From f7885b8f260ca11c2f4a405525d9fc4e554f41a8 Mon Sep 17 00:00:00 2001 From: Ali Saidi Date: Tue, 18 Jan 2011 16:30:06 -0600 Subject: ARM/O3: Add regressions for ARM w/ O3 CPU. --- .../50.vortex/ref/arm/linux/o3-timing/config.ini | 517 +++++++++++++++++++++ .../long/50.vortex/ref/arm/linux/o3-timing/simerr | 15 + .../long/50.vortex/ref/arm/linux/o3-timing/simout | 18 + .../50.vortex/ref/arm/linux/o3-timing/stats.txt | 497 ++++++++++++++++++++ 4 files changed, 1047 insertions(+) create mode 100644 tests/long/50.vortex/ref/arm/linux/o3-timing/config.ini create mode 100755 tests/long/50.vortex/ref/arm/linux/o3-timing/simerr create mode 100755 tests/long/50.vortex/ref/arm/linux/o3-timing/simout create mode 100644 tests/long/50.vortex/ref/arm/linux/o3-timing/stats.txt (limited to 'tests/long/50.vortex/ref/arm') diff --git a/tests/long/50.vortex/ref/arm/linux/o3-timing/config.ini b/tests/long/50.vortex/ref/arm/linux/o3-timing/config.ini new file mode 100644 index 000000000..d32286142 --- /dev/null +++ b/tests/long/50.vortex/ref/arm/linux/o3-timing/config.ini @@ -0,0 +1,517 @@ +[root] +type=Root +children=system +dummy=0 + +[system] +type=System +children=cpu membus physmem +mem_mode=atomic +physmem=system.physmem + +[system.cpu] +type=DerivO3CPU +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=0 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu.fuPool +function_trace=false +function_trace_start=0 +globalCtrBits=2 +globalHistoryBits=13 +globalPredictorSize=8192 +iewToCommitDelay=1 +iewToDecodeDelay=1 +iewToFetchDelay=1 +iewToRenameDelay=1 +instShiftAmt=2 +issueToExecuteDelay=1 +issueWidth=8 +itb=system.cpu.itb +localCtrBits=2 +localHistoryBits=11 +localHistoryTableSize=2048 +localPredictorSize=2048 +max_insts_all_threads=0 +max_insts_any_thread=0 +max_loads_all_threads=0 +max_loads_any_thread=0 +numIQEntries=64 +numPhysFloatRegs=256 +numPhysIntRegs=256 +numROBEntries=192 +numRobs=1 +numThreads=1 +phase=0 +predType=tournament +progress_interval=0 +renameToDecodeDelay=1 +renameToFetchDelay=1 +renameToIEWDelay=2 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu.workload +dcache_port=system.cpu.dcache.cpu_side +icache_port=system.cpu.icache.cpu_side + +[system.cpu.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=262144 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.dcache_port +mem_side=system.cpu.toL2Bus.port[1] + +[system.cpu.dtb] +type=ArmTLB +size=64 + +[system.cpu.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 FUList8 +FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 system.cpu.fuPool.FUList8 + +[system.cpu.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu.fuPool.FUList0.opList + +[system.cpu.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 + +[system.cpu.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 + +[system.cpu.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 + +[system.cpu.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu.fuPool.FUList4.opList + +[system.cpu.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu.fuPool.FUList5] +type=FUDesc +children=opList00 opList01 opList02 opList03 opList04 opList05 opList06 opList07 opList08 opList09 opList10 opList11 opList12 opList13 opList14 opList15 opList16 opList17 opList18 opList19 +count=4 +opList=system.cpu.fuPool.FUList5.opList00 system.cpu.fuPool.FUList5.opList01 system.cpu.fuPool.FUList5.opList02 system.cpu.fuPool.FUList5.opList03 system.cpu.fuPool.FUList5.opList04 system.cpu.fuPool.FUList5.opList05 system.cpu.fuPool.FUList5.opList06 system.cpu.fuPool.FUList5.opList07 system.cpu.fuPool.FUList5.opList08 system.cpu.fuPool.FUList5.opList09 system.cpu.fuPool.FUList5.opList10 system.cpu.fuPool.FUList5.opList11 system.cpu.fuPool.FUList5.opList12 system.cpu.fuPool.FUList5.opList13 system.cpu.fuPool.FUList5.opList14 system.cpu.fuPool.FUList5.opList15 system.cpu.fuPool.FUList5.opList16 system.cpu.fuPool.FUList5.opList17 system.cpu.fuPool.FUList5.opList18 system.cpu.fuPool.FUList5.opList19 + +[system.cpu.fuPool.FUList5.opList00] +type=OpDesc +issueLat=1 +opClass=SimdAdd +opLat=1 + +[system.cpu.fuPool.FUList5.opList01] +type=OpDesc +issueLat=1 +opClass=SimdAddAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList02] +type=OpDesc +issueLat=1 +opClass=SimdAlu +opLat=1 + +[system.cpu.fuPool.FUList5.opList03] +type=OpDesc +issueLat=1 +opClass=SimdCmp +opLat=1 + +[system.cpu.fuPool.FUList5.opList04] +type=OpDesc +issueLat=1 +opClass=SimdCvt +opLat=1 + +[system.cpu.fuPool.FUList5.opList05] +type=OpDesc +issueLat=1 +opClass=SimdMisc +opLat=1 + +[system.cpu.fuPool.FUList5.opList06] +type=OpDesc +issueLat=1 +opClass=SimdMult +opLat=1 + +[system.cpu.fuPool.FUList5.opList07] +type=OpDesc +issueLat=1 +opClass=SimdMultAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList08] +type=OpDesc +issueLat=1 +opClass=SimdShift +opLat=1 + +[system.cpu.fuPool.FUList5.opList09] +type=OpDesc +issueLat=1 +opClass=SimdShiftAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList10] +type=OpDesc +issueLat=1 +opClass=SimdSqrt +opLat=1 + +[system.cpu.fuPool.FUList5.opList11] +type=OpDesc +issueLat=1 +opClass=SimdFloatAdd +opLat=1 + +[system.cpu.fuPool.FUList5.opList12] +type=OpDesc +issueLat=1 +opClass=SimdFloatAlu +opLat=1 + +[system.cpu.fuPool.FUList5.opList13] +type=OpDesc +issueLat=1 +opClass=SimdFloatCmp +opLat=1 + +[system.cpu.fuPool.FUList5.opList14] +type=OpDesc +issueLat=1 +opClass=SimdFloatCvt +opLat=1 + +[system.cpu.fuPool.FUList5.opList15] +type=OpDesc +issueLat=1 +opClass=SimdFloatDiv +opLat=1 + +[system.cpu.fuPool.FUList5.opList16] +type=OpDesc +issueLat=1 +opClass=SimdFloatMisc +opLat=1 + +[system.cpu.fuPool.FUList5.opList17] +type=OpDesc +issueLat=1 +opClass=SimdFloatMult +opLat=1 + +[system.cpu.fuPool.FUList5.opList18] +type=OpDesc +issueLat=1 +opClass=SimdFloatMultAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList19] +type=OpDesc +issueLat=1 +opClass=SimdFloatSqrt +opLat=1 + +[system.cpu.fuPool.FUList6] +type=FUDesc +children=opList +count=0 +opList=system.cpu.fuPool.FUList6.opList + +[system.cpu.fuPool.FUList6.