20059356500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 20059356500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 1773658 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 2229981 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 221434 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 771090 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 2544748 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 2544748 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.191337 # miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_miss_rate 0.994129 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.320476 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.230468 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.230468 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34156.839518 # average ReadReq miss latency -system.cpu.l2cache.UpgradeReq_avg_miss_latency 44.293476 # average UpgradeReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34266.039026 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34202.851068 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34202.851068 # average overall miss latency +system.cpu.l2cache.replacements 575774 # number of replacements +system.cpu.l2cache.tagsinuse 21621.732877 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3195554 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 594946 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 5.371166 # Average number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 268816776000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.occ_blocks::0 7838.250700 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 13783.482177 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.239204 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.420638 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 1434280 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 2229936 # number of Writeback hits +system.cpu.l2cache.UpgradeReq_hits 1289 # number of UpgradeReq hits +system.cpu.l2cache.ReadExReq_hits 524029 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 1958309 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 1958309 # number of overall hits +system.cpu.l2cache.ReadReq_misses 339456 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 219771 # number of UpgradeReq misses +system.cpu.l2cache.ReadExReq_misses 247125 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 586581 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 586581 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 11594725000 # number of ReadReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_latency 9650000 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 8467808500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 20062533500 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 20062533500 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 1773736 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 2229936 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 221060 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 771154 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 2544890 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 2544890 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.191379 # miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_miss_rate 0.994169 # miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.320461 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.230494 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.230494 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34156.783206 # average ReadReq miss latency +system.cpu.l2cache.UpgradeReq_avg_miss_latency 43.909342 # average UpgradeReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34265.284775 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34202.494626 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34202.494626 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -456,31 +457,31 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 411522 # number of writebacks +system.cpu.l2cache.writebacks 411540 # number of writebacks system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 339366 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 220134 # number of UpgradeReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 247116 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 586482 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 586482 # number of overall MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 339456 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 219771 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 247125 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 586581 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 586581 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 10527298500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 6824577500 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 7661565500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 18188864000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 18188864000 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 10530013500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 6813351000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 7661828500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 18191842000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 18191842000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.191337 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.994129 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.320476 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.230468 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.230468 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31020.486731 # average ReadReq mshr miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31001.923828 # average UpgradeReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31003.923259 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31013.507661 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31013.507661 # average overall mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.191379 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.994169 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.320461 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.230494 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.230494 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31020.260358 # average ReadReq mshr miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31002.047586 # average UpgradeReq mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31003.858371 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31013.350245 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31013.350245 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/30.eon/ref/arm/linux/o3-timing/config.ini b/tests/long/se/30.eon/ref/arm/linux/o3-timing/config.ini index 297538e80..46adc802e 100644 --- a/tests/long/se/30.eon/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/30.eon/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=eon chair.control.cook chair.camera chair.surfaces chair.cook.ppm ppm pixels_out.cook -cwd=build/ARM_SE/tests/opt/long/30.eon/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/30.eon/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/eon +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/eon gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/30.eon/ref/arm/linux/o3-timing/simout b/tests/long/se/30.eon/ref/arm/linux/o3-timing/simout index 2948fc7c4..df63c01b7 100755 --- a/tests/long/se/30.eon/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/30.eon/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/30.eon/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/30.eon/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 08:57:55 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/30.eon/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/30.eon/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:22 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/30.eon/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/30.eon/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. @@ -13,4 +15,4 @@ info: Increasing stack size by one page. info: Increasing stack size by one page. info: Increasing stack size by one page. OO-style eon Time= 0.100000 -Exiting @ tick 104497559500 because target called exit() +Exiting @ tick 104492506500 because target called exit() diff --git a/tests/long/se/30.eon/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/30.eon/ref/arm/linux/o3-timing/stats.txt index 995432cc7..44e129451 100644 --- a/tests/long/se/30.eon/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/30.eon/ref/arm/linux/o3-timing/stats.txt @@ -1,23 +1,23 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.104498 # Number of seconds simulated -sim_ticks 104497559500 # Number of ticks simulated -final_tick 104497559500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.104493 # Number of seconds simulated +sim_ticks 104492506500 # Number of ticks simulated +final_tick 104492506500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 155883 # Simulator instruction rate (inst/s) -host_tick_rate 46665641 # Simulator tick rate (ticks/s) -host_mem_usage 228988 # Number of bytes of host memory used -host_seconds 2239.28 # Real time elapsed on the host +host_inst_rate 80425 # Simulator instruction rate (inst/s) +host_tick_rate 24075162 # Simulator tick rate (ticks/s) +host_mem_usage 264476 # Number of bytes of host memory used +host_seconds 4340.26 # Real time elapsed on the host sim_insts 349066034 # Number of instructions simulated -system.physmem.bytes_read 464512 # Number of bytes read from this memory -system.physmem.bytes_inst_read 192704 # Number of instructions bytes read from this memory +system.physmem.bytes_read 464000 # Number of bytes read from this memory +system.physmem.bytes_inst_read 192512 # Number of instructions bytes read from this memory system.physmem.bytes_written 0 # Number of bytes written to this memory -system.physmem.num_reads 7258 # Number of read requests responded to by this memory +system.physmem.num_reads 7250 # Number of read requests responded to by this memory system.physmem.num_writes 0 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 4445195 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 1844100 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_total 4445195 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 4440510 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 1842352 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_total 4440510 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -61,105 +61,105 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 191 # Number of system calls -system.cpu.numCycles 208995120 # number of cpu cycles simulated +system.cpu.numCycles 208985014 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 38326507 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 21101495 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 3258977 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 27386254 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 21276883 # Number of BTB hits +system.cpu.BPredUnit.lookups 38314474 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 21092938 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 3256966 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 27298627 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 21213565 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 7682399 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 61114 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 43645867 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 338408122 # Number of instructions fetch has processed -system.cpu.fetch.Branches 38326507 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 28959282 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 79027162 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 10989913 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 78526305 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 5 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 81 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 41243030 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 908340 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 208882385 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.119969 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.192320 # Number of instructions fetched each cycle (Total) +system.cpu.BPredUnit.usedRAS 7683795 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 61136 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 43642080 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 338343690 # Number of instructions fetch has processed +system.cpu.fetch.Branches 38314474 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 28897360 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 78995706 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 10989579 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 78549841 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 4 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 92 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 41237520 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 904571 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 208872334 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.119807 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.192773 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 130507129 62.48% 62.48% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 9423807 4.51% 66.99% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 6028759 2.89% 69.88% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 6771553 3.24% 73.12% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 5439017 2.60% 75.72% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 4859666 2.33% 78.05% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 3802857 1.82% 79.87% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 4240079 2.03% 81.90% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 37809518 18.10% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 130527843 62.49% 62.49% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 9429667 4.51% 67.01% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 6020154 2.88% 69.89% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 6750748 3.23% 73.12% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 5430125 2.60% 75.72% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 4858478 2.33% 78.05% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 3783272 1.81% 79.86% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 4242115 2.03% 81.89% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 37829932 18.11% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 208882385 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.183385 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.619215 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 51208963 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 73647751 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 72596931 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 3816657 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 7612083 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 7463930 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 71162 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 431701457 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 197547 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 7612083 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 58859623 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 1188483 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 57604104 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 68958235 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 14659857 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 416634975 # Number of instructions processed by rename +system.cpu.fetch.rateDist::total 208872334 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.183336 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.618985 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 51215510 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 73658589 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 72565491 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 3819053 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 7613691 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 7463255 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 71181 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 431647720 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 198442 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 7613691 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 58863443 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 1188654 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 57607169 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 68932187 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 14667190 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 416637973 # Number of instructions processed by rename system.cpu.rename.IQFullEvents 21102 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 8024802 # Number of times rename has blocked due to LSQ full +system.cpu.rename.LSQFullEvents 8032684 # Number of times rename has blocked due to LSQ full system.cpu.rename.FullRegisterEvents 88 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 455431964 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 2446622850 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 1351809132 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 1094813718 # Number of floating rename lookups +system.cpu.rename.RenamedOperands 455385433 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 2446563589 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 1351891912 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 1094671677 # Number of floating rename lookups system.cpu.rename.CommittedMaps 384568599 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 70863365 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 3987641 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 4044473 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 48252141 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 108792162 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 93099672 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 3342545 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 2273908 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 394239255 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 3865155 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 379120981 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 1801347 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 46369193 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 143590674 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 309514 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 208882385 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.814997 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.995935 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 70816834 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 3986585 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 4043449 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 48232782 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 108804127 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 93109820 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 3374999 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 2307513 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 394258042 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 3864226 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 379117437 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 1806866 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 46393196 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 143558304 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 308585 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 208872334 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.815068 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.996247 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 82049002 39.28% 39.28% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 34801326 16.66% 55.94% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 24478546 11.72% 67.66% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 18529016 8.87% 76.53% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 21712805 10.39% 86.92% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 15357191 7.35% 94.28% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 8402907 4.02% 98.30% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 2691838 1.29% 99.59% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 859754 0.41% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 82047947 39.28% 39.28% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 34785806 16.65% 55.94% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 24508634 11.73% 67.67% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 18508923 8.86% 76.53% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 21724585 10.40% 86.93% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 15318663 7.33% 94.27% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 8418302 4.03% 98.30% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 2689665 1.29% 99.58% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 869809 0.42% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 208882385 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 208872334 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 2250 0.01% 0.01% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 2261 0.01% 0.01% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 5043 0.03% 0.04% # attempts to use FU when none available system.cpu.iq.fu_full::IntDiv 0 0.00% 0.04% # attempts to use FU when none available system.cpu.iq.fu_full::FloatAdd 0 0.00% 0.04% # attempts to use FU when none available @@ -179,22 +179,22 @@ system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 0.04% # at system.cpu.iq.fu_full::SimdShift 0 0.00% 0.04% # attempts to use FU when none available system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 0.04% # attempts to use FU when none available system.cpu.iq.fu_full::SimdSqrt 0 0.00% 0.04% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 10815 0.06% 0.10% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 10246 0.06% 0.10% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 0.10% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 2509 0.01% 0.12% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 2469 0.01% 0.12% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatCvt 378 0.00% 0.12% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatDiv 3 0.00% 0.12% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 64370 0.37% 0.49% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 798 0.00% 0.50% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 177500 1.02% 1.52% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 64552 0.37% 0.49% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 790 0.00% 0.49% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 177361 1.02% 1.52% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 1.52% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 9658261 55.66% 57.18% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 7430721 42.82% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 9662090 55.64% 57.16% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 7440153 42.84% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 129606192 34.19% 34.19% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 2147281 0.57% 34.75% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 129612173 34.19% 34.19% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 2147283 0.57% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 34.75% # Type of FU issued @@ -205,7 +205,7 @@ system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 34.75% # Ty system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 34.75% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 13 0.00% 34.75% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 15 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdMult 0 0.00% 34.75% # Type of FU issued @@ -213,94 +213,94 @@ system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 34.75% # Ty system.cpu.iq.FU_type_0::SimdShift 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 34.75% # Type of FU issued system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 34.75% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 6746387 1.78% 36.53% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 6745842 1.78% 36.53% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 36.53% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 8673518 2.29% 38.82% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 3499070 0.92% 39.74% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 1584810 0.42% 40.16% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 21149805 5.58% 45.74% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 7187648 1.90% 47.64% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 7147289 1.89% 49.52% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 8678031 2.29% 38.82% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 3497767 0.92% 39.75% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 1584514 0.42% 40.16% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 21146877 5.58% 45.74% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 7187357 1.90% 47.64% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 7146686 1.89% 49.52% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 175286 0.05% 49.57% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 103746274 27.36% 76.93% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 87457408 23.07% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 103748568 27.37% 76.93% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 87447038 23.07% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 379120981 # Type of FU issued -system.cpu.iq.rate 1.814018 # Inst issue rate -system.cpu.iq.fu_busy_cnt 17352648 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.045771 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 735350759 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 310614656 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 251531674 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 250927583 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 133866908 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 118270115 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 267600383 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 128873246 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 7282081 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 379117437 # Type of FU issued +system.cpu.iq.rate 1.814089 # Inst issue rate +system.cpu.iq.fu_busy_cnt 17365346 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.045805 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 735356252 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 310675933 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 251537712 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 250923168 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 133847541 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 118277096 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 267613476 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 128869307 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 7295740 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 14143162 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 112354 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 8279 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 10723841 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 14155127 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 112471 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 8340 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 10733989 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 272 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.rescheduledLoads 274 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 117 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 7612083 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 19341 # Number of cycles IEW is blocking +system.cpu.iew.iewSquashCycles 7613691 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 19337 # Number of cycles IEW is blocking system.cpu.iew.iewUnblockCycles 437 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 398151655 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 2633597 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 108792162 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 93099672 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 3853935 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispatchedInsts 398169516 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 2638152 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 108804127 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 93109820 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 3853005 # Number of dispatched non-speculative instructions system.cpu.iew.iewIQFullEvents 34 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewLSQFullEvents 205 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 8279 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 3193235 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 309338 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 3502573 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 373031388 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 102121270 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 6089593 # Number of squashed instructions skipped in execute +system.cpu.iew.memOrderViolationEvents 8340 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 3192687 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 308539 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 3501226 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 373035381 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 102118243 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 6082056 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 47245 # number of nop insts executed -system.cpu.iew.exec_refs 188074720 # number of memory reference insts executed -system.cpu.iew.exec_branches 32215232 # Number of branches executed -system.cpu.iew.exec_stores 85953450 # Number of stores executed -system.cpu.iew.exec_rate 1.784881 # Inst execution rate -system.cpu.iew.wb_sent 370805637 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 369801789 # cumulative count of insts written-back -system.cpu.iew.wb_producers 175613931 # num instructions producing a value -system.cpu.iew.wb_consumers 345608979 # num instructions consuming a value +system.cpu.iew.exec_nop 47248 # number of nop insts executed +system.cpu.iew.exec_refs 188073317 # number of memory reference insts executed +system.cpu.iew.exec_branches 32214551 # Number of branches executed +system.cpu.iew.exec_stores 85955074 # Number of stores executed +system.cpu.iew.exec_rate 1.784986 # Inst execution rate +system.cpu.iew.wb_sent 370819014 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 369814808 # cumulative count of insts written-back +system.cpu.iew.wb_producers 175635069 # num instructions producing a value +system.cpu.iew.wb_consumers 345639533 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.769428 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.508129 # average fanout of values written-back +system.cpu.iew.wb_rate 1.769576 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.508145 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 349066646 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 49085191 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 49103053 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 3555641 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 3229927 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 201270303 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.734318 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.320939 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 3227876 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 201258644 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.734418 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.321139 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 89873146 44.65% 44.65% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 39586205 19.67% 64.32% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 17962686 8.92% 73.25% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 13145817 6.53% 79.78% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 14573998 7.24% 87.02% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 7584463 3.77% 90.79% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 3507612 1.74% 92.53% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 3437369 1.71% 94.24% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 11599007 5.76% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 89876372 44.66% 44.66% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 39560210 19.66% 64.31% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 17969648 8.93% 73.24% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 13168483 6.54% 79.79% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 14551255 7.23% 87.02% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 7589820 3.77% 90.79% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 3505620 1.74% 92.53% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 3424037 1.70% 94.23% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 11613199 5.77% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 201270303 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 201258644 # Number of insts commited each cycle system.cpu.commit.count 349066646 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 177024831 # Number of memory references committed @@ -310,50 +310,50 @@ system.cpu.commit.branches 30521879 # Nu system.cpu.commit.fp_insts 114216705 # Number of committed floating point instructions. system.cpu.commit.int_insts 279585929 # Number of committed integer instructions. system.cpu.commit.function_calls 6225114 # Number of function calls committed. -system.cpu.commit.bw_lim_events 11599007 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 11613199 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 587820610 # The number of ROB reads -system.cpu.rob.rob_writes 803918901 # The number of ROB writes -system.cpu.timesIdled 2585 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 112735 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 587812621 # The number of ROB reads +system.cpu.rob.rob_writes 803956224 # The number of ROB writes +system.cpu.timesIdled 2582 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 112680 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 349066034 # Number of Instructions Simulated system.cpu.committedInsts_total 349066034 # Number of Instructions Simulated -system.cpu.cpi 0.598727 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.598727 # CPI: Total CPI of All Threads -system.cpu.ipc 1.670211 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.670211 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 1781871579 # number of integer regfile reads -system.cpu.int_regfile_writes 235815438 # number of integer regfile writes -system.cpu.fp_regfile_reads 188771754 # number of floating regfile reads -system.cpu.fp_regfile_writes 133861667 # number of floating regfile writes -system.cpu.misc_regfile_reads 1003473737 # number of misc regfile reads +system.cpu.cpi 0.598698 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.598698 # CPI: Total CPI of All Threads +system.cpu.ipc 1.670292 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.670292 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 1781918480 # number of integer regfile reads +system.cpu.int_regfile_writes 235832393 # number of integer regfile writes +system.cpu.fp_regfile_reads 188783884 # number of floating regfile reads +system.cpu.fp_regfile_writes 133870920 # number of floating regfile writes +system.cpu.misc_regfile_reads 1003409978 # number of misc regfile reads system.cpu.misc_regfile_writes 34422193 # number of misc regfile writes -system.cpu.icache.replacements 14107 # number of replacements -system.cpu.icache.tagsinuse 1842.677380 # Cycle average of tags in use -system.cpu.icache.total_refs 41226387 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 15987 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 2578.744417 # Average number of references to valid blocks. +system.cpu.icache.replacements 14108 # number of replacements +system.cpu.icache.tagsinuse 1842.733120 # Cycle average of tags in use +system.cpu.icache.total_refs 41220872 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 15988 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 2578.238179 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1842.677380 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.899745 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 41226387 # number of ReadReq hits -system.cpu.icache.demand_hits 41226387 # number of demand (read+write) hits -system.cpu.icache.overall_hits 41226387 # number of overall hits -system.cpu.icache.ReadReq_misses 16643 # number of ReadReq misses -system.cpu.icache.demand_misses 16643 # number of demand (read+write) misses -system.cpu.icache.overall_misses 16643 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 201090500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 201090500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 201090500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 41243030 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 41243030 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 41243030 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 1842.733120 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.899772 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 41220872 # number of ReadReq hits +system.cpu.icache.demand_hits 41220872 # number of demand (read+write) hits +system.cpu.icache.overall_hits 41220872 # number of overall hits +system.cpu.icache.ReadReq_misses 16648 # number of ReadReq misses +system.cpu.icache.demand_misses 16648 # number of demand (read+write) misses +system.cpu.icache.overall_misses 16648 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 201025000 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 201025000 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 201025000 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 41237520 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 41237520 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 