diff options
author | Steve Reinhardt <steve.reinhardt@amd.com> | 2014-06-22 14:33:09 -0700 |
---|---|---|
committer | Steve Reinhardt <steve.reinhardt@amd.com> | 2014-06-22 14:33:09 -0700 |
commit | 5b08e211ab35fd6d936dafda45014c78b5e68300 (patch) | |
tree | 771950b6f1e0c775d83a5f03f2387f2e3850cc58 /tests/quick/se/00.hello/ref/alpha/tru64 | |
parent | b085db84afcbb4824d34b8755f4c09c1fcfefcee (diff) | |
download | gem5-5b08e211ab35fd6d936dafda45014c78b5e68300.tar.xz |
stats: update for O3 changes
Mostly small differences in total ticks, but O3 stall causes
shifted significantly.
30.eon does speed up by ~6% on Alpha and ARM, and 50.vortex
by 4.5% on ARM. At the other extreme, X86 70.twolf is 0.8%
slower.
Diffstat (limited to 'tests/quick/se/00.hello/ref/alpha/tru64')
3 files changed, 254 insertions, 245 deletions
diff --git a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/config.ini b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/config.ini index 15208c06e..5d14be284 100644 --- a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/config.ini @@ -18,6 +18,7 @@ eventq_index=0 init_param=0 kernel= load_addr_mask=1099511627775 +load_offset=0 mem_mode=timing mem_ranges= memories=system.physmem @@ -115,6 +116,7 @@ smtLSQThreshold=100 smtNumFetchingThreads=1 smtROBPolicy=Partitioned smtROBThreshold=100 +socket_id=0 squashWidth=8 store_set_clear_period=250000 switched_out=false @@ -599,7 +601,7 @@ env= errout=cerr euid=100 eventq_index=0 -executable=/dist/test-progs/hello/bin/alpha/tru64/hello +executable=/home/stever/hg/m5sim.org/gem5/tests/test-progs/hello/bin/alpha/tru64/hello gid=100 input=cin max_stack_size=67108864 @@ -628,9 +630,9 @@ master=system.physmem.port slave=system.system_port system.cpu.l2cache.mem_side [system.physmem] -type=SimpleDRAM +type=DRAMCtrl activation_limit=4 -addr_mapping=RaBaChCo +addr_mapping=RoRaBaChCo banks_per_rank=8 burst_length=8 channels=1 @@ -641,27 +643,33 @@ device_rowbuffer_size=1024 devices_per_rank=8 eventq_index=0 in_addr_map=true +max_accesses_per_row=16 mem_sched_policy=frfcfs +min_writes_per_switch=16 null=false -page_policy=open +page_policy=open_adaptive range=0:134217727 ranks_per_channel=2 read_buffer_size=32 static_backend_latency=10000 static_frontend_latency=10000 tBURST=5000 +tCK=1250 tCL=13750 tRAS=35000 tRCD=13750 tREFI=7800000 -tRFC=300000 +tRFC=260000 tRP=13750 -tRRD=6250 +tRRD=6000 +tRTP=7500 +tRTW=2500 +tWR=15000 tWTR=7500 -tXAW=40000 -write_buffer_size=32 -write_high_thresh_perc=70 -write_low_thresh_perc=0 +tXAW=30000 +write_buffer_size=64 +write_high_thresh_perc=85 +write_low_thresh_perc=50 port=system.membus.master[0] [system.voltage_domain] diff --git a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/simout b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/simout index da1484dec..757b668d6 100755 --- a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/simout +++ b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/simout @@ -1,12 +1,14 @@ +Redirecting stdout to build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing/simout +Redirecting stderr to build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing/simerr gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 22 2014 16:27:55 -gem5 started Jan 22 2014 17:24:20 -gem5 executing on u200540-lin -command line: build/ALPHA/gem5.opt -d build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing -re tests/run.py build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing +gem5 compiled Jun 21 2014 10:36:29 +gem5 started Jun 21 2014 10:38:16 +gem5 executing on phenom +command line: build/ALPHA/gem5.opt -d build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing -re /home/stever/hg/m5sim.org/gem5/tests/run.py build/ALPHA/tests/opt/quick/se/00.hello/alpha/tru64/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... info: Increasing stack size by one page. Hello world! -Exiting @ tick 11990500 because target called exit() +Exiting @ tick 11975500 because target called exit() diff --git a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/stats.txt b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/stats.txt index 8c004be4e..827c29bcd 100644 --- a/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/stats.txt +++ b/tests/quick/se/00.hello/ref/alpha/tru64/o3-timing/stats.txt @@ -4,11 +4,11 @@ sim_seconds 0.000012 # Nu sim_ticks 11975500 # Number of ticks simulated final_tick 11975500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 56599 # Simulator instruction rate (inst/s) -host_op_rate 56579 # Simulator op (including micro ops) rate (op/s) -host_tick_rate 283759448 # Simulator tick rate (ticks/s) -host_mem_usage 265424 # Number of bytes of host memory used -host_seconds 0.04 # Real time elapsed on the host +host_inst_rate 28986 # Simulator instruction rate (inst/s) +host_op_rate 28981 # Simulator op (including micro ops) rate (op/s) +host_tick_rate 145369893 # Simulator tick rate (ticks/s) +host_mem_usage 220536 # Number of bytes of host memory used +host_seconds 0.08 # Real time elapsed on the host sim_insts 2387 # Number of instructions simulated sim_ops 2387 # Number of ops (including micro ops) simulated system.voltage_domain.voltage 1 # Voltage in Volts @@ -238,40 +238,40 @@ system.membus.tot_pkt_size_system.cpu.l2cache.mem_side::system.physmem.port system.membus.tot_pkt_size::total 17472 # Cumulative packet size per connected master and slave (bytes) system.membus.data_through_bus 17472 # Total data (bytes) system.membus.snoop_data_through_bus 0 # Total snoop data (bytes) -system.membus.reqLayer0.occupancy 344500 # Layer occupancy (ticks) +system.membus.reqLayer0.occupancy 344000 # Layer occupancy (ticks) system.membus.reqLayer0.utilization 2.9 # Layer utilization (%) -system.membus.respLayer1.occupancy 2556250 # Layer occupancy (ticks) +system.membus.respLayer1.occupancy 2554750 # Layer occupancy (ticks) system.membus.respLayer1.utilization 21.3 # Layer utilization (%) system.cpu_clk_domain.clock 500 # Clock period in ticks -system.cpu.branchPred.lookups 1176 # Number of BP lookups -system.cpu.branchPred.condPredicted 619 # Number of conditional branches predicted +system.cpu.branchPred.lookups 1179 # Number of BP lookups +system.cpu.branchPred.condPredicted 620 # Number of conditional branches predicted system.cpu.branchPred.condIncorrect 258 # Number of conditional branches incorrect -system.cpu.branchPred.BTBLookups 804 # Number of BTB lookups -system.cpu.branchPred.BTBHits 253 # Number of BTB hits +system.cpu.branchPred.BTBLookups 806 # Number of BTB lookups +system.cpu.branchPred.BTBHits 254 # Number of BTB hits system.cpu.branchPred.