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu.fuPool.FUList7] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu.fuPool.FUList7.opList0 system.cpu.fuPool.FUList7.opList1 + +[system.cpu.fuPool.FUList7.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu.fuPool.FUList7.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu.fuPool.FUList8] +type=FUDesc +children=opList +count=1 +opList=system.cpu.fuPool.FUList8.opList + +[system.cpu.fuPool.FUList8.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=131072 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.icache_port +mem_side=system.cpu.toL2Bus.port[0] + +[system.cpu.itb] +type=ArmTLB +size=64 + +[system.cpu.l2cache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=2097152 +subblock_size=0 +tgts_per_mshr=5 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.toL2Bus.port[2] +mem_side=system.membus.port[1] + +[system.cpu.toL2Bus] +type=Bus +block_size=64 +bus_id=0 +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 + +[system.cpu.tracer] +type=ExeTracer + +[system.cpu.workload] +type=LiveProcess +cmd=vortex lendian.raw +cwd=build/ARM_SE/tests/fast/long/50.vortex/arm/linux/o3-timing +egid=100 +env= +errout=cerr +euid=100 +executable=/chips/pd/randd/dist/cpu2000/binaries/arm/linux/vortex +gid=100 +input=cin +max_stack_size=67108864 +output=cout +pid=100 +ppid=99 +simpoint=0 +system=system +uid=100 + +[system.membus] +type=Bus +block_size=64 +bus_id=0 +clock=1000 +header_cycles=1 +use_default_range=false +width=64 +port=system.physmem.port[0] system.cpu.l2cache.mem_side + +[system.physmem] +type=PhysicalMemory +file= +latency=30000 +latency_var=0 +null=false +range=0:134217727 +zero=false +port=system.membus.port[0] + diff --git a/tests/long/50.vortex/ref/arm/linux/o3-timing/simerr b/tests/long/50.vortex/ref/arm/linux/o3-timing/simerr new file mode 100755 index 000000000..71ce94393 --- /dev/null +++ b/tests/long/50.vortex/ref/arm/linux/o3-timing/simerr @@ -0,0 +1,15 @@ +warn: Sockets disabled, not accepting gdb connections +For more information see: http://www.m5sim.org/warn/d946bea6 +warn: Bad interworking branch address 0x7002. +For more information see: http://www.m5sim.org/warn/55f199fd +warn: Bad interworking branch address 0xa. +For more information see: http://www.m5sim.org/warn/55f199fd +warn: Bad interworking branch address 0xa. +For more information see: http://www.m5sim.org/warn/55f199fd +warn: Bad interworking branch address 0xa. +For more information see: http://www.m5sim.org/warn/55f199fd +warn: Bad interworking branch address 0xa. +For more information see: http://www.m5sim.org/warn/55f199fd +warn: Bad interworking branch address 0xa. +For more information see: http://www.m5sim.org/warn/55f199fd +hack: be nice to actually delete the event here diff --git a/tests/long/50.vortex/ref/arm/linux/o3-timing/simout b/tests/long/50.vortex/ref/arm/linux/o3-timing/simout new file mode 100755 index 000000000..4650e6a0c --- /dev/null +++ b/tests/long/50.vortex/ref/arm/linux/o3-timing/simout @@ -0,0 +1,18 @@ +Redirecting stdout to build/ARM_SE/tests/fast/long/50.vortex/arm/linux/o3-timing/simout +Redirecting stderr to build/ARM_SE/tests/fast/long/50.vortex/arm/linux/o3-timing/simerr +M5 Simulator System + +Copyright (c) 2001-2008 +The Regents of The University of Michigan +All Rights Reserved + + +M5 compiled Jan 18 2011 03:54:36 +M5 revision 218f733923f8 7861 default qtip int/arm_gdb.patch tip +M5 started Jan 18 2011 04:19:02 +M5 executing on aus-bc2-b9 +command line: build/ARM_SE/m5.fast -d build/ARM_SE/tests/fast/long/50.vortex/arm/linux/o3-timing -re tests/run.py build/ARM_SE/tests/fast/long/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 59259979500 because target called exit() diff --git a/tests/long/50.vortex/ref/arm/linux/o3-timing/stats.txt b/tests/long/50.vortex/ref/arm/linux/o3-timing/stats.txt new file mode 100644 index 000000000..c8769189d --- /dev/null +++ b/tests/long/50.vortex/ref/arm/linux/o3-timing/stats.txt @@ -0,0 +1,497 @@ + +---------- Begin Simulation Statistics ---------- +host_inst_rate 156565 # Simulator instruction rate (inst/s) +host_mem_usage 260328 # Number of bytes of host memory used +host_seconds 631.29 # Real time elapsed on the host +host_tick_rate 93871242 # Simulator tick rate (ticks/s) +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 98838077 # Number of instructions simulated +sim_seconds 0.059260 # Number of seconds simulated +sim_ticks 59259979500 # Number of ticks simulated +system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu.BPredUnit.BTBHits 10631376 # Number of BTB hits +system.cpu.BPredUnit.BTBLookups 17355232 # Number of BTB lookups +system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu.BPredUnit.condIncorrect 914560 # Number of conditional branches incorrect +system.cpu.BPredUnit.condPredicted 17451382 # Number of conditional branches predicted +system.cpu.BPredUnit.lookups 17451382 # Number of BP lookups +system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. +system.cpu.commit.COM:branches 12133384 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 1268932 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_limited 0 # number of insts not committed due to BW limits +system.cpu.commit.COM:committed_per_cycle::samples 114018884 