41237520 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000404 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000404 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000404 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 12082.587274 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 12082.587274 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 12082.587274 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 12075.024027 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 12075.024027 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 12075.024027 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -366,64 +366,64 @@ system.cpu.icache.writebacks 0 # nu system.cpu.icache.ReadReq_mshr_hits 637 # number of ReadReq MSHR hits system.cpu.icache.demand_mshr_hits 637 # number of demand (read+write) MSHR hits system.cpu.icache.overall_mshr_hits 637 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 16006 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 16006 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 16006 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_misses 16011 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 16011 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 16011 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 136032000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 136032000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 136032000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 135953500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 135953500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 135953500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000388 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000388 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000388 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 8498.812945 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 8498.812945 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 8498.812945 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 8491.256011 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 8491.256011 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 8491.256011 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 1408 # number of replacements -system.cpu.dcache.tagsinuse 3101.194672 # Cycle average of tags in use -system.cpu.dcache.total_refs 176614084 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 4596 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 38427.781549 # Average number of references to valid blocks. +system.cpu.dcache.replacements 1410 # number of replacements +system.cpu.dcache.tagsinuse 3098.497902 # Cycle average of tags in use +system.cpu.dcache.total_refs 176602100 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 4594 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 38441.902481 # Average number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 3101.194672 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.757128 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 94558380 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 82033210 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 11361 # number of LoadLockedReq hits +system.cpu.dcache.occ_blocks::0 3098.497902 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.756469 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 94546395 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 82033205 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 11358 # number of LoadLockedReq hits system.cpu.dcache.StoreCondReq_hits 11114 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 176591590 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 176591590 # number of overall hits -system.cpu.dcache.ReadReq_misses 3380 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 19484 # number of WriteReq misses +system.cpu.dcache.demand_hits 176579600 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 176579600 # number of overall hits +system.cpu.dcache.ReadReq_misses 3383 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 19489 # number of WriteReq misses system.cpu.dcache.LoadLockedReq_misses 2 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 22864 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 22864 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 111762500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 649531500 # number of WriteReq miss cycles +system.cpu.dcache.demand_misses 22872 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 22872 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 111712500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 649715000 # number of WriteReq miss cycles system.cpu.dcache.LoadLockedReq_miss_latency 76000 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 761294000 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 761294000 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 94561760 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.demand_miss_latency 761427500 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 761427500 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 94549778 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 82052694 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 11363 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.LoadLockedReq_accesses 11360 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.StoreCondReq_accesses 11114 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 176614454 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 176614454 # number of overall (read+write) accesses +system.cpu.dcache.demand_accesses 176602472 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 176602472 # number of overall (read+write) accesses system.cpu.dcache.ReadReq_miss_rate 0.000036 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.000237 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.000238 # miss rate for WriteReq accesses system.cpu.dcache.LoadLockedReq_miss_rate 0.000176 # miss rate for LoadLockedReq accesses -system.cpu.dcache.demand_miss_rate 0.000129 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.000129 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 33065.828402 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 33336.660850 # average WriteReq miss latency +system.cpu.dcache.demand_miss_rate 0.000130 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.000130 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 33021.726278 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 33337.523731 # average WriteReq miss latency system.cpu.dcache.LoadLockedReq_avg_miss_latency 38000 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 33296.623513 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 33296.623513 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency 33290.814096 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 33290.814096 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 307500 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -432,73 +432,73 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets 27954.545455 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 1030 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 1630 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 16619 # number of WriteReq MSHR hits +system.cpu.dcache.writebacks 1034 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 1633 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 16622 # number of WriteReq MSHR hits system.cpu.dcache.LoadLockedReq_mshr_hits 2 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 18249 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 18249 # number of overall MSHR hits +system.cpu.dcache.demand_mshr_hits 18255 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 18255 # number of overall MSHR hits system.cpu.dcache.ReadReq_mshr_misses 1750 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 2865 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 4615 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 4615 # number of overall MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 2867 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 4617 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 4617 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 53437000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 101725000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 155162000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 155162000 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 53344000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 101787500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 155131500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 155131500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000019 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.000035 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.000026 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.000026 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 30535.428571 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35506.108202 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 33621.235103 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 33621.235103 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 30482.285714 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35503.139170 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 33600.064977 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 33600.064977 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.l2cache.replacements 57 # number of replacements -system.cpu.l2cache.tagsinuse 3897.011564 # Cycle average of tags in use -system.cpu.l2cache.total_refs 13334 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 5354 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 2.490474 # Average number of references to valid blocks. +system.cpu.l2cache.tagsinuse 3892.486015 # Cycle average of tags in use +system.cpu.l2cache.total_refs 13341 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 5352 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 2.492713 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 3518.810301 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 378.201262 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.107386 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.011542 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 13251 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 1030 # number of Writeback hits +system.cpu.l2cache.occ_blocks::0 3513.908293 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 378.577721 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.107236 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.011553 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 13258 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 1034 # number of Writeback hits system.cpu.l2cache.ReadExReq_hits 19 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 13270 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 13270 # number of overall hits -system.cpu.l2cache.ReadReq_misses 4485 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 19 # number of UpgradeReq misses -system.cpu.l2cache.ReadExReq_misses 2828 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 7313 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 7313 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 153892500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 97502000 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 251394500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 251394500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 17736 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 1030 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 19 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 2847 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 20583 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 20583 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.252876 # miss rate for ReadReq accesses +system.cpu.l2cache.demand_hits 13277 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 13277 # number of overall hits +system.cpu.l2cache.ReadReq_misses 4479 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 23 # number of UpgradeReq misses +system.cpu.l2cache.ReadExReq_misses 2826 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 7305 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 7305 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 153679500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 97429500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 251109000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 251109000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 17737 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 1034 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 23 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 2845 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 20582 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 20582 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.252523 # miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.993326 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.355293 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.355293 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34312.709030 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34477.369165 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34376.384521 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34376.384521 # average overall miss latency +system.cpu.l2cache.ReadExReq_miss_rate 0.993322 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.354922 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.354922 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34311.118553 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34476.114650 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34374.948665 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34374.948665 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -511,28 +511,28 @@ system.cpu.l2cache.writebacks 0 # nu system.cpu.l2cache.ReadReq_mshr_hits 55 # number of ReadReq MSHR hits system.cpu.l2cache.demand_mshr_hits 55 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 55 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 4430 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 19 # number of UpgradeReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 2828 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 7258 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 7258 # number of overall MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 4424 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 23 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 2826 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 7250 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 7250 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 138008000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 589000 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 88479500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 226487500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 226487500 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 137822500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 713000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 88418000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 226240500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 226240500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.249774 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.249422 # mshr miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.993326 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.352621 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.352621 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31153.047404 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.993322 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.352250 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.352250 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31153.367993 # average ReadReq mshr miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000 # average UpgradeReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31286.951909 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31205.221824 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31205.221824 # average overall mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31287.331918 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31205.586207 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31205.586207 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/config.ini b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/config.ini index 7e5e4838d..78c85cac9 100644 --- a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=perlbmk -I. -I lib lgred.makerand.pl -cwd=build/ARM_SE/tests/opt/long/40.perlbmk/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/40.perlbmk/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/perlbmk +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/perlbmk gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/simout b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/simout index af8b043ac..76bc74d1e 100755 --- a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/40.perlbmk/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/40.perlbmk/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 09:08:55 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/40.perlbmk/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/40.perlbmk/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:22 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/40.perlbmk/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/40.perlbmk/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. @@ -1385,4 +1387,4 @@ info: Increasing stack size by one page. 2000: 760651391 1000: 4031656975 0: 2206428413 -Exiting @ tick 708403313500 because target called exit() +Exiting @ tick 708285420500 because target called exit() diff --git a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/stats.txt index 7b72f7ce4..801f115d2 100644 --- a/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/40.perlbmk/ref/arm/linux/o3-timing/stats.txt @@ -1,24 +1,24 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.708403 # Number of seconds simulated -sim_ticks 708403313500 # Number of ticks simulated -final_tick 708403313500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.708285 # Number of seconds simulated +sim_ticks 708285420500 # Number of ticks simulated +final_tick 708285420500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 118434 # Simulator instruction rate (inst/s) -host_tick_rate 44501063 # Simulator tick rate (ticks/s) -host_mem_usage 226576 # Number of bytes of host memory used -host_seconds 15918.80 # Real time elapsed on the host +host_inst_rate 74841 # Simulator instruction rate (inst/s) +host_tick_rate 28116271 # Simulator tick rate (ticks/s) +host_mem_usage 262240 # Number of bytes of host memory used +host_seconds 25191.30 # Real time elapsed on the host sim_insts 1885333786 # Number of instructions simulated -system.physmem.bytes_read 94812032 # Number of bytes read from this memory -system.physmem.bytes_inst_read 200960 # Number of instructions bytes read from this memory +system.physmem.bytes_read 94806144 # Number of bytes read from this memory +system.physmem.bytes_inst_read 201024 # Number of instructions bytes read from this memory system.physmem.bytes_written 4230336 # Number of bytes written to this memory -system.physmem.num_reads 1481438 # Number of read requests responded to by this memory +system.physmem.num_reads 1481346 # Number of read requests responded to by this memory system.physmem.num_writes 66099 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 133839058 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 283680 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 5971649 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 139810707 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 133853022 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 283818 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 5972643 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 139825665 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,107 +62,106 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 1411 # Number of system calls -system.cpu.numCycles 1416806628 # number of cpu cycles simulated +system.cpu.numCycles 1416570842 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 503033036 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 388160087 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 32894916 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 402481986 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 281923865 # Number of BTB hits +system.cpu.BPredUnit.lookups 502965792 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 388083906 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 32892883 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 402994214 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 282903329 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 59796610 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 2840141 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 410550003 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 2542460473 # Number of instructions fetch has processed -system.cpu.fetch.Branches 503033036 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 341720475 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 682921340 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 205013758 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 105428035 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 2115 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 34704 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 384233965 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 12151873 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 1365478165 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.588855 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.160415 # Number of instructions fetched each cycle (Total) +system.cpu.BPredUnit.usedRAS 59754999 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 2839304 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 410473974 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 2542481038 # Number of instructions fetch has processed +system.cpu.fetch.Branches 502965792 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 342658328 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 682850611 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 204993234 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 105359667 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 2118 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 34717 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 384198016 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 12176398 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 1365244569 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.589439 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.160393 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 682595631 49.99% 49.99% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 48342952 3.54% 53.53% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 108702790 7.96% 61.49% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 62379051 4.57% 66.06% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 89292584 6.54% 72.60% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 54148565 3.97% 76.56% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 35470304 2.60% 79.16% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 34965610 2.56% 81.72% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 249580678 18.28% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 682433791 49.99% 49.99% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 48186597 3.53% 53.52% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 108652804 7.96% 61.47% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 62364195 4.57% 66.04% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 89334703 6.54% 72.59% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 54302238 3.98% 76.56% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 35506449 2.60% 79.16% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 34966658 2.56% 81.73% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 249497134 18.27% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 1365478165 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.355047 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.794501 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 455361727 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 85217138 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 647145530 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 11223736 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 166530034 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 68649997 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 12124 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 3424361675 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 24057 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 166530034 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 496888956 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 29110139 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 3718079 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 615295356 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 53935601 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 3298153337 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 14 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 4569845 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 42334817 # Number of times rename has blocked due to LSQ full -system.cpu.rename.FullRegisterEvents 3 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 3261061532 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 15624755618 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 14989571898 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 635183720 # Number of floating rename lookups +system.cpu.fetch.rateDist::total 1365244569 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.355059 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.794814 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 455297388 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 85147033 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 647142661 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 11145809 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 166511678 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 68705297 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 11995 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 3424572913 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 23770 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 166511678 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 496865002 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 29032521 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 3717307 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 615240410 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 53877651 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 3297959575 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 31 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 4556255 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 42355939 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RenamedOperands 3260022737 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 15624313135 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 14988978570 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 635334565 # Number of floating rename lookups system.cpu.rename.CommittedMaps 1993153599 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 1267907933 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 310582 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 306325 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 155884977 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 1045137132 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 527476218 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 35886570 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 45267364 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 3077754179 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 303954 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 2619291842 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 18689867 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 1192085861 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 2899457281 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 92624 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 1365478165 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.918223 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.900205 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 1266869138 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 309495 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 305230 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 155871874 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 1045378245 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 527599628 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 35911477 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 45240488 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 3077735106 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 301755 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 2619169948 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 18682763 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 1192120154 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 2900187573 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 90425 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 1365244569 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.918462 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.900067 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 480779837 35.21% 35.21% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 182587607 13.37% 48.58% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 216609244 15.86% 64.44% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 179766275 13.17% 77.61% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 150868799 11.05% 88.66% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 89721779 6.57% 95.23% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 48758870 3.57% 98.80% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 11536421 0.84% 99.64% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 4849333 0.36% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 480555764 35.20% 35.20% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 182601458 13.37% 48.57% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 216587645 15.86% 64.44% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 179670065 13.16% 77.60% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 151134600 11.07% 88.67% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 89532476 6.56% 95.23% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 48791102 3.57% 98.80% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 11536059 0.84% 99.65% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 4835400 0.35% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 1365478165 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 1365244569 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 2044403 2.26% 2.26% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 23929 0.03% 2.28% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 2042243 2.25% 2.25% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 23945 0.03% 2.28% # attempts to use FU when none available system.cpu.iq.fu_full::IntDiv 0 0.00% 2.28% # attempts to use FU when none available system.cpu.iq.fu_full::FloatAdd 0 0.00% 2.28% # attempts to use FU when none available system.cpu.iq.fu_full::FloatCmp 0 0.00% 2.28% # attempts to use FU when none available @@ -190,119 +189,119 @@ system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 2.28% # at system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 2.28% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 2.28% # attempts to use FU when none available system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 2.28% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 55649007 61.42% 63.70% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 32885475 36.30% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 55656078 61.41% 63.69% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 32910645 36.31% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 1200920026 45.85% 45.85% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 11234109 0.43% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::IntDiv 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatMult 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMult 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShift 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 46.28% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 1375289 0.05% 46.33% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 46.33% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 6876476 0.26% 46.59% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 5505406 0.21% 46.80% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 46.80% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 24362118 0.93% 47.73% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 47.73% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 47.73% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 47.73% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 895924024 34.20% 81.94% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 473094394 18.06% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 1200490200 45.83% 45.83% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 11234425 0.43% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::IntDiv 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatMult 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMult 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShift 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 46.26% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 1375289 0.05% 46.32% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 46.32% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 6876478 0.26% 46.58% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 5505051 0.21% 46.79% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 46.79% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 24362738 0.93% 47.72% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 47.72% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 47.72% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 47.72% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 896045352 34.21% 81.93% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 473280415 18.07% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 2619291842 # Type of FU issued -system.cpu.iq.rate 1.848729 # Inst issue rate -system.cpu.iq.fu_busy_cnt 90602814 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.034591 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 6584849993 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 4170838685 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 2409550549 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 128504537 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 99358414 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 57073276 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 2644267181 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 65627475 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 71974387 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 2619169948 # Type of FU issued +system.cpu.iq.rate 1.848951 # Inst issue rate +system.cpu.iq.fu_busy_cnt 90632911 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.034604 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 6584397091 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 4170852442 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 2409395411 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 128503048 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 99357739 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 57077748 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 2644176123 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 65626736 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 71999032 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 413748263 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 264274 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 1389738 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 250479234 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 413989376 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 268082 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 1389984 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 250602644 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 88 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.rescheduledLoads 86 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 24 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 166530034 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 16377218 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 1473925 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 3078126585 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 12745051 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 1045137132 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 527476218 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 292477 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 1470662 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 166511678 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 16376007 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 1473970 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 3078105405 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 12712072 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 1045378245 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 527599628 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 290278 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 1470963 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewLSQFullEvents 212 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 1389738 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 34580674 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 8873578 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 43454252 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 2534450261 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 842463670 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 