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -system.cpu.branchPred.BTBHitPct 31.467662 # BTB Hit Percentage +system.cpu.branchPred.BTBHitPct 31.513648 # BTB Hit Percentage system.cpu.branchPred.usedRAS 212 # Number of times the RAS was used to get a target. system.cpu.branchPred.RASInCorrect 37 # Number of incorrect RAS predictions. system.cpu.dtb.fetch_hits 0 # ITB hits system.cpu.dtb.fetch_misses 0 # ITB misses system.cpu.dtb.fetch_acv 0 # ITB acv system.cpu.dtb.fetch_accesses 0 # ITB accesses -system.cpu.dtb.read_hits 710 # DTB read hits +system.cpu.dtb.read_hits 712 # DTB read hits system.cpu.dtb.read_misses 31 # DTB read misses system.cpu.dtb.read_acv 1 # DTB read access violations -system.cpu.dtb.read_accesses 741 # DTB read accesses +system.cpu.dtb.read_accesses 743 # DTB read accesses system.cpu.dtb.write_hits 368 # DTB write hits system.cpu.dtb.write_misses 20 # DTB write misses system.cpu.dtb.write_acv 0 # DTB write access violations system.cpu.dtb.write_accesses 388 # DTB write accesses -system.cpu.dtb.data_hits 1078 # DTB hits +system.cpu.dtb.data_hits 1080 # DTB hits system.cpu.dtb.data_misses 51 # DTB misses system.cpu.dtb.data_acv 1 # DTB access violations -system.cpu.dtb.data_accesses 1129 # DTB accesses -system.cpu.itb.fetch_hits 1065 # ITB hits +system.cpu.dtb.data_accesses 1131 # DTB accesses +system.cpu.itb.fetch_hits 1070 # ITB hits system.cpu.itb.fetch_misses 30 # ITB misses system.cpu.itb.fetch_acv 0 # ITB acv -system.cpu.itb.fetch_accesses 1095 # ITB accesses +system.cpu.itb.fetch_accesses 1100 # ITB accesses system.cpu.itb.read_hits 0 # DTB read hits system.cpu.itb.read_misses 0 # DTB read misses system.cpu.itb.read_acv 0 # DTB read access violations @@ -288,93 +288,92 @@ system.cpu.workload.num_syscalls 4 # Nu system.cpu.numCycles 23952 # 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.fetch.icacheStallCycles 4342 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.Insts 7011 # Number of instructions fetch has processed -system.cpu.fetch.Branches 1176 # Number of branches that fetch encountered -system.cpu.fetch.predictedBranches 465 # Number of branches that fetch has predicted taken -system.cpu.fetch.Cycles 1209 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.SquashCycles 869 # Number of cycles fetch has spent squashing -system.cpu.fetch.BlockedCycles 531 # Number of cycles fetch has spent blocked +system.cpu.fetch.icacheStallCycles 4349 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.Insts 7041 # Number of instructions fetch has processed +system.cpu.fetch.Branches 1179 # Number of branches that fetch encountered +system.cpu.fetch.predictedBranches 466 # Number of branches that fetch has predicted taken +system.cpu.fetch.Cycles 1215 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.SquashCycles 872 # Number of cycles fetch has spent squashing +system.cpu.fetch.BlockedCycles 516 # 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 1022 # Number of stall cycles due to pending traps system.cpu.fetch.IcacheWaitRetryStallCycles 11 # Number of stall cycles due to full MSHR -system.cpu.fetch.CacheLines 1065 # Number of cache lines fetched +system.cpu.fetch.CacheLines 1070 # Number of cache lines fetched system.cpu.fetch.IcacheSquashes 187 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 7705 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 0.909929 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 2.316850 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::samples 7706 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 0.913704 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 2.320621 # 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 6496 84.31% 84.31% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::1 53 0.69% 85.00% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 115 1.49% 86.49% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::3 95 1.23% 87.72% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::4 176 2.28% 90.01% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::5 76 0.99% 90.99% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::6 64 0.83% 91.82% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 65 0.84% 92.67% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 565 7.33% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 6491 84.23% 84.23% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 53 0.69% 84.92% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 117 1.52% 86.44% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 96 1.25% 87.68% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 176 2.28% 89.97% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 76 0.99% 90.96% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 64 0.83% 91.79% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 66 0.86% 92.64% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 567 7.36% 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 7705 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.branchRate 0.049098 # Number of branch fetches per cycle -system.cpu.fetch.rate 0.292710 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 5480 # Number of cycles decode is idle -system.cpu.decode.BlockedCycles 569 # Number of cycles decode is blocked -system.cpu.decode.RunCycles 1153 # Number of cycles decode is running -system.cpu.decode.UnblockCycles 9 # Number of cycles decode is unblocking -system.cpu.decode.SquashCycles 494 # Number of cycles decode is squashing -system.cpu.decode.BranchResolved 165 # Number of times decode resolved a branch +system.cpu.fetch.rateDist::total 7706 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.branchRate 0.049223 # Number of branch fetches per cycle +system.cpu.fetch.rate 0.293963 # Number of inst fetches per cycle +system.cpu.decode.IdleCycles 5479 # Number of cycles decode is idle +system.cpu.decode.BlockedCycles 562 # Number of cycles decode is blocked +system.cpu.decode.RunCycles 1164 # Number of cycles decode is running +system.cpu.decode.UnblockCycles 4 # Number of cycles decode is unblocking +system.cpu.decode.SquashCycles 497 # Number of cycles decode is squashing +system.cpu.decode.BranchResolved 166 # Number of times decode resolved a branch system.cpu.decode.BranchMispred 81 # Number of times decode detected a branch misprediction -system.cpu.decode.DecodedInsts 6199 # Number of instructions handled by decode +system.cpu.decode.DecodedInsts 6225 # Number of instructions handled by decode system.cpu.decode.SquashedInsts 292 # Number of squashed instructions handled by decode -system.cpu.rename.SquashCycles 494 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 5578 # Number of cycles rename is idle -system.cpu.rename.BlockCycles 254 # Number of cycles rename is blocking +system.cpu.rename.SquashCycles 497 # Number of cycles rename is squashing +system.cpu.rename.IdleCycles 5576 # Number of cycles rename is idle +system.cpu.rename.BlockCycles 257 # Number