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::mean 0.866857 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::stdev 1.400756 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::0 59418042 52.11% 52.11% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::1 36575306 32.08% 84.19% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::2 7815756 6.85% 91.05% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::3 3335762 2.93% 93.97% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::4 3218602 2.82% 96.79% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::5 1142108 1.00% 97.80% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::6 823063 0.72% 98.52% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::7 421313 0.37% 98.89% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::8 1268932 1.11% 100.00% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::total 114018884 # Number of insts commited each cycle +system.cpu.commit.COM:count 98838077 # Number of instructions committed +system.cpu.commit.COM:loads 27315295 # Number of loads committed +system.cpu.commit.COM:membars 0 # Number of memory barriers committed +system.cpu.commit.COM:refs 47871033 # Number of memory references committed +system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu.commit.branchMispredicts 2496869 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 98838077 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 667791 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 18231626 # The number of squashed insts skipped by commit +system.cpu.committedInsts 98838077 # Number of Instructions Simulated +system.cpu.committedInsts_total 98838077 # Number of Instructions Simulated +system.cpu.cpi 1.199133 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.199133 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 28495397 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 22617.028157 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 18828.183694 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 28388709 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 2412965500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.003744 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 106688 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 49985 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 1067614500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.001990 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 56703 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 19865820 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 32612.870291 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 34110.136388 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 18320719 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 50390178500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.077777 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 1545101 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 1438347 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 3641393500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.005374 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 106754 # number of WriteReq MSHR misses +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 21500 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 285.786157 # Average number of references to valid blocks. +system.cpu.dcache.blocked::no_mshrs 0 # number of cycles access was blocked +system.cpu.dcache.blocked::no_targets 1 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles::no_mshrs 0 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles::no_targets 21500 # number of cycles access was blocked +system.cpu.dcache.cache_copies 0 # number of cache copies performed +system.cpu.dcache.demand_accesses 48361217 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 31967.245211 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 28808.848810 # average overall mshr miss latency +system.cpu.dcache.demand_hits 46709428 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 52803144000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.034155 # miss rate for demand accesses +system.cpu.dcache.demand_misses 1651789 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 1488332 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 4709008000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.003380 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 163457 # number of demand (read+write) MSHR misses +system.cpu.dcache.fast_writes 0 # number of fast writes performed +system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.dcache.occ_%::0 0.995663 # Average percentage of cache occupancy +system.cpu.dcache.occ_blocks::0 4078.236319 # Average occupied blocks per context +system.cpu.dcache.overall_accesses 48361217 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 31967.245211 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 28808.848810 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.dcache.overall_hits 46709428 # number of overall hits +system.cpu.dcache.overall_miss_latency 52803144000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.034155 # miss rate for overall accesses +system.cpu.dcache.overall_misses 1651789 # number of overall misses +system.cpu.dcache.overall_mshr_hits 1488332 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 4709008000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.003380 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 163457 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.dcache.replacements 159346 # number of replacements +system.cpu.dcache.sampled_refs 163442 # Sample count of references to valid