84841581 # Number of squashed instructions skipped in execute +system.cpu.iew.memOrderViolationEvents 1389984 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 34573717 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 8788062 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 43361779 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 2534356508 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 842568807 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 84813440 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 68452 # number of nop insts executed -system.cpu.iew.exec_refs 1294415982 # number of memory reference insts executed -system.cpu.iew.exec_branches 344601931 # Number of branches executed -system.cpu.iew.exec_stores 451952312 # Number of stores executed -system.cpu.iew.exec_rate 1.788847 # Inst execution rate -system.cpu.iew.wb_sent 2495608341 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 2466623825 # cumulative count of insts written-back -system.cpu.iew.wb_producers 1448525550 # num instructions producing a value -system.cpu.iew.wb_consumers 2707902616 # num instructions consuming a value +system.cpu.iew.exec_nop 68544 # number of nop insts executed +system.cpu.iew.exec_refs 1294694969 # number of memory reference insts executed +system.cpu.iew.exec_branches 344427498 # Number of branches executed +system.cpu.iew.exec_stores 452126162 # Number of stores executed +system.cpu.iew.exec_rate 1.789079 # Inst execution rate +system.cpu.iew.wb_sent 2495474043 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 2466473159 # cumulative count of insts written-back +system.cpu.iew.wb_producers 1448284961 # num instructions producing a value +system.cpu.iew.wb_consumers 2707735412 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.740974 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.534925 # average fanout of values written-back +system.cpu.iew.wb_rate 1.741158 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.534869 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 1885344802 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 1192782047 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 1192760864 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 211330 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 38420798 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 1198948133 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.572499 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.256451 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 38418907 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 1198732893 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.572781 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.256860 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 532143962 44.38% 44.38% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 299077946 24.95% 69.33% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 106761313 8.90% 78.23% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 77538501 6.47% 84.70% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 53400435 4.45% 89.15% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 23357302 1.95% 91.10% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 17130441 1.43% 92.53% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 9348033 0.78% 93.31% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 80190200 6.69% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 532007294 44.38% 44.38% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 299056293 24.95% 69.33% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 106726660 8.90% 78.23% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 77517857 6.47% 84.70% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 53371752 4.45% 89.15% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 23357463 1.95% 91.10% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 17108647 1.43% 92.53% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 9340003 0.78% 93.31% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 80246924 6.69% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 1198948133 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 1198732893 # Number of insts commited each cycle system.cpu.commit.count 1885344802 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 908385853 # Number of memory references committed @@ -312,50 +311,50 @@ system.cpu.commit.branches 291350232 # Nu system.cpu.commit.fp_insts 52289415 # Number of committed floating point instructions. system.cpu.commit.int_insts 1653705623 # Number of committed integer instructions. system.cpu.commit.function_calls 41577833 # Number of function calls committed. -system.cpu.commit.bw_lim_events 80190200 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 80246924 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 4196866437 # The number of ROB reads -system.cpu.rob.rob_writes 6322804382 # The number of ROB writes -system.cpu.timesIdled 1340913 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 51328463 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 4196573290 # The number of ROB reads +system.cpu.rob.rob_writes 6322749564 # The number of ROB writes +system.cpu.timesIdled 1340847 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 51326273 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 1885333786 # Number of Instructions Simulated system.cpu.committedInsts_total 1885333786 # Number of Instructions Simulated -system.cpu.cpi 0.751488 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.751488 # CPI: Total CPI of All Threads -system.cpu.ipc 1.330692 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.330692 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 12567203807 # number of integer regfile reads -system.cpu.int_regfile_writes 2360160094 # number of integer regfile writes -system.cpu.fp_regfile_reads 68800597 # number of floating regfile reads -system.cpu.fp_regfile_writes 50187558 # number of floating regfile writes -system.cpu.misc_regfile_reads 3980455481 # number of misc regfile reads +system.cpu.cpi 0.751363 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.751363 # CPI: Total CPI of All Threads +system.cpu.ipc 1.330914 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.330914 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 12567200244 # number of integer regfile reads +system.cpu.int_regfile_writes 2359430733 # number of integer regfile writes +system.cpu.fp_regfile_reads 68800397 # number of floating regfile reads +system.cpu.fp_regfile_writes 50191784 # number of floating regfile writes +system.cpu.misc_regfile_reads 3980708505 # number of misc regfile reads system.cpu.misc_regfile_writes 13776276 # number of misc regfile writes -system.cpu.icache.replacements 27305 # number of replacements -system.cpu.icache.tagsinuse 1638.856970 # Cycle average of tags in use -system.cpu.icache.total_refs 384199729 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 28984 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 13255.579941 # Average number of references to valid blocks. +system.cpu.icache.replacements 27241 # number of replacements +system.cpu.icache.tagsinuse 1638.335274 # Cycle average of tags in use +system.cpu.icache.total_refs 384162744 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 28920 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 13283.635685 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1638.856970 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.800223 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 384199814 # number of ReadReq hits -system.cpu.icache.demand_hits 384199814 # number of demand (read+write) hits -system.cpu.icache.overall_hits 384199814 # number of overall hits -system.cpu.icache.ReadReq_misses 34151 # number of ReadReq misses -system.cpu.icache.demand_misses 34151 # number of demand (read+write) misses -system.cpu.icache.overall_misses 34151 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 301141000 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 301141000 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 301141000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 384233965 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 384233965 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 384233965 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 1638.335274 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.799968 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 384163979 # number of ReadReq hits +system.cpu.icache.demand_hits 384163979 # number of demand (read+write) hits +system.cpu.icache.overall_hits 384163979 # number of overall hits +system.cpu.icache.ReadReq_misses 34037 # number of ReadReq misses +system.cpu.icache.demand_misses 34037 # number of demand (read+write) misses +system.cpu.icache.overall_misses 34037 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 300707500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 300707500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 300707500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 384198016 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 384198016 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 384198016 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000089 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000089 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000089 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 8817.926269 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 8817.926269 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 8817.926269 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 8834.723977 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 8834.723977 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 8834.723977 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -365,67 +364,67 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 772 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 772 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 772 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 33379 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 33379 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 33379 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 775 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 775 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 775 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 33262 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 33262 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 33262 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 180850500 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 180850500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 180850500 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 180621500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 180621500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 180621500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000087 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000087 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000087 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5418.092214 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5418.092214 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5418.092214 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5430.265769 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5430.265769 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5430.265769 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 1531788 # number of replacements -system.cpu.dcache.tagsinuse 4094.791932 # Cycle average of tags in use -system.cpu.dcache.total_refs 1029449306 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 1535884 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 670.265011 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 305577000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4094.791932 # Average occupied blocks per context +system.cpu.dcache.replacements 1531781 # number of replacements +system.cpu.dcache.tagsinuse 4094.791758 # Cycle average of tags in use +system.cpu.dcache.total_refs 1029515809 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 1535877 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 670.311365 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 305571000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4094.791758 # Average occupied blocks per context system.cpu.dcache.occ_percent::0 0.999705 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 753290045 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 276118528 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 15313 # number of LoadLockedReq hits +system.cpu.dcache.ReadReq_hits 753356755 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 276118556 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 15246 # number of LoadLockedReq hits system.cpu.dcache.StoreCondReq_hits 11672 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 1029408573 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 1029408573 # number of overall hits -system.cpu.dcache.ReadReq_misses 1938158 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 817150 # number of WriteReq misses +system.cpu.dcache.demand_hits 1029475311 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 1029475311 # number of overall hits +system.cpu.dcache.ReadReq_misses 1938073 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 817122 # number of WriteReq misses system.cpu.dcache.LoadLockedReq_misses 3 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 2755308 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 2755308 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 69348240500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 28488261000 # number of WriteReq miss cycles +system.cpu.dcache.demand_misses 2755195 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 2755195 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 69347083500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 28485572000 # number of WriteReq miss cycles system.cpu.dcache.LoadLockedReq_miss_latency 108500 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 97836501500 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 97836501500 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 755228203 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.demand_miss_latency 97832655500 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 97832655500 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 755294828 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 276935678 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 15316 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.LoadLockedReq_accesses 15249 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.StoreCondReq_accesses 11672 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 1032163881 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 1032163881 # number of overall (read+write) accesses +system.cpu.dcache.demand_accesses 1032230506 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 1032230506 # number of overall (read+write) accesses system.cpu.dcache.ReadReq_miss_rate 0.002566 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.002951 # miss rate for WriteReq accesses -system.cpu.dcache.LoadLockedReq_miss_rate 0.000196 # miss rate for LoadLockedReq accesses +system.cpu.dcache.LoadLockedReq_miss_rate 0.000197 # miss rate for LoadLockedReq accesses system.cpu.dcache.demand_miss_rate 0.002669 # miss rate for demand accesses system.cpu.dcache.overall_miss_rate 0.002669 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 35780.488742 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 34862.951722 # average WriteReq miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 35781.461018 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 34860.855539 # average WriteReq miss latency system.cpu.dcache.LoadLockedReq_avg_miss_latency 36166.666667 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 35508.372022 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 35508.372022 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency 35508.432434 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 35508.432434 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 62000 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -434,74 +433,74 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets 15500 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 106544 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 474971 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 740057 # number of WriteReq MSHR hits +system.cpu.dcache.writebacks 106815 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 474897 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 740078 # number of WriteReq MSHR hits system.cpu.dcache.LoadLockedReq_mshr_hits 3 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 1215028 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 1215028 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 1463187 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 77093 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 1540280 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 1540280 # number of overall MSHR misses +system.cpu.dcache.demand_mshr_hits 1214975 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 1214975 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 1463176 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 77044 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 1540220 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 1540220 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 50020048000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 2484862000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 52504910000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 52504910000 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 50021914000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 2483063000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 52504977000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 52504977000 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.001937 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.000278 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.001492 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.001492 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34185.683716 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 32232.005500 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 34087.899603 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 34087.899603 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34187.216029 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 32229.154769 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 34089.271013 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 34089.271013 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 1480006 # number of replacements -system.cpu.l2cache.tagsinuse 31970.917218 # Cycle average of tags in use -system.cpu.l2cache.total_refs 84924 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 1512726 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 0.056140 # Average number of references to valid blocks. +system.cpu.l2cache.replacements 1480005 # number of replacements +system.cpu.l2cache.tagsinuse 31970.457215 # Cycle average of tags in use +system.cpu.l2cache.total_refs 85123 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 1512725 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 0.056271 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 29008.328912 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 2962.588306 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.885264 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.090411 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 76788 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 106544 # number of Writeback hits +system.cpu.l2cache.occ_blocks::0 29003.484666 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 2966.972548 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.885116 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.090545 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 76806 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 106815 # number of Writeback hits system.cpu.l2cache.UpgradeReq_hits 4 # number of UpgradeReq hits -system.cpu.l2cache.ReadExReq_hits 6616 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 83404 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 83404 # number of overall hits -system.cpu.l2cache.ReadReq_misses 1415384 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 4391 # number of UpgradeReq misses +system.cpu.l2cache.ReadExReq_hits 6620 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 83426 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 83426 # number of overall hits +system.cpu.l2cache.ReadReq_misses 1415291 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 4338 # number of UpgradeReq misses system.cpu.l2cache.ReadExReq_misses 66082 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 1481466 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 1481466 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 48555371000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 2252634000 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 50808005000 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 50808005000 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 1492172 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 106544 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 4395 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 72698 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 1564870 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 1564870 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.948539 # miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_miss_rate 0.999090 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.908993 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.946702 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.946702 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34305.440078 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34088.465845 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34295.761766 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34295.761766 # average overall miss latency +system.cpu.l2cache.demand_misses 1481373 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 1481373 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 48556724500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 2252633500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 50809358000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 50809358000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 1492097 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 106815 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 4342 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 72702 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 1564799 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 1564799 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.948525 # miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_miss_rate 0.999079 # miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.908943 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.946686 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.946686 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34308.650659 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34088.458279 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34298.828182 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34298.828182 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -511,31 +510,31 @@ system.cpu.l2cache.avg_blocked_cycles::no_targets no_value system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed system.cpu.l2cache.writebacks 66099 # number of writebacks -system.cpu.l2cache.ReadReq_mshr_hits 28 # number of ReadReq MSHR hits -system.cpu.l2cache.demand_mshr_hits 28 # number of demand (read+write) MSHR hits -system.cpu.l2cache.overall_mshr_hits 28 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 1415356 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 4391 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_hits 27 # number of ReadReq MSHR hits +system.cpu.l2cache.demand_mshr_hits 27 # number of demand (read+write) MSHR hits +system.cpu.l2cache.overall_mshr_hits 27 # number of overall MSHR hits +system.cpu.l2cache.ReadReq_mshr_misses 1415264 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 4338 # number of UpgradeReq MSHR misses system.cpu.l2cache.ReadExReq_mshr_misses 66082 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 1481438 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 1481438 # number of overall MSHR misses +system.cpu.l2cache.demand_mshr_misses 1481346 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 1481346 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 43973863500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 136121000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 43971004500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 134478000 # number of UpgradeReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_latency 2048597500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 46022461000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 46022461000 # number of overall MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 46019602000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 46019602000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.948521 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.999090 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.908993 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.946684 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.946684 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31069.118653 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.948507 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.999079 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.908943 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.946669 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.946669 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31069.118200 # average ReadReq mshr miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000 # average UpgradeReq mshr miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31000.839866 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31066.072964 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31066.072964 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31066.072342 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31066.072342 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/config.ini b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/config.ini index 1feff9641..18c9a5809 100644 --- a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=vortex lendian.raw -cwd=build/ARM_SE/tests/opt/long/50.vortex/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/50.vortex/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/vortex +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/vortex gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/simout b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/simout index 41153b9d0..08b53cf2f 100755 --- a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/simout @@ -1,11 +1,13 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/50.vortex/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/50.vortex/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 09:34:51 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/50.vortex/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/50.vortex/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:22 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/50.vortex/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/50.vortex/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. -Exiting @ tick 31183407000 because target called exit() +Exiting @ tick 31189496500 because target called exit() diff --git a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/stats.txt index 858b9d08f..b5c5ac05d 100644 --- a/tests/long/se/50.vortex/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/50.vortex/ref/arm/linux/o3-timing/stats.txt @@ -1,24 +1,24 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.031183 # Number of seconds simulated -sim_ticks 31183407000 # Number of ticks simulated -final_tick 31183407000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.031189 # Number of seconds simulated +sim_ticks 31189496500 # Number of ticks simulated +final_tick 31189496500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 157932 # Simulator instruction rate (inst/s) -host_tick_rate 48938242 # Simulator tick rate (ticks/s) -host_mem_usage 229072 # Number of bytes of host memory used -host_seconds 637.20 # Real time elapsed on the host -sim_insts 100634165 # Number of instructions simulated -system.physmem.bytes_read 8651648 # Number of bytes read from this memory -system.physmem.bytes_inst_read 350016 # Number of instructions bytes read from this memory -system.physmem.bytes_written 5661184 # Number of bytes written to this memory -system.physmem.num_reads 135182 # Number of read requests responded to by this memory -system.physmem.num_writes 88456 # Number of write requests responded to by this memory +host_inst_rate 53036 # Simulator instruction rate (inst/s) +host_tick_rate 16437569 # Simulator tick rate (ticks/s) +host_mem_usage 264816 # Number of bytes of host memory used +host_seconds 1897.45 # Real time elapsed on the host +sim_insts 100634170 # Number of instructions simulated +system.physmem.bytes_read 8651712 # Number of bytes read from this memory +system.physmem.bytes_inst_read 350080 # Number of instructions bytes read from this memory +system.physmem.bytes_written 5661248 # Number of bytes written to this memory +system.physmem.num_reads 135183 # Number of read requests responded to by this memory +system.physmem.num_writes 88457 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 277443962 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 11224431 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 181544756 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 458988718 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 277391846 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 11224291 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 181511362 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 458903208 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,143 +62,143 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 1946 # Number of system calls -system.cpu.numCycles 62366815 # number of cpu cycles simulated +system.cpu.numCycles 62378994 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 17631068 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 11525225 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 822451 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 15041021 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 9743390 # Number of BTB hits +system.cpu.BPredUnit.lookups 17633191 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 11526968 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 822695 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 15043788 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 9743985 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 1887340 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 176888 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 12968459 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 88523933 # Number of instructions fetch has processed -system.cpu.fetch.Branches 17631068 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 11630730 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 22984896 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 2898005 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 23107334 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 15 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 525 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 12208408 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 230644 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 61059715 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.021356 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.077680 # Number of instructions fetched each cycle (Total) +system.cpu.BPredUnit.usedRAS 1887457 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 176874 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 12969342 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 88531281 # Number of instructions fetch has processed +system.cpu.fetch.Branches 17633191 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 11631442 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 22985471 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 2899094 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 23117489 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 14 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 528 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 12209631 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 231060 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 61072156 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.021104 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.077628 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 38090584 62.38% 62.38% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 2437224 3.99% 66.37% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 2605062 4.27% 70.64% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 2470326 4.05% 74.69% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 1717744 2.81% 77.50% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 1704134 2.79% 80.29% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 1004081 1.64% 81.93% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 1295541 2.12% 84.06% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 9735019 15.94% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 38102442 62.39% 62.39% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 2437370 3.99% 66.38% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 2604913 4.27% 70.65% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 2468790 4.04% 74.69% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 1717886 2.81% 77.50% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 1703957 2.79% 80.29% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 1004465 1.64% 81.94% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 1297144 2.12% 84.06% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 9735189 15.94% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 61059715 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.282700 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.419408 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 14872380 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 21838408 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 21376813 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 1070090 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 1902024 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 3467429 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 98061 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 120316029 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 332599 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 1902024 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 16801594 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 2005674 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 15516104 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 20489827 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 4344492 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 117017437 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 7 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 3607 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 2996198 # Number of times rename has blocked due to LSQ full -system.cpu.rename.FullRegisterEvents 60 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 118959985 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 538237718 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 538236225 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 1493 # Number of floating rename lookups -system.cpu.rename.CommittedMaps 99144333 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 19815652 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 778147 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 778546 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 12135199 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 29749057 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 22305499 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 2463618 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 3436887 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 111737256 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 774255 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 107616850 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 306406 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 11658627 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 29328565 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 71223 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 61059715 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.762485 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.902924 # Number of insts issued each cycle +system.cpu.fetch.rateDist::total 61072156 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.282678 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.419248 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 14874533 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 21847562 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 21380234 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 1066852 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 1902975 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 3467400 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 97940 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 120324997 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 332105 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 1902975 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 16806585 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 2006065 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 15518837 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 20487124 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 4350570 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 117025506 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 6 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 3620 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 3001536 # Number of times rename has blocked due to LSQ full +system.cpu.rename.FullRegisterEvents 62 # Number of times there has been no free registers +system.cpu.rename.RenamedOperands 