of cycles rename is blocking system.cpu.rename.serializeStallCycles 280 # count of cycles rename stalled for serializing inst -system.cpu.rename.RunCycles 1063 # Number of cycles rename is running -system.cpu.rename.UnblockCycles 36 # Number of cycles rename is unblocking -system.cpu.rename.RenamedInsts 5900 # Number of instructions processed by rename +system.cpu.rename.RunCycles 1068 # Number of cycles rename is running +system.cpu.rename.UnblockCycles 28 # Number of cycles rename is unblocking +system.cpu.rename.RenamedInsts 5913 # Number of instructions processed by rename system.cpu.rename.ROBFullEvents 1 # Number of times rename has blocked due to ROB full -system.cpu.rename.IQFullEvents 14 # Number of times rename has blocked due to IQ full -system.cpu.rename.LSQFullEvents 13 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RenamedOperands 4279 # Number of destination operands rename has renamed -system.cpu.rename.RenameLookups 6674 # Number of register rename lookups that rename has made -system.cpu.rename.int_rename_lookups 6667 # Number of integer rename lookups +system.cpu.rename.IQFullEvents 20 # Number of times rename has blocked due to IQ full +system.cpu.rename.RenamedOperands 4287 # Number of destination operands rename has renamed +system.cpu.rename.RenameLookups 6690 # Number of register rename lookups that rename has made +system.cpu.rename.int_rename_lookups 6683 # Number of integer rename lookups system.cpu.rename.fp_rename_lookups 6 # Number of floating rename lookups system.cpu.rename.CommittedMaps 1768 # Number of HB maps that are committed -system.cpu.rename.UndoneMaps 2511 # Number of HB maps that are undone due to squashing +system.cpu.rename.UndoneMaps 2519 # Number of HB maps that are undone due to squashing system.cpu.rename.serializingInsts 8 # count of serializing insts renamed system.cpu.rename.tempSerializingInsts 6 # count of temporary serializing insts renamed -system.cpu.rename.skidInsts 139 # count of insts added to the skid buffer -system.cpu.memDep0.insertedLoads 956 # Number of loads inserted to the mem dependence unit. -system.cpu.memDep0.insertedStores 469 # Number of stores inserted to the mem dependence unit. +system.cpu.rename.skidInsts 93 # count of insts added to the skid buffer +system.cpu.memDep0.insertedLoads 957 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 470 # Number of stores inserted to the mem dependence unit. system.cpu.memDep0.conflictingLoads 3 # Number of conflicting loads. system.cpu.memDep0.conflictingStores 3 # Number of conflicting stores. -system.cpu.iq.iqInstsAdded 4966 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsAdded 4974 # Number of instructions added to the IQ (excludes non-spec) system.cpu.iq.iqNonSpecInstsAdded 6 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqInstsIssued 4045 # Number of instructions issued +system.cpu.iq.iqInstsIssued 4048 # Number of instructions issued system.cpu.iq.iqSquashedInstsIssued 54 # Number of squashed instructions issued -system.cpu.iq.iqSquashedInstsExamined 2341 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedOperandsExamined 1389 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedInstsExamined 2349 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedOperandsExamined 1396 # Number of squashed operands that are examined and possibly removed from graph system.cpu.iq.iqSquashedNonSpecRemoved 2 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 7705 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 0.524984 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.239779 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::samples 7706 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 0.525305 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.241065 # 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 6081 78.92% 78.92% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 6082 78.93% 78.93% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::1 565 7.33% 86.26% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::2 401 5.20% 91.46% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::3 263 3.41% 94.87% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::4 200 2.60% 97.47% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::5 120 1.56% 99.03% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::6 47 0.61% 99.64% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::4 198 2.57% 97.44% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::5 121 1.57% 99.01% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::6 48 0.62% 99.64% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::7 17 0.22% 99.86% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::8 11 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 7705 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 7706 # 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 3 6.82% 6.82% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 0 0.00% 6.82% # attempts to use FU when none available @@ -410,7 +409,7 @@ system.cpu.iq.fu_full::MemWrite 22 50.00% 100.00% # at 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 2864 70.80% 70.80% # Type of FU issued +system.cpu.iq.FU_type_0::IntAlu 2866 70.80% 70.80% # Type of FU issued system.cpu.iq.FU_type_0::IntMult 1 0.02% 70.83% # Type of FU issued system.cpu.iq.FU_type_0::IntDiv 0 0.00% 70.83% # Type of FU issued system.cpu.iq.FU_type_0::FloatAdd 0 0.00% 70.83% # Type of FU issued @@ -439,40 +438,40 @@ system.cpu.iq.FU_type_0::SimdFloatMisc 0 0.00% 70.83% # Ty system.cpu.iq.FU_type_0::SimdFloatMult 0 0.00% 70.83% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatMultAcc 0 0.00% 70.83% # Type of FU issued system.cpu.iq.FU_type_0::SimdFloatSqrt 0 0.00% 70.83% # Type of FU issued -system.cpu.iq.FU_type_0::MemRead 785 19.41% 90.23% # Type of FU issued -system.cpu.iq.FU_type_0::MemWrite 395 9.77% 100.00% # Type of FU issued +system.cpu.iq.FU_type_0::MemRead 786 19.42% 90.24% # Type of FU issued +system.cpu.iq.FU_type_0::MemWrite 395 9.76% 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 4045 # Type of FU issued -system.cpu.iq.rate 0.168879 # Inst issue rate +system.cpu.iq.FU_type_0::total 4048 # Type of FU issued +system.cpu.iq.rate 0.169005 # Inst issue rate system.cpu.iq.fu_busy_cnt 44 # FU busy when requested -system.cpu.iq.fu_busy_rate 0.010878 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 15880 # Number of integer instruction queue reads -system.cpu.iq.int_inst_queue_writes 7311 # Number of integer instruction queue writes -system.cpu.iq.int_inst_queue_wakeup_accesses 3652 # Number of integer instruction queue wakeup accesses +system.cpu.iq.fu_busy_rate 0.010870 # FU busy rate (busy events/executed inst) +system.cpu.iq.int_inst_queue_reads 15887 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_writes 