blocks. +system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.dcache.tagsinuse 4078.236319 # Cycle average of tags in use +system.cpu.dcache.total_refs 46709461 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 393981000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 124385 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 14942645 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 127014948 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 27511704 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 70998513 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 3514572 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 566022 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 0 # DTB accesses +system.cpu.dtb.align_faults 0 # Number of TLB faults due to alignment restrictions +system.cpu.dtb.domain_faults 0 # Number of TLB faults due to domain restrictions +system.cpu.dtb.flush_entries 0 # Number of entries that have been flushed from TLB +system.cpu.dtb.flush_tlb 0 # Number of times complete TLB was flushed +system.cpu.dtb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID +system.cpu.dtb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA +system.cpu.dtb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID +system.cpu.dtb.hits 0 # DTB hits +system.cpu.dtb.inst_accesses 0 # ITB inst accesses +system.cpu.dtb.inst_hits 0 # ITB inst hits +system.cpu.dtb.inst_misses 0 # ITB inst misses +system.cpu.dtb.misses 0 # DTB misses +system.cpu.dtb.perms_faults 0 # Number of TLB faults due to permissions restrictions +system.cpu.dtb.prefetch_faults 0 # Number of TLB faults due to prefetch +system.cpu.dtb.read_accesses 0 # DTB read accesses +system.cpu.dtb.read_hits 0 # DTB read hits +system.cpu.dtb.read_misses 0 # DTB read misses +system.cpu.dtb.write_accesses 0 # DTB write accesses +system.cpu.dtb.write_hits 0 # DTB write hits +system.cpu.dtb.write_misses 0 # DTB write misses +system.cpu.fetch.Branches 17451382 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 12122688 # Number of cache lines fetched +system.cpu.fetch.Cycles 73872074 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 96174 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 95885012 # Number of instructions fetch has processed +system.cpu.fetch.MiscStallCycles 34128 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.SquashCycles 2507897 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.147244 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 12122688 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 10631376 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.809020 # Number of inst fetches per cycle +system.cpu.fetch.rateDist::samples 117533456 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.108172 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 1.634523 # 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 43866274 37.32% 37.32% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 53998301 45.94% 83.27% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 9118937 7.76% 91.02% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 3358983 2.86% 93.88% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 1352835 1.15% 95.03% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 476061 0.41% 95.44% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 1116299 0.95% 96.39% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 521407 0.44% 96.83% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 3724359 3.17% 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 117533456 # Number of instructions fetched each cycle (Total) +system.cpu.icache.ReadReq_accesses 12122688 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 12759.423411 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 9476.994450 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 12098546 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 308038000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.001991 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 24142 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 539 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 223685500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.001947 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 23603 # number of ReadReq MSHR misses +system.cpu.icache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked +system.cpu.icache.avg_refs 512.911056 # Average number of references to valid blocks. +system.cpu.icache.blocked::no_mshrs 0 # number of cycles access was blocked +system.cpu.icache.blocked::no_targets 0 # number of cycles access was blocked +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.cache_copies 0 # number of cache copies performed +system.cpu.icache.demand_accesses 12122688 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 12759.423411 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 9476.994450 # average overall mshr miss latency +system.cpu.icache.demand_hits 12098546 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 308038000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.001991 # miss rate for demand accesses +system.cpu.icache.demand_misses 24142 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 539 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 223685500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.001947 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 23603 # number of demand (read+write) MSHR misses +system.cpu.icache.fast_writes 0 # number of fast writes performed +system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.icache.occ_%::0 0.878284 # Average percentage of cache occupancy +system.cpu.icache.occ_blocks::0 1798.726213 # Average occupied blocks per context +system.cpu.icache.overall_accesses 12122688 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 12759.423411 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 9476.994450 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.icache.overall_hits 12098546 # number of overall hits +system.cpu.icache.overall_miss_latency 308038000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.001991 # miss rate for overall accesses +system.cpu.icache.overall_misses 24142 # number of overall misses +system.cpu.icache.overall_mshr_hits 539 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 223685500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.001947 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 23603 # number of overall MSHR misses +system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.icache.replacements 21558 # number of replacements +system.cpu.icache.sampled_refs 23588 # Sample count of references to valid blocks. +system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.icache.tagsinuse 1798.726213 # Cycle average of tags in use +system.cpu.icache.total_refs 12098546 # Total number of references to valid blocks. +system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.icache.writebacks 0 # number of writebacks +system.cpu.idleCycles 986504 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 13347127 # Number of branches executed +system.cpu.iew.EXEC:nop 0 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.903568 # Inst execution rate +system.cpu.iew.EXEC:refs 50902903 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 21266898 # Number of stores executed +system.cpu.iew.EXEC:swp 0 # number of swp insts executed +system.cpu.iew.WB:consumers 83917531 # num instructions consuming a value +system.cpu.iew.WB:count 104978436 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.516830 # average fanout of values written-back +system.cpu.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ +system.cpu.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu.iew.WB:producers 43371139 # num instructions producing a value +system.cpu.iew.WB:rate 0.885745 # insts written-back per cycle +system.cpu.iew.WB:sent 106195350 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 2628455 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 987035 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 32508348 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 1016199 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 2305298 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 23389031 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 117101137 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 29636005 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2065669 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 107090838 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 2107 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle +system.cpu.iew.iewLSQFullEvents 908 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 3514572 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 39558 # Number of cycles IEW is unblocking +system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding +system.cpu.iew.lsq.thread.0.cacheBlocked 5 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 247077 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 2317 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu.iew.lsq.thread.0.memOrderViolation 39532 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 7 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 5193052 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 2833293 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 39532 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 1768227 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 860228 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.833936 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.833936 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0::No_OpClass 0 0.00% 0.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntAlu 57364104 52.55% 52.55% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntMult 80354 0.07% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntDiv 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatAdd 124 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCmp 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCvt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatMult 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatDiv 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatSqrt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAdd 1 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAlu 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCmp 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCvt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMisc 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMult 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShift 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdSqrt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc 7 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt 0 0.00% 52.63% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemRead 30140236 27.61% 80.24% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemWrite 21571681 19.76% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::total 109156507 # Type of FU issued +system.cpu.iq.ISSUE:fu_busy_cnt 1323138 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.012121 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntAlu 1303 