diff options
Diffstat (limited to 'tests/quick/00.hello/ref/alpha/tru64')
9 files changed, 352 insertions, 274 deletions
diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini index f5eb9b8b9..d3406f49b 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt index 536bed0d1..ffd2f7ab7 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 143 # Number of BTB hits -global.BPredUnit.BTBLookups 610 # Number of BTB lookups -global.BPredUnit.RASInCorrect 32 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 212 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 394 # Number of conditional branches predicted -global.BPredUnit.lookups 779 # Number of BP lookups -global.BPredUnit.usedRAS 155 # Number of times the RAS was used to get a target. -host_inst_rate 72558 # Simulator instruction rate (inst/s) -host_mem_usage 196048 # Number of bytes of host memory used -host_seconds 0.03 # Real time elapsed on the host -host_tick_rate 63572637 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 8 # Number of conflicting loads. +global.BPredUnit.BTBHits 156 # Number of BTB hits +global.BPredUnit.BTBLookups 642 # Number of BTB lookups +global.BPredUnit.RASInCorrect 35 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 213 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 401 # Number of conditional branches predicted +global.BPredUnit.lookups 824 # Number of BP lookups +global.BPredUnit.usedRAS 163 # Number of times the RAS was used to get a target. +host_inst_rate 31893 # Simulator instruction rate (inst/s) +host_mem_usage 179460 # Number of bytes of host memory used +host_seconds 0.08 # Real time elapsed on the host +host_tick_rate 32096529 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 7 # Number of conflicting loads. memdepunit.memDep.conflictingStores 7 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 636 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 369 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 698 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 412 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2387 # Number of instructions simulated sim_seconds 0.000002 # Number of seconds simulated -sim_ticks 2104000 # Number of ticks simulated +sim_ticks 2410000 # Number of ticks simulated system.cpu.commit.COM:branches 396 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 35 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 32 # 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.start_dist # Number of insts commited each cycle -system.cpu.commit.COM:committed_per_cycle.samples 3945 +system.cpu.commit.COM:committed_per_cycle.samples 4452 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 2992 7584.28% - 1 255 646.39% - 2 335 849.18% - 3 139 352.34% - 4 66 167.30% - 5 69 174.90% - 6 33 83.65% - 7 21 53.23% - 8 35 88.72% + 0 3490 7839.17% + 1 258 579.51% + 2 340 763.70% + 3 140 314.47% + 4 70 157.23% + 5 70 157.23% + 6 32 71.88% + 7 20 44.92% + 8 32 71.88% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,69 +43,69 @@ system.cpu.commit.COM:loads 415 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 709 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 131 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 132 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 2576 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 4 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 1134 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 1380 # The number of squashed insts skipped by commit system.cpu.committedInsts 2387 # Number of Instructions Simulated system.cpu.committedInsts_total 2387 # Number of Instructions Simulated -system.cpu.cpi 1.747382 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.747382 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 519 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 8729.508197 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5745.901639 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 458 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 532500 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.117534 # miss rate for ReadReq accesses +system.cpu.cpi 1.984080 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.984080 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 528 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 8639.344262 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5655.737705 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 467 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 527000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.115530 # miss rate for ReadReq accesses system.cpu.dcache.ReadReq_misses 61 # number of ReadReq misses system.cpu.dcache.ReadReq_mshr_hits 10 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 350500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.117534 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_latency 345000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.115530 # mshr miss rate for ReadReq accesses system.cpu.dcache.ReadReq_mshr_misses 61 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 240 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 18810.810811 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6202.702703 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 18297.297297 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5986.486486 # average WriteReq mshr miss latency system.cpu.dcache.WriteReq_hits 203 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 696000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 677000 # number of WriteReq miss cycles system.cpu.dcache.WriteReq_miss_rate 0.154167 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 37 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_hits 54 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 229500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 221500 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.154167 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 37 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 7.929412 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 8.035294 # 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 0 # 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 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 759 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 12535.714286 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5918.367347 # average overall mshr miss latency -system.cpu.dcache.demand_hits 661 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1228500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.129117 # miss rate for demand accesses +system.cpu.dcache.demand_accesses 768 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 12285.714286 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5780.612245 # average overall mshr miss latency +system.cpu.dcache.demand_hits 670 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 1204000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.127604 # miss rate for demand accesses system.cpu.dcache.demand_misses 98 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 64 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 580000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.129117 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_latency 566500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.127604 # mshr miss rate for demand accesses system.cpu.dcache.demand_mshr_misses 98 # 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.overall_accesses 759 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 12535.714286 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5918.367347 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 768 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 12285.714286 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5780.612245 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 661 # number of overall hits -system.cpu.dcache.overall_miss_latency 1228500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.129117 # miss rate for overall accesses +system.cpu.dcache.overall_hits 670 # number of overall hits +system.cpu.dcache.overall_miss_latency 1204000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.127604 # miss rate for overall accesses system.cpu.dcache.overall_misses 98 # number of overall misses system.cpu.dcache.overall_mshr_hits 64 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 580000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.129117 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_latency 566500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.127604 # mshr miss rate for overall accesses system.cpu.dcache.overall_mshr_misses 98 # 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 @@ -121,89 +121,101 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 85 # 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 50.690606 # Cycle average of tags in use -system.cpu.dcache.total_refs 674 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 47.072215 # Cycle average of tags in use +system.cpu.dcache.total_refs 683 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 91 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BlockedCycles 93 # Number of cycles decode is blocked system.cpu.decode.DECODE:BranchMispred 83 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 126 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 4236 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 3045 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 809 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 225 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 304 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:BranchResolved 135 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 4564 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 3475 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 884 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 283 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 303 # Number of squashed instructions handled by decode system.cpu.decode.DECODE:UnblockCycles 1 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 779 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 691 # Number of cache lines fetched -system.cpu.fetch.Cycles 1534 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 112 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 4961 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 223 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.186766 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 691 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 298 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.189403 # Number of inst fetches per cycle +system.cpu.dtb.accesses 931 # DTB accesses +system.cpu.dtb.acv 1 # DTB access violations +system.cpu.dtb.hits 904 # DTB hits +system.cpu.dtb.misses 27 # DTB misses +system.cpu.dtb.read_accesses 575 # DTB read accesses +system.cpu.dtb.read_acv 1 # DTB read access violations +system.cpu.dtb.read_hits 563 # DTB read hits +system.cpu.dtb.read_misses 12 # DTB read misses +system.cpu.dtb.write_accesses 356 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 341 # DTB write hits +system.cpu.dtb.write_misses 15 # DTB write misses +system.cpu.fetch.Branches 824 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 707 # Number of cache lines fetched +system.cpu.fetch.Cycles 1626 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 101 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 5268 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 242 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.173986 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 707 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 319 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.112331 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 4171 +system.cpu.fetch.rateDist.samples 4736 system.cpu.fetch.rateDist.min_value 0 - 0 3330 7983.70% - 1 36 86.31% - 2 85 203.79% - 3 57 136.66% - 4 109 261.33% - 5 54 129.47% - 6 40 95.90% - 7 42 100.70% - 8 418 1002.16% + 0 3845 8118.67% + 1 38 80.24% + 2 85 179.48% + 3 63 133.02% + 4 118 249.16% + 5 55 116.13% + 6 42 88.68% + 7 48 101.35% + 8 442 933.28% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 674 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7774.193548 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5451.612903 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 488 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 1446000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.275964 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 186 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 17 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 1014000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.275964 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 186 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 692 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7648.351648 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5370.879121 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 510 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 1392000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.263006 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 182 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 15 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 977500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.263006 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 182 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 2.623656 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 2.802198 # 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 674 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7774.193548 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5451.612903 # average overall mshr miss latency -system.cpu.icache.demand_hits 488 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 1446000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.275964 # miss rate for demand accesses -system.cpu.icache.demand_misses 186 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 17 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 1014000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.275964 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 186 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 692 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7648.351648 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5370.879121 # average overall mshr miss latency +system.cpu.icache.demand_hits 510 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 1392000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.263006 # miss rate for demand accesses +system.cpu.icache.demand_misses 182 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 15 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 977500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.263006 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 182 # 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.overall_accesses 674 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7774.193548 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5451.612903 # average overall mshr miss latency +system.cpu.icache.overall_accesses 692 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7648.351648 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5370.879121 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 488 # number of overall hits -system.cpu.icache.overall_miss_latency 1446000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.275964 # miss rate for overall accesses -system.cpu.icache.overall_misses 186 # number of overall misses -system.cpu.icache.overall_mshr_hits 17 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 1014000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.275964 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 186 # number of overall MSHR misses +system.cpu.icache.overall_hits 510 # number of overall hits +system.cpu.icache.overall_miss_latency 1392000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.263006 # miss rate for overall accesses +system.cpu.icache.overall_misses 182 # number of overall misses +system.cpu.icache.overall_mshr_hits 15 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 977500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.263006 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 182 # 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.