7327 # Number of integer instruction queue writes +system.cpu.iq.int_inst_queue_wakeup_accesses 3655 # Number of integer instruction queue wakeup accesses system.cpu.iq.fp_inst_queue_reads 13 # Number of floating instruction queue reads system.cpu.iq.fp_inst_queue_writes 6 # Number of floating instruction queue writes system.cpu.iq.fp_inst_queue_wakeup_accesses 6 # Number of floating instruction queue wakeup accesses -system.cpu.iq.int_alu_accesses 4082 # Number of integer alu accesses +system.cpu.iq.int_alu_accesses 4085 # Number of integer alu accesses system.cpu.iq.fp_alu_accesses 7 # Number of floating point alu accesses system.cpu.iew.lsq.thread0.forwLoads 33 # 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 541 # Number of loads squashed +system.cpu.iew.lsq.thread0.squashedLoads 542 # Number of loads squashed system.cpu.iew.lsq.thread0.ignoredResponses 1 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread0.memOrderViolation 4 # Number of memory ordering violations -system.cpu.iew.lsq.thread0.squashedStores 175 # Number of stores squashed +system.cpu.iew.lsq.thread0.squashedStores 176 # 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 0 # Number of loads that were rescheduled system.cpu.iew.lsq.thread0.cacheBlocked 16 # 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 494 # Number of cycles IEW is squashing -system.cpu.iew.iewBlockCycles 228 # Number of cycles IEW is blocking -system.cpu.iew.iewUnblockCycles 4 # Number of cycles IEW is unblocking -system.cpu.iew.iewDispatchedInsts 5308 # Number of instructions dispatched to IQ +system.cpu.iew.iewSquashCycles 497 # Number of cycles IEW is squashing +system.cpu.iew.iewBlockCycles 231 # Number of cycles IEW is blocking +system.cpu.iew.iewUnblockCycles 3 # Number of cycles IEW is unblocking +system.cpu.iew.iewDispatchedInsts 5316 # Number of instructions dispatched to IQ system.cpu.iew.iewDispSquashedInsts 162 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispLoadInsts 956 # Number of dispatched load instructions -system.cpu.iew.iewDispStoreInsts 469 # Number of dispatched store instructions +system.cpu.iew.iewDispLoadInsts 957 # Number of dispatched load instructions +system.cpu.iew.iewDispStoreInsts 470 # Number of dispatched store instructions system.cpu.iew.iewDispNonSpecInsts 6 # Number of dispatched non-speculative instructions system.cpu.iew.iewIQFullEvents 2 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall @@ -480,31 +479,31 @@ system.cpu.iew.memOrderViolationEvents 4 # Nu system.cpu.iew.predictedTakenIncorrect 53 # Number of branches that were predicted taken incorrectly system.cpu.iew.predictedNotTakenIncorrect 162 # Number of branches that were predicted not taken incorrectly system.cpu.iew.branchMispredicts 215 # Number of branch mispredicts detected at execute -system.cpu.iew.iewExecutedInsts 3855 # Number of executed instructions -system.cpu.iew.iewExecLoadInsts 742 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 190 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 3860 # Number of executed instructions +system.cpu.iew.iewExecLoadInsts 744 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 188 # Number of squashed instructions skipped in execute system.cpu.iew.exec_swp 0 # number of swp insts executed system.cpu.iew.exec_nop 336 # number of nop insts executed -system.cpu.iew.exec_refs 1130 # number of memory reference insts executed +system.cpu.iew.exec_refs 1132 # number of memory reference insts executed system.cpu.iew.exec_branches 644 # Number of branches executed system.cpu.iew.exec_stores 388 # Number of stores executed -system.cpu.iew.exec_rate 0.160947 # Inst execution rate -system.cpu.iew.wb_sent 3738 # cumulative count of insts sent to commit -system.cpu.iew.wb_count 3658 # cumulative count of insts written-back -system.cpu.iew.wb_producers 1710 # num instructions producing a value -system.cpu.iew.wb_consumers 2211 # num instructions consuming a value +system.cpu.iew.exec_rate 0.161156 # Inst execution rate +system.cpu.iew.wb_sent 3742 # cumulative count of insts sent to commit +system.cpu.iew.wb_count 3661 # cumulative count of insts written-back +system.cpu.iew.wb_producers 1713 # num instructions producing a value +system.cpu.iew.wb_consumers 2215 # 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 0.152722 # insts written-back per cycle -system.cpu.iew.wb_fanout 0.773406 # average fanout of values written-back +system.cpu.iew.wb_rate 0.152847 # insts written-back per cycle +system.cpu.iew.wb_fanout 0.773363 # 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.commitSquashedInsts 2726 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 2734 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 4 # The number of times commit has been forced to stall to communicate backwards system.cpu.commit.branchMispredicts 180 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 7211 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 0.357232 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.199732 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::samples 7209 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 0.357331 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.199884 # 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 6342 87.95% 87.95% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 6340 87.95% 87.95% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::1 204 2.83% 90.78% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::2 308 4.27% 95.05% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::3 114 1.58% 96.63% # Number of insts commited each cycle @@ -516,7 +515,7 @@ system.cpu.commit.committed_per_cycle::8 63 0.87% 100.00% # Nu 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 7211 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 7209 # Number of insts commited each cycle system.cpu.commit.committedInsts 2576 # Number of instructions committed system.cpu.commit.committedOps 2576 # Number of ops (including micro ops) committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed @@ -564,18 +563,18 @@ system.cpu.commit.op_class_0::InstPrefetch 0 0.00% 100.00% # system.cpu.commit.op_class_0::total 2576 # Class of committed instruction system.cpu.commit.bw_lim_events 63 # 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 12203 # The number of ROB reads -system.cpu.rob.rob_writes 11111 # The number of ROB writes +system.cpu.rob.rob_reads 12209 # The number of ROB reads +system.cpu.rob.rob_writes 11130 # The number of ROB writes system.cpu.timesIdled 157 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 16247 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.idleCycles 16246 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 2387 # Number of Instructions