118973415 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 538271633 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 538269997 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 1636 # Number of floating rename lookups +system.cpu.rename.CommittedMaps 99144341 # Number of HB maps that are committed +system.cpu.rename.UndoneMaps 19829074 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 778296 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 778691 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 12144889 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 29749506 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 22307130 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 2475389 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 3455641 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 111742619 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 774376 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 107620542 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 306039 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 11663320 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 29339036 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 71343 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 61072156 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.762187 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.902803 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 22160160 36.29% 36.29% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 11614525 19.02% 55.31% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 8577298 14.05% 69.36% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 7396039 12.11% 81.47% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 4782616 7.83% 89.31% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 3521695 5.77% 95.07% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 1664317 2.73% 97.80% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 809749 1.33% 99.13% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 533316 0.87% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 22164835 36.29% 36.29% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 11626045 19.04% 55.33% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 8572984 14.04% 69.37% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 7394656 12.11% 81.47% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 4788181 7.84% 89.32% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 3517678 5.76% 95.08% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 1664983 2.73% 97.80% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 808803 1.32% 99.13% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 533991 0.87% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 61059715 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 61072156 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 88066 3.33% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 3.33% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 1488278 56.33% 59.66% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 1065734 40.34% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 87531 3.32% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 3.32% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 1485029 56.34% 59.66% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 1063128 40.34% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 57002654 52.97% 52.97% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 87399 0.08% 53.05% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 57005331 52.97% 52.97% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 87377 0.08% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 53.05% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 39 0.00% 53.05% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 40 0.00% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::FloatMult 0 0.00% 53.05% # Type of FU issued @@ -224,138 +224,138 @@ system.cpu.iq.FU_type_0::SimdFloatMisc 7 0.00% 53.05% # Ty system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 53.05% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 53.05% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 28992824 26.94% 79.99% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 21533927 20.01% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 28993103 26.94% 79.99% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 21534684 20.01% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 107616850 # Type of FU issued -system.cpu.iq.rate 1.725547 # Inst issue rate -system.cpu.iq.fu_busy_cnt 2642078 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.024551 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 279241693 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 124185257 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 105412682 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 206 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 204 # Number of floating instruction queue writes +system.cpu.iq.FU_type_0::total 107620542 # Type of FU issued +system.cpu.iq.rate 1.725269 # Inst issue rate +system.cpu.iq.fu_busy_cnt 2635688 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.024491 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 279254757 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 124195436 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 105415832 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 210 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 218 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 76 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 110258821 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 107 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 1870348 # Number of loads that had data forwarded from stores +system.cpu.iq.int_alu_accesses 110256122 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 108 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 1866930 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 2440492 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 3482 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 15956 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 1748305 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 2440940 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 3458 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 15970 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 1749935 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 52 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 53 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.rescheduledLoads 51 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.cacheBlocked 52 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 1902024 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 953128 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 28578 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 112587966 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 618611 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 29749057 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 22305499 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 756996 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 1135 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 1192 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 15956 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 682416 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 198748 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 881164 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 106274273 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 28622040 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 1342577 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 1902975 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 953135 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 28579 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 112593446 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 617881 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 29749506 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 22307130 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 757118 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 1133 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 1194 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 15970 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 682654 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 198883 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 881537 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 106278016 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 28622846 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 1342526 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 76455 # number of nop insts executed -system.cpu.iew.exec_refs 49853649 # number of memory reference insts executed -system.cpu.iew.exec_branches 14601408 # Number of branches executed -system.cpu.iew.exec_stores 21231609 # Number of stores executed -system.cpu.iew.exec_rate 1.704020 # Inst execution rate -system.cpu.iew.wb_sent 105725224 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 105412758 # cumulative count of insts written-back -system.cpu.iew.wb_producers 52507879 # num instructions producing a value -system.cpu.iew.wb_consumers 101154765 # num instructions consuming a value +system.cpu.iew.exec_nop 76451 # number of nop insts executed +system.cpu.iew.exec_refs 49854993 # number of memory reference insts executed +system.cpu.iew.exec_branches 14601868 # Number of branches executed +system.cpu.iew.exec_stores 21232147 # Number of stores executed +system.cpu.iew.exec_rate 1.703747 # Inst execution rate +system.cpu.iew.wb_sent 105729046 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 105415908 # cumulative count of insts written-back +system.cpu.iew.wb_producers 52516965 # num instructions producing a value +system.cpu.iew.wb_consumers 101175097 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.690206 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.519085 # average fanout of values written-back +system.cpu.iew.wb_rate 1.689926 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.519070 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.commit.commitCommittedInsts 100639717 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 11948697 # The number of squashed insts skipped by commit -system.cpu.commit.commitNonSpecStalls 703032 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 788200 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 59157692 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.701211 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.430896 # Number of insts commited each cycle +system.cpu.commit.commitCommittedInsts 100639722 # The number of committed instructions +system.cpu.commit.commitSquashedInsts 11954174 # The number of squashed insts skipped by commit +system.cpu.commit.commitNonSpecStalls 703033 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.branchMispredicts 788567 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 59169182 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.700881 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.430495 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 26246617 44.37% 44.37% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 14635662 24.74% 69.11% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 4223894 7.14% 76.25% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 3641491 6.16% 82.40% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 2268632 3.83% 86.24% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 1889350 3.19% 89.43% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 703853 1.19% 90.62% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 498146 0.84% 91.46% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 5050047 8.54% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 26246833 44.36% 44.36% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 14645427 24.75% 69.11% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 4228470 7.15% 76.26% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 3643076 6.16% 82.41% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 2266929 3.83% 86.25% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 1888235 3.19% 89.44% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 703093 1.19% 90.62% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 496274 0.84% 91.46% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 5050845 8.54% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 59157692 # Number of insts commited each cycle -system.cpu.commit.count 100639717 # Number of instructions committed +system.cpu.commit.committed_per_cycle::total 59169182 # Number of insts commited each cycle +system.cpu.commit.count 100639722 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.refs 47865759 # Number of memory references committed -system.cpu.commit.loads 27308565 # Number of loads committed +system.cpu.commit.refs 47865761 # Number of memory references committed +system.cpu.commit.loads 27308566 # Number of loads committed system.cpu.commit.membars 15920 # Number of memory barriers committed -system.cpu.commit.branches 13670084 # Number of branches committed +system.cpu.commit.branches 13670085 # Number of branches committed system.cpu.commit.fp_insts 56 # Number of committed floating point instructions. -system.cpu.commit.int_insts 91478611 # Number of committed integer instructions. +system.cpu.commit.int_insts 91478615 # Number of committed integer instructions. system.cpu.commit.function_calls 1679850 # Number of function calls committed. -system.cpu.commit.bw_lim_events 5050047 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 5050845 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 166670760 # The number of ROB reads -system.cpu.rob.rob_writes 227084538 # The number of ROB writes -system.cpu.timesIdled 61622 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 1307100 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.committedInsts 100634165 # Number of Instructions Simulated -system.cpu.committedInsts_total 100634165 # Number of Instructions Simulated -system.cpu.cpi 0.619738 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.619738 # CPI: Total CPI of All Threads -system.cpu.ipc 1.613585 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.613585 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 511657086 # number of integer regfile reads -system.cpu.int_regfile_writes 103892124 # number of integer regfile writes +system.cpu.rob.rob_reads 166686934 # The number of ROB reads +system.cpu.rob.rob_writes 227096473 # The number of ROB writes +system.cpu.timesIdled 61617 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 1306838 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.committedInsts 100634170 # Number of Instructions Simulated +system.cpu.committedInsts_total 100634170 # Number of Instructions Simulated +system.cpu.cpi 0.619859 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.619859 # CPI: Total CPI of All Threads +system.cpu.ipc 1.613270 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.613270 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 511674990 # number of integer regfile reads +system.cpu.int_regfile_writes 103897673 # number of integer regfile writes system.cpu.fp_regfile_reads 166 # number of floating regfile reads system.cpu.fp_regfile_writes 126 # number of floating regfile writes -system.cpu.misc_regfile_reads 146210782 # number of misc regfile reads -system.cpu.misc_regfile_writes 34752 # number of misc regfile writes -system.cpu.icache.replacements 26083 # number of replacements -system.cpu.icache.tagsinuse 1805.405384 # Cycle average of tags in use -system.cpu.icache.total_refs 12179175 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 28115 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 433.191357 # Average number of references to valid blocks. +system.cpu.misc_regfile_reads 146219619 # number of misc regfile reads +system.cpu.misc_regfile_writes 34754 # number of misc regfile writes +system.cpu.icache.replacements 26131 # number of replacements +system.cpu.icache.tagsinuse 1805.600642 # Cycle average of tags in use +system.cpu.icache.total_refs 12180358 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 28166 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 432.448981 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1805.405384 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.881546 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 12179178 # number of ReadReq hits -system.cpu.icache.demand_hits 12179178 # number of demand (read+write) hits -system.cpu.icache.overall_hits 12179178 # number of overall hits -system.cpu.icache.ReadReq_misses 29230 # number of ReadReq misses -system.cpu.icache.demand_misses 29230 # number of demand (read+write) misses -system.cpu.icache.overall_misses 29230 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 357885000 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 357885000 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 357885000 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 12208408 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 12208408 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 12208408 # number of overall (read+write) accesses -system.cpu.icache.ReadReq_miss_rate 0.002394 # miss rate for ReadReq accesses -system.cpu.icache.demand_miss_rate 0.002394 # miss rate for demand accesses -system.cpu.icache.overall_miss_rate 0.002394 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 12243.756415 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 12243.756415 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 12243.756415 # average overall miss latency +system.cpu.icache.occ_blocks::0 1805.600642 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.881641 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 12180359 # number of ReadReq hits +system.cpu.icache.demand_hits 12180359 # number of demand (read+write) hits +system.cpu.icache.overall_hits 12180359 # number of overall hits +system.cpu.icache.ReadReq_misses 29272 # number of ReadReq misses +system.cpu.icache.demand_misses 29272 # number of demand (read+write) misses +system.cpu.icache.overall_misses 29272 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 357988500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 357988500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 357988500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 12209631 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 12209631 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 12209631 # number of overall (read+write) accesses +system.cpu.icache.ReadReq_miss_rate 0.002397 # miss rate for ReadReq accesses +system.cpu.icache.demand_miss_rate 0.002397 # miss rate for demand accesses +system.cpu.icache.overall_miss_rate 0.002397 # miss rate for overall accesses +system.cpu.icache.ReadReq_avg_miss_latency 12229.724652 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 12229.724652 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 12229.724652 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -365,67 +365,67 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 1 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 1069 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 1069 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 1069 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 28161 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 28161 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 28161 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 1063 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 1063 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 1063 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 28209 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 28209 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 28209 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 246973000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 246973000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 246973000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 247071500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 247071500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 247071500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.002307 # mshr miss rate for ReadReq accesses -system.cpu.icache.demand_mshr_miss_rate 0.002307 # mshr miss rate for demand accesses -system.cpu.icache.overall_mshr_miss_rate 0.002307 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 8770.036575 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 8770.036575 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 8770.036575 # average overall mshr miss latency +system.cpu.icache.ReadReq_mshr_miss_rate 0.002310 # mshr miss rate for ReadReq accesses +system.cpu.icache.demand_mshr_miss_rate 0.002310 # mshr miss rate for demand accesses +system.cpu.icache.overall_mshr_miss_rate 0.002310 # mshr miss rate for overall accesses +system.cpu.icache.ReadReq_avg_mshr_miss_latency 8758.605410 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 8758.605410 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 8758.605410 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 157879 # number of replacements -system.cpu.dcache.tagsinuse 4072.329363 # Cycle average of tags in use -system.cpu.dcache.total_refs 44742203 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 161975 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 276.229066 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 306596000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4072.329363 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.994221 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 26395464 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 18310275 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 18919 # number of LoadLockedReq hits -system.cpu.dcache.StoreCondReq_hits 17375 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 44705739 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 44705739 # number of overall hits -system.cpu.dcache.ReadReq_misses 108834 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 1539626 # number of WriteReq misses -system.cpu.dcache.LoadLockedReq_misses 27 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 1648460 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 1648460 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 2418698500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 52283649500 # number of WriteReq miss cycles -system.cpu.dcache.LoadLockedReq_miss_latency 386000 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 54702348000 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 54702348000 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 26504298 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.replacements 157892 # number of replacements +system.cpu.dcache.tagsinuse 4072.334227 # Cycle average of tags in use +system.cpu.dcache.total_refs 44746410 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 161988 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 276.232869 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 306594000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4072.334227 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.994222 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 26399659 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 18310286 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 18924 # number of LoadLockedReq hits +system.cpu.dcache.StoreCondReq_hits 17376 # number of StoreCondReq hits +system.cpu.dcache.demand_hits 44709945 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 44709945 # number of overall hits +system.cpu.dcache.ReadReq_misses 108879 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 1539615 # number of WriteReq misses +system.cpu.dcache.LoadLockedReq_misses 26 # number of LoadLockedReq misses +system.cpu.dcache.demand_misses 1648494 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 1648494 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 2418798500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 52283607500 # number of WriteReq miss cycles +system.cpu.dcache.LoadLockedReq_miss_latency 349000 # number of LoadLockedReq miss cycles +system.cpu.dcache.demand_miss_latency 54702406000 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 54702406000 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 26508538 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 19849901 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 18946 # number of LoadLockedReq accesses(hits+misses) -system.cpu.dcache.StoreCondReq_accesses 17375 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 46354199 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 46354199 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.004106 # miss rate for ReadReq accesses +system.cpu.dcache.LoadLockedReq_accesses 18950 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.StoreCondReq_accesses 17376 # number of StoreCondReq accesses(hits+misses) +system.cpu.dcache.demand_accesses 46358439 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 46358439 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.004107 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.077563 # miss rate for WriteReq accesses -system.cpu.dcache.LoadLockedReq_miss_rate 0.001425 # miss rate for LoadLockedReq accesses -system.cpu.dcache.demand_miss_rate 0.035562 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.035562 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 22223.739824 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 33958.668859 # average WriteReq miss latency -system.cpu.dcache.LoadLockedReq_avg_miss_latency 14296.296296 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 33183.909831 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 33183.909831 # average overall miss latency +system.cpu.dcache.LoadLockedReq_miss_rate 0.001372 # miss rate for LoadLockedReq accesses +system.cpu.dcache.demand_miss_rate 0.035560 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.035560 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 22215.473140 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 33958.884202 # average WriteReq miss latency +system.cpu.dcache.LoadLockedReq_avg_miss_latency 13423.076923 # average LoadLockedReq miss latency +system.cpu.dcache.demand_avg_miss_latency 33183.260600 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 33183.260600 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 190500 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -434,74 +434,74 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets 19050 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 123472 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 53734 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 1432703 # number of WriteReq MSHR hits -system.cpu.dcache.LoadLockedReq_mshr_hits 27 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 1486437 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 1486437 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 55100 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 106923 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 162023 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 162023 # number of overall MSHR misses +system.cpu.dcache.writebacks 123473 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 53766 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 1432695 # number of WriteReq MSHR hits +system.cpu.dcache.LoadLockedReq_mshr_hits 26 # number of LoadLockedReq MSHR hits +system.cpu.dcache.demand_mshr_hits 1486461 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 1486461 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 55113 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 106920 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 162033 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 162033 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 1035726000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 3662471000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 4698197000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 4698197000 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 1035745500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 3662420000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 4698165500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 4698165500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.002079 # mshr miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_mshr_miss_rate 0.005387 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.005386 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.003495 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.003495 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 18797.205082 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34253.350542 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 28997.099177 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 28997.099177 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 18793.125034 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34253.834643 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 28995.115193 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 28995.115193 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 114920 # number of replacements -system.cpu.l2cache.tagsinuse 18304.700184 # Cycle average of tags in use -system.cpu.l2cache.total_refs 72415 # Total number of references to valid blocks. +system.cpu.l2cache.replacements 114916 # number of replacements +system.cpu.l2cache.tagsinuse 18304.706842 # Cycle average of tags in use +system.cpu.l2cache.total_refs 72481 # Total number of references to valid blocks. system.cpu.l2cache.sampled_refs 133774 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 0.541323 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.541817 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 2370.650310 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 15934.049874 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.072347 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.486269 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 50510 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 123473 # number of Writeback hits -system.cpu.l2cache.UpgradeReq_hits 16 # number of UpgradeReq hits -system.cpu.l2cache.ReadExReq_hits 4309 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 54819 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 54819 # number of overall hits -system.cpu.l2cache.ReadReq_misses 32664 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 31 # number of UpgradeReq misses -system.cpu.l2cache.ReadExReq_misses 102598 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 135262 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 135262 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 1118309000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 3526121000 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 4644430000 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 4644430000 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 83174 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 123473 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 47 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.occ_blocks::0 2370.559791 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 15934.147051 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.072344 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.486272 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 50571 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 123474 # number of Writeback hits +system.cpu.l2cache.UpgradeReq_hits 14 # number of UpgradeReq hits +system.cpu.l2cache.ReadExReq_hits 4310 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 54881 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 54881 # number of overall hits +system.cpu.l2cache.ReadReq_misses 32667 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 30 # number of UpgradeReq misses +system.cpu.l2cache.ReadExReq_misses 102597 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 135264 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 135264 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 1118379000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 3526118000 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 4644497000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 4644497000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 83238 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 123474 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 44 # number of UpgradeReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_accesses 106907 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 190081 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 190081 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.392719 # miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_miss_rate 0.659574 # miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.959694 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.711602 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.711602 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34236.743816 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34368.321020 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34336.546850 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34336.546850 # average overall miss latency +system.cpu.l2cache.demand_accesses 190145 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 190145 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.392453 # miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_miss_rate 0.681818 # miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.959685 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.711373 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.711373 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34235.742492 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34368.626763 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34336.534481 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34336.534481 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -510,32 +510,32 @@ system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 88456 # number of writebacks -system.cpu.l2cache.ReadReq_mshr_hits 80 # number of ReadReq MSHR hits -system.cpu.l2cache.demand_mshr_hits 80 # number of demand (read+write) MSHR hits -system.cpu.l2cache.overall_mshr_hits 80 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 32584 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 31 # number of UpgradeReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 102598 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 135182 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 135182 # number of overall MSHR misses +system.cpu.l2cache.writebacks 88457 # number of writebacks +system.cpu.l2cache.ReadReq_mshr_hits 81 # number of ReadReq MSHR hits +system.cpu.l2cache.demand_mshr_hits 81 # number of demand (read+write) MSHR hits +system.cpu.l2cache.overall_mshr_hits 81 # number of overall MSHR hits +system.cpu.l2cache.ReadReq_mshr_misses 32586 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 30 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 102597 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 135183 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 135183 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 1012754000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 962000 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 3197891500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 4210645500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 4210645500 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 1012814500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 931000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 3197894500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 4210709000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 4210709000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.391757 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.659574 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.959694 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.711181 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.711181 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31081.328259 # average ReadReq mshr miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31032.258065 # average UpgradeReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31169.140724 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31147.974582 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31147.974582 # average overall mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.391480 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.681818 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.959685 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.710947 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.710947 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31081.277236 # average ReadReq mshr miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31033.333333 # average UpgradeReq mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31169.473766 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31148.213903 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31148.213903 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/config.ini b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/config.ini index 669a8b83b..5b9d120fe 100644 --- a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=bzip2 input.source 1 -cwd=build/ARM_SE/tests/opt/long/60.bzip2/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/60.bzip2/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/bzip2 +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/bzip2 gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/simout b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/simout index 1474108e5..90c937ca7 100755 --- a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/simout @@ -1,10 +1,12 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/60.bzip2/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/60.bzip2/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 09:36:09 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/60.bzip2/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/60.bzip2/arm/linux/o3-timing +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:20 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/60.bzip2/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/60.bzip2/arm/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... spec_init @@ -24,4 +26,4 @@ Uncompressing Data Uncompressed data 1048576 bytes in length Uncompressed data compared correctly Tested 1MB buffer: OK! -Exiting @ tick 483463019500 because target called exit() +Exiting @ tick 483300356500 because target called exit() diff --git