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -216,61 +228,61 @@ system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.icache.replacements 0 # number of replacements -system.cpu.icache.sampled_refs 186 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 182 # 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 102.643576 # Cycle average of tags in use -system.cpu.icache.total_refs 488 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 92.900452 # Cycle average of tags in use +system.cpu.icache.total_refs 510 # 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 26984 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 522 # Number of branches executed -system.cpu.iew.EXEC:nop 242 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.736514 # Inst execution rate -system.cpu.iew.EXEC:refs 896 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 333 # Number of stores executed +system.cpu.idleCycles 56472 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 538 # Number of branches executed +system.cpu.iew.EXEC:nop 274 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.670608 # Inst execution rate +system.cpu.iew.EXEC:refs 934 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 356 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1736 # num instructions consuming a value -system.cpu.iew.WB:count 3002 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.793779 # average fanout of values written-back +system.cpu.iew.WB:consumers 1781 # num instructions consuming a value +system.cpu.iew.WB:count 3084 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.794497 # 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 1378 # num instructions producing a value -system.cpu.iew.WB:rate 0.719731 # insts written-back per cycle -system.cpu.iew.WB:sent 3020 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 147 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 1415 # num instructions producing a value +system.cpu.iew.WB:rate 0.651182 # insts written-back per cycle +system.cpu.iew.WB:sent 3123 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 149 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 0 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 636 # Number of dispatched load instructions +system.cpu.iew.iewDispLoadInsts 698 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 6 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 85 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 369 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 3727 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 563 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 108 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 3072 # Number of executed instructions +system.cpu.iew.iewDispSquashedInsts 83 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 412 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 4056 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 578 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 105 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 3176 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # 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 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 225 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 283 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # 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 0 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.lsq.thread.0.forwLoads 25 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 1 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.ignoredResponses 2 # 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 13 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 11 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 221 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 75 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 13 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 99 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 48 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.572285 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.572285 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 3180 # Type of FU issued +system.cpu.iew.lsq.thread.0.squashedLoads 283 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 118 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 11 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 97 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 52 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.504012 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.504012 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 3281 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 0 0.00% # Type of FU issued - IntAlu 2258 71.01% # Type of FU issued + IntAlu 2319 70.68% # Type of FU issued IntMult 1 0.03% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 0 0.00% # Type of FU issued @@ -279,16 +291,16 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 581 18.27% # Type of FU issued - MemWrite 340 10.69% # Type of FU issued + MemRead 597 18.20% # Type of FU issued + MemWrite 364 11.09% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.end_dist -system.cpu.iq.ISSUE:fu_busy_cnt 36 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.011321 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 35 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.010667 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist No_OpClass 0 0.00% # attempts to use FU when none available - IntAlu 2 5.56% # attempts to use FU when none available + IntAlu 1 2.86% # attempts to use FU when none available IntMult 0 0.00% # attempts to use FU when none available IntDiv 0 0.00% # attempts to use FU when none available FloatAdd 0 0.00% # attempts to use FU when none available @@ -297,59 +309,63 @@ system.cpu.iq.ISSUE:fu_full.start_dist FloatMult 0 0.00% # attempts to use FU when none available FloatDiv 0 0.00% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 12 33.33% # attempts to use FU when none available - MemWrite 22 61.11% # attempts to use FU when none available + MemRead 12 34.29% # attempts to use FU when none available + MemWrite 22 62.86% # attempts to use FU when none available IprAccess 0 0.00% # attempts to use FU when none available InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 4171 +system.cpu.iq.ISSUE:issued_per_cycle.samples 4736 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 2877 6897.63% - 1 465 1114.84% - 2 300 719.25% - 3 228 546.63% - 4 154 369.22% - 5 89 213.38% - 6 40 95.90% - 7 14 33.57% - 8 4 9.59% + 0 3384 7145.27% + 1 494 1043.07% + 2 314 663.01% + 3 237 500.42% + 4 163 344.17% + 5 88 185.81% + 6 40 84.46% + 7 12 25.34% + 8 4 8.45% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.762407 # Inst issue rate -system.cpu.iq.iqInstsAdded 3479 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 3180 # Number of instructions issued +system.cpu.iq.ISSUE:rate 0.692779 # Inst issue rate +system.cpu.iq.iqInstsAdded 3776 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 3281 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 6 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 944 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsExamined 1238 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedInstsIssued 1 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 2 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 473 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedOperandsExamined 742 