Simulated system.cpu.committedOps 2387 # Number of Ops (including micro ops) Simulated system.cpu.cpi 10.034353 # CPI: Cycles Per Instruction system.cpu.cpi_total 10.034353 # CPI: Total CPI of All Threads system.cpu.ipc 0.099658 # IPC: Instructions Per Cycle system.cpu.ipc_total 0.099658 # IPC: Total IPC of All Threads -system.cpu.int_regfile_reads 4672 # number of integer regfile reads -system.cpu.int_regfile_writes 2825 # number of integer regfile writes +system.cpu.int_regfile_reads 4676 # number of integer regfile reads +system.cpu.int_regfile_writes 2829 # number of integer regfile writes system.cpu.fp_regfile_reads 6 # number of floating regfile reads system.cpu.misc_regfile_reads 1 # number of misc regfile reads system.cpu.misc_regfile_writes 1 # number of misc regfile writes @@ -599,56 +598,56 @@ system.cpu.toL2Bus.respLayer0.utilization 2.6 # L system.cpu.toL2Bus.respLayer1.occupancy 133500 # Layer occupancy (ticks) system.cpu.toL2Bus.respLayer1.utilization 1.1 # Layer utilization (%) system.cpu.icache.tags.replacements 0 # number of replacements -system.cpu.icache.tags.tagsinuse 93.052511 # Cycle average of tags in use -system.cpu.icache.tags.total_refs 815 # Total number of references to valid blocks. +system.cpu.icache.tags.tagsinuse 93.052678 # Cycle average of tags in use +system.cpu.icache.tags.total_refs 820 # Total number of references to valid blocks. system.cpu.icache.tags.sampled_refs 188 # Sample count of references to valid blocks. -system.cpu.icache.tags.avg_refs 4.335106 # Average number of references to valid blocks. +system.cpu.icache.tags.avg_refs 4.361702 # Average number of references to valid blocks. system.cpu.icache.tags.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.icache.tags.occ_blocks::cpu.inst 93.052511 # Average occupied blocks per requestor +system.cpu.icache.tags.occ_blocks::cpu.inst 93.052678 # Average occupied blocks per requestor system.cpu.icache.tags.occ_percent::cpu.inst 0.045436 # Average percentage of cache occupancy system.cpu.icache.tags.occ_percent::total 0.045436 # Average percentage of cache occupancy system.cpu.icache.tags.occ_task_id_blocks::1024 188 # Occupied blocks per task id system.cpu.icache.tags.age_task_id_blocks_1024::0 161 # Occupied blocks per task id system.cpu.icache.tags.age_task_id_blocks_1024::1 27 # Occupied blocks per task id system.cpu.icache.tags.occ_task_id_percent::1024 0.091797 # Percentage of cache occupancy per task id -system.cpu.icache.tags.tag_accesses 2318 # Number of tag accesses -system.cpu.icache.tags.data_accesses 2318 # Number of data accesses -system.cpu.icache.ReadReq_hits::cpu.inst 815 # number of ReadReq hits -system.cpu.icache.ReadReq_hits::total 815 # number of ReadReq hits -system.cpu.icache.demand_hits::cpu.inst 815 # number of demand (read+write) hits -system.cpu.icache.demand_hits::total 815 # number of demand (read+write) hits -system.cpu.icache.overall_hits::cpu.inst 815 # number of overall hits -system.cpu.icache.overall_hits::total 815 # number of overall hits +system.cpu.icache.tags.tag_accesses 2328 # Number of tag accesses +system.cpu.icache.tags.data_accesses 2328 # Number of data accesses +system.cpu.icache.ReadReq_hits::cpu.inst 820 # number of ReadReq hits +system.cpu.icache.ReadReq_hits::total 820 # number of ReadReq hits +system.cpu.icache.demand_hits::cpu.inst 820 # number of demand (read+write) hits +system.cpu.icache.demand_hits::total 820 # number of demand (read+write) hits +system.cpu.icache.overall_hits::cpu.inst 820 # number of overall hits +system.cpu.icache.overall_hits::total 820 # number of overall hits system.cpu.icache.ReadReq_misses::cpu.inst 250 # number of ReadReq misses system.cpu.icache.ReadReq_misses::total 250 # number of ReadReq misses system.cpu.icache.demand_misses::cpu.inst 250 # number of demand (read+write) misses system.cpu.icache.demand_misses::total 250 # number of demand (read+write) misses system.cpu.icache.overall_misses::cpu.inst 250 # number of overall misses system.cpu.icache.overall_misses::total 250 # number of overall misses -system.cpu.icache.ReadReq_miss_latency::cpu.inst 17506249 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_latency::total 17506249 # number of ReadReq miss cycles -system.cpu.icache.demand_miss_latency::cpu.inst 17506249 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_latency::total 17506249 # number of demand (read+write) miss cycles -system.cpu.icache.overall_miss_latency::cpu.inst 17506249 # number of overall miss cycles -system.cpu.icache.overall_miss_latency::total 17506249 # number of overall miss cycles -system.cpu.icache.ReadReq_accesses::cpu.inst 1065 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_accesses::total 1065 # number of ReadReq accesses(hits+misses) -system.cpu.icache.demand_accesses::cpu.inst 1065 # number of demand (read+write) accesses -system.cpu.icache.demand_accesses::total 1065 # number of demand (read+write) accesses -system.cpu.icache.overall_accesses::cpu.inst 1065 # number of overall (read+write) accesses -system.cpu.icache.overall_accesses::total 1065 # number of overall (read+write) accesses -system.cpu.icache.ReadReq_miss_rate::cpu.inst 0.234742 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_miss_rate::total 0.234742 # miss rate for ReadReq accesses -system.cpu.icache.demand_miss_rate::cpu.inst 0.234742 # miss rate for demand accesses -system.cpu.icache.demand_miss_rate::total 0.234742 # miss rate for demand accesses -system.cpu.icache.overall_miss_rate::cpu.inst 0.234742 # miss rate for overall accesses -system.cpu.icache.overall_miss_rate::total 0.234742 # miss rate for overall accesses -system.cpu.icache.ReadReq_avg_miss_latency::cpu.inst 70024.996000 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_miss_latency::total 70024.996000 # average ReadReq miss latency -system.cpu.icache.demand_avg_miss_latency::cpu.inst 70024.996000 # average overall miss latency -system.cpu.icache.demand_avg_miss_latency::total 70024.996000 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency::cpu.inst 70024.996000 # average overall miss latency -system.cpu.icache.overall_avg_miss_latency::total 70024.996000 # average overall miss latency +system.cpu.icache.ReadReq_miss_latency::cpu.inst 17505249 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_latency::total 17505249 # number of ReadReq miss cycles +system.cpu.icache.demand_miss_latency::cpu.inst 17505249 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency::total 17505249 # number of demand (read+write) miss cycles +system.cpu.icache.overall_miss_latency::cpu.inst 17505249 # number of overall miss cycles +system.cpu.icache.overall_miss_latency::total 17505249 # number of overall miss cycles +system.cpu.icache.ReadReq_accesses::cpu.inst 1070 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses::total 