a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/stats.txt index bd2b3efef..8595a64e2 100644 --- a/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/60.bzip2/ref/arm/linux/o3-timing/stats.txt @@ -1,24 +1,24 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.483463 # Number of seconds simulated -sim_ticks 483463019500 # Number of ticks simulated -final_tick 483463019500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.483300 # Number of seconds simulated +sim_ticks 483300356500 # Number of ticks simulated +final_tick 483300356500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 152421 # Simulator instruction rate (inst/s) -host_tick_rate 42766664 # Simulator tick rate (ticks/s) -host_mem_usage 220608 # Number of bytes of host memory used -host_seconds 11304.67 # Real time elapsed on the host +host_inst_rate 96252 # Simulator instruction rate (inst/s) +host_tick_rate 26997552 # Simulator tick rate (ticks/s) +host_mem_usage 256412 # Number of bytes of host memory used +host_seconds 17901.64 # Real time elapsed on the host sim_insts 1723073849 # Number of instructions simulated -system.physmem.bytes_read 188174592 # Number of bytes read from this memory -system.physmem.bytes_inst_read 45888 # Number of instructions bytes read from this memory -system.physmem.bytes_written 77926272 # Number of bytes written to this memory -system.physmem.num_reads 2940228 # Number of read requests responded to by this memory -system.physmem.num_writes 1217598 # Number of write requests responded to by this memory +system.physmem.bytes_read 188191232 # Number of bytes read from this memory +system.physmem.bytes_inst_read 45952 # Number of instructions bytes read from this memory +system.physmem.bytes_written 77928320 # Number of bytes written to this memory +system.physmem.num_reads 2940488 # Number of read requests responded to by this memory +system.physmem.num_writes 1217630 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 389222307 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 94915 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_write 161183522 # Write bandwidth from this memory (bytes/s) -system.physmem.bw_total 550405829 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 389387737 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 95080 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_write 161242008 # Write bandwidth from this memory (bytes/s) +system.physmem.bw_total 550629745 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -62,141 +62,141 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 46 # Number of system calls -system.cpu.numCycles 966926040 # number of cpu cycles simulated +system.cpu.numCycles 966600714 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 298898243 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 243989412 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 18339920 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 264347245 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 238745657 # Number of BTB hits +system.cpu.BPredUnit.lookups 298802813 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 243899992 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 18315213 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 264194846 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 238628617 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 17668157 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 3423 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 295953389 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 2175230772 # Number of instructions fetch has processed -system.cpu.fetch.Branches 298898243 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 256413814 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 484717826 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 87053301 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 107577195 # Number of cycles fetch has spent blocked +system.cpu.BPredUnit.usedRAS 17678661 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 3338 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 296004888 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 2174228266 # Number of instructions fetch has processed +system.cpu.fetch.Branches 298802813 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 256307278 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 484507329 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 86919023 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 107617273 # Number of cycles fetch has spent blocked system.cpu.fetch.MiscStallCycles 8 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 142 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 285045078 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 5311594 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 956547645 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.521914 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.026495 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.PendingTrapStallCycles 140 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 285078339 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 5300000 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 956319158 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.521362 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.026261 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 471829873 49.33% 49.33% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 35367236 3.70% 53.02% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 65085859 6.80% 59.83% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 66860371 6.99% 66.82% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 46850107 4.90% 71.72% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 59747954 6.25% 77.96% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 54343246 5.68% 83.64% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 17692463 1.85% 85.49% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 138770536 14.51% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 471811881 49.34% 49.34% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 35281645 3.69% 53.03% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 65131283 6.81% 59.84% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 66854544 6.99% 66.83% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 46816923 4.90% 71.72% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 59777101 6.25% 77.97% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 54237422 5.67% 83.64% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 17725648 1.85% 85.50% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 138682711 14.50% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 956547645 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.309122 # Number of branch fetches per cycle -system.cpu.fetch.rate 2.249635 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 322987122 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 92097194 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 459538157 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 13626726 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 68298446 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 46874540 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 671 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 2352694278 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 2235 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 68298446 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 343127088 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 46537686 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 27220 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 451783493 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 46773712 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 2295847883 # Number of instructions processed by rename -system.cpu.rename.ROBFullEvents 19963 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 2697037 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 37730930 # Number of times rename has blocked due to LSQ full +system.cpu.fetch.rateDist::total 956319158 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.309127 # Number of branch fetches per cycle +system.cpu.fetch.rate 2.249355 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 322991638 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 92138952 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 459388324 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 13611363 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 68188881 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 46868404 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 664 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 2351885426 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 2233 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 68188881 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 343108382 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 46584354 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 25758 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 451644595 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 46767188 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 2295012184 # Number of instructions processed by rename +system.cpu.rename.ROBFullEvents 19840 # Number of times rename has blocked due to ROB full +system.cpu.rename.IQFullEvents 2699078 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 37731214 # Number of times rename has blocked due to LSQ full system.cpu.rename.FullRegisterEvents 3 # Number of times there has been no free registers -system.cpu.rename.RenamedOperands 2264588148 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 10605407368 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 10605405778 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 1590 # Number of floating rename lookups +system.cpu.rename.RenamedOperands 2263685405 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 10601312044 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 10601310861 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 1183 # Number of floating rename lookups system.cpu.rename.CommittedMaps 1706319951 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 558268197 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 10043 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 10038 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 98804137 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 618742816 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 222099567 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 74239442 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 61602093 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 2187718033 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 2090 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 2018498325 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 3274725 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 458502719 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 1049949895 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 1587 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 956547645 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 2.110191 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.840946 # Number of insts issued each cycle +system.cpu.rename.UndoneMaps 557365454 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 9613 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 9609 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 98574159 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 618665433 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 221947140 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 73974093 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 60832432 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 2187079584 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 2062 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 2018219576 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 3314512 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 457863024 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 1047846495 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 1559 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 956319158 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 2.110404 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.840875 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 262039584 27.39% 27.39% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 150878554 15.77% 43.17% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 168430661 17.61% 60.78% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 136432052 14.26% 75.04% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 124835406 13.05% 88.09% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 73540708 7.69% 95.78% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 29241453 3.06% 98.83% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 10225405 1.07% 99.90% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 923822 0.10% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 261846751 27.38% 27.38% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 150992981 15.79% 43.17% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 168342829 17.60% 60.77% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 136328017 14.26% 75.03% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 124939866 13.06% 88.09% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 73493141 7.69% 95.78% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 29213551 3.05% 98.83% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 10245765 1.07% 99.90% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 916257 0.10% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 956547645 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 956319158 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 901388 3.68% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 177 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 3.68% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 19016870 77.70% 81.38% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 4557312 18.62% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 899945 3.67% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 187 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 3.67% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 19005921 77.47% 81.14% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 4627423 18.86% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 1238993791 61.38% 61.38% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 1017752 0.05% 61.43% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 1238740250 61.38% 61.38% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 1017622 0.05% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 2 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 61.43% # Type of FU issued @@ -218,91 +218,91 @@ system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 61.43% # Ty system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 61.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 14 0.00% 61.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 3 0.00% 61.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 13 0.00% 61.43% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 2 0.00% 61.43% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 6 0.00% 61.43% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 1 0.00% 61.43% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 7 0.00% 61.43% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 61.43% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 61.43% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 583952461 28.93% 90.36% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 194534287 9.64% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 583895352 28.93% 90.36% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 194566336 9.64% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 2018498325 # Type of FU issued -system.cpu.iq.rate 2.087542 # Inst issue rate -system.cpu.iq.fu_busy_cnt 24475747 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.012126 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 5021294480 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 2646401011 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 1958335598 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 287 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 294 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 124 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 2042973928 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 144 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 55719619 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 2018219576 # Type of FU issued +system.cpu.iq.rate 2.087956 # Inst issue rate +system.cpu.iq.fu_busy_cnt 24533476 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.012156 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 5020606045 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 2645122896 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 1958251270 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 253 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 238 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 108 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 2042752922 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 130 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 55694024 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 132816045 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 210497 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 180679 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 47252521 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 132738662 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 211257 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 180594 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 47100094 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread0.rescheduledLoads 2 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread0.cacheBlocked 451790 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread0.cacheBlocked 451914 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 68298446 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 22155006 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 1213609 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 2187738627 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 7300026 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 618742816 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 222099567 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 2027 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 219640 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 61277 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 180679 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 18953795 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 1821941 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 20775736 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 1986087052 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 570299160 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 32411273 # Number of squashed instructions skipped in execute +system.cpu.iew.iewSquashCycles 68188881 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 22161421 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 1213363 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 2187099355 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 7278228 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 618665433 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 221947140 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 1999 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 219629 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 61218 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 180594 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 18897487 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 1819209 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 20716696 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 1985947715 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 570245268 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 32271861 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 18504 # number of nop insts executed -system.cpu.iew.exec_refs 761501875 # number of memory reference insts executed -system.cpu.iew.exec_branches 238650211 # Number of branches executed -system.cpu.iew.exec_stores 191202715 # Number of stores executed -system.cpu.iew.exec_rate 2.054022 # Inst execution rate -system.cpu.iew.wb_sent 1967277607 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 1958335722 # cumulative count of insts written-back -system.cpu.iew.wb_producers 1288034280 # num instructions producing a value -system.cpu.iew.wb_consumers 2036866160 # num instructions consuming a value +system.cpu.iew.exec_nop 17709 # number of nop insts executed +system.cpu.iew.exec_refs 761448250 # number of memory reference insts executed +system.cpu.iew.exec_branches 238637230 # Number of branches executed +system.cpu.iew.exec_stores 191202982 # Number of stores executed +system.cpu.iew.exec_rate 2.054569 # Inst execution rate +system.cpu.iew.wb_sent 1967185295 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 1958251378 # cumulative count of insts written-back +system.cpu.iew.wb_producers 1288041557 # num instructions producing a value +system.cpu.iew.wb_consumers 2036752533 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 2.025321 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.632361 # average fanout of values written-back +system.cpu.iew.wb_rate 2.025916 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.632400 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 1723073867 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 464746992 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 464107908 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 503 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 18339818 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 888249200 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.939854 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 2.672088 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 18315306 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 888130278 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.940114 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 2.672278 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 383075847 43.13% 43.13% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 200735352 22.60% 65.73% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 81917807 9.22% 74.95% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 38649475 4.35% 79.30% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 19675094 2.22% 81.51% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 31029952 3.49% 85.01% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 22284246 2.51% 87.52% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 12052552 1.36% 88.87% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 98828875 11.13% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 382955223 43.12% 43.12% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 200739073 22.60% 65.72% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 81923550 9.22% 74.95% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 38679338 4.36% 79.30% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 19675426 2.22% 81.52% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 30976281 3.49% 85.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 22277703 2.51% 87.51% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 12029119 1.35% 88.87% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 98874565 11.13% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 888249200 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 888130278 # Number of insts commited each cycle system.cpu.commit.count 1723073867 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 660773817 # Number of memory references committed @@ -312,50 +312,50 @@ system.cpu.commit.branches 213462365 # Nu system.cpu.commit.fp_insts 36 # Number of committed floating point instructions. system.cpu.commit.int_insts 1536941853 # Number of committed integer instructions. system.cpu.commit.function_calls 13665177 # Number of function calls committed. -system.cpu.commit.bw_lim_events 98828875 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 98874565 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 2977240585 # The number of ROB reads -system.cpu.rob.rob_writes 4444170390 # The number of ROB writes -system.cpu.timesIdled 920776 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 10378395 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 2976436889 # The number of ROB reads +system.cpu.rob.rob_writes 4442782654 # The number of ROB writes +system.cpu.timesIdled 920078 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 10281556 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 1723073849 # Number of Instructions Simulated system.cpu.committedInsts_total 1723073849 # Number of Instructions Simulated -system.cpu.cpi 0.561163 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.561163 # CPI: Total CPI of All Threads -system.cpu.ipc 1.782012 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.782012 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 9942029327 # number of integer regfile reads -system.cpu.int_regfile_writes 1939848996 # number of integer regfile writes -system.cpu.fp_regfile_reads 117 # number of floating regfile reads -system.cpu.fp_regfile_writes 59 # number of floating regfile writes -system.cpu.misc_regfile_reads 2913839911 # number of misc regfile reads +system.cpu.cpi 0.560975 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.560975 # CPI: Total CPI of All Threads +system.cpu.ipc 1.782612 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.782612 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 9941434858 # number of integer regfile reads +system.cpu.int_regfile_writes 1939754373 # number of integer regfile writes +system.cpu.fp_regfile_reads 96 # number of floating regfile reads +system.cpu.fp_regfile_writes 31 # number of floating regfile writes +system.cpu.misc_regfile_reads 2912823996 # number of misc regfile reads system.cpu.misc_regfile_writes 126 # number of misc regfile writes system.cpu.icache.replacements 10 # number of replacements -system.cpu.icache.tagsinuse 609.858480 # Cycle average of tags in use -system.cpu.icache.total_refs 285044064 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 744 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 383123.741935 # Average number of references to valid blocks. +system.cpu.icache.tagsinuse 609.966952 # Cycle average of tags in use +system.cpu.icache.total_refs 285077321 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 746 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 382141.180965 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 609.858480 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.297782 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 285044064 # number of ReadReq hits -system.cpu.icache.demand_hits 285044064 # number of demand (read+write) hits -system.cpu.icache.overall_hits 285044064 # number of overall hits -system.cpu.icache.ReadReq_misses 1014 # number of ReadReq misses -system.cpu.icache.demand_misses 1014 # number of demand (read+write) misses -system.cpu.icache.overall_misses 1014 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 35191500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 35191500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 35191500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 285045078 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 285045078 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 285045078 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 609.966952 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.297835 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 285077321 # number of ReadReq hits +system.cpu.icache.demand_hits 285077321 # number of demand (read+write) hits +system.cpu.icache.overall_hits 285077321 # number of overall hits +system.cpu.icache.ReadReq_misses 1018 # number of ReadReq misses +system.cpu.icache.demand_misses 1018 # number of demand (read+write) misses +system.cpu.icache.overall_misses 1018 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 35270500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 35270500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 35270500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 285078339 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 285078339 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 285078339 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000004 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000004 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000004 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 34705.621302 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 34705.621302 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 34705.621302 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 34646.856582 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 34646.856582 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 34646.856582 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -365,169 +365,169 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 270 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 270 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 270 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 744 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 744 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 744 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 272 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 272 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 272 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 746 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 746 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 746 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 25627000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 25627000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 25627000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 25653000 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 25653000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 25653000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000003 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000003 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000003 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 34444.892473 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 34444.892473 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 34444.892473 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 34387.399464 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 34387.399464 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 34387.399464 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 9570827 # number of replacements -system.cpu.dcache.tagsinuse 4087.732038 # Cycle average of tags in use -system.cpu.dcache.total_refs 666909210 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 9574923 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 69.651653 # Average number of references to valid blocks. -system.cpu.dcache.warmup_cycle 3484303000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 4087.732038 # Average occupied blocks per context +system.cpu.dcache.replacements 9570609 # number of replacements +system.cpu.dcache.tagsinuse 4087.729265 # Cycle average of tags in use +system.cpu.dcache.total_refs 666885051 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 9574705 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 69.650715 # Average number of references to valid blocks. +system.cpu.dcache.warmup_cycle 3484295000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.occ_blocks::0 4087.729265 # Average occupied blocks per context system.cpu.dcache.occ_percent::0 0.997981 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 499513800 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 167395288 # number of WriteReq hits +system.cpu.dcache.ReadReq_hits 499489564 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 167395365 # number of WriteReq hits system.cpu.dcache.LoadLockedReq_hits 60 # number of LoadLockedReq hits system.cpu.dcache.StoreCondReq_hits 62 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 666909088 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 666909088 # number of overall hits -system.cpu.dcache.ReadReq_misses 10448466 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 5190759 # number of WriteReq misses +system.cpu.dcache.demand_hits 666884929 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 666884929 # number of overall hits +system.cpu.dcache.ReadReq_misses 10445560 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 5190682 # number of WriteReq misses system.cpu.dcache.LoadLockedReq_misses 3 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 15639225 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 15639225 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 184465722500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 128555474171 # number of WriteReq miss cycles +system.cpu.dcache.demand_misses 15636242 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 15636242 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 184478558500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 128511717246 # number of WriteReq miss cycles system.cpu.dcache.LoadLockedReq_miss_latency 113500 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 313021196671 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 313021196671 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 509962266 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.demand_miss_latency 312990275746 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 312990275746 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 509935124 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 172586047 # number of WriteReq accesses(hits+misses) system.cpu.dcache.LoadLockedReq_accesses 63 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.StoreCondReq_accesses 62 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 682548313 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 682548313 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.020489 # miss rate for ReadReq accesses +system.cpu.dcache.demand_accesses 682521171 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 682521171 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.020484 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.030076 # miss rate for WriteReq accesses system.cpu.dcache.LoadLockedReq_miss_rate 0.047619 # miss rate for LoadLockedReq accesses -system.cpu.dcache.demand_miss_rate 0.022913 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate 0.022913 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 17654.813874 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 24766.219000 # average WriteReq miss latency +system.cpu.dcache.demand_miss_rate 0.022910 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate 0.022910 # miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_miss_latency 17660.954367 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 24758.156490 # average WriteReq miss latency system.cpu.dcache.LoadLockedReq_avg_miss_latency 37833.333333 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 20015.134808 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 20015.134808 # average overall miss latency -system.cpu.dcache.blocked_cycles::no_mshrs 266703683 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles::no_targets 196000 # number of cycles access was blocked -system.cpu.dcache.blocked::no_mshrs 90656 # number of cycles access was blocked -system.cpu.dcache.blocked::no_targets 12 # number of cycles access was blocked -system.cpu.dcache.avg_blocked_cycles::no_mshrs 2941.930848 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles::no_targets 16333.333333 # average number of cycles each access was blocked +system.cpu.dcache.demand_avg_miss_latency 20016.975674 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 20016.975674 # average overall miss latency +system.cpu.dcache.blocked_cycles::no_mshrs 266779202 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles::no_targets 225500 # number of cycles access was blocked +system.cpu.dcache.blocked::no_mshrs 90534 # number of cycles access was blocked +system.cpu.dcache.blocked::no_targets 14 # number of cycles access was blocked +system.cpu.dcache.avg_blocked_cycles::no_mshrs 2946.729428 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles::no_targets 16107.142857 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 3128328 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 2766203 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 3298099 # number of WriteReq MSHR hits +system.cpu.dcache.writebacks 3128454 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 2763491 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 3298046 # number of WriteReq MSHR hits system.cpu.dcache.LoadLockedReq_mshr_hits 3 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 6064302 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 6064302 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 7682263 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 1892660 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 9574923 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 9574923 # number of overall MSHR misses +system.cpu.dcache.demand_mshr_hits 6061537 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 6061537 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 7682069 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 1892636 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 9574705 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 9574705 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 92044930000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 45262385908 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 137307315908 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 137307315908 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 92052400500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 45263240996 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 137315641496 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 137315641496 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.015064 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate 0.015065 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.010966 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.014028 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.014028 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 11981.486445 