0.10% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntMult 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntDiv 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatAdd 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCmp 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCvt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatMult 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatDiv 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatSqrt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAdd 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAddAcc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAlu 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCmp 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCvt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMisc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMult 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMultAcc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShift 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShiftAcc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdSqrt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAdd 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAlu 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCmp 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCvt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatDiv 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMisc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMult 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt 0 0.00% 0.10% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemRead 1094336 82.71% 82.81% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemWrite 227499 17.19% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:issued_per_cycle::samples 117533456 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::mean 0.928727 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.126434 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::0 53481972 45.50% 45.50% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::1 35549975 30.25% 75.75% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::2 18295748 15.57% 91.32% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::3 5807729 4.94% 96.26% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::4 2883694 2.45% 98.71% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::5 1109227 0.94% 99.66% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::6 329629 0.28% 99.94% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::7 70692 0.06% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::8 4790 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::min_value 0 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::max_value 8 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::total 117533456 # Number of insts issued each cycle +system.cpu.iq.ISSUE:rate 0.920997 # Inst issue rate +system.cpu.iq.iqInstsAdded 116084938 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 109156507 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 1016199 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 17094247 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 68325 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 348408 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 30276342 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 0 # DTB accesses +system.cpu.itb.align_faults 0 # Number of TLB faults due to alignment restrictions +system.cpu.itb.domain_faults 0 # Number of TLB faults due to domain restrictions +system.cpu.itb.flush_entries 0 # Number of entries that have been flushed from TLB +system.cpu.itb.flush_tlb 0 # Number of times complete TLB was flushed +system.cpu.itb.flush_tlb_asid 0 # Number of times TLB was flushed by ASID +system.cpu.itb.flush_tlb_mva 0 # Number of times TLB was flushed by MVA +system.cpu.itb.flush_tlb_mva_asid 0 # Number of times TLB was flushed by MVA & ASID +system.cpu.itb.hits 0 # DTB hits +system.cpu.itb.inst_accesses 0 # ITB inst accesses +system.cpu.itb.inst_hits 0 # ITB inst hits +system.cpu.itb.inst_misses 0 # ITB inst misses +system.cpu.itb.misses 0 # DTB misses +system.cpu.itb.perms_faults 0 # Number of TLB faults due to permissions restrictions +system.cpu.itb.prefetch_faults 0 # Number of TLB faults due to prefetch +system.cpu.itb.read_accesses 0 # DTB read accesses +system.cpu.itb.read_hits 0 # DTB read hits +system.cpu.itb.read_misses 0 # DTB read misses +system.cpu.itb.write_accesses 0 # DTB write accesses +system.cpu.itb.write_hits 0 # DTB write hits +system.cpu.itb.write_misses 0 # DTB write misses +system.cpu.l2cache.ReadExReq_accesses 106739 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 34385.177402 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31198.626723 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_hits 4429 # number of ReadExReq hits +system.cpu.l2cache.ReadExReq_miss_latency 3517947500 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 0.958506 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 102310 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 3191931500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.958506 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 102310 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 80290 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 34268.509897 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31112.930905 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 46997 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1140901500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.414659 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 33293 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_hits 78 # number of ReadReq MSHR hits +system.cpu.l2cache.ReadReq_mshr_miss_latency 1033416000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.413688 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 33215 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 15 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 3450 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31300 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_hits 5 # number of UpgradeReq hits +system.cpu.l2cache.UpgradeReq_miss_latency 34500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 0.666667 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 10 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 313000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.666667 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 10 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 124385 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 124385 # number of Writeback hits +system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value # 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.avg_refs 0.522459 # Average number of references to valid blocks. +system.cpu.l2cache.blocked::no_mshrs 0 # number of cycles access was blocked +system.cpu.l2cache.blocked::no_targets 0 # number of cycles access was blocked +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.cache_copies 0 # number of cache copies performed +system.cpu.l2cache.demand_accesses 187029 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 34356.533410 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31177.624055 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 51426 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 4658849000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.725037 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 135603 # number of demand (read+write) misses +system.cpu.l2cache.demand_mshr_hits 78 # number of demand (read+write) MSHR hits +system.cpu.l2cache.demand_mshr_miss_latency 4225347500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.724620 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 135525 # number of demand (read+write) MSHR misses +system.cpu.l2cache.fast_writes 0 # number of fast writes performed +system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated +system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate +system.cpu.l2cache.occ_%::0 0.075665 # Average percentage of cache occupancy +system.cpu.l2cache.occ_%::1 0.490596 # Average percentage of cache occupancy +system.cpu.l2cache.occ_blocks::0 2479.385419 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 16075.863311 # Average occupied blocks per context +system.cpu.l2cache.overall_accesses 187029 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 34356.533410 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31177.624055 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.l2cache.overall_hits 51426 # number of overall hits +system.cpu.l2cache.overall_miss_latency 4658849000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.725037 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 135603 # number of overall misses +system.cpu.l2cache.overall_mshr_hits 78 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_miss_latency 4225347500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.724620 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 135525 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles +system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses +system.cpu.l2cache.replacements 115260 # number of replacements +system.cpu.l2cache.sampled_refs 134133 # Sample count of references to valid blocks. +system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions +system.cpu.l2cache.tagsinuse 18555.248730 # Cycle average of tags in use +system.cpu.l2cache.total_refs 70079 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 88459 # number of writebacks +system.cpu.memDep0.conflictingLoads 7990320 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 10924699 # Number of conflicting stores. +system.cpu.memDep0.insertedLoads 32508348 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 23389031 # Number of stores inserted to the mem dependence unit. +system.cpu.numCycles 118519960 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 1866194 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 74745628 # Number of HB maps that are committed +system.cpu.rename.RENAME:IQFullEvents 1883 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 30389505 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 833530 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 4 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 333412635 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 124050705 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 93358658 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 68672790 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 3514572 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 1591233 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 18613027 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 11499162 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 818368 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 3724500 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 819368 # count of temporary serializing insts renamed +system.cpu.timesIdled 60726 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.workload.PROG:num_syscalls 1946 # Number of system calls + +---------- End Simulation Statistics ---------- -- cgit v1.2.3