1070 # number of ReadReq accesses(hits+misses) +system.cpu.icache.demand_accesses::cpu.inst 1070 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses::total 1070 # number of demand (read+write) accesses +system.cpu.icache.overall_accesses::cpu.inst 1070 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses::total 1070 # number of overall (read+write) accesses +system.cpu.icache.ReadReq_miss_rate::cpu.inst 0.233645 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate::total 0.233645 # miss rate for ReadReq accesses +system.cpu.icache.demand_miss_rate::cpu.inst 0.233645 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate::total 0.233645 # miss rate for demand accesses +system.cpu.icache.overall_miss_rate::cpu.inst 0.233645 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate::total 0.233645 # miss rate for overall accesses +system.cpu.icache.ReadReq_avg_miss_latency::cpu.inst 70020.996000 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_miss_latency::total 70020.996000 # average ReadReq miss latency +system.cpu.icache.demand_avg_miss_latency::cpu.inst 70020.996000 # average overall miss latency +system.cpu.icache.demand_avg_miss_latency::total 70020.996000 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency::cpu.inst 70020.996000 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency::total 70020.996000 # average overall miss latency system.cpu.icache.blocked_cycles::no_mshrs 112 # 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 2 # number of cycles access was blocked @@ -669,33 +668,33 @@ system.cpu.icache.demand_mshr_misses::cpu.inst 188 system.cpu.icache.demand_mshr_misses::total 188 # number of demand (read+write) MSHR misses system.cpu.icache.overall_mshr_misses::cpu.inst 188 # number of overall MSHR misses system.cpu.icache.overall_mshr_misses::total 188 # number of overall MSHR misses -system.cpu.icache.ReadReq_mshr_miss_latency::cpu.inst 13110499 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_latency::total 13110499 # number of ReadReq MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency::cpu.inst 13110499 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency::total 13110499 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency::cpu.inst 13110499 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency::total 13110499 # number of overall MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate::cpu.inst 0.176526 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_miss_rate::total 0.176526 # mshr miss rate for ReadReq accesses -system.cpu.icache.demand_mshr_miss_rate::cpu.inst 0.176526 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_miss_rate::total 0.176526 # mshr miss rate for demand accesses -system.cpu.icache.overall_mshr_miss_rate::cpu.inst 0.176526 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_miss_rate::total 0.176526 # mshr miss rate for overall accesses -system.cpu.icache.ReadReq_avg_mshr_miss_latency::cpu.inst 69736.696809 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency::total 69736.696809 # average ReadReq mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency::cpu.inst 69736.696809 # average overall mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency::total 69736.696809 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency::cpu.inst 69736.696809 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency::total 69736.696809 # average overall mshr miss latency +system.cpu.icache.ReadReq_mshr_miss_latency::cpu.inst 13109499 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency::total 13109499 # number of ReadReq MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency::cpu.inst 13109499 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency::total 13109499 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency::cpu.inst 13109499 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency::total 13109499 # number of overall MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate::cpu.inst 0.175701 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate::total 0.175701 # mshr miss rate for ReadReq accesses +system.cpu.icache.demand_mshr_miss_rate::cpu.inst 0.175701 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate::total 0.175701 # mshr miss rate for demand accesses +system.cpu.icache.overall_mshr_miss_rate::cpu.inst 0.175701 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate::total 0.175701 # mshr miss rate for overall accesses +system.cpu.icache.ReadReq_avg_mshr_miss_latency::cpu.inst 69731.377660 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency::total 69731.377660 # average ReadReq mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency::cpu.inst 69731.377660 # average overall mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency::total 69731.377660 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency::cpu.inst 69731.377660 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency::total 69731.377660 # average overall mshr miss latency system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.l2cache.tags.replacements 0 # number of replacements -system.cpu.l2cache.tags.tagsinuse 121.888429 # Cycle average of tags in use +system.cpu.l2cache.tags.tagsinuse 121.888470 # Cycle average of tags in use system.cpu.l2cache.tags.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.tags.sampled_refs 249 # Sample count of references to valid blocks. system.cpu.l2cache.tags.avg_refs 0 # Average number of references to valid blocks. system.cpu.l2cache.tags.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.tags.occ_blocks::cpu.inst 93.250749 # Average occupied blocks per requestor -system.cpu.l2cache.tags.occ_blocks::cpu.data 28.637680 # Average occupied blocks per requestor +system.cpu.l2cache.tags.occ_blocks::cpu.inst 93.250833 # Average occupied blocks per requestor +system.cpu.l2cache.tags.occ_blocks::cpu.data 28.637638 # Average occupied blocks per requestor system.cpu.l2cache.tags.occ_percent::cpu.inst 0.002846 # Average percentage of cache occupancy system.cpu.l2cache.tags.occ_percent::cpu.data 0.000874 # Average percentage of cache occupancy system.cpu.l2cache.tags.occ_percent::total 0.003720 # Average percentage of cache occupancy @@ -716,17 +715,17 @@ system.cpu.l2cache.demand_misses::total 273 # nu system.cpu.l2cache.overall_misses::cpu.inst 188 # number of overall misses system.cpu.l2cache.overall_misses::cpu.data 85 # number of overall misses system.cpu.l2cache.overall_misses::total 273 # number of overall misses -system.cpu.l2cache.ReadReq_miss_latency::cpu.inst 12921750 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_latency::cpu.data 4652500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_latency::total 17574250 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency::cpu.inst 