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 23914.694614 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 14340.304972 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 14340.304972 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 11982.761480 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 23915.449667 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 14341.501017 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 14341.501017 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.replacements 2927819 # number of replacements -system.cpu.l2cache.tagsinuse 26780.774124 # Cycle average of tags in use -system.cpu.l2cache.total_refs 7851022 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 2955142 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 2.656733 # Average number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 102041743500 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 15984.490640 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 10796.283484 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.487808 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.329476 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 5655252 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 3128328 # number of Writeback hits -system.cpu.l2cache.ReadExReq_hits 980176 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 6635428 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 6635428 # number of overall hits -system.cpu.l2cache.ReadReq_misses 2027753 # number of ReadReq misses -system.cpu.l2cache.ReadExReq_misses 912486 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 2940239 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 2940239 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 69614113000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 31648901500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 101263014500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 101263014500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 7683005 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 3128328 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses 1892662 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 9575667 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 9575667 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.263927 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_miss_rate 0.482118 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.307053 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.307053 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34330.666999 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34684.259813 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34440.402464 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34440.402464 # average overall miss latency -system.cpu.l2cache.blocked_cycles::no_mshrs 56231500 # number of cycles access was blocked +system.cpu.l2cache.replacements 2928111 # number of replacements +system.cpu.l2cache.tagsinuse 26779.513847 # Cycle average of tags in use +system.cpu.l2cache.total_refs 7850665 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 2955434 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 2.656349 # Average number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 102043879500 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.occ_blocks::0 15980.141778 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 10799.372069 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.487675 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.329571 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 5654844 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 3128454 # number of Writeback hits +system.cpu.l2cache.ReadExReq_hits 980108 # number of ReadExReq hits +system.cpu.l2cache.demand_hits 6634952 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 6634952 # number of overall hits +system.cpu.l2cache.ReadReq_misses 2027970 # number of ReadReq misses +system.cpu.l2cache.ReadExReq_misses 912529 # number of ReadExReq misses +system.cpu.l2cache.demand_misses 2940499 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 2940499 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 69622687500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 31651212500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 101273900000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 101273900000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 7682814 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 3128454 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses 1892637 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.demand_accesses 9575451 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 9575451 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.263962 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_miss_rate 0.482147 # miss rate for ReadExReq accesses +system.cpu.l2cache.demand_miss_rate 0.307087 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.307087 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34331.221616 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34685.157951 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34441.059154 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34441.059154 # average overall miss latency +system.cpu.l2cache.blocked_cycles::no_mshrs 56425000 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked -system.cpu.l2cache.blocked::no_mshrs 6603 # number of cycles access was blocked +system.cpu.l2cache.blocked::no_mshrs 6634 # number of cycles access was blocked system.cpu.l2cache.blocked::no_targets 0 # number of cycles access was blocked -system.cpu.l2cache.avg_blocked_cycles::no_mshrs 8516.053309 # average number of cycles each access was blocked +system.cpu.l2cache.avg_blocked_cycles::no_mshrs 8505.426590 # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.writebacks 1217598 # number of writebacks +system.cpu.l2cache.writebacks 1217630 # number of writebacks system.cpu.l2cache.ReadReq_mshr_hits 11 # number of ReadReq MSHR hits system.cpu.l2cache.demand_mshr_hits 11 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 11 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 2027742 # number of ReadReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses 912486 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 2940228 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 2940228 # number of overall MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 2027959 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses 912529 # number of ReadExReq MSHR misses +system.cpu.l2cache.demand_mshr_misses 2940488 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 2940488 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 63235914500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency 28815026500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 92050941000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 92050941000 # number of overall MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 63243262500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 28812389000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 92055651500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 92055651500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.263926 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.482118 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.307052 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.307052 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31185.384778 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31578.595726 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31307.415955 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31307.415955 # average overall mshr miss latency +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.263960 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.482147 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.307086 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.307086 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31185.671160 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31574.217367 # average ReadExReq mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31306.249677 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31306.249677 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/config.ini b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/config.ini index 8db3f9119..ce56be1ef 100644 --- a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/config.ini +++ b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -80,6 +89,7 @@ max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 max_loads_any_thread=0 +needsTSO=false numIQEntries=64 numPhysFloatRegs=256 numPhysIntRegs=256 @@ -88,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -148,7 +159,16 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=ArmTLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -445,9 +465,21 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=ArmInterrupts + [system.cpu.itb] type=ArmTLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=ArmTableWalker +max_backoff=100000 +min_backoff=0 +sys=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -478,7 +510,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -489,7 +521,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -497,12 +529,12 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=twolf smred -cwd=build/ARM_SE/tests/opt/long/70.twolf/arm/linux/o3-timing +cwd=build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing egid=100 env= errout=cerr euid=100 -executable=/dist/m5/cpu2000/binaries/arm/linux/twolf +executable=/scratch/nilay/GEM5/dist/m5/cpu2000/binaries/arm/linux/twolf gid=100 input=cin max_stack_size=67108864 diff --git a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/simout b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/simout index bee9aa417..442ecd78f 100755 --- a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/simout +++ b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/simout @@ -1,12 +1,14 @@ +Redirecting stdout to build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 23 2012 04:16:21 -gem5 started Jan 23 2012 09:47:07 -gem5 executing on zizzer -command line: build/ARM_SE/gem5.opt -d build/ARM_SE/tests/opt/long/70.twolf/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/opt/long/70.twolf/arm/linux/o3-timing -Couldn't unlink build/ARM_SE/tests/opt/long/70.twolf/arm/linux/o3-timing/smred.sav -Couldn't unlink build/ARM_SE/tests/opt/long/70.twolf/arm/linux/o3-timing/smred.sv2 +gem5 compiled Feb 10 2012 00:18:03 +gem5 started Feb 10 2012 00:18:20 +gem5 executing on ribera.cs.wisc.edu +command line: build/ARM/gem5.opt -d build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing -re tests/run.py build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing +Couldn't unlink build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing/smred.sav +Couldn't unlink build/ARM/tests/opt/long/se/70.twolf/arm/linux/o3-timing/smred.sv2 Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -23,4 +25,4 @@ info: Increasing stack size by one page. 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 -122 123 124 Exiting @ tick 105874925000 because target called exit() +122 123 124 Exiting @ tick 105850842000 because target called exit() diff --git a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/stats.txt b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/stats.txt index 4282a0231..83e315e2a 100644 --- a/tests/long/se/70.twolf/ref/arm/linux/o3-timing/stats.txt +++ b/tests/long/se/70.twolf/ref/arm/linux/o3-timing/stats.txt @@ -1,23 +1,23 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.105875 # Number of seconds simulated -sim_ticks 105874925000 # Number of ticks simulated -final_tick 105874925000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.105851 # Number of seconds simulated +sim_ticks 105850842000 # Number of ticks simulated +final_tick 105850842000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 103612 # Simulator instruction rate (inst/s) -host_tick_rate 58144234 # Simulator tick rate (ticks/s) -host_mem_usage 224188 # Number of bytes of host memory used -host_seconds 1820.90 # Real time elapsed on the host -sim_insts 188667572 # Number of instructions simulated -system.physmem.bytes_read 240192 # Number of bytes read from this memory -system.physmem.bytes_inst_read 128512 # Number of instructions bytes read from this memory +host_inst_rate 46914 # Simulator instruction rate (inst/s) +host_tick_rate 26320721 # Simulator tick rate (ticks/s) +host_mem_usage 259812 # Number of bytes of host memory used +host_seconds 4021.58 # Real time elapsed on the host +sim_insts 188667627 # Number of instructions simulated +system.physmem.bytes_read 239936 # Number of bytes read from this memory +system.physmem.bytes_inst_read 128320 # Number of instructions bytes read from this memory system.physmem.bytes_written 0 # Number of bytes written to this memory -system.physmem.num_reads 3753 # Number of read requests responded to by this memory +system.physmem.num_reads 3749 # Number of read requests responded to by this memory system.physmem.num_writes 0 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 2268639 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 1213810 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_total 2268639 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 2266737 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 1212272 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_total 2266737 # Total bandwidth to/from this memory (bytes/s) system.cpu.dtb.inst_hits 0 # ITB inst hits system.cpu.dtb.inst_misses 0 # ITB inst misses system.cpu.dtb.read_hits 0 # DTB read hits @@ -61,105 +61,105 @@ system.cpu.itb.hits 0 # DT system.cpu.itb.misses 0 # DTB misses system.cpu.itb.accesses 0 # DTB accesses system.cpu.workload.num_syscalls 400 # Number of system calls -system.cpu.numCycles 211749851 # number of cpu cycles simulated +system.cpu.numCycles 211701685 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 102127285 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 80698368 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 9933568 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 84243150 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 79257318 # Number of BTB hits +system.cpu.BPredUnit.lookups 102100879 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 80677195 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 9930193 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 84233443 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 79245701 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.BPredUnit.usedRAS 4698618 # Number of times the RAS was used to get a target. -system.cpu.BPredUnit.RASInCorrect 111511 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 44551125 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 416786863 # Number of instructions fetch has processed -system.cpu.fetch.Branches 102127285 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 83955936 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 108810185 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 33218375 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 35074253 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 9 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 251 # Number of stall cycles due to pending traps +system.cpu.BPredUnit.usedRAS 4698090 # Number of times the RAS was used to get a target. +system.cpu.BPredUnit.RASInCorrect 111402 # Number of incorrect RAS predictions. +system.cpu.fetch.icacheStallCycles 44542965 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 416708415 # Number of instructions fetch has processed +system.cpu.fetch.Branches 102100879 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 83943791 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 108793327 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 33207424 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 35058719 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 11 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 259 # Number of stall cycles due to pending traps system.cpu.fetch.PendingQuiesceStallCycles 1 # Number of stall cycles due to pending quiesce instructions -system.cpu.fetch.CacheLines 40624886 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 2204416 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 211691341 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.135529 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 2.646861 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.CacheLines 40619675 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 2204435 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 211643202 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.135620 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 2.646860 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 103083318 48.70% 48.70% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 4611723 2.18% 50.87% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 32955553 15.57% 66.44% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 18242297 8.62% 75.06% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 9176940 4.34% 79.39% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 12529739 5.92% 85.31% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 8472403 4.00% 89.31% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 4322449 2.04% 91.36% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 18296919 8.64% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 103052143 48.69% 48.69% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 4614041 2.18% 50.87% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 32953123 15.57% 66.44% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 18235328 8.62% 75.06% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 9171108 4.33% 79.39% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 12530200 5.92% 85.31% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 8476968 4.01% 89.32% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 4316297 2.04% 91.36% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 18293994 8.64% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 211691341 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.482302 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.968298 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 53244805 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 33622636 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 100506105 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 1219607 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 23098188 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 14186059 # Number of times decode resolved a branch -system.cpu.decode.BranchMispred 166456 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 422686981 # Number of instructions handled by decode -system.cpu.decode.SquashedInsts 695509 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 23098188 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 62205667 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 461892 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 28663713 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 92688664 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 4573217 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 388586256 # Number of instructions processed by rename -system.cpu.rename.IQFullEvents 22473 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 2248529 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RenamedOperands 666261253 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 1656600047 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 1638859233 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 17740814 # Number of floating rename lookups -system.cpu.rename.CommittedMaps 298061848 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 368199405 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 2723713 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 2675909 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 23519864 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 46897665 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 16902365 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 3883401 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 2525721 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 332696460 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqNonSpecInstsAdded 2225712 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 261853052 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 956132 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 143515224 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 342118821 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.iq.iqSquashedNonSpecRemoved 589705 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 211691341 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.236957 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.489139 # Number of insts issued each cycle +system.cpu.fetch.rateDist::total 211643202 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.482287 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.968376 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 53231519 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 33609414 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 100494512 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 1217161 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 23090596 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 14181130 # Number of times decode resolved a branch +system.cpu.decode.BranchMispred 166488 # Number of times decode detected a branch misprediction +system.cpu.decode.DecodedInsts 422617374 # Number of instructions handled by decode +system.cpu.decode.SquashedInsts 695976 # Number of squashed instructions handled by decode +system.cpu.rename.SquashCycles 23090596 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 62189594 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 455687 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 28663702 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 92677243 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 4566380 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 388527700 # Number of instructions processed by rename +system.cpu.rename.IQFullEvents 20997 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 2241803 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RenamedOperands 666137382 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 1656361753 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 1638646831 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 17714922 # Number of floating rename lookups +system.cpu.rename.CommittedMaps 298061936 # Number of HB maps that are committed +system.cpu.rename.UndoneMaps 368075446 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 2723266 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 2675408 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 23504222 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 46900559 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 16903337 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 3858030 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 2525525 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 332647611 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqNonSpecInstsAdded 2225423 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqInstsIssued 261830951 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 960204 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 143464205 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 342029155 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedNonSpecRemoved 589405 # Number of squashed non-spec instructions that were removed +system.cpu.iq.issued_per_cycle::samples 211643202 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.237134 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.489338 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 97854722 46.23% 46.23% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 37874169 17.89% 64.12% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 34110087 16.11% 80.23% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 22786114 10.76% 90.99% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 11453676 5.41% 96.40% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 4761165 2.25% 98.65% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 2318956 1.10% 99.75% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 393514 0.19% 99.93% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 138938 0.07% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 97826086 46.22% 46.22% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 37864076 17.89% 64.11% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 34104807 16.11% 80.23% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 22781361 10.76% 90.99% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 11447248 5.41% 96.40% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 4765675 2.25% 98.65% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 2321089 1.10% 99.75% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 393603 0.19% 99.93% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 139257 0.07% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 211691341 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 211643202 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 398184 18.25% 18.25% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 397917 18.24% 18.24% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 5522 0.25% 18.50% # attempts to use FU when none available system.cpu.iq.fu_full::IntDiv 0 0.00% 18.50% # attempts to use FU when none available system.cpu.iq.fu_full::FloatAdd 0 0.00% 18.50% # attempts to use FU when none available @@ -179,22 +179,22 @@ system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 18.50% # at system.cpu.iq.fu_full::SimdShift 0 0.00% 18.50% # attempts to use FU when none available system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 18.50% # attempts to use FU when none available system.cpu.iq.fu_full::SimdSqrt 0 0.00% 18.50% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 54 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 48 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 18.51% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 1324595 60.71% 79.22% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 453293 20.78% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 50 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 46 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 18.50% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 1324685 60.73% 79.23% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 453082 20.77% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 204944335 78.27% 78.27% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 928862 0.35% 78.62% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 204918446 78.26% 78.26% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 928788 0.35% 78.62% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 78.62% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 78.62% # Type of FU issued system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 78.62% # Type of FU issued @@ -213,147 +213,147 @@ system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 78.62% # Ty system.cpu.iq.FU_type_0::SimdShift 0 0.00% 78.62% # Type of FU issued system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 78.62% # Type of FU issued system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 78.62% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 33072 0.01% 78.63% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 33078 0.01% 78.63% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 78.63% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 166569 0.06% 78.70% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 257495 0.10% 78.80% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 76397 0.03% 78.83% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 468208 0.18% 79.00% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 207568 0.08% 79.08% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 71821 0.03% 79.11% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 166576 0.06% 78.69% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 257183 0.10% 78.79% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 76398 0.03% 78.82% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 467924 0.18% 79.00% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 207596 0.08% 79.08% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 71825 0.03% 79.11% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 325 0.00% 79.11% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 40739224 15.56% 94.67% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 13959176 5.33% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 40744644 15.56% 94.67% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 13958168 5.33% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 261853052 # Type of FU issued -system.cpu.iq.rate 1.236615 # Inst issue rate -system.cpu.iq.fu_busy_cnt 2181696 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.008332 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 734785745 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 476212492 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 242882419 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 3749528 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 2237188 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 1845400 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 262148601 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 1886147 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 1588917 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 261830951 # Type of FU issued +system.cpu.iq.rate 1.236792 # Inst issue rate +system.cpu.iq.fu_busy_cnt 2181302 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.008331 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 734699293 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 476117347 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 242859396 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 3747317 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 2232204 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 1844998 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 262127165 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 1885088 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 1590290 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 17045968 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 31330 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 12732 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 4255519 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 17048851 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 31549 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 12762 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 4256480 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 19 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.rescheduledLoads 20 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 1 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 23098188 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 13857 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 833 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 334975630 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 3751995 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 46897665 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 16902365 # Number of dispatched store instructions -system.cpu.iew.iewDispNonSpecInsts 2201836 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 328 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 23090596 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 13781 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 840 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 334926486 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 3752435 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 46900559 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 16903337 # Number of dispatched store instructions +system.cpu.iew.iewDispNonSpecInsts 2201532 # Number of dispatched non-speculative instructions +system.cpu.iew.iewIQFullEvents 340 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewLSQFullEvents 255 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 12732 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 9997150 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 1695546 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 11692696 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 249230612 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 38607191 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 12622440 # Number of squashed instructions skipped in execute +system.cpu.iew.memOrderViolationEvents 12762 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 9994816 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 1695108 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 11689924 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 249206258 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 38606621 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 12624693 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed -system.cpu.iew.exec_nop 53458 # number of nop insts executed -system.cpu.iew.exec_refs 52205543 # number of memory reference insts executed -system.cpu.iew.exec_branches 52589382 # Number of branches executed -system.cpu.iew.exec_stores 13598352 # Number of stores executed -system.cpu.iew.exec_rate 1.177005 # Inst execution rate -system.cpu.iew.wb_sent 246260336 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 244727819 # cumulative count of insts written-back -system.cpu.iew.wb_producers 148531018 # num instructions producing a value -system.cpu.iew.wb_consumers 247826872 # num instructions consuming a value +system.cpu.iew.exec_nop 53452 # number of nop insts executed +system.cpu.iew.exec_refs 52203623 # number of memory reference insts executed +system.cpu.iew.exec_branches 52584405 # Number of branches executed +system.cpu.iew.exec_stores 13597002 # Number of stores executed +system.cpu.iew.exec_rate 1.177158 # Inst execution rate +system.cpu.iew.wb_sent 246234772 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 244704394 # cumulative count of insts written-back +system.cpu.iew.wb_producers 148512928 # num instructions producing a value +system.cpu.iew.wb_consumers 247801271 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.155740 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.599334 # average fanout of values written-back +system.cpu.iew.wb_rate 1.155893 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.599323 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.commit.commitCommittedInsts 188681960 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 146293697 # The number of squashed insts skipped by commit -system.cpu.commit.commitNonSpecStalls 1636007 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 9795278 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 188593154 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.000471 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.681076 # Number of insts commited each cycle +system.cpu.commit.commitCommittedInsts 188682015 # The number of committed instructions +system.cpu.commit.commitSquashedInsts 146244510 # The number of squashed insts skipped by commit +system.cpu.commit.commitNonSpecStalls 1636018 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.branchMispredicts 9791900 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 188552607 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.000686 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.681539 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 105401505 55.89% 55.89% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 40855723 21.66% 77.55% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 19482895 10.33% 87.88% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 8763575 4.65% 92.53% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 4920568 2.61% 95.14% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 2013461 1.07% 96.21% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 1707502 0.91% 97.11% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 1008267 0.53% 97.65% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 4439658 2.35% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 105375521 55.89% 55.89% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 40844225 21.66% 77.55% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 19484606 10.33% 87.88% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 8759294 4.65% 92.53% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 4914501 2.61% 95.13% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 2011973 1.07% 96.20% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 1708688 0.91% 97.11% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 1009693 0.54% 97.64% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 4444106 2.36% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 188593154 # Number of insts commited each cycle -system.cpu.commit.count 188681960 # Number of instructions committed +system.cpu.commit.committed_per_cycle::total 188552607 # Number of insts commited each cycle +system.cpu.commit.count 188682015 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.refs 42498543 # Number of memory references committed -system.cpu.commit.loads 29851697 # Number of loads committed +system.cpu.commit.refs 42498565 # Number of memory references committed +system.cpu.commit.loads 29851708 # Number of loads committed system.cpu.commit.membars 22408 # Number of memory barriers committed -system.cpu.commit.branches 40283895 # Number of branches committed +system.cpu.commit.branches 40283906 # Number of branches committed system.cpu.commit.fp_insts 1752310 # Number of committed floating point instructions. -system.cpu.commit.int_insts 150115073 # Number of committed integer instructions. +system.cpu.commit.int_insts 150115117 # Number of committed integer instructions. system.cpu.commit.function_calls 1848934 # Number of function calls committed. -system.cpu.commit.bw_lim_events 4439658 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 4444106 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 519123952 # The number of ROB reads -system.cpu.rob.rob_writes 693113124 # The number of ROB writes -system.cpu.timesIdled 1721 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 58510 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.committedInsts 188667572 # Number of Instructions Simulated -system.cpu.committedInsts_total 188667572 # Number of Instructions Simulated -system.cpu.cpi 1.122344 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.122344 # CPI: Total CPI