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 735 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 707 # ITB hits +system.cpu.itb.misses 28 # ITB misses system.cpu.l2cache.ReadExReq_accesses 24 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4750 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2750 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 114000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_avg_miss_latency 4604.166667 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2604.166667 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 110500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses system.cpu.l2cache.ReadExReq_misses 24 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 66000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 62500 # number of ReadExReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses system.cpu.l2cache.ReadExReq_mshr_misses 24 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 247 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4354.251012 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2354.251012 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 1075500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_accesses 243 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4304.526749 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2304.526749 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_miss_latency 1046000 # number of ReadReq miss cycles system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 247 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 581500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_misses 243 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 560000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 247 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 243 # number of ReadReq MSHR misses system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4250 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2250 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 59500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4178.571429 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2178.571429 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 58500 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 31500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 30500 # number of UpgradeReq MSHR miss cycles system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses system.cpu.l2cache.UpgradeReq_mshr_misses 14 # number of UpgradeReq MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked @@ -360,32 +376,32 @@ system.cpu.l2cache.blocked_no_targets 0 # nu 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 271 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4389.298893 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2389.298893 # average overall mshr miss latency +system.cpu.l2cache.demand_accesses 267 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4331.460674 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2331.460674 # average overall mshr miss latency system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 1189500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 1156500 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 271 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses 267 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 647500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 622500 # number of demand (read+write) MSHR miss cycles system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 271 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses 267 # 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.overall_accesses 271 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4389.298893 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2389.298893 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 267 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4331.460674 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2331.460674 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 1189500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 1156500 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 271 # number of overall misses +system.cpu.l2cache.overall_misses 267 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 647500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 622500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 271 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses 267 # 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.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -398,28 +414,28 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 233 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 229 # 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 127.304233 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 115.687599 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks -system.cpu.numCycles 4171 # number of cpu cycles simulated +system.cpu.numCycles 4736 # number of cpu cycles simulated system.cpu.rename.RENAME:CommittedMaps 1768 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 3117 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 1 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 4657 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 4106 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 2936 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 738 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 225 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 7 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 1168 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:IdleCycles 3552 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 2 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 4989 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 4410 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 3154 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 808 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 283 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 9 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 1386 # Number of HB maps that are undone due to squashing system.cpu.rename.RENAME:serializeStallCycles 84 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 8 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 50 # count of insts added to the skid buffer +system.cpu.rename.RENAME:skidInsts 60 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 6 # count of temporary serializing insts renamed -system.cpu.timesIdled 16 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 28 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout index 57159efac..895bd710c 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:41 2007 -M5 executing on zeep +M5 compiled Aug 13 2007 17:39:24 +M5 started Mon Aug 13 17:39:27 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/o3-timing tests/run.py quick/00.hello/alpha/tru64/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 2104000 because target called exit() +Exiting @ tick 2410000 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini index 16ea738bc..ac0ec32b8 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=tracer workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -31,6 +33,14 @@ workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.tracer] type=ExeTracer @@ -41,7 +51,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/tru64/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/tru64/hello gid=100 input=cin output=cout diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt index dfc8b7f6b..28ff448c6 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 34280 # Simulator instruction rate (inst/s) -host_mem_usage 147884 # Number of bytes of host memory used -host_seconds 0.08 # Real time elapsed on the host -host_tick_rate 17043200 # Simulator tick rate (ticks/s) +host_inst_rate 124133 # Simulator instruction rate (inst/s) +host_mem_usage 171628 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 61574601 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2578 # Number of instructions simulated +sim_insts 2577 # Number of instructions simulated sim_seconds 0.000001 # Number of seconds simulated -sim_ticks 1288500 # Number of ticks simulated +sim_ticks 1297500 # Number of ticks simulated +system.cpu.dtb.accesses 717 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 709 # DTB hits +system.cpu.dtb.misses 8 # DTB misses +system.cpu.dtb.read_accesses 419 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 415 # DTB read hits +system.cpu.dtb.read_misses 4 # DTB read misses +system.cpu.dtb.write_accesses 298 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 294 # DTB write hits +system.cpu.dtb.write_misses 4 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2596 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2585 # ITB hits +system.cpu.itb.misses 11 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 2578 # number of cpu cycles simulated -system.cpu.num_insts 2578 # Number of instructions executed -system.cpu.num_refs 710 # Number of memory references +system.cpu.numCycles 2596 # number of cpu cycles simulated +system.cpu.num_insts 2577 # Number of instructions executed +system.cpu.num_refs 717 # Number of memory references system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout index 6e78c47eb..89de75b41 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 3 2007 03:56:47 -M5 started Fri Aug 3 04:17:14 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 17:36:58 +M5 started Tue Aug 14 17:40:04 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-atomic tests/run.py quick/00.hello/alpha/tru64/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 1288500 because target called exit() +Exiting @ tick 1297500 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini index f8e125ea1..48fcc2b94 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 @@ -156,7 +166,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/tru64/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/tru64/hello gid=100 input=cin output=cout diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt index 23e886f55..942cc1b79 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 196854 # Simulator instruction rate (inst/s) -host_mem_usage 195480 # Number of bytes of host memory used -host_seconds 0.01 # Real time elapsed on the host -host_tick_rate 706389035 # Simulator tick rate (ticks/s) +host_inst_rate 123219 # Simulator instruction rate (inst/s) +host_mem_usage 178996 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 443932267 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2578 # Number of instructions simulated +sim_insts 2577 # Number of instructions simulated sim_seconds 0.000009 # Number of seconds simulated -sim_ticks 9431000 # Number of ticks simulated +sim_ticks 9438000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 415 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -76,53 +76,65 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 82 # 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 48.863963 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 48.838317 # Cycle average of tags in use system.cpu.dcache.total_refs 627 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_accesses 2579 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 717 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 709 # DTB hits +system.cpu.dtb.misses 8 # DTB misses +system.cpu.dtb.read_accesses 419 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 415 # DTB read hits +system.cpu.dtb.read_misses 4 # DTB read misses +system.cpu.dtb.write_accesses 298 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 294 # DTB write hits +system.cpu.dtb.write_misses 4 # DTB write misses +system.cpu.icache.ReadReq_accesses 2586 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 2416 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 2423 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 4075000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.063203 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.063032 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 163 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 3749000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.063203 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate 0.063032 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 163 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 14.822086 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 14.865031 # 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 2579 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 2586 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 23000 # average overall mshr miss latency -system.cpu.icache.demand_hits 2416 # number of demand (read+write) hits +system.cpu.icache.demand_hits 2423 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 4075000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.063203 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.063032 # miss rate for demand accesses system.cpu.icache.demand_misses 163 # number of demand (read+write) misses system.cpu.icache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.icache.demand_mshr_miss_latency 3749000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.063203 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate 0.063032 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 163 # 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.overall_accesses 2579 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 2586 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 23000 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 2416 # number of overall hits +system.cpu.icache.overall_hits 2423 # number of overall hits system.cpu.icache.overall_miss_latency 4075000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.063203 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.063032 # miss rate for overall accesses system.cpu.icache.overall_misses 163 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.icache.overall_mshr_miss_latency 3749000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.063203 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate 0.063032 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 163 # 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 @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 163 # 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 83.443652 # Cycle average of tags in use -system.cpu.icache.total_refs 2416 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 83.395749 # Cycle average of tags in use +system.cpu.icache.total_refs 2423 # 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.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2597 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2586 # ITB hits +system.cpu.itb.misses 11 # ITB misses system.cpu.l2cache.ReadExReq_accesses 27 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -218,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 207 # 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 106.620093 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 106.559981 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 9431000 # number of cpu cycles simulated -system.cpu.num_insts 2578 # Number of instructions executed -system.cpu.num_refs 710 # Number of memory references +system.cpu.numCycles 9438000 # number of cpu cycles simulated +system.cpu.num_insts 2577 # Number of instructions executed +system.cpu.num_refs 717 # Number of memory references system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout index eb8910969..8d08b94be 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:42 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 17:58:14 +M5 started Tue Aug 14 17:59:08 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-timing tests/run.py quick/00.hello/alpha/tru64/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 9431000 because target called exit() +Exiting @ tick 9438000 because target called exit() |