12920750 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency::cpu.data 4652000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency::total 17572750 # number of ReadReq miss cycles system.cpu.l2cache.ReadExReq_miss_latency::cpu.data 1688000 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_latency::total 1688000 # number of ReadExReq miss cycles -system.cpu.l2cache.demand_miss_latency::cpu.inst 12921750 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_latency::cpu.data 6340500 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_latency::total 19262250 # number of demand (read+write) miss cycles -system.cpu.l2cache.overall_miss_latency::cpu.inst 12921750 # number of overall miss cycles -system.cpu.l2cache.overall_miss_latency::cpu.data 6340500 # number of overall miss cycles -system.cpu.l2cache.overall_miss_latency::total 19262250 # number of overall miss cycles +system.cpu.l2cache.demand_miss_latency::cpu.inst 12920750 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency::cpu.data 6340000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency::total 19260750 # number of demand (read+write) miss cycles +system.cpu.l2cache.overall_miss_latency::cpu.inst 12920750 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency::cpu.data 6340000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency::total 19260750 # number of overall miss cycles system.cpu.l2cache.ReadReq_accesses::cpu.inst 188 # number of ReadReq accesses(hits+misses) system.cpu.l2cache.ReadReq_accesses::cpu.data 61 # number of ReadReq accesses(hits+misses) system.cpu.l2cache.ReadReq_accesses::total 249 # number of ReadReq accesses(hits+misses) @@ -749,17 +748,17 @@ system.cpu.l2cache.demand_miss_rate::total 1 # system.cpu.l2cache.overall_miss_rate::cpu.inst 1 # miss rate for overall accesses system.cpu.l2cache.overall_miss_rate::cpu.data 1 # miss rate for overall accesses system.cpu.l2cache.overall_miss_rate::total 1 # miss rate for overall accesses -system.cpu.l2cache.ReadReq_avg_miss_latency::cpu.inst 68732.712766 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_miss_latency::cpu.data 76270.491803 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_miss_latency::total 70579.317269 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_miss_latency::cpu.inst 68727.393617 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_miss_latency::cpu.data 76262.295082 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_miss_latency::total 70573.293173 # average ReadReq miss latency system.cpu.l2cache.ReadExReq_avg_miss_latency::cpu.data 70333.333333 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_miss_latency::total 70333.333333 # average ReadExReq miss latency -system.cpu.l2cache.demand_avg_miss_latency::cpu.inst 68732.712766 # average overall miss latency -system.cpu.l2cache.demand_avg_miss_latency::cpu.data 74594.117647 # average overall miss latency -system.cpu.l2cache.demand_avg_miss_latency::total 70557.692308 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency::cpu.inst 68732.712766 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency::cpu.data 74594.117647 # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency::total 70557.692308 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency::cpu.inst 68727.393617 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency::cpu.data 74588.235294 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency::total 70552.197802 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency::cpu.inst 68727.393617 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency::cpu.data 74588.235294 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency::total 70552.197802 # 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 @@ -815,9 +814,9 @@ system.cpu.l2cache.overall_avg_mshr_miss_latency::total 58044.871795 system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate system.cpu.dcache.tags.replacements 0 # number of replacements system.cpu.dcache.tags.tagsinuse 45.583444 # Cycle average of tags in use -system.cpu.dcache.tags.total_refs 759 # Total number of references to valid blocks. +system.cpu.dcache.tags.total_refs 761 # Total number of references to valid blocks. system.cpu.dcache.tags.sampled_refs 85 # Sample count of references to valid blocks. -system.cpu.dcache.tags.avg_refs 8.929412 # Average number of references to valid blocks. +system.cpu.dcache.tags.avg_refs 8.952941 # Average number of references to valid blocks. system.cpu.dcache.tags.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.tags.occ_blocks::cpu.data 45.583444 # Average occupied blocks per requestor system.cpu.dcache.tags.occ_percent::cpu.data 0.011129 # Average percentage of cache occupancy @@ -826,16 +825,16 @@ system.cpu.dcache.tags.occ_task_id_blocks::1024 85 system.cpu.dcache.tags.age_task_id_blocks_1024::0 67 # Occupied blocks per task id system.cpu.dcache.tags.age_task_id_blocks_1024::1 18 # Occupied blocks per task id system.cpu.dcache.tags.occ_task_id_percent::1024 0.020752 # Percentage of cache occupancy per task id -system.cpu.dcache.tags.tag_accesses 1995 # Number of tag accesses -system.cpu.dcache.tags.data_accesses 1995 # Number of data accesses -system.cpu.dcache.ReadReq_hits::cpu.data 546 # number of ReadReq hits -system.cpu.dcache.ReadReq_hits::total 546 # number of ReadReq hits +system.cpu.dcache.tags.tag_accesses 1999 # Number of tag accesses +system.cpu.dcache.tags.data_accesses 1999 # Number of data accesses +system.cpu.dcache.ReadReq_hits::cpu.data 548 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits::total 548 # number of ReadReq hits system.cpu.dcache.WriteReq_hits::cpu.data 213 # number of WriteReq hits system.cpu.dcache.WriteReq_hits::total 213 # number of WriteReq hits -system.cpu.dcache.demand_hits::cpu.data 759 # number of demand (read+write) hits -system.cpu.dcache.demand_hits::total 759 # number of demand (read+write) hits -system.cpu.dcache.overall_hits::cpu.data 759 # number of overall hits -system.cpu.dcache.overall_hits::total 759 # number of overall hits +system.cpu.dcache.demand_hits::cpu.data 761 # number of demand (read+write) hits +system.cpu.dcache.demand_hits::total 761 # number of demand (read+write) hits +system.cpu.dcache.overall_hits::cpu.data 761 # number of overall hits +system.cpu.dcache.overall_hits::total 761 # number of overall hits system.cpu.dcache.ReadReq_misses::cpu.data 115 # number of ReadReq misses system.cpu.dcache.ReadReq_misses::total 115 # number of ReadReq misses system.cpu.dcache.WriteReq_misses::cpu.data 81 # number of WriteReq misses @@ -852,22 +851,22 @@ system.cpu.dcache.demand_miss_latency::cpu.data 13179000 system.cpu.dcache.demand_miss_latency::total 13179000 # number of demand (read+write) miss cycles system.cpu.dcache.overall_miss_latency::cpu.data 13179000 # number of overall miss cycles system.cpu.dcache.overall_miss_latency::total 13179000 # number of overall miss cycles -system.cpu.dcache.ReadReq_accesses::cpu.data 661 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_accesses::total 661 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses::cpu.data 663 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses::total 663 # number of ReadReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses::cpu.data 294 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_accesses::total 294 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.demand_accesses::cpu.data 955 # number of demand (read+write) accesses -system.cpu.dcache.demand_accesses::total 955 # number of demand (read+write) accesses -system.cpu.dcache.overall_accesses::cpu.data 955 # number of overall (read+write) accesses -system.cpu.dcache.overall_accesses::total 955 # number of overall (read+write) accesses -system.cpu.dcache.ReadReq_miss_rate::cpu.data 0.173979 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_miss_rate::total 0.173979 # miss rate for ReadReq accesses +system.cpu.dcache.demand_accesses::cpu.data 957 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses::total 957 # number of demand (read+write) accesses +system.cpu.dcache.overall_accesses::cpu.data 957 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses::total 957 # number of overall (read+write) accesses +system.cpu.dcache.ReadReq_miss_rate::cpu.data 0.173454 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_miss_rate::total 0.173454 # miss rate for ReadReq accesses system.cpu.dcache.WriteReq_miss_rate::cpu.data 0.275510 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_miss_rate::total 0.275510 # miss rate for WriteReq accesses -system.cpu.dcache.demand_miss_rate::cpu.data 0.205236 # miss rate for demand accesses -system.cpu.dcache.demand_miss_rate::total 0.205236 # miss rate for demand accesses -system.cpu.dcache.overall_miss_rate::cpu.data 0.205236 # miss rate for overall accesses -system.cpu.dcache.overall_miss_rate::total 0.205236 # miss rate for overall accesses +system.cpu.dcache.demand_miss_rate::cpu.data 0.204807 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate::total 0.204807 # miss rate for demand accesses +system.cpu.dcache.overall_miss_rate::cpu.data 0.204807 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate::total 0.204807 # miss rate for overall accesses system.cpu.dcache.ReadReq_avg_miss_latency::cpu.data 68493.478261 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_miss_latency::total 68493.478261 # average ReadReq miss latency system.cpu.dcache.WriteReq_avg_miss_latency::cpu.data 65459.876543 # average WriteReq miss latency @@ -900,30 +899,30 @@ system.cpu.dcache.demand_mshr_misses::cpu.data 85 system.cpu.dcache.demand_mshr_misses::total 85 # number of demand (read+write) MSHR misses system.cpu.dcache.overall_mshr_misses::cpu.data 85 # number of overall MSHR misses system.cpu.dcache.overall_mshr_misses::total 85 # number of overall MSHR misses -system.cpu.dcache.ReadReq_mshr_miss_latency::cpu.data 4713500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_latency::total 4713500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency::cpu.data 4713000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency::total 4713000 # number of ReadReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_latency::cpu.data 1713500 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_latency::total 1713500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency::cpu.data 6427000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency::total 6427000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency::cpu.data 6427000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency::total 6427000 # number of overall MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate::cpu.data 0.092284 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_miss_rate::total 0.092284 # mshr miss rate for ReadReq accesses +system.cpu.dcache.demand_mshr_miss_latency::cpu.data 6426500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency::total 6426500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency::cpu.data 6426500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency::total 6426500 # number of overall MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate::cpu.data 0.092006 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_rate::total 0.092006 # mshr miss rate for ReadReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate::cpu.data 0.081633 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_miss_rate::total 0.081633 # mshr miss rate for WriteReq accesses -system.cpu.dcache.demand_mshr_miss_rate::cpu.data 0.089005 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_miss_rate::total 0.089005 # mshr miss rate for demand accesses -system.cpu.dcache.overall_mshr_miss_rate::cpu.data 0.089005 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_miss_rate::total 0.089005 # mshr miss rate for overall accesses -system.cpu.dcache.ReadReq_avg_mshr_miss_latency::cpu.data 77270.491803 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency::total 77270.491803 # average ReadReq mshr miss latency +system.cpu.dcache.demand_mshr_miss_rate::cpu.data 0.088819 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate::total 0.088819 # mshr miss rate for demand accesses +system.cpu.dcache.overall_mshr_miss_rate::cpu.data 0.088819 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate::total 0.088819 # mshr miss rate for overall accesses +system.cpu.dcache.ReadReq_avg_mshr_miss_latency::cpu.data 77262.295082 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency::total 77262.295082 # average ReadReq mshr miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency::cpu.data 71395.833333 # average WriteReq mshr miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency::total 71395.833333 # average WriteReq mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency::cpu.data 75611.764706 # average overall mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency::total 75611.764706 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency::cpu.data 75611.764706 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency::total 75611.764706 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency::cpu.data 75605.882353 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency::total 75605.882353 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency::cpu.data 75605.882353 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency::total 75605.882353 # average overall mshr miss latency system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate ---------- End Simulation Statistics ---------- |