of All Threads -system.cpu.ipc 0.890993 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.890993 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 1112090730 # number of integer regfile reads -system.cpu.int_regfile_writes 407417013 # number of integer regfile writes -system.cpu.fp_regfile_reads 2928432 # number of floating regfile reads -system.cpu.fp_regfile_writes 2499453 # number of floating regfile writes -system.cpu.misc_regfile_reads 503028333 # number of misc regfile reads -system.cpu.misc_regfile_writes 824460 # number of misc regfile writes -system.cpu.icache.replacements 1929 # number of replacements -system.cpu.icache.tagsinuse 1329.893683 # Cycle average of tags in use -system.cpu.icache.total_refs 40620654 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 3638 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 11165.655305 # Average number of references to valid blocks. +system.cpu.rob.rob_reads 519029825 # The number of ROB reads +system.cpu.rob.rob_writes 693007050 # The number of ROB writes +system.cpu.timesIdled 1719 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 58483 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.committedInsts 188667627 # Number of Instructions Simulated +system.cpu.committedInsts_total 188667627 # Number of Instructions Simulated +system.cpu.cpi 1.122088 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.122088 # CPI: Total CPI of All Threads +system.cpu.ipc 0.891196 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.891196 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 1111988877 # number of integer regfile reads +system.cpu.int_regfile_writes 407368356 # number of integer regfile writes +system.cpu.fp_regfile_reads 2928539 # number of floating regfile reads +system.cpu.fp_regfile_writes 2498508 # number of floating regfile writes +system.cpu.misc_regfile_reads 502946356 # number of misc regfile reads +system.cpu.misc_regfile_writes 824482 # number of misc regfile writes +system.cpu.icache.replacements 1934 # number of replacements +system.cpu.icache.tagsinuse 1329.301324 # Cycle average of tags in use +system.cpu.icache.total_refs 40615441 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 3640 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 11158.088187 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1329.893683 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.649362 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 40620654 # number of ReadReq hits -system.cpu.icache.demand_hits 40620654 # number of demand (read+write) hits -system.cpu.icache.overall_hits 40620654 # number of overall hits -system.cpu.icache.ReadReq_misses 4232 # number of ReadReq misses -system.cpu.icache.demand_misses 4232 # number of demand (read+write) misses -system.cpu.icache.overall_misses 4232 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 101343500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 101343500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 101343500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 40624886 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 40624886 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 40624886 # number of overall (read+write) accesses +system.cpu.icache.occ_blocks::0 1329.301324 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.649073 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 40615441 # number of ReadReq hits +system.cpu.icache.demand_hits 40615441 # number of demand (read+write) hits +system.cpu.icache.overall_hits 40615441 # number of overall hits +system.cpu.icache.ReadReq_misses 4234 # number of ReadReq misses +system.cpu.icache.demand_misses 4234 # number of demand (read+write) misses +system.cpu.icache.overall_misses 4234 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 101275500 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 101275500 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 101275500 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 40619675 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 40619675 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 40619675 # number of overall (read+write) accesses system.cpu.icache.ReadReq_miss_rate 0.000104 # miss rate for ReadReq accesses system.cpu.icache.demand_miss_rate 0.000104 # miss rate for demand accesses system.cpu.icache.overall_miss_rate 0.000104 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 23946.951796 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 23946.951796 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 23946.951796 # average overall miss latency +system.cpu.icache.ReadReq_avg_miss_latency 23919.579594 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 23919.579594 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 23919.579594 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -366,64 +366,64 @@ system.cpu.icache.writebacks 0 # nu system.cpu.icache.ReadReq_mshr_hits 594 # number of ReadReq MSHR hits system.cpu.icache.demand_mshr_hits 594 # number of demand (read+write) MSHR hits system.cpu.icache.overall_mshr_hits 594 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 3638 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 3638 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 3638 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_misses 3640 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 3640 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 3640 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 74666000 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 74666000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 74666000 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 74572500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 74572500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 74572500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000090 # mshr miss rate for ReadReq accesses system.cpu.icache.demand_mshr_miss_rate 0.000090 # mshr miss rate for demand accesses system.cpu.icache.overall_mshr_miss_rate 0.000090 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 20523.914239 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 20523.914239 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 20523.914239 # average overall mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 20486.950549 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 20486.950549 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 20486.950549 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 55 # number of replacements -system.cpu.dcache.tagsinuse 1403.749083 # Cycle average of tags in use -system.cpu.dcache.total_refs 48644661 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 1849 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 26308.632234 # Average number of references to valid blocks. +system.cpu.dcache.replacements 53 # number of replacements +system.cpu.dcache.tagsinuse 1403.723956 # Cycle average of tags in use +system.cpu.dcache.total_refs 48643693 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 1846 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 26350.862947 # Average number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 1403.749083 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.342712 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 36235521 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 12356728 # number of WriteReq hits -system.cpu.dcache.LoadLockedReq_hits 27793 # number of LoadLockedReq hits -system.cpu.dcache.StoreCondReq_hits 24619 # number of StoreCondReq hits -system.cpu.dcache.demand_hits 48592249 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 48592249 # number of overall hits -system.cpu.dcache.ReadReq_misses 1802 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 7559 # number of WriteReq misses +system.cpu.dcache.occ_blocks::0 1403.723956 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.342706 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 36234545 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 12356727 # number of WriteReq hits +system.cpu.dcache.LoadLockedReq_hits 27791 # number of LoadLockedReq hits +system.cpu.dcache.StoreCondReq_hits 24630 # number of StoreCondReq hits +system.cpu.dcache.demand_hits 48591272 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 48591272 # number of overall hits +system.cpu.dcache.ReadReq_misses 1808 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 7560 # number of WriteReq misses system.cpu.dcache.LoadLockedReq_misses 2 # number of LoadLockedReq misses -system.cpu.dcache.demand_misses 9361 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 9361 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 59198500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 237194000 # number of WriteReq miss cycles +system.cpu.dcache.demand_misses 9368 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 9368 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 59529000 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 237156500 # number of WriteReq miss cycles system.cpu.dcache.LoadLockedReq_miss_latency 63500 # number of LoadLockedReq miss cycles -system.cpu.dcache.demand_miss_latency 296392500 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 296392500 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 36237323 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.demand_miss_latency 296685500 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 296685500 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 36236353 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 12364287 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_accesses 27795 # number of LoadLockedReq accesses(hits+misses) -system.cpu.dcache.StoreCondReq_accesses 24619 # number of StoreCondReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 48601610 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 48601610 # number of overall (read+write) accesses +system.cpu.dcache.LoadLockedReq_accesses 27793 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.StoreCondReq_accesses 24630 # number of StoreCondReq accesses(hits+misses) +system.cpu.dcache.demand_accesses 48600640 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 48600640 # number of overall (read+write) accesses system.cpu.dcache.ReadReq_miss_rate 0.000050 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate 0.000611 # miss rate for WriteReq accesses system.cpu.dcache.LoadLockedReq_miss_rate 0.000072 # miss rate for LoadLockedReq accesses system.cpu.dcache.demand_miss_rate 0.000193 # miss rate for demand accesses system.cpu.dcache.overall_miss_rate 0.000193 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 32851.553829 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 31379.018389 # average WriteReq miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 32925.331858 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 31369.907407 # average WriteReq miss latency system.cpu.dcache.LoadLockedReq_avg_miss_latency 31750 # average LoadLockedReq miss latency -system.cpu.dcache.demand_avg_miss_latency 31662.482641 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 31662.482641 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency 31670.100342 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 31670.100342 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 20000 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -432,70 +432,70 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets 20000 # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 19 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 1044 # number of ReadReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits 6468 # number of WriteReq MSHR hits +system.cpu.dcache.writebacks 18 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 1053 # number of ReadReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits 6469 # number of WriteReq MSHR hits system.cpu.dcache.LoadLockedReq_mshr_hits 2 # number of LoadLockedReq MSHR hits -system.cpu.dcache.demand_mshr_hits 7512 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 7512 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 758 # number of ReadReq MSHR misses +system.cpu.dcache.demand_mshr_hits 7522 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 7522 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 755 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_mshr_misses 1091 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 1849 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 1849 # number of overall MSHR misses +system.cpu.dcache.demand_mshr_misses 1846 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 1846 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 24153000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 24116500 # number of ReadReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_latency 38344000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 62497000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 62497000 # number of overall MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 62460500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 62460500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000021 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate 0.000088 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.000038 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.000038 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 31864.116095 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 31942.384106 # average ReadReq mshr miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35145.737855 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 33800.432666 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 33800.432666 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 33835.590466 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 33835.590466 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.tagsinuse 1924.111202 # Cycle average of tags in use -system.cpu.l2cache.total_refs 1711 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 2681 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 0.638195 # Average number of references to valid blocks. +system.cpu.l2cache.tagsinuse 1923.480613 # Cycle average of tags in use +system.cpu.l2cache.total_refs 1714 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 2676 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 0.640508 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 1920.073953 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 4.037248 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.058596 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.000123 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 1711 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 19 # number of Writeback hits +system.cpu.l2cache.occ_blocks::0 1919.476269 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 4.004344 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.058578 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.000122 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 1714 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 18 # number of Writeback hits system.cpu.l2cache.ReadExReq_hits 9 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 1720 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 1720 # number of overall hits -system.cpu.l2cache.ReadReq_misses 2685 # number of ReadReq misses +system.cpu.l2cache.demand_hits 1723 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 1723 # number of overall hits +system.cpu.l2cache.ReadReq_misses 2681 # number of ReadReq misses system.cpu.l2cache.ReadExReq_misses 1082 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 3767 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 3767 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 92055500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 37184500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 129240000 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 129240000 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 4396 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 19 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.demand_misses 3763 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 3763 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 91922000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 37184000 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 129106000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 129106000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 4395 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 18 # number of Writeback accesses(hits+misses) system.cpu.l2cache.ReadExReq_accesses 1091 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 5487 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 5487 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.610783 # miss rate for ReadReq accesses +system.cpu.l2cache.demand_accesses 5486 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 5486 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.610011 # miss rate for ReadReq accesses system.cpu.l2cache.ReadExReq_miss_rate 0.991751 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.686532 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.686532 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34285.102421 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34366.451017 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34308.468277 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34308.468277 # average overall miss latency +system.cpu.l2cache.demand_miss_rate 0.685928 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.685928 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34286.460276 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34365.988909 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34309.327664 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34309.327664 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -508,24 +508,24 @@ system.cpu.l2cache.writebacks 0 # nu system.cpu.l2cache.ReadReq_mshr_hits 14 # number of ReadReq MSHR hits system.cpu.l2cache.demand_mshr_hits 14 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 14 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 2671 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 2667 # number of ReadReq MSHR misses system.cpu.l2cache.ReadExReq_mshr_misses 1082 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 3753 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 3753 # number of overall MSHR misses +system.cpu.l2cache.demand_mshr_misses 3749 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 3749 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 83018000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 82895000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_latency 33590000 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 116608000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 116608000 # number of overall MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 116485000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 116485000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.607598 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.606826 # mshr miss rate for ReadReq accesses system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.991751 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.683980 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.683980 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31081.242980 # average ReadReq mshr miss latency +system.cpu.l2cache.demand_mshr_miss_rate 0.683376 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.683376 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31081.739783 # average ReadReq mshr miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31044.362292 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31070.610179 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31070.610179 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31070.952254 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31070.952254 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions diff --git a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/config.ini b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/config.ini index b8115d922..9f72e3b54 100644 --- a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/config.ini +++ b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/config.ini @@ -1,6 +1,7 @@ [root] type=Root children=system +full_system=false time_sync_enable=false time_sync_period=100000000000 time_sync_spin_threshold=100000000 @@ -8,10 +9,16 @@ time_sync_spin_threshold=100000000 [system] type=System children=cpu membus physmem +boot_osflags=a +init_param=0 +kernel= +load_addr_mask=1099511627775 mem_mode=atomic memories=system.physmem num_work_ids=16 physmem=system.physmem +readfile= +symbolfile= work_begin_ckpt_count=0 work_begin_cpu_id_exit=-1 work_begin_exit_count=0 @@ -23,7 +30,7 @@ system_port=system.membus.port[0] [system.cpu] type=DerivO3CPU -children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache interrupts itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -52,6 +59,7 @@ decodeWidth=8 defer_registration=false dispatchWidth=8 do_checkpoint_insts=true +do_quiesce=true do_statistics_insts=true dtb=system.cpu.dtb fetchToDecodeDelay=1 @@ -69,6 +77,7 @@ iewToDecodeDelay=1 iewToFetchDelay=1 iewToRenameDelay=1 instShiftAmt=2 +interrupts=system.cpu.interrupts issueToExecuteDelay=1 issueWidth=8 itb=system.cpu.itb @@ -89,6 +98,7 @@ numRobs=1 numThreads=1 phase=0 predType=tournament +profile=0 progress_interval=0 renameToDecodeDelay=1 renameToFetchDelay=1 @@ -149,7 +159,14 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.dtb] type=X86TLB +children=walker size=64 +walker=system.cpu.dtb.walker + +[system.cpu.dtb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[3] [system.cpu.fuPool] type=FUPool @@ -446,9 +463,25 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.interrupts] +type=X86LocalApic +int_latency=1000 +pio_addr=2305843009213693952 +pio_latency=1000 +system=system +int_port=system.membus.port[4] +pio=system.membus.port[3] + [system.cpu.itb] type=X86TLB +children=walker size=64 +walker=system.cpu.itb.walker + +[system.cpu.itb.walker] +type=X86PagetableWalker +system=system +port=system.cpu.toL2Bus.port[2] [system.cpu.l2cache] type=BaseCache @@ -479,7 +512,7 @@ tgts_per_mshr=5 trace_addr=0 two_queue=false write_buffers=8 -cpu_side=system.cpu.toL2Bus.port[2] +cpu_side=system.cpu.toL2Bus.port[4] mem_side=system.membus.port[2] [system.cpu.toL2Bus] @@ -490,7 +523,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.itb.walker.port system.cpu.dtb.walker.port system.cpu.l2cache.cpu_side [system.cpu.tracer] type=ExeTracer @@ -498,7 +531,7 @@ type=ExeTracer [system.cpu.workload] type=LiveProcess cmd=twolf smred -cwd=build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing +cwd=build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing egid=100 env= errout=cerr @@ -522,7 +555,7 @@ clock=1000 header_cycles=1 use_default_range=false width=64 -port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side +port=system.system_port system.physmem.port[0] system.cpu.l2cache.mem_side system.cpu.interrupts.pio system.cpu.interrupts.int_port [system.physmem] type=PhysicalMemory diff --git a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/simout b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/simout index 3d5ba32f2..0b6a80ec2 100755 --- a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/simout +++ b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/simout @@ -1,14 +1,14 @@ -Redirecting stdout to build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/simout -Redirecting stderr to build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/simerr +Redirecting stdout to build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing/simout +Redirecting stderr to build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 28 2012 12:11:40 -gem5 started Jan 28 2012 12:12:43 +gem5 compiled Feb 9 2012 12:45:55 +gem5 started Feb 9 2012 12:46:40 gem5 executing on ribera.cs.wisc.edu -command line: build/X86_SE/gem5.opt -d build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing -Couldn't unlink build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sav -Couldn't unlink build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sv2 +command line: build/X86/gem5.opt -d build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing +Couldn't unlink build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing/smred.sav +Couldn't unlink build/X86/tests/opt/long/se/70.twolf/x86/linux/o3-timing/smred.sv2 Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... @@ -26,4 +26,4 @@ info: Increasing stack size by one page. 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 -122 123 124 Exiting @ tick 96605044000 because target called exit() +122 123 124 Exiting @ tick 96266258000 because target called exit() diff --git a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/stats.txt b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/stats.txt index 5be6519a9..2a68affc2 100644 --- a/tests/long/se/70.twolf/ref/x86/linux/o3-timing/stats.txt +++ b/tests/long/se/70.twolf/ref/x86/linux/o3-timing/stats.txt @@ -1,261 +1,261 @@ ---------- Begin Simulation Statistics ---------- -sim_seconds 0.096605 # Number of seconds simulated -sim_ticks 96605044000 # Number of ticks simulated -final_tick 96605044000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) +sim_seconds 0.096266 # Number of seconds simulated +sim_ticks 96266258000 # Number of ticks simulated +final_tick 96266258000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 67425 # Simulator instruction rate (inst/s) -host_tick_rate 29425038 # Simulator tick rate (ticks/s) -host_mem_usage 253272 # Number of bytes of host memory used -host_seconds 3283.09 # Real time elapsed on the host +host_inst_rate 60515 # Simulator instruction rate (inst/s) +host_tick_rate 26316743 # Simulator tick rate (ticks/s) +host_mem_usage 262352 # Number of bytes of host memory used +host_seconds 3657.99 # Real time elapsed on the host sim_insts 221363017 # Number of instructions simulated -system.physmem.bytes_read 339456 # Number of bytes read from this memory -system.physmem.bytes_inst_read 214848 # Number of instructions bytes read from this memory +system.physmem.bytes_read 339712 # Number of bytes read from this memory +system.physmem.bytes_inst_read 214912 # Number of instructions bytes read from this memory system.physmem.bytes_written 0 # Number of bytes written to this memory -system.physmem.num_reads 5304 # Number of read requests responded to by this memory +system.physmem.num_reads 5308 # Number of read requests responded to by this memory system.physmem.num_writes 0 # Number of write requests responded to by this memory system.physmem.num_other 0 # Number of other requests responded to by this memory -system.physmem.bw_read 3513854 # Total read bandwidth from this memory (bytes/s) -system.physmem.bw_inst_read 2223983 # Instruction read bandwidth from this memory (bytes/s) -system.physmem.bw_total 3513854 # Total bandwidth to/from this memory (bytes/s) +system.physmem.bw_read 3528879 # Total read bandwidth from this memory (bytes/s) +system.physmem.bw_inst_read 2232475 # Instruction read bandwidth from this memory (bytes/s) +system.physmem.bw_total 3528879 # Total bandwidth to/from this memory (bytes/s) system.cpu.workload.num_syscalls 400 # Number of system calls -system.cpu.numCycles 193210089 # number of cpu cycles simulated +system.cpu.numCycles 192532517 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.BPredUnit.lookups 25792325 # Number of BP lookups -system.cpu.BPredUnit.condPredicted 25792325 # Number of conditional branches predicted -system.cpu.BPredUnit.condIncorrect 2895497 # Number of conditional branches incorrect -system.cpu.BPredUnit.BTBLookups 23600664 # Number of BTB lookups -system.cpu.BPredUnit.BTBHits 20878395 # Number of BTB hits +system.cpu.BPredUnit.lookups 25728486 # Number of BP lookups +system.cpu.BPredUnit.condPredicted 25728486 # Number of conditional branches predicted +system.cpu.BPredUnit.condIncorrect 2892788 # Number of conditional branches incorrect +system.cpu.BPredUnit.BTBLookups 23533152 # Number of BTB lookups +system.cpu.BPredUnit.BTBHits 20839978 # Number of BTB hits system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -system.cpu.fetch.icacheStallCycles 30964428 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 261331282 # Number of instructions fetch has processed -system.cpu.fetch.Branches 25792325 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 20878395 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 70767464 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 26891019 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 67713706 # Number of cycles fetch has spent blocked -system.cpu.fetch.MiscStallCycles 142 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs -system.cpu.fetch.PendingTrapStallCycles 1189 # Number of stall cycles due to pending traps -system.cpu.fetch.CacheLines 28829274 # Number of cache lines fetched -system.cpu.fetch.IcacheSquashes 550737 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 193129824 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 2.258996 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 3.335178 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.icacheStallCycles 30657479 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 260466955 # Number of instructions fetch has processed +system.cpu.fetch.Branches 25728486 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 20839978 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 70644215 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 26785814 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 67566342 # Number of cycles fetch has spent blocked +system.cpu.fetch.MiscStallCycles 136 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.PendingTrapStallCycles 1120 # Number of stall cycles due to pending traps +system.cpu.fetch.CacheLines 28758661 # Number of cache lines fetched +system.cpu.fetch.IcacheSquashes 555177 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.rateDist::samples 192452166 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 2.262310 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 3.335029 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::0 124221202 64.32% 64.32% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 4112630 2.13% 66.45% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 3244602 1.68% 68.13% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 4465272 2.31% 70.44% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 4293373 2.22% 72.66% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 4464358 2.31% 74.98% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 5413333 2.80% 77.78% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 3013911 1.56% 79.34% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 39901143 20.66% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 123644733 64.25% 64.25% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 4091160 2.13% 66.37% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 3200074 1.66% 68.04% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 4567374 2.37% 70.41% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 4265123 2.22% 72.63% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 4442159 2.31% 74.93% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 5459285 2.84% 77.77% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 3091960 1.61% 79.38% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 39690298 20.62% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::total 193129824 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.133494 # Number of branch fetches per cycle -system.cpu.fetch.rate 1.352576 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 44734521 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 57786241 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 57127863 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 9798304 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 23682895 # Number of cycles decode is squashing -system.cpu.decode.DecodedInsts 423946385 # Number of instructions handled by decode -system.cpu.rename.SquashCycles 23682895 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 53367953 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 14712731 # Number of cycles rename is blocking -system.cpu.rename.serializeStallCycles 23142 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 57547510 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 43795593 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 411406798 # Number of instructions processed by rename +system.cpu.fetch.rateDist::total 192452166 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.133632 # Number of branch fetches per cycle +system.cpu.fetch.rate 1.352847 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 44411978 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 57625858 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 56973408 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 9858048 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 23582874 # Number of cycles decode is squashing +system.cpu.decode.DecodedInsts 423042956 # Number of instructions handled by decode +system.cpu.rename.SquashCycles 23582874 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 52998252 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 14705836 # Number of cycles rename is blocking +system.cpu.rename.serializeStallCycles 23082 # count of cycles rename stalled for serializing inst +system.cpu.rename.RunCycles 57546904 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 43595218 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 410638323 # Number of instructions processed by rename system.cpu.rename.ROBFullEvents 10 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 18855699 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 22517657 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RenamedOperands 437782007 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 1065797846 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 1054993887 # Number of integer rename lookups -system.cpu.rename.fp_rename_lookups 10803959 # Number of floating rename lookups +system.cpu.rename.IQFullEvents 18885984 # Number of times rename has blocked due to IQ full +system.cpu.rename.LSQFullEvents 22330558 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RenamedOperands 437009036 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 1063910767 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 1053088723 # Number of integer rename lookups +system.cpu.rename.fp_rename_lookups 10822044 # Number of floating rename lookups system.cpu.rename.CommittedMaps 234363409 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 203418598 # Number of HB maps that are undone due to squashing -system.cpu.rename.serializingInsts 1777 # count of serializing insts renamed -system.cpu.rename.tempSerializingInsts 1771 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 94869536 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 104184220 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 37252864 # Number of stores inserted to the mem dependence unit. -system.cpu.memDep0.conflictingLoads 66898151 # Number of conflicting loads. -system.cpu.memDep0.conflictingStores 21504625 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 396406110 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.rename.UndoneMaps 202645627 # Number of HB maps that are undone due to squashing +system.cpu.rename.serializingInsts 1783 # count of serializing insts renamed +system.cpu.rename.tempSerializingInsts 1777 # count of temporary serializing insts renamed +system.cpu.rename.skidInsts 94569707 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 103994638 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 37171273 # Number of stores inserted to the mem dependence unit. +system.cpu.memDep0.conflictingLoads 66711674 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 21456392 # Number of conflicting stores. +system.cpu.iq.iqInstsAdded 395555693 # Number of instructions added to the IQ (excludes non-spec) system.cpu.iq.iqNonSpecInstsAdded 2683 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 287681996 # Number of instructions issued -system.cpu.iq.iqSquashedInstsIssued 245770 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 174447554 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 349871098 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqInstsIssued 287296212 # Number of instructions issued +system.cpu.iq.iqSquashedInstsIssued 238230 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 173600960 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 348497721 # Number of squashed operands that are examined and possibly removed from graph system.cpu.iq.iqSquashedNonSpecRemoved 1437 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 193129824 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 1.489578 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.482432 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::samples 192452166 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 1.492819 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.482262 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 60692059 31.43% 31.43% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::1 53894832 27.91% 59.33% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::2 35675096 18.47% 77.80% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::3 21030275 10.89% 88.69% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 13671463 7.08% 95.77% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 5219808 2.70% 98.47% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 2207559 1.14% 99.62% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::7 593955 0.31% 99.93% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::8 144777 0.07% 100.00% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 60170871 31.27% 31.27% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::1 53695201 27.90% 59.17% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::2 36000837 18.71% 77.87% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::3 20815986 10.82% 88.69% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 13514067 7.02% 95.71% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 5325466 2.77% 98.48% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 2181156 1.13% 99.61% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::7 607811 0.32% 99.93% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::8 140771 0.07% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 193129824 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 192452166 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available -system.cpu.iq.fu_full::IntAlu 112792 4.13% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::IntMult 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::IntDiv 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatAdd 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCmp 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatCvt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatMult 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatDiv 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::FloatSqrt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAdd 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdAlu 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCmp 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdCvt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMisc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMult 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShift 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdSqrt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 4.13% # attempts to use FU when none available -system.cpu.iq.fu_full::MemRead 2307770 84.43% 88.56% # attempts to use FU when none available -system.cpu.iq.fu_full::MemWrite 312724 11.44% 100.00% # attempts to use FU when none available +system.cpu.iq.fu_full::IntAlu 103783 3.80% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::IntMult 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::IntDiv 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatAdd 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCmp 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatCvt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatMult 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatDiv 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::FloatSqrt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAdd 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAddAcc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdAlu 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCmp 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdCvt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMisc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMult 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdMultAcc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShift 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdShiftAcc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdSqrt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAdd 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatAlu 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCmp 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatCvt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatDiv 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMisc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMult 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatMultAcc 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::SimdFloatSqrt 0 0.00% 3.80% # attempts to use FU when none available +system.cpu.iq.fu_full::MemRead 2313613 84.82% 88.62% # attempts to use FU when none available +system.cpu.iq.fu_full::MemWrite 310319 11.38% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available system.cpu.iq.fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available -system.cpu.iq.FU_type_0::No_OpClass 1204873 0.42% 0.42% # Type of FU issued -system.cpu.iq.FU_type_0::IntAlu 186986858 65.00% 65.42% # Type of FU issued -system.cpu.iq.FU_type_0::IntMult 0 0.00% 65.42% # Type of FU issued -system.cpu.iq.FU_type_0::IntDiv 0 0.00% 65.42% # Type of FU issued -system.cpu.iq.FU_type_0::FloatAdd 1646787 0.57% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::FloatMult 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMult 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShift 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 65.99% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 73289266 25.48% 91.46% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 24554212 8.54% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::No_OpClass 1202882 0.42% 0.42% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 186701896 64.99% 65.40% # Type of FU issued +system.cpu.iq.FU_type_0::IntMult 0 0.00% 65.40% # Type of FU issued +system.cpu.iq.FU_type_0::IntDiv 0 0.00% 65.40% # Type of FU issued +system.cpu.iq.FU_type_0::FloatAdd 1648118 0.57% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCmp 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::FloatCvt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::FloatMult 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::FloatDiv 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::FloatSqrt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAdd 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAddAcc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdAlu 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCmp 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdCvt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMisc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMult 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdMultAcc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShift 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdShiftAcc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdSqrt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAdd 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatAlu 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCmp 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatCvt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatDiv 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 65.98% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 73212241 25.48% 91.46% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 24531075 8.54% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued system.cpu.iq.FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued -system.cpu.iq.FU_type_0::total 287681996 # Type of FU issued -system.cpu.iq.rate 1.488959 # Inst issue rate -system.cpu.iq.fu_busy_cnt 2733286 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.009501 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 765968498 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 565842765 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 278370688 # Number of integer instruction queue wakeup accesses -system.cpu.iq.fp_inst_queue_reads 5504374 # Number of floating instruction queue reads -system.cpu.iq.fp_inst_queue_writes 5354879 # Number of floating instruction queue writes -system.cpu.iq.fp_inst_queue_wakeup_accesses 2643921 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 286442288 # Number of integer alu accesses -system.cpu.iq.fp_alu_accesses 2768121 # Number of floating point alu accesses -system.cpu.iew.lsq.thread0.forwLoads 18982398 # Number of loads that had data forwarded from stores +system.cpu.iq.FU_type_0::total 287296212 # Type of FU issued +system.cpu.iq.rate 1.492196 # Inst issue rate +system.cpu.iq.fu_busy_cnt 2727715 # FU busy when requested +system.cpu.iq.fu_busy_rate 0.009494 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 764505561 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 564134434 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 277997574 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fp_inst_queue_reads 5504974 # Number of floating instruction queue reads +system.cpu.iq.fp_inst_queue_writes 5363501 # Number of floating instruction queue writes +system.cpu.iq.fp_inst_queue_wakeup_accesses 2644368 # Number of floating instruction queue wakeup accesses +system.cpu.iq.int_alu_accesses 286052729 # Number of integer alu accesses +system.cpu.iq.fp_alu_accesses 2768316 # Number of floating point alu accesses +system.cpu.iew.lsq.thread0.forwLoads 18967849 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread0.invAddrLoads 0 # Number of loads ignored due to an invalid address -system.cpu.iew.lsq.thread0.squashedLoads 47534630 # Number of loads squashed -system.cpu.iew.lsq.thread0.ignoredResponses 34246 # Number of memory responses ignored because the instruction is squashed -system.cpu.iew.lsq.thread0.memOrderViolation 347654 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 16737148 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedLoads 47345048 # Number of loads squashed +system.cpu.iew.lsq.thread0.ignoredResponses 33748 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread0.memOrderViolation 344727 # Number of memory ordering violations +system.cpu.iew.lsq.thread0.squashedStores 16655557 # Number of stores squashed system.cpu.iew.lsq.thread0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address system.cpu.iew.lsq.thread0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread0.rescheduledLoads 48277 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread0.rescheduledLoads 48770 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle -system.cpu.iew.iewSquashCycles 23682895 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 506655 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 213138 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 396408793 # Number of instructions dispatched to IQ -system.cpu.iew.iewDispSquashedInsts 134440 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 104184220 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 37252864 # Number of dispatched store instructions +system.cpu.iew.iewSquashCycles 23582874 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 506702 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 199063 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 395558376 # Number of instructions dispatched to IQ +system.cpu.iew.iewDispSquashedInsts 136305 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispLoadInsts 103994638 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 37171273 # Number of dispatched store instructions system.cpu.iew.iewDispNonSpecInsts 1768 # Number of dispatched non-speculative instructions -system.cpu.iew.iewIQFullEvents 119463 # Number of times the IQ has become full, causing a stall -system.cpu.iew.iewLSQFullEvents 15480 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.memOrderViolationEvents 347654 # Number of memory order violations -system.cpu.iew.predictedTakenIncorrect 2501516 # Number of branches that were predicted taken incorrectly -system.cpu.iew.predictedNotTakenIncorrect 594763 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.branchMispredicts 3096279 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 283823488 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 71745820 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 3858508 # Number of squashed instructions skipped in execute +system.cpu.iew.iewIQFullEvents 106766 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewLSQFullEvents 14420 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.memOrderViolationEvents 344727 # Number of memory order violations +system.cpu.iew.predictedTakenIncorrect 2499729 # Number of branches that were predicted taken incorrectly +system.cpu.iew.predictedNotTakenIncorrect 593078 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.branchMispredicts 3092807 # Number of branch mispredicts detected at execute +system.cpu.iew.iewExecutedInsts 283409034 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 71642320 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 3887178 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 0 # number of nop insts executed -system.cpu.iew.exec_refs 95800830 # number of memory reference insts executed -system.cpu.iew.exec_branches 15659373 # Number of branches executed -system.cpu.iew.exec_stores 24055010 # Number of stores executed -system.cpu.iew.exec_rate 1.468989 # Inst execution rate -system.cpu.iew.wb_sent 282310074 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 281014609 # cumulative count of insts written-back -system.cpu.iew.wb_producers 227952457 # num instructions producing a value -system.cpu.iew.wb_consumers 378837228 # num instructions consuming a value +system.cpu.iew.exec_refs 95673519 # number of memory reference insts executed +system.cpu.iew.exec_branches 15642768 # Number of branches executed +system.cpu.iew.exec_stores 24031199 # Number of stores executed +system.cpu.iew.exec_rate 1.472006 # Inst execution rate +system.cpu.iew.wb_sent 281921944 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 280641942 # cumulative count of insts written-back +system.cpu.iew.wb_producers 227553614 # num instructions producing a value +system.cpu.iew.wb_consumers 378165457 # num instructions consuming a value system.cpu.iew.wb_penalized 0 # number of instrctions required to write to 'other' IQ -system.cpu.iew.wb_rate 1.454451 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.601716 # average fanout of values written-back +system.cpu.iew.wb_rate 1.457634 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.601730 # average fanout of values written-back system.cpu.iew.wb_penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.commit.commitCommittedInsts 221363017 # The number of committed instructions -system.cpu.commit.commitSquashedInsts 175071707 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 174222633 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 1246 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.branchMispredicts 2895631 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 169446929 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 1.306386 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.743043 # Number of insts commited each cycle +system.cpu.commit.branchMispredicts 2892920 # The number of times a branch was mispredicted +system.cpu.commit.committed_per_cycle::samples 168869292 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 1.310854 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.745147 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 63655929 37.57% 37.57% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 62181133 36.70% 74.26% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 15647987 9.23% 83.50% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 11995121 7.08% 90.58% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::4 5411057 3.19% 93.77% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::5 2989620 1.76% 95.53% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::6 2014905 1.19% 96.72% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::7 1190627 0.70% 97.43% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::8 4360550 2.57% 100.00% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 63124360 37.38% 37.38% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 62150025 36.80% 74.18% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 15630374 9.26% 83.44% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 11975959 7.09% 90.53% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::4 5416595 3.21% 93.74% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::5 2994905 1.77% 95.51% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::6 2021663 1.20% 96.71% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::7 1189804 0.70% 97.41% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::8 4365607 2.59% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 169446929 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 168869292 # Number of insts commited each cycle system.cpu.commit.count 221363017 # Number of instructions committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed system.cpu.commit.refs 77165306 # Number of memory references committed @@ -265,50 +265,50 @@ system.cpu.commit.branches 12326943 # Nu system.cpu.commit.fp_insts 2162459 # Number of committed floating point instructions. system.cpu.commit.int_insts 220339606 # Number of committed integer instructions. system.cpu.commit.function_calls 0 # Number of function calls committed. -system.cpu.commit.bw_lim_events 4360550 # number cycles where commit BW limit reached +system.cpu.commit.bw_lim_events 4365607 # number cycles where commit BW limit reached system.cpu.commit.bw_limited 0 # number of insts not committed due to BW limits -system.cpu.rob.rob_reads 561521103 # The number of ROB reads -system.cpu.rob.rob_writes 816599274 # The number of ROB writes -system.cpu.timesIdled 1748 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 80265 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.rob.rob_reads 560089335 # The number of ROB reads +system.cpu.rob.rob_writes 814800236 # The number of ROB writes +system.cpu.timesIdled 1747 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.idleCycles 80351 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 221363017 # Number of Instructions Simulated system.cpu.committedInsts_total 221363017 # Number of Instructions Simulated -system.cpu.cpi 0.872820 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.872820 # CPI: Total CPI of All Threads -system.cpu.ipc 1.145711 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.145711 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 530797158 # number of integer regfile reads -system.cpu.int_regfile_writes 288957450 # number of integer regfile writes -system.cpu.fp_regfile_reads 3607584 # number of floating regfile reads -system.cpu.fp_regfile_writes 2298041 # number of floating regfile writes -system.cpu.misc_regfile_reads 149916629 # number of misc regfile reads +system.cpu.cpi 0.869759 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.869759 # CPI: Total CPI of All Threads +system.cpu.ipc 1.149744 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.149744 # IPC: Total IPC of All Threads +system.cpu.int_regfile_reads 530367480 # number of integer regfile reads +system.cpu.int_regfile_writes 288604591 # number of integer regfile writes +system.cpu.fp_regfile_reads 3608788 # number of floating regfile reads +system.cpu.fp_regfile_writes 2298113 # number of floating regfile writes +system.cpu.misc_regfile_reads 149639402 # number of misc regfile reads system.cpu.misc_regfile_writes 844 # number of misc regfile writes -system.cpu.icache.replacements 4194 # number of replacements -system.cpu.icache.tagsinuse 1596.157530 # Cycle average of tags in use -system.cpu.icache.total_refs 28821740 # Total number of references to valid blocks. -system.cpu.icache.sampled_refs 6159 # Sample count of references to valid blocks. -system.cpu.icache.avg_refs 4679.613574 # Average number of references to valid blocks. +system.cpu.icache.replacements 4205 # number of replacements +system.cpu.icache.tagsinuse 1597.649860 # Cycle average of tags in use +system.cpu.icache.total_refs 28751182 # Total number of references to valid blocks. +system.cpu.icache.sampled_refs 6167 # Sample count of references to valid blocks. +system.cpu.icache.avg_refs 4662.101832 # Average number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.occ_blocks::0 1596.157530 # Average occupied blocks per context -system.cpu.icache.occ_percent::0 0.779374 # Average percentage of cache occupancy -system.cpu.icache.ReadReq_hits 28821740 # number of ReadReq hits -system.cpu.icache.demand_hits 28821740 # number of demand (read+write) hits -system.cpu.icache.overall_hits 28821740 # number of overall hits -system.cpu.icache.ReadReq_misses 7534 # number of ReadReq misses -system.cpu.icache.demand_misses 7534 # number of demand (read+write) misses -system.cpu.icache.overall_misses 7534 # number of overall misses -system.cpu.icache.ReadReq_miss_latency 174012500 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency 174012500 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency 174012500 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses 28829274 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses 28829274 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses 28829274 # number of overall (read+write) accesses -system.cpu.icache.ReadReq_miss_rate 0.000261 # miss rate for ReadReq accesses -system.cpu.icache.demand_miss_rate 0.000261 # miss rate for demand accesses -system.cpu.icache.overall_miss_rate 0.000261 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency 23096.960446 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency 23096.960446 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency 23096.960446 # average overall miss latency +system.cpu.icache.occ_blocks::0 1597.649860 # Average occupied blocks per context +system.cpu.icache.occ_percent::0 0.780102 # Average percentage of cache occupancy +system.cpu.icache.ReadReq_hits 28751182 # number of ReadReq hits +system.cpu.icache.demand_hits 28751182 # number of demand (read+write) hits +system.cpu.icache.overall_hits 28751182 # number of overall hits +system.cpu.icache.ReadReq_misses 7479 # number of ReadReq misses +system.cpu.icache.demand_misses 7479 # number of demand (read+write) misses +system.cpu.icache.overall_misses 7479 # number of overall misses +system.cpu.icache.ReadReq_miss_latency 173725000 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency 173725000 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency 173725000 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses 28758661 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses 28758661 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses 28758661 # number of overall (read+write) accesses +system.cpu.icache.ReadReq_miss_rate 0.000260 # miss rate for ReadReq accesses +system.cpu.icache.demand_miss_rate 0.000260 # miss rate for demand accesses +system.cpu.icache.overall_miss_rate 0.000260 # miss rate for overall accesses +system.cpu.icache.ReadReq_avg_miss_latency 23228.372777 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency 23228.372777 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency 23228.372777 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -318,59 +318,59 @@ system.cpu.icache.avg_blocked_cycles::no_targets no_value system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.cache_copies 0 # number of cache copies performed system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_mshr_hits 1131 # number of ReadReq MSHR hits -system.cpu.icache.demand_mshr_hits 1131 # number of demand (read+write) MSHR hits -system.cpu.icache.overall_mshr_hits 1131 # number of overall MSHR hits -system.cpu.icache.ReadReq_mshr_misses 6403 # number of ReadReq MSHR misses -system.cpu.icache.demand_mshr_misses 6403 # number of demand (read+write) MSHR misses -system.cpu.icache.overall_mshr_misses 6403 # number of overall MSHR misses +system.cpu.icache.ReadReq_mshr_hits 1119 # number of ReadReq MSHR hits +system.cpu.icache.demand_mshr_hits 1119 # number of demand (read+write) MSHR hits +system.cpu.icache.overall_mshr_hits 1119 # number of overall MSHR hits +system.cpu.icache.ReadReq_mshr_misses 6360 # number of ReadReq MSHR misses +system.cpu.icache.demand_mshr_misses 6360 # number of demand (read+write) MSHR misses +system.cpu.icache.overall_mshr_misses 6360 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.icache.ReadReq_mshr_miss_latency 125261500 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency 125261500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency 125261500 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 125233500 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 125233500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 125233500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000222 # mshr miss rate for ReadReq accesses -system.cpu.icache.demand_mshr_miss_rate 0.000222 # mshr miss rate for demand accesses -system.cpu.icache.overall_mshr_miss_rate 0.000222 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency 19562.939247 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 19562.939247 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 19562.939247 # average overall mshr miss latency +system.cpu.icache.ReadReq_mshr_miss_rate 0.000221 # mshr miss rate for ReadReq accesses +system.cpu.icache.demand_mshr_miss_rate 0.000221 # mshr miss rate for demand accesses +system.cpu.icache.overall_mshr_miss_rate 0.000221 # mshr miss rate for overall accesses +system.cpu.icache.ReadReq_avg_mshr_miss_latency 19690.801887 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 19690.801887 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 19690.801887 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.replacements 57 # number of replacements -system.cpu.dcache.tagsinuse 1416.139533 # Cycle average of tags in use -system.cpu.dcache.total_refs 73025896 # Total number of references to valid blocks. -system.cpu.dcache.sampled_refs 1980 # Sample count of references to valid blocks. -system.cpu.dcache.avg_refs 36881.765657 # Average number of references to valid blocks. +system.cpu.dcache.replacements 56 # number of replacements +system.cpu.dcache.tagsinuse 1415.486536 # Cycle average of tags in use +system.cpu.dcache.total_refs 72938173 # Total number of references to valid blocks. +system.cpu.dcache.sampled_refs 1987 # Sample count of references to valid blocks. +system.cpu.dcache.avg_refs 36707.686462 # Average number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.occ_blocks::0 1416.139533 # Average occupied blocks per context -system.cpu.dcache.occ_percent::0 0.345737 # Average percentage of cache occupancy -system.cpu.dcache.ReadReq_hits 52511655 # number of ReadReq hits -system.cpu.dcache.WriteReq_hits 20513921 # number of WriteReq hits -system.cpu.dcache.demand_hits 73025576 # number of demand (read+write) hits -system.cpu.dcache.overall_hits 73025576 # number of overall hits -system.cpu.dcache.ReadReq_misses 756 # number of ReadReq misses -system.cpu.dcache.WriteReq_misses 1809 # number of WriteReq misses -system.cpu.dcache.demand_misses 2565 # number of demand (read+write) misses -system.cpu.dcache.overall_misses 2565 # number of overall misses -system.cpu.dcache.ReadReq_miss_latency 24125500 # number of ReadReq miss cycles -system.cpu.dcache.WriteReq_miss_latency 68553000 # number of WriteReq miss cycles -system.cpu.dcache.demand_miss_latency 92678500 # number of demand (read+write) miss cycles -system.cpu.dcache.overall_miss_latency 92678500 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses 52512411 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.occ_blocks::0 1415.486536 # Average occupied blocks per context +system.cpu.dcache.occ_percent::0 0.345578 # Average percentage of cache occupancy +system.cpu.dcache.ReadReq_hits 52423955 # number of ReadReq hits +system.cpu.dcache.WriteReq_hits 20513973 # number of WriteReq hits +system.cpu.dcache.demand_hits 72937928 # number of demand (read+write) hits +system.cpu.dcache.overall_hits 72937928 # number of overall hits +system.cpu.dcache.ReadReq_misses 771 # number of ReadReq misses +system.cpu.dcache.WriteReq_misses 1757 # number of WriteReq misses +system.cpu.dcache.demand_misses 2528 # number of demand (read+write) misses +system.cpu.dcache.overall_misses 2528 # number of overall misses +system.cpu.dcache.ReadReq_miss_latency 24605500 # number of ReadReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 66582500 # number of WriteReq miss cycles +system.cpu.dcache.demand_miss_latency 91188000 # number of demand (read+write) miss cycles +system.cpu.dcache.overall_miss_latency 91188000 # number of overall miss cycles +system.cpu.dcache.ReadReq_accesses 52424726 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses 20515730 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.demand_accesses 73028141 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses 73028141 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate 0.000014 # miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_miss_rate 0.000088 # miss rate for WriteReq accesses +system.cpu.dcache.demand_accesses 72940456 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses 72940456 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate 0.000015 # miss rate for ReadReq accesses +system.cpu.dcache.WriteReq_miss_rate 0.000086 # miss rate for WriteReq accesses system.cpu.dcache.demand_miss_rate 0.000035 # miss rate for demand accesses system.cpu.dcache.overall_miss_rate 0.000035 # miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_miss_latency 31912.037037 # average ReadReq miss latency -system.cpu.dcache.WriteReq_avg_miss_latency 37895.522388 # average WriteReq miss latency -system.cpu.dcache.demand_avg_miss_latency 36131.968811 # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency 36131.968811 # average overall miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 31913.748379 # average ReadReq miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 37895.560615 # average WriteReq miss latency +system.cpu.dcache.demand_avg_miss_latency 36071.202532 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency 36071.202532 # average overall miss latency system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -379,72 +379,72 @@ system.cpu.dcache.avg_blocked_cycles::no_mshrs no_value system.cpu.dcache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.writebacks 14 # number of writebacks -system.cpu.dcache.ReadReq_mshr_hits 336 # number of ReadReq MSHR hits +system.cpu.dcache.writebacks 13 # number of writebacks +system.cpu.dcache.ReadReq_mshr_hits 344 # number of ReadReq MSHR hits system.cpu.dcache.WriteReq_mshr_hits 2 # number of WriteReq MSHR hits -system.cpu.dcache.demand_mshr_hits 338 # number of demand (read+write) MSHR hits -system.cpu.dcache.overall_mshr_hits 338 # number of overall MSHR hits -system.cpu.dcache.ReadReq_mshr_misses 420 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_mshr_misses 1807 # number of WriteReq MSHR misses -system.cpu.dcache.demand_mshr_misses 2227 # number of demand (read+write) MSHR misses -system.cpu.dcache.overall_mshr_misses 2227 # number of overall MSHR misses +system.cpu.dcache.demand_mshr_hits 346 # number of demand (read+write) MSHR hits +system.cpu.dcache.overall_mshr_hits 346 # number of overall MSHR hits +system.cpu.dcache.ReadReq_mshr_misses 427 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_mshr_misses 1755 # number of WriteReq MSHR misses +system.cpu.dcache.demand_mshr_misses 2182 # number of demand (read+write) MSHR misses +system.cpu.dcache.overall_mshr_misses 2182 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.dcache.ReadReq_mshr_miss_latency 13927500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency 63059000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency 76986500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency 76986500 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 14039500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 61244500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 75284000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 75284000 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000008 # mshr miss rate for ReadReq accesses -system.cpu.dcache.WriteReq_mshr_miss_rate 0.000088 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_miss_rate 0.000086 # mshr miss rate for WriteReq accesses system.cpu.dcache.demand_mshr_miss_rate 0.000030 # mshr miss rate for demand accesses system.cpu.dcache.overall_mshr_miss_rate 0.000030 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 33160.714286 # average ReadReq mshr miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34897.066962 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 34569.600359 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 34569.600359 # average overall mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 32879.391101 # average ReadReq mshr miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34897.150997 # average WriteReq mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 34502.291476 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 34502.291476 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.tagsinuse 2497.262524 # Cycle average of tags in use -system.cpu.l2cache.total_refs 2830 # Total number of references to valid blocks. -system.cpu.l2cache.sampled_refs 3752 # Sample count of references to valid blocks. -system.cpu.l2cache.avg_refs 0.754264 # Average number of references to valid blocks. +system.cpu.l2cache.tagsinuse 2496.824684 # Cycle average of tags in use +system.cpu.l2cache.total_refs 2842 # Total number of references to valid blocks. +system.cpu.l2cache.sampled_refs 3755 # Sample count of references to valid blocks. +system.cpu.l2cache.avg_refs 0.756858 # Average number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.occ_blocks::0 2495.282024 # Average occupied blocks per context -system.cpu.l2cache.occ_blocks::1 1.980500 # Average occupied blocks per context -system.cpu.l2cache.occ_percent::0 0.076150 # Average percentage of cache occupancy -system.cpu.l2cache.occ_percent::1 0.000060 # Average percentage of cache occupancy -system.cpu.l2cache.ReadReq_hits 2828 # number of ReadReq hits -system.cpu.l2cache.Writeback_hits 14 # number of Writeback hits +system.cpu.l2cache.occ_blocks::0 2494.880189 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 1.944495 # Average occupied blocks per context +system.cpu.l2cache.occ_percent::0 0.076138 # Average percentage of cache occupancy +system.cpu.l2cache.occ_percent::1 0.000059 # Average percentage of cache occupancy +system.cpu.l2cache.ReadReq_hits 2840 # number of ReadReq hits +system.cpu.l2cache.Writeback_hits 13 # number of Writeback hits system.cpu.l2cache.ReadExReq_hits 8 # number of ReadExReq hits -system.cpu.l2cache.demand_hits 2836 # number of demand (read+write) hits -system.cpu.l2cache.overall_hits 2836 # number of overall hits -system.cpu.l2cache.ReadReq_misses 3749 # number of ReadReq misses -system.cpu.l2cache.UpgradeReq_misses 245 # number of UpgradeReq misses +system.cpu.l2cache.demand_hits 2848 # number of demand (read+write) hits +system.cpu.l2cache.overall_hits 2848 # number of overall hits +system.cpu.l2cache.ReadReq_misses 3753 # number of ReadReq misses +system.cpu.l2cache.UpgradeReq_misses 193 # number of UpgradeReq misses system.cpu.l2cache.ReadExReq_misses 1555 # number of ReadExReq misses -system.cpu.l2cache.demand_misses 5304 # number of demand (read+write) misses -system.cpu.l2cache.overall_misses 5304 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency 128398000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency 53104500 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency 181502500 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency 181502500 # number of overall miss cycles -system.cpu.l2cache.ReadReq_accesses 6577 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.Writeback_accesses 14 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses 245 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.demand_misses 5308 # number of demand (read+write) misses +system.cpu.l2cache.overall_misses 5308 # number of overall misses +system.cpu.l2cache.ReadReq_miss_latency 128533500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency 53066500 # number of ReadExReq miss cycles +system.cpu.l2cache.demand_miss_latency 181600000 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency 181600000 # number of overall miss cycles +system.cpu.l2cache.ReadReq_accesses 6593 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.Writeback_accesses 13 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses 193 # number of UpgradeReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_accesses 1563 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.demand_accesses 8140 # number of demand (read+write) accesses -system.cpu.l2cache.overall_accesses 8140 # number of overall (read+write) accesses -system.cpu.l2cache.ReadReq_miss_rate 0.570017 # miss rate for ReadReq accesses +system.cpu.l2cache.demand_accesses 8156 # number of demand (read+write) accesses +system.cpu.l2cache.overall_accesses 8156 # number of overall (read+write) accesses +system.cpu.l2cache.ReadReq_miss_rate 0.569240 # miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses system.cpu.l2cache.ReadExReq_miss_rate 0.994882 # miss rate for ReadExReq accesses -system.cpu.l2cache.demand_miss_rate 0.651597 # miss rate for demand accesses -system.cpu.l2cache.overall_miss_rate 0.651597 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency 34248.599627 # average ReadReq miss latency -system.cpu.l2cache.ReadExReq_avg_miss_latency 34150.803859 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency 34219.928356 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency 34219.928356 # average overall miss latency +system.cpu.l2cache.demand_miss_rate 0.650809 # miss rate for demand accesses +system.cpu.l2cache.overall_miss_rate 0.650809 # miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_miss_latency 34248.201439 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_avg_miss_latency 34126.366559 # average ReadExReq miss latency +system.cpu.l2cache.demand_avg_miss_latency 34212.509420 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 34212.509420 # average overall miss latency system.cpu.l2cache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles::no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked @@ -456,28 +456,28 @@ system.cpu.l2cache.cache_copies 0 # nu system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.ReadReq_mshr_misses 3749 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses 245 # number of UpgradeReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 3753 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 193 # number of UpgradeReq MSHR misses system.cpu.l2cache.ReadExReq_mshr_misses 1555 # number of ReadExReq MSHR misses -system.cpu.l2cache.demand_mshr_misses 5304 # number of demand (read+write) MSHR misses -system.cpu.l2cache.overall_mshr_misses 5304 # number of overall MSHR misses +system.cpu.l2cache.demand_mshr_misses 5308 # number of demand (read+write) MSHR misses +system.cpu.l2cache.overall_mshr_misses 5308 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 116287000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 7595000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency 116413500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 5983000 # number of UpgradeReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_latency 48232500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency 164519500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency 164519500 # number of overall MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 164646000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 164646000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.570017 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.569240 # mshr miss rate for ReadReq accesses system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.994882 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.demand_mshr_miss_rate 0.651597 # mshr miss rate for demand accesses -system.cpu.l2cache.overall_mshr_miss_rate 0.651597 # mshr miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31018.138170 # average ReadReq mshr miss latency +system.cpu.l2cache.demand_mshr_miss_rate 0.650809 # mshr miss rate for demand accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.650809 # mshr miss rate for overall accesses +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31018.784972 # average ReadReq mshr miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31000 # average UpgradeReq mshr miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31017.684887 # average ReadExReq mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 31018.005279 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 31018.005279 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31018.462698 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31018.462698 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions |