m5stats.txt
来自「M5,一个功能强大的多处理器系统模拟器.很多针对处理器架构,性能的研究都使用它作」· 文本 代码 · 共 603 行 · 第 1/5 页
TXT
603 行
---------- Begin Simulation Statistics ----------global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.global.BPredUnit.BTBHits 722 # Number of BTB hitsglobal.BPredUnit.BTBLookups 3569 # Number of BTB lookupsglobal.BPredUnit.RASInCorrect 133 # Number of incorrect RAS predictions.global.BPredUnit.condIncorrect 1125 # Number of conditional branches incorrectglobal.BPredUnit.condPredicted 2392 # Number of conditional branches predictedglobal.BPredUnit.lookups 4127 # Number of BP lookupsglobal.BPredUnit.usedRAS 550 # Number of times the RAS was used to get a target.host_inst_rate 41846 # Simulator instruction rate (inst/s)host_mem_usage 152588 # Number of bytes of host memory usedhost_seconds 0.27 # Real time elapsed on the hosthost_tick_rate 23650670 # Simulator tick rate (ticks/s)memdepunit.memDep.conflictingLoads 18 # Number of conflicting loads.memdepunit.memDep.conflictingLoads 17 # Number of conflicting loads.memdepunit.memDep.conflictingStores 33 # Number of conflicting stores.memdepunit.memDep.conflictingStores 36 # Number of conflicting stores.memdepunit.memDep.insertedLoads 1975 # Number of loads inserted to the mem dependence unit.memdepunit.memDep.insertedLoads 2036 # Number of loads inserted to the mem dependence unit.memdepunit.memDep.insertedStores 1163 # Number of stores inserted to the mem dependence unit.memdepunit.memDep.insertedStores 1158 # Number of stores inserted to the mem dependence unit.sim_freq 1000000000000 # Frequency of simulated tickssim_insts 11247 # Number of instructions simulatedsim_seconds 0.000006 # Number of seconds simulatedsim_ticks 6363000 # Number of ticks simulatedsystem.cpu.commit.COM:branches 1724 # Number of branches committedsystem.cpu.commit.COM:branches_0 862 # Number of branches committedsystem.cpu.commit.COM:branches_1 862 # Number of branches committedsystem.cpu.commit.COM:bw_lim_events 145 # number cycles where commit BW limit reachedsystem.cpu.commit.COM:bw_limited 0 # number of insts not committed due to BW limitssystem.cpu.commit.COM:bw_limited_0 0 # number of insts not committed due to BW limitssystem.cpu.commit.COM:bw_limited_1 0 # number of insts not committed due to BW limitssystem.cpu.commit.COM:committed_per_cycle.start_dist # Number of insts commited each cyclesystem.cpu.commit.COM:committed_per_cycle.samples 12623 system.cpu.commit.COM:committed_per_cycle.min_value 0 0 7897 6256.04% 1 2220 1758.69% 2 993 786.66% 3 507 401.65% 4 332 263.01% 5 219 173.49% 6 199 157.65% 7 111 87.93% 8 145 114.87% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_distsystem.cpu.commit.COM:count 11281 # Number of instructions committedsystem.cpu.commit.COM:count_0 5640 # Number of instructions committedsystem.cpu.commit.COM:count_1 5641 # Number of instructions committedsystem.cpu.commit.COM:loads 1958 # Number of loads committedsystem.cpu.commit.COM:loads_0 979 # Number of loads committedsystem.cpu.commit.COM:loads_1 979 # Number of loads committedsystem.cpu.commit.COM:membars 0 # Number of memory barriers committedsystem.cpu.commit.COM:membars_0 0 # Number of memory barriers committedsystem.cpu.commit.COM:membars_1 0 # Number of memory barriers committedsystem.cpu.commit.COM:refs 3582 # Number of memory references committedsystem.cpu.commit.COM:refs_0 1791 # Number of memory references committedsystem.cpu.commit.COM:refs_1 1791 # Number of memory references committedsystem.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committedsystem.cpu.commit.COM:swp_count_0 0 # Number of s/w prefetches committedsystem.cpu.commit.COM:swp_count_1 0 # Number of s/w prefetches committedsystem.cpu.commit.branchMispredicts 885 # The number of times a branch was mispredictedsystem.cpu.commit.commitCommittedInsts 11281 # The number of committed instructionssystem.cpu.commit.commitNonSpecStalls 34 # The number of times commit has been forced to stall to communicate backwardssystem.cpu.commit.commitSquashedInsts 8502 # The number of squashed insts skipped by commitsystem.cpu.committedInsts_0 5623 # Number of Instructions Simulatedsystem.cpu.committedInsts_1 5624 # Number of Instructions Simulatedsystem.cpu.committedInsts_total 11247 # Number of Instructions Simulatedsystem.cpu.cpi_0 2.263383 # CPI: Cycles Per Instructionsystem.cpu.cpi_1 2.262980 # CPI: Cycles Per Instructionsystem.cpu.cpi_total 1.131591 # CPI: Total CPI of All Threadssystem.cpu.dcache.ReadReq_accesses 3079 # number of ReadReq accesses(hits+misses)system.cpu.dcache.ReadReq_accesses_0 3079 # number of ReadReq accesses(hits+misses)system.cpu.dcache.ReadReq_avg_miss_latency_0 12116.724739 # average ReadReq miss latencysystem.cpu.dcache.ReadReq_avg_mshr_miss_latency_0 10527.918782 # average ReadReq mshr miss latencysystem.cpu.dcache.ReadReq_hits 2792 # number of ReadReq hitssystem.cpu.dcache.ReadReq_hits_0 2792 # number of ReadReq hitssystem.cpu.dcache.ReadReq_miss_latency 3477500 # number of ReadReq miss cyclessystem.cpu.dcache.ReadReq_miss_latency_0 3477500 # number of ReadReq miss cyclessystem.cpu.dcache.ReadReq_miss_rate_0 0.093212 # miss rate for ReadReq accessessystem.cpu.dcache.ReadReq_misses 287 # number of ReadReq missessystem.cpu.dcache.ReadReq_misses_0 287 # number of ReadReq missessystem.cpu.dcache.ReadReq_mshr_hits 90 # number of ReadReq MSHR hitssystem.cpu.dcache.ReadReq_mshr_hits_0 90 # number of ReadReq MSHR hitssystem.cpu.dcache.ReadReq_mshr_miss_latency 2074000 # number of ReadReq MSHR miss cyclessystem.cpu.dcache.ReadReq_mshr_miss_latency_0 2074000 # number of ReadReq MSHR miss cyclessystem.cpu.dcache.ReadReq_mshr_miss_rate_0 0.063982 # mshr miss rate for ReadReq accessessystem.cpu.dcache.ReadReq_mshr_misses 197 # number of ReadReq MSHR missessystem.cpu.dcache.ReadReq_mshr_misses_0 197 # number of ReadReq MSHR missessystem.cpu.dcache.WriteReq_accesses 1624 # number of WriteReq accesses(hits+misses)system.cpu.dcache.WriteReq_accesses_0 1624 # number of WriteReq accesses(hits+misses)system.cpu.dcache.WriteReq_avg_miss_latency_0 9139.837398 # average WriteReq miss latencysystem.cpu.dcache.WriteReq_avg_mshr_miss_latency_0 8686.781609 # average WriteReq mshr miss latencysystem.cpu.dcache.WriteReq_hits 1009 # number of WriteReq hitssystem.cpu.dcache.WriteReq_hits_0 1009 # number of WriteReq hitssystem.cpu.dcache.WriteReq_miss_latency 5621000 # number of WriteReq miss cyclessystem.cpu.dcache.WriteReq_miss_latency_0 5621000 # number of WriteReq miss cyclessystem.cpu.dcache.WriteReq_miss_rate_0 0.378695 # miss rate for WriteReq accessessystem.cpu.dcache.WriteReq_misses 615 # number of WriteReq missessystem.cpu.dcache.WriteReq_misses_0 615 # number of WriteReq missessystem.cpu.dcache.WriteReq_mshr_hits 441 # number of WriteReq MSHR hitssystem.cpu.dcache.WriteReq_mshr_hits_0 441 # number of WriteReq MSHR hitssystem.cpu.dcache.WriteReq_mshr_miss_latency 1511500 # number of WriteReq MSHR miss cyclessystem.cpu.dcache.WriteReq_mshr_miss_latency_0 1511500 # number of WriteReq MSHR miss cyclessystem.cpu.dcache.WriteReq_mshr_miss_rate_0 0.107143 # mshr miss rate for WriteReq accessessystem.cpu.dcache.WriteReq_mshr_misses 174 # number of WriteReq MSHR missessystem.cpu.dcache.WriteReq_mshr_misses_0 174 # number of WriteReq MSHR missessystem.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blockedsystem.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blockedsystem.cpu.dcache.avg_refs 11.266082 # Average number of references to valid blocks.system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blockedsystem.cpu.dcache.blocked_no_targets 0 # number of cycles access was blockedsystem.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blockedsystem.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blockedsystem.cpu.dcache.cache_copies 0 # number of cache copies performedsystem.cpu.dcache.demand_accesses 4703 # number of demand (read+write) accessessystem.cpu.dcache.demand_accesses_0 4703 # number of demand (read+write) accessessystem.cpu.dcache.demand_accesses_1 0 # number of demand (read+write) accessessystem.cpu.dcache.demand_avg_miss_latency <err: div-0> # average overall miss latency
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?