diff options
| author | Kevin Lim <ktlim@umich.edu> | 2007-04-15 22:29:37 -0400 |
|---|---|---|
| committer | Kevin Lim <ktlim@umich.edu> | 2007-04-15 22:29:37 -0400 |
| commit | 733a57d45a6a99a6259bff979ac7e40e5231f84f (patch) | |
| tree | d4b44f2feab3aecf667ae034472dd3e5d2e94091 /tests | |
| parent | 64b4572c3ea103a274fd125dff66cdaafd20178b (diff) | |
| download | gem5-733a57d45a6a99a6259bff979ac7e40e5231f84f.tar.xz | |
Update long test refs.
tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini:
tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.out:
tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt:
tests/long/00.gzip/ref/alpha/tru64/o3-timing/stderr:
tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini:
tests/long/30.eon/ref/alpha/tru64/o3-timing/config.out:
tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt:
tests/long/30.eon/ref/alpha/tru64/o3-timing/stderr:
tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini:
tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.out:
tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt:
tests/long/50.vortex/ref/alpha/tru64/o3-timing/stderr:
tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini:
tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.out:
tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt:
tests/long/60.bzip2/ref/alpha/tru64/o3-timing/stderr:
tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini:
tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.out:
tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt:
tests/long/70.twolf/ref/alpha/tru64/o3-timing/smred.out:
tests/long/70.twolf/ref/alpha/tru64/o3-timing/stderr:
Update refs.
--HG--
extra : convert_revision : 19483a5a18e76338a3208a58d7460a922377acd3
Diffstat (limited to 'tests')
21 files changed, 1490 insertions, 1826 deletions
diff --git a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini index fa5ac1725..853e93096 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini @@ -1,48 +1,7 @@ [root] type=Root children=system -checkpoint= -clock=1000000000000 -max_tick=0 -output_file=cout -progress_interval=0 - -[exetrace] -intel_format=false -legion_lockstep=false -pc_symbol=true -print_cpseq=false -print_cycle=true -print_data=true -print_effaddr=true -print_fetchseq=false -print_iregs=false -print_opclass=true -print_thread=true -speculative=true -trace_system=client - -[serialize] -count=10 -cycle=0 -dir=cpt.%012d -period=0 - -[stats] -descriptions=true -dump_cycle=0 -dump_period=0 -dump_reset=false -ignore_events= -mysql_db= -mysql_host= -mysql_password= -mysql_user= -project_name=test -simulation_name=test -simulation_sample=0 -text_compat=true -text_file=m5stats.txt +dummy=0 [system] type=System @@ -70,6 +29,7 @@ commitToFetchDelay=1 commitToIEWDelay=1 commitToRenameDelay=1 commitWidth=8 +cpu_id=0 decodeToFetchDelay=1 decodeToRenameDelay=1 decodeWidth=8 @@ -155,7 +115,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -331,7 +291,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -388,7 +348,7 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=gzip input.log 1 -cwd=build/ALPHA_SE/tests/fast/long/00.gzip/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/00.gzip/alpha/tru64/o3-timing egid=100 env= euid=100 diff --git a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.out b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.out index 8744b6907..e04428224 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.out +++ b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.out @@ -1,9 +1,6 @@ [root] type=Root -clock=1000000000000 -max_tick=0 -progress_interval=0 -output_file=cout +dummy=0 [system.physmem] type=PhysicalMemory @@ -31,7 +28,7 @@ executable=/dist/m5/cpu2000/binaries/alpha/tru64/gzip input=cin output=cout env= -cwd=build/ALPHA_SE/tests/fast/long/00.gzip/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/00.gzip/alpha/tru64/o3-timing system=system uid=100 euid=100 @@ -173,6 +170,7 @@ type=DerivO3CPU clock=1 phase=0 numThreads=1 +cpu_id=0 activity=0 workload=system.cpu.workload checker=null @@ -253,7 +251,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -291,7 +289,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -367,39 +365,3 @@ clock=1000 width=64 responder_set=false -[stats] -descriptions=true -project_name=test -simulation_name=test -simulation_sample=0 -text_file=m5stats.txt -text_compat=true -mysql_db= -mysql_user= -mysql_password= -mysql_host= -events_start=-1 -dump_reset=false -dump_cycle=0 -dump_period=0 -ignore_events= - -[exetrace] -speculative=true -print_cycle=true -print_opclass=true -print_thread=true -print_effaddr=true -print_data=true -print_iregs=false -print_fetchseq=false -print_cpseq=false -print_reg_delta=false -pc_symbol=true -intel_format=false -legion_lockstep=false -trace_system=client - -[statsreset] -reset_cycle=0 - diff --git a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt index 8303336ed..78a2b3f52 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/00.gzip/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 97621780 # Number of BTB hits -global.BPredUnit.BTBLookups 104888901 # Number of BTB lookups -global.BPredUnit.RASInCorrect 203 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 4270829 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 101462576 # Number of conditional branches predicted -global.BPredUnit.lookups 108029652 # Number of BP lookups -global.BPredUnit.usedRAS 1765818 # Number of times the RAS was used to get a target. -host_inst_rate 64442 # Simulator instruction rate (inst/s) -host_mem_usage 296420 # Number of bytes of host memory used -host_seconds 8776.17 # Real time elapsed on the host -host_tick_rate 192322 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 20975706 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 18042230 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 207074480 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 57063120 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 71631614 # Number of BTB hits +global.BPredUnit.BTBLookups 80215513 # Number of BTB lookups +global.BPredUnit.RASInCorrect 194 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 4366377 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 76991765 # Number of conditional branches predicted +global.BPredUnit.lookups 83232960 # Number of BP lookups +global.BPredUnit.usedRAS 1776050 # Number of times the RAS was used to get a target. +host_inst_rate 91613 # Simulator instruction rate (inst/s) +host_mem_usage 151676 # Number of bytes of host memory used +host_seconds 6173.25 # Real time elapsed on the host +host_tick_rate 271486 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 26015543 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 23632204 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 134244919 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 44983310 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 565552443 # Number of instructions simulated -sim_seconds 0.001688 # Number of seconds simulated -sim_ticks 1687849017 # Number of ticks simulated +sim_seconds 0.001676 # Number of seconds simulated +sim_ticks 1675949017 # Number of ticks simulated system.cpu.commit.COM:branches 62547159 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 17132854 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 16353031 # 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 701581491 +system.cpu.commit.COM:committed_per_cycle.samples 801372491 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 480309675 6846.10% - 1 104094392 1483.71% - 2 40244499 573.63% - 3 11990473 170.91% - 4 15113210 215.42% - 5 17360338 247.45% - 6 10367558 147.77% - 7 4968492 70.82% - 8 17132854 244.20% + 0 580782547 7247.35% + 1 101892793 1271.48% + 2 41339172 515.85% + 3 11939444 148.99% + 4 15719123 196.15% + 5 17754998 221.56% + 6 10147917 126.63% + 7 5443466 67.93% + 8 16353031 204.06% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,70 @@ system.cpu.commit.COM:loads 115049510 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 154862033 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 4270194 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 4365734 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 601856963 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 17 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 331156834 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 90079827 # The number of squashed insts skipped by commit system.cpu.committedInsts 565552443 # Number of Instructions Simulated system.cpu.committedInsts_total 565552443 # Number of Instructions Simulated -system.cpu.cpi 2.984425 # CPI: Cycles Per Instruction -system.cpu.cpi_total 2.984425 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 114919015 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 3573.284961 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 3259.194046 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 114199728 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 2570217420 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.006259 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 719287 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 495902 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 728055062 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.001944 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 223385 # number of ReadReq MSHR misses +system.cpu.cpi 2.963384 # CPI: Cycles Per Instruction +system.cpu.cpi_total 2.963384 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 120253770 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 3927.286441 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 3434.366579 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 119156440 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 4309529230 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.009125 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 1097330 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 872988 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 770472667 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.001866 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 224342 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 39451321 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 3753.412851 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 3080.837357 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 38221364 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 4616536410 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.031177 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 1229957 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 972712 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 792530006 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.006521 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 257245 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 329.539233 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 2285.588257 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 317.127712 # Average number of references to valid blocks. -system.cpu.dcache.blocked_no_mshrs 3492 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 327032 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 1150751 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 747460499 # number of cycles access was blocked +system.cpu.dcache.WriteReq_avg_miss_latency 9089.303046 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 9344.661839 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 37503702 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 17702499310 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.049368 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 1947619 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 1690762 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 2400241806 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.006511 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 256857 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 327.941025 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 3498.764706 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 325.562069 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 3493 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 17 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 1145498 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 59479 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 154370336 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 3686.944185 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 3163.733159 # average overall mshr miss latency -system.cpu.dcache.demand_hits 152421092 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 7186753830 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.012627 # miss rate for demand accesses -system.cpu.dcache.demand_misses 1949244 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 1468614 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1520585068 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.003113 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 480630 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 159705091 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 7229.030286 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 6589.195890 # average overall mshr miss latency +system.cpu.dcache.demand_hits 156660142 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 22012028540 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.019066 # miss rate for demand accesses +system.cpu.dcache.demand_misses 3044949 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 2563750 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 3170714473 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.003013 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 481199 # 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 154370336 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 3686.944185 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 3163.733159 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 159705091 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 7229.030286 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 6589.195890 # 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 152421092 # number of overall hits -system.cpu.dcache.overall_miss_latency 7186753830 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.012627 # miss rate for overall accesses -system.cpu.dcache.overall_misses 1949244 # number of overall misses -system.cpu.dcache.overall_mshr_hits 1468614 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1520585068 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.003113 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 480630 # number of overall MSHR misses +system.cpu.dcache.overall_hits 156660142 # number of overall hits +system.cpu.dcache.overall_miss_latency 22012028540 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.019066 # miss rate for overall accesses +system.cpu.dcache.overall_misses 3044949 # number of overall misses +system.cpu.dcache.overall_mshr_hits 2563750 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 3170714473 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.003013 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 481199 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +118,92 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 476534 # number of replacements -system.cpu.dcache.sampled_refs 480630 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 477103 # number of replacements +system.cpu.dcache.sampled_refs 481199 # 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 4061.534340 # Cycle average of tags in use -system.cpu.dcache.total_refs 152421092 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 22778000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 337990 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 113629190 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 667 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 4610173 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 1474333999 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 347767079 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 231043933 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 53597030 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 1980 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 9141290 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 108029652 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 167528188 # Number of cache lines fetched -system.cpu.fetch.Cycles 410392582 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 7840605 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 1486495774 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 39151172 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.143052 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 167528188 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 99387598 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.968403 # Number of inst fetches per cycle +system.cpu.dcache.tagsinuse 4063.174314 # Cycle average of tags in use +system.cpu.dcache.total_refs 156660142 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 20910000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 338217 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 515310439 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 681 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 4340917 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 740208637 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 161139948 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 116871564 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 14453620 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 2001 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 8050541 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 83232960 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 72135284 # Number of cache lines fetched +system.cpu.fetch.Cycles 198811102 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 1485258 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 751818937 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 5990379 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.102023 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 72135284 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 73407664 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.921543 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 755178522 +system.cpu.fetch.rateDist.samples 815826112 system.cpu.fetch.rateDist.min_value 0 - 0 512314112 6784.01% - 1 11453310 151.66% - 2 16801464 222.48% - 3 16318450 216.09% - 4 18767749 248.52% - 5 15201778 201.30% - 6 32935567 436.13% - 7 7297838 96.64% - 8 124088254 1643.16% + 0 689150299 8447.27% + 1 10579353 129.68% + 2 12110332 148.44% + 3 11560507 141.70% + 4 9007686 110.41% + 5 3425511 41.99% + 6 3768928 46.20% + 7 3222436 39.50% + 8 73001060 894.81% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 167528184 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5600.855285 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4703.251892 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 167526954 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 6889052 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000007 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 1230 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 305 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 4350508 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000006 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 925 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 72135284 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 5699.600162 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4917.297556 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 72134046 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 7056105 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000017 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 1238 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 297 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 4627177 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000013 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 941 # 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 5880.941176 # average number of cycles each access was blocked -system.cpu.icache.avg_refs 181110.220541 # Average number of references to valid blocks. +system.cpu.icache.avg_blocked_cycles_no_targets 3783 # average number of cycles each access was blocked +system.cpu.icache.avg_refs 76656.797024 # 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 17 # number of cycles access was blocked +system.cpu.icache.blocked_no_targets 1 # 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 99976 # number of cycles access was blocked +system.cpu.icache.blocked_cycles_no_targets 3783 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 167528184 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5600.855285 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4703.251892 # average overall mshr miss latency -system.cpu.icache.demand_hits 167526954 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 6889052 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000007 # miss rate for demand accesses -system.cpu.icache.demand_misses 1230 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 305 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 4350508 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000006 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 925 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 72135284 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 5699.600162 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4917.297556 # average overall mshr miss latency +system.cpu.icache.demand_hits 72134046 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 7056105 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000017 # miss rate for demand accesses +system.cpu.icache.demand_misses 1238 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 297 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 4627177 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000013 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 941 # 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 167528184 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5600.855285 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4703.251892 # average overall mshr miss latency +system.cpu.icache.overall_accesses 72135284 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 5699.600162 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4917.297556 # 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 167526954 # number of overall hits -system.cpu.icache.overall_miss_latency 6889052 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000007 # miss rate for overall accesses -system.cpu.icache.overall_misses 1230 # number of overall misses -system.cpu.icache.overall_mshr_hits 305 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 4350508 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000006 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 925 # number of overall MSHR misses +system.cpu.icache.overall_hits 72134046 # number of overall hits +system.cpu.icache.overall_miss_latency 7056105 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000017 # miss rate for overall accesses +system.cpu.icache.overall_misses 1238 # number of overall misses +system.cpu.icache.overall_mshr_hits 297 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 4627177 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000013 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 941 # 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 @@ -215,63 +215,63 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 47 # number of replacements -system.cpu.icache.sampled_refs 925 # Sample count of references to valid blocks. +system.cpu.icache.replacements 44 # number of replacements +system.cpu.icache.sampled_refs 941 # 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 739.927243 # Cycle average of tags in use -system.cpu.icache.total_refs 167526954 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 749.515669 # Cycle average of tags in use +system.cpu.icache.total_refs 72134046 # 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 932670496 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 92484798 # Number of branches executed -system.cpu.iew.EXEC:nop 154927960 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.987080 # Inst execution rate -system.cpu.iew.EXEC:refs 253735466 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 51400640 # Number of stores executed +system.cpu.idleCycles 860122906 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 67691806 # Number of branches executed +system.cpu.iew.EXEC:nop 43795429 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.748142 # Inst execution rate +system.cpu.iew.EXEC:refs 168635664 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 41396142 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 486804101 # num instructions consuming a value -system.cpu.iew.WB:count 671280122 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.809385 # average fanout of values written-back +system.cpu.iew.WB:consumers 508232399 # num instructions consuming a value +system.cpu.iew.WB:count 603225060 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.792920 # 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 394011709 # num instructions producing a value -system.cpu.iew.WB:rate 0.888903 # insts written-back per cycle -system.cpu.iew.WB:sent 673021204 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 4738518 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 26824121 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 207074480 # Number of dispatched load instructions +system.cpu.iew.WB:producers 402987686 # num instructions producing a value +system.cpu.iew.WB:rate 0.739404 # insts written-back per cycle +system.cpu.iew.WB:sent 604785539 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 4695315 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 442855270 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 134244919 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 25 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 169524029 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 57063120 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 933012139 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 202334826 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 7294318 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 745421559 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 36474 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewDispSquashedInsts 5961708 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 44983310 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 691933738 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 127239522 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 6754480 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 610353566 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 42801 # 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 1439 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 53597030 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 214253 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 5548 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 70837719 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 7377596 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 20150 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 120734 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 14453620 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 431168 # 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 1871526 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 4575118 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 24838 # 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 1892 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 5548 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 92024970 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 17250597 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 1892 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 530187 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 4208331 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.335073 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.335073 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 752715877 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 1001889 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 5578 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 19195409 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 5170787 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 1001889 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 542024 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 4153291 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.337452 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.337452 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 617108046 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 0 0.00% # Type of FU issued - IntAlu 496182294 65.92% # Type of FU issued - IntMult 8208 0.00% # Type of FU issued + IntAlu 445691749 72.22% # Type of FU issued + IntMult 6563 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 33 0.00% # Type of FU issued FloatCmp 6 0.00% # Type of FU issued @@ -279,16 +279,16 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 5 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 204178453 27.13% # Type of FU issued - MemWrite 52346873 6.95% # Type of FU issued + MemRead 129192933 20.94% # Type of FU issued + MemWrite 42216752 6.84% # 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 3466320 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.004605 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 3402065 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.005513 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available - IntAlu 2723724 78.58% # attempts to use FU when none available + IntAlu 2626203 77.19% # 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 @@ -297,80 +297,80 @@ 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 683243 19.71% # attempts to use FU when none available - MemWrite 59353 1.71% # attempts to use FU when none available + MemRead 644339 18.94% # attempts to use FU when none available + MemWrite 131523 3.87% # 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 755178522 +system.cpu.iq.ISSUE:issued_per_cycle.samples 815826112 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 450030250 5959.26% - 1 91846319 1216.22% - 2 83470092 1105.30% - 3 53962116 714.56% - 4 57175468 757.11% - 5 10089384 133.60% - 6 7448894 98.64% - 7 1047122 13.87% - 8 108877 1.44% + 0 553114491 6779.81% + 1 85371128 1046.44% + 2 77782451 953.42% + 3 52154516 639.28% + 4 28098332 344.42% + 5 10103046 123.84% + 6 7930576 97.21% + 7 956122 11.72% + 8 315450 3.87% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.996739 # Inst issue rate -system.cpu.iq.iqInstsAdded 778084154 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 752715877 # Number of instructions issued +system.cpu.iq.ISSUE:rate 0.756421 # Inst issue rate +system.cpu.iq.iqInstsAdded 648138284 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 617108046 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 25 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 210836257 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 250496 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 80438129 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 1088392 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 8 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 119170992 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 481555 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 6806.870170 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2221.284395 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 455236 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 179150016 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.054654 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 26319 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 58461984 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.054654 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 26319 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 337990 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 337990 # number of Writeback hits +system.cpu.iq.iqSquashedOperandsExamined 57507029 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 482140 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 8078.944187 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2363.998861 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 455802 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 212783232 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.054627 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 26338 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 62263002 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.054627 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 26338 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 338217 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 338217 # number of Writeback hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 30.138911 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 30.147278 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 481555 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 6806.870170 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2221.284395 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 455236 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 179150016 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.054654 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 26319 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 482140 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 8078.944187 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2363.998861 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 455802 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 212783232 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.054627 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 26338 # 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 58461984 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.054654 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 26319 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 62263002 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.054627 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 26338 # 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 819545 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 6806.870170 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2221.284395 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 820357 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 8078.944187 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2363.998861 # 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 793226 # number of overall hits -system.cpu.l2cache.overall_miss_latency 179150016 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.032114 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 26319 # number of overall misses +system.cpu.l2cache.overall_hits 794019 # number of overall hits +system.cpu.l2cache.overall_miss_latency 212783232 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.032106 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 26338 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 58461984 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.032114 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 26319 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 62263002 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.032106 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 26338 # 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 @@ -382,32 +382,32 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 934 # number of replacements -system.cpu.l2cache.sampled_refs 26319 # Sample count of references to valid blocks. +system.cpu.l2cache.replacements 935 # number of replacements +system.cpu.l2cache.sampled_refs 26338 # 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 24352.046438 # Cycle average of tags in use -system.cpu.l2cache.total_refs 793226 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 24391.955858 # Cycle average of tags in use +system.cpu.l2cache.total_refs 794019 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.writebacks 907 # number of writebacks -system.cpu.numCycles 755178522 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 71954881 # Number of cycles rename is blocking +system.cpu.l2cache.writebacks 908 # number of writebacks +system.cpu.numCycles 815826112 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 467231804 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 463854889 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 32102756 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 363513131 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 18414484 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 164520 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 1301215151 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 1374424300 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 698904999 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 224329578 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 53597030 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 41747264 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 235050110 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 36638 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:IQFullEvents 38638370 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 170863189 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 8553533 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 36121 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 961623776 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 729244091 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 554812455 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 115192044 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 14453620 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 48042805 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 90957566 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 42650 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 30 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 105666858 # count of insts added to the skid buffer +system.cpu.rename.RENAME:skidInsts 77555696 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 28 # count of temporary serializing insts renamed -system.cpu.timesIdled 349047 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 308219 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/stderr b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/stderr index eb1796ead..f33d007a7 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/stderr +++ b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/stderr @@ -1,2 +1,2 @@ -0: system.remote_gdb.listener: listening for remote gdb on port 7000 warn: Entering event queue @ 0. Starting simulation... +warn: Increasing stack size by one page. diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini index 915a6967f..7d8c8259e 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini @@ -1,48 +1,7 @@ [root] type=Root children=system -checkpoint= -clock=1000000000000 -max_tick=0 -output_file=cout -progress_interval=0 - -[exetrace] -intel_format=false -legion_lockstep=false -pc_symbol=true -print_cpseq=false -print_cycle=true -print_data=true -print_effaddr=true -print_fetchseq=false -print_iregs=false -print_opclass=true -print_thread=true -speculative=true -trace_system=client - -[serialize] -count=10 -cycle=0 -dir=cpt.%012d -period=0 - -[stats] -descriptions=true -dump_cycle=0 -dump_period=0 -dump_reset=false -ignore_events= -mysql_db= -mysql_host= -mysql_password= -mysql_user= -project_name=test -simulation_name=test -simulation_sample=0 -text_compat=true -text_file=m5stats.txt +dummy=0 [system] type=System @@ -70,6 +29,7 @@ commitToFetchDelay=1 commitToIEWDelay=1 commitToRenameDelay=1 commitWidth=8 +cpu_id=0 decodeToFetchDelay=1 decodeToRenameDelay=1 decodeWidth=8 @@ -155,7 +115,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -331,7 +291,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -388,7 +348,7 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=eon chair.control.cook chair.camera chair.surfaces chair.cook.ppm ppm pixels_out.cook -cwd=build/ALPHA_SE/tests/fast/long/30.eon/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/30.eon/alpha/tru64/o3-timing egid=100 env= euid=100 @@ -417,12 +377,3 @@ range=0:134217727 zero=false port=system.membus.port[0] -[trace] -bufsize=0 -cycle=0 -dump_on_exit=false -file=cout -flags= -ignore= -start=0 - diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.out b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.out index 80e067401..96829f8a9 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.out +++ b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.out @@ -1,9 +1,6 @@ [root] type=Root -clock=1000000000000 -max_tick=0 -progress_interval=0 -output_file=cout +dummy=0 [system.physmem] type=PhysicalMemory @@ -31,7 +28,7 @@ executable=/dist/m5/cpu2000/binaries/alpha/tru64/eon input=cin output=cout env= -cwd=build/ALPHA_SE/tests/fast/long/30.eon/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/30.eon/alpha/tru64/o3-timing system=system uid=100 euid=100 @@ -173,6 +170,7 @@ type=DerivO3CPU clock=1 phase=0 numThreads=1 +cpu_id=0 activity=0 workload=system.cpu.workload checker=null @@ -253,7 +251,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -291,7 +289,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -367,51 +365,3 @@ clock=1000 width=64 responder_set=false -[trace] -flags= -start=0 -cycle=0 -bufsize=0 -file=cout -dump_on_exit=false -ignore= - -[stats] -descriptions=true -project_name=test -simulation_name=test -simulation_sample=0 -text_file=m5stats.txt -text_compat=true -mysql_db= -mysql_user= -mysql_password= -mysql_host= -events_start=-1 -dump_reset=false -dump_cycle=0 -dump_period=0 -ignore_events= - -[random] -seed=1 - -[exetrace] -speculative=true -print_cycle=true -print_opclass=true -print_thread=true -print_effaddr=true -print_data=true -print_iregs=false -print_fetchseq=false -print_cpseq=false -print_reg_delta=false -pc_symbol=true -intel_format=false -legion_lockstep=false -trace_system=client - -[statsreset] -reset_cycle=0 - diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt index 9d00cb146..bca3fa536 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/30.eon/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 38046005 # Number of BTB hits -global.BPredUnit.BTBLookups 46765160 # Number of BTB lookups -global.BPredUnit.RASInCorrect 1072 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 5897447 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 36345249 # Number of conditional branches predicted -global.BPredUnit.lookups 64275681 # Number of BP lookups -global.BPredUnit.usedRAS 12928446 # Number of times the RAS was used to get a target. -host_inst_rate 88491 # Simulator instruction rate (inst/s) -host_mem_usage 183984 # Number of bytes of host memory used -host_seconds 4244.22 # Real time elapsed on the host -host_tick_rate 69460 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 64217134 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 49870920 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 126084683 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 92646936 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 36573856 # Number of BTB hits +global.BPredUnit.BTBLookups 48300104 # Number of BTB lookups +global.BPredUnit.RASInCorrect 1110 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 6040473 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 37489973 # Number of conditional branches predicted +global.BPredUnit.lookups 66376995 # Number of BP lookups +global.BPredUnit.usedRAS 13616030 # Number of times the RAS was used to get a target. +host_inst_rate 78938 # Simulator instruction rate (inst/s) +host_mem_usage 153528 # Number of bytes of host memory used +host_seconds 4757.83 # Real time elapsed on the host +host_tick_rate 66128 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 89962751 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 64024234 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 131935591 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 95765344 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 375574675 # Number of instructions simulated -sim_seconds 0.000295 # Number of seconds simulated -sim_ticks 294803028 # Number of ticks simulated +sim_seconds 0.000315 # Number of seconds simulated +sim_ticks 314625027 # Number of ticks simulated system.cpu.commit.COM:branches 44587523 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 16167573 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 13381546 # 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 260352657 +system.cpu.commit.COM:committed_per_cycle.samples 276331431 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 139362663 5352.84% - 1 37755491 1450.17% - 2 23927219 919.03% - 3 17243764 662.32% - 4 9550787 366.84% - 5 7718539 296.46% - 6 5199548 199.71% - 7 3427073 131.63% - 8 16167573 620.99% + 0 148231465 5364.26% + 1 40756250 1474.90% + 2 28135615 1018.18% + 3 18140880 656.49% + 4 10622787 384.42% + 5 8112500 293.58% + 6 5544405 200.64% + 7 3405983 123.26% + 8 13381546 484.26% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,70 @@ system.cpu.commit.COM:loads 100651988 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 174183388 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 5893264 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 6036288 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 398664447 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 215 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 98024957 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 118579541 # The number of squashed insts skipped by commit system.cpu.committedInsts 375574675 # Number of Instructions Simulated system.cpu.committedInsts_total 375574675 # Number of Instructions Simulated -system.cpu.cpi 0.784939 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.784939 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 94465294 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 5573.350269 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5155.812183 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 94463621 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 9324215 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.000018 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 1673 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 688 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 5078475 # number of ReadReq MSHR miss cycles +system.cpu.cpi 0.837716 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.837716 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 96374626 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 5603.456853 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5219.612576 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 96372656 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 11038810 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000020 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 1970 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 984 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 5146538 # number of ReadReq MSHR miss cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000010 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 985 # number of ReadReq MSHR misses +system.cpu.dcache.ReadReq_mshr_misses 986 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 73520727 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 5442.694460 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5169.706416 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 73508218 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 68082665 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.000170 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 12509 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 9314 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 16517212 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_avg_miss_latency 6647.641993 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6867.316020 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 73501543 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 127528364 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.000261 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 19184 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 15988 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 21947942 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.000043 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 3195 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 2708.631579 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 3690.984252 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 40184.650478 # Average number of references to valid blocks. +system.cpu.dcache.WriteReq_mshr_misses 3196 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 2800 # 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 40620.324964 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 19 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 2032 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 51464 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 7500080 # 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 53200 # 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 167986021 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 5458.107460 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5166.432297 # average overall mshr miss latency -system.cpu.dcache.demand_hits 167971839 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 77406880 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.000084 # miss rate for demand accesses -system.cpu.dcache.demand_misses 14182 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 10002 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 21595687 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_accesses 169895353 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 6550.400586 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 6478.833094 # average overall mshr miss latency +system.cpu.dcache.demand_hits 169874199 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 138567174 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000125 # miss rate for demand accesses +system.cpu.dcache.demand_misses 21154 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 16972 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 27094480 # number of demand (read+write) MSHR miss cycles system.cpu.dcache.demand_mshr_miss_rate 0.000025 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 4180 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses 4182 # 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 167986021 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 5458.107460 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5166.432297 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 169895353 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 6550.400586 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 6478.833094 # 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 167971839 # number of overall hits -system.cpu.dcache.overall_miss_latency 77406880 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.000084 # miss rate for overall accesses -system.cpu.dcache.overall_misses 14182 # number of overall misses -system.cpu.dcache.overall_mshr_hits 10002 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 21595687 # number of overall MSHR miss cycles +system.cpu.dcache.overall_hits 169874199 # number of overall hits +system.cpu.dcache.overall_miss_latency 138567174 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000125 # miss rate for overall accesses +system.cpu.dcache.overall_misses 21154 # number of overall misses +system.cpu.dcache.overall_mshr_hits 16972 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 27094480 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_miss_rate 0.000025 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 4180 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses 4182 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +118,92 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 784 # number of replacements -system.cpu.dcache.sampled_refs 4180 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 786 # number of replacements +system.cpu.dcache.sampled_refs 4182 # 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 3190.140908 # Cycle average of tags in use -system.cpu.dcache.total_refs 167971839 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 3211.654167 # Cycle average of tags in use +system.cpu.dcache.total_refs 169874199 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 637 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 19324711 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 4274 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 11555430 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 538406721 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 137426232 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 102617017 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 16124012 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 12594 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 984698 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 64275681 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 66044385 # Number of cache lines fetched -system.cpu.fetch.Cycles 172472243 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 1233740 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 552850318 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 6527825 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.232481 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 66044385 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 50974451 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.999627 # Number of inst fetches per cycle +system.cpu.dcache.writebacks 639 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 32658535 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 4257 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 11810746 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 562730439 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 143183566 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 99541453 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 18560140 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 12611 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 947878 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 66376995 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 68531131 # Number of cache lines fetched +system.cpu.fetch.Cycles 171584130 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 1722712 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 577337575 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 6483468 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.225089 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 68531131 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 50189886 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.957796 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 276476670 +system.cpu.fetch.rateDist.samples 294891572 system.cpu.fetch.rateDist.min_value 0 - 0 170048750 6150.56% - 1 11707777 423.46% - 2 11563595 418.25% - 3 7250668 262.25% - 4 16393688 592.95% - 5 9178756 331.99% - 6 6871715 248.55% - 7 4129243 149.35% - 8 39332478 1422.63% + 0 191838575 6505.39% + 1 8000057 271.29% + 2 8353997 283.29% + 3 6793291 230.37% + 4 15387795 521.81% + 5 8442060 286.28% + 6 8794810 298.24% + 7 2528585 85.75% + 8 44752402 1517.59% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 66044384 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 4697.455355 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 3736.572860 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 66039333 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 23726847 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000076 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 5051 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 1160 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 14539005 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000059 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 3891 # number of ReadReq MSHR misses -system.cpu.icache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked -system.cpu.icache.avg_blocked_cycles_no_targets 5023.260870 # average number of cycles each access was blocked -system.cpu.icache.avg_refs 16972.329221 # Average number of references to valid blocks. +system.cpu.icache.ReadReq_accesses 68531131 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 4689.224645 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 3850.973049 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 68526132 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 23441434 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000073 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 4999 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 1103 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 15003391 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000057 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 3896 # 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 17588.842916 # 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 69 # 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 346605 # 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 66044384 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 4697.455355 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 3736.572860 # average overall mshr miss latency -system.cpu.icache.demand_hits 66039333 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 23726847 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000076 # miss rate for demand accesses -system.cpu.icache.demand_misses 5051 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 1160 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 14539005 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000059 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 3891 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 68531131 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 4689.224645 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 3850.973049 # average overall mshr miss latency +system.cpu.icache.demand_hits 68526132 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 23441434 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000073 # miss rate for demand accesses +system.cpu.icache.demand_misses 4999 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 1103 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 15003391 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000057 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 3896 # 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 66044384 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 4697.455355 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 3736.572860 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_uncacheable_latency no value # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 66039333 # number of overall hits -system.cpu.icache.overall_miss_latency 23726847 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000076 # miss rate for overall accesses -system.cpu.icache.overall_misses 5051 # number of overall misses -system.cpu.icache.overall_mshr_hits 1160 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 14539005 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000059 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 3891 # number of overall MSHR misses +system.cpu.icache.overall_accesses 68531131 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 4689.224645 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 3850.973049 # 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 68526132 # number of overall hits +system.cpu.icache.overall_miss_latency 23441434 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000073 # miss rate for overall accesses +system.cpu.icache.overall_misses 4999 # number of overall misses +system.cpu.icache.overall_mshr_hits 1103 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 15003391 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000057 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 3896 # 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 @@ -215,162 +215,162 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 1971 # number of replacements -system.cpu.icache.sampled_refs 3891 # Sample count of references to valid blocks. +system.cpu.icache.replacements 1976 # number of replacements +system.cpu.icache.sampled_refs 3896 # 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 1776.887115 # Cycle average of tags in use -system.cpu.icache.total_refs 66039333 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1786.777118 # Cycle average of tags in use +system.cpu.icache.total_refs 68526132 # 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 18326359 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 51280930 # Number of branches executed -system.cpu.iew.EXEC:nop 27455299 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.521589 # Inst execution rate -system.cpu.iew.EXEC:refs 191354897 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 79285920 # Number of stores executed +system.cpu.idleCycles 19733456 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 52475714 # Number of branches executed +system.cpu.iew.EXEC:nop 28200659 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.439607 # Inst execution rate +system.cpu.iew.EXEC:refs 190729803 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 78992420 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 293982680 # num instructions consuming a value -system.cpu.iew.WB:count 415403944 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.694108 # average fanout of values written-back +system.cpu.iew.WB:consumers 302582293 # num instructions consuming a value +system.cpu.iew.WB:count 419651187 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.683002 # 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 204055700 # num instructions producing a value -system.cpu.iew.WB:rate 1.502492 # insts written-back per cycle -system.cpu.iew.WB:sent 416259284 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 6316593 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 2856011 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 126084683 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 240 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 7411275 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 92646936 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 496689311 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 112068977 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 8996952 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 420683841 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 114816 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 206664160 # num instructions producing a value +system.cpu.iew.WB:rate 1.423069 # insts written-back per cycle +system.cpu.iew.WB:sent 420984328 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 6525670 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 4581779 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 131935591 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 243 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 8433935 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 95765344 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 517242480 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 111737383 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 7591261 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 424527920 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 366722 # 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 1986 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 16124012 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 416926 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 183286 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 727659 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 9888553 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 47660 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 32377 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 18560140 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 737234 # 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 8882 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 8984961 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 39727 # 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 81366 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 183286 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 25432695 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 19115536 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 81366 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 996952 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 5319641 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.273985 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.273985 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 429680793 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 675434 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 175954 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 31283603 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 22233944 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 675434 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 1009222 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 5516448 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.193722 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.193722 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 432119181 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 33581 0.01% # Type of FU issued - IntAlu 167723328 39.03% # Type of FU issued - IntMult 2137299 0.50% # Type of FU issued + IntAlu 171100299 39.60% # Type of FU issued + IntMult 2148839 0.50% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 34928239 8.13% # Type of FU issued - FloatCmp 8071357 1.88% # Type of FU issued - FloatCvt 3141242 0.73% # Type of FU issued - FloatMult 16626981 3.87% # Type of FU issued - FloatDiv 1577676 0.37% # Type of FU issued + FloatAdd 35472672 8.21% # Type of FU issued + FloatCmp 7906658 1.83% # Type of FU issued + FloatCvt 2966336 0.69% # Type of FU issued + FloatMult 16725823 3.87% # Type of FU issued + FloatDiv 1566508 0.36% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 114426564 26.63% # Type of FU issued - MemWrite 81014526 18.85% # Type of FU issued + MemRead 113251606 26.21% # Type of FU issued + MemWrite 80946859 18.73% # 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 9055324 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.021075 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 9237965 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.021378 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available - IntAlu 66610 0.74% # attempts to use FU when none available + IntAlu 31984 0.35% # 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 110487 1.22% # attempts to use FU when none available - FloatCmp 35273 0.39% # attempts to use FU when none available - FloatCvt 2828 0.03% # attempts to use FU when none available - FloatMult 2149754 23.74% # attempts to use FU when none available - FloatDiv 664669 7.34% # attempts to use FU when none available + FloatAdd 74124 0.80% # attempts to use FU when none available + FloatCmp 35886 0.39% # attempts to use FU when none available + FloatCvt 5384 0.06% # attempts to use FU when none available + FloatMult 1393766 15.09% # attempts to use FU when none available + FloatDiv 1142138 12.36% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 4545406 50.20% # attempts to use FU when none available - MemWrite 1480297 16.35% # attempts to use FU when none available + MemRead 5413419 58.60% # attempts to use FU when none available + MemWrite 1141264 12.35% # 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 276476670 +system.cpu.iq.ISSUE:issued_per_cycle.samples 294891572 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 105552217 3817.76% - 1 55104063 1993.08% - 2 43517427 1574.00% - 3 31483356 1138.73% - 4 21726208 785.82% - 5 11633875 420.79% - 6 4624667 167.27% - 7 2409257 87.14% - 8 425600 15.39% + 0 116554693 3952.46% + 1 58404803 1980.55% + 2 49059967 1663.66% + 3 31805455 1078.55% + 4 23494336 796.71% + 5 9548381 323.79% + 6 4038173 136.94% + 7 1656320 56.17% + 8 329444 11.17% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.554130 # Inst issue rate -system.cpu.iq.iqInstsAdded 469233772 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 429680793 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 240 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 93305351 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 1513608 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 25 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 71392848 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 8070 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4399.297838 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2193.473956 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 717 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 32348037 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.911152 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 7353 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 16128614 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.911152 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 7353 # number of ReadReq MSHR misses -system.cpu.l2cache.WriteReqNoAck|Writeback_accesses 637 # number of WriteReqNoAck|Writeback accesses(hits+misses) -system.cpu.l2cache.WriteReqNoAck|Writeback_hits 637 # number of WriteReqNoAck|Writeback hits +system.cpu.iq.ISSUE:rate 1.465349 # Inst issue rate +system.cpu.iq.iqInstsAdded 489041578 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 432119181 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 243 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 113088119 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 1629891 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 28 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 97430194 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 8078 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4922.926872 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2406.841240 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 721 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 36217973 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.910745 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 7357 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 17707131 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.910745 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 7357 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 639 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 639 # number of Writeback hits system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.184143 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.184858 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 8070 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4399.297838 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2193.473956 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 717 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 32348037 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.911152 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 7353 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 8078 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4922.926872 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2406.841240 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 721 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 36217973 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.910745 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 7357 # 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 16128614 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.911152 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 7353 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 17707131 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.910745 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 7357 # 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 8707 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4399.297838 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2193.473956 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 8717 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4922.926872 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2406.841240 # 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 1354 # number of overall hits -system.cpu.l2cache.overall_miss_latency 32348037 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.844493 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 7353 # number of overall misses +system.cpu.l2cache.overall_hits 1360 # number of overall hits +system.cpu.l2cache.overall_miss_latency 36217973 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.843983 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 7357 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 16128614 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.844493 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 7353 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 17707131 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.843983 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 7357 # 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 @@ -383,31 +383,31 @@ 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 7353 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 7357 # 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 6415.706550 # Cycle average of tags in use -system.cpu.l2cache.total_refs 1354 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 6462.850486 # Cycle average of tags in use +system.cpu.l2cache.total_refs 1360 # 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 276476670 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 8743693 # Number of cycles rename is blocking +system.cpu.numCycles 294891572 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 14686909 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 259532206 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 653030 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 142074266 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 8196045 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 109 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 687565953 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 524563034 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 338654872 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 98656303 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 16124012 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 9950983 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 79122666 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 927413 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 40317 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 23109451 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 249 # count of temporary serializing insts renamed -system.cpu.timesIdled 6216 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 2446116 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 148616326 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 11769281 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 32 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 721460314 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 549210935 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 355537016 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 94743971 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 18560140 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 15563294 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 96004810 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 2720932 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 38133 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 34543353 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 264 # count of temporary serializing insts renamed +system.cpu.timesIdled 6492 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 215 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/stderr b/tests/long/30.eon/ref/alpha/tru64/o3-timing/stderr index d414f5cfe..4bb0d9bbe 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/stderr +++ b/tests/long/30.eon/ref/alpha/tru64/o3-timing/stderr @@ -1,10 +1,11 @@ -0: system.remote_gdb.listener: listening for remote gdb on port 7002 warn: Entering event queue @ 0. Starting simulation... +warn: Increasing stack size by one page. getting pixel output filename pixels_out.cook opening control file chair.control.cook opening camera file chair.camera opening surfaces file chair.surfaces reading data +warn: Increasing stack size by one page. processing 8parts Grid measure is 6 by 3.0001 by 6 cell dimension is 0.863065 diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini index cf4e15676..d565e945f 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini @@ -1,48 +1,7 @@ [root] type=Root children=system -checkpoint= -clock=1000000000000 -max_tick=0 -output_file=cout -progress_interval=0 - -[exetrace] -intel_format=false -legion_lockstep=false -pc_symbol=true -print_cpseq=false -print_cycle=true -print_data=true -print_effaddr=true -print_fetchseq=false -print_iregs=false -print_opclass=true -print_thread=true -speculative=true -trace_system=client - -[serialize] -count=10 -cycle=0 -dir=cpt.%012d -period=0 - -[stats] -descriptions=true -dump_cycle=0 -dump_period=0 -dump_reset=false -ignore_events= -mysql_db= -mysql_host= -mysql_password= -mysql_user= -project_name=test -simulation_name=test -simulation_sample=0 -text_compat=true -text_file=m5stats.txt +dummy=0 [system] type=System @@ -70,6 +29,7 @@ commitToFetchDelay=1 commitToIEWDelay=1 commitToRenameDelay=1 commitWidth=8 +cpu_id=0 decodeToFetchDelay=1 decodeToRenameDelay=1 decodeWidth=8 @@ -155,7 +115,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -331,7 +291,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -388,7 +348,7 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=vortex lendian.raw -cwd=build/ALPHA_SE/tests/fast/long/50.vortex/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/50.vortex/alpha/tru64/o3-timing egid=100 env= euid=100 diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.out b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.out index 52c225902..85be70a92 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.out +++ b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.out @@ -1,9 +1,6 @@ [root] type=Root -clock=1000000000000 -max_tick=0 -progress_interval=0 -output_file=cout +dummy=0 [system.physmem] type=PhysicalMemory @@ -31,7 +28,7 @@ executable=/dist/m5/cpu2000/binaries/alpha/tru64/vortex input=cin output=cout env= -cwd=build/ALPHA_SE/tests/fast/long/50.vortex/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/50.vortex/alpha/tru64/o3-timing system=system uid=100 euid=100 @@ -173,6 +170,7 @@ type=DerivO3CPU clock=1 phase=0 numThreads=1 +cpu_id=0 activity=0 workload=system.cpu.workload checker=null @@ -253,7 +251,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -291,7 +289,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -367,39 +365,3 @@ clock=1000 width=64 responder_set=false -[stats] -descriptions=true -project_name=test -simulation_name=test -simulation_sample=0 -text_file=m5stats.txt -text_compat=true -mysql_db= -mysql_user= -mysql_password= -mysql_host= -events_start=-1 -dump_reset=false -dump_cycle=0 -dump_period=0 -ignore_events= - -[exetrace] -speculative=true -print_cycle=true -print_opclass=true -print_thread=true -print_effaddr=true -print_data=true -print_iregs=false -print_fetchseq=false -print_cpseq=false -print_reg_delta=false -pc_symbol=true -intel_format=false -legion_lockstep=false -trace_system=client - -[statsreset] -reset_cycle=0 - diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt index 3069385f0..00598f40d 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/50.vortex/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 13202034 # Number of BTB hits -global.BPredUnit.BTBLookups 22107115 # Number of BTB lookups -global.BPredUnit.RASInCorrect 30370 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 454360 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 16498204 # Number of conditional branches predicted -global.BPredUnit.lookups 27047110 # Number of BP lookups -global.BPredUnit.usedRAS 4878193 # Number of times the RAS was used to get a target. -host_inst_rate 69520 # Simulator instruction rate (inst/s) -host_mem_usage 239908 # Number of bytes of host memory used -host_seconds 1144.87 # Real time elapsed on the host -host_tick_rate 987535 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 14725847 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 11490673 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 28863760 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 16312214 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 7945230 # Number of BTB hits +global.BPredUnit.BTBLookups 13714223 # Number of BTB lookups +global.BPredUnit.RASInCorrect 29001 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 454297 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 10141226 # Number of conditional branches predicted +global.BPredUnit.lookups 15617287 # Number of BP lookups +global.BPredUnit.usedRAS 1851141 # Number of times the RAS was used to get a target. +host_inst_rate 91600 # Simulator instruction rate (inst/s) +host_mem_usage 155864 # Number of bytes of host memory used +host_seconds 868.91 # Real time elapsed on the host +host_tick_rate 1051887 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 16262618 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 12842437 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 22199501 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 16236124 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 79591756 # Number of instructions simulated -sim_seconds 0.001131 # Number of seconds simulated -sim_ticks 1130602014 # Number of ticks simulated +sim_seconds 0.000914 # Number of seconds simulated +sim_ticks 913992014 # Number of ticks simulated system.cpu.commit.COM:branches 13754477 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 3893678 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 3798224 # 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 89505192 +system.cpu.commit.COM:committed_per_cycle.samples 61093189 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 62882698 7025.59% - 1 8753972 978.04% - 2 5175203 578.20% - 3 3243621 362.39% - 4 2169519 242.39% - 5 1432847 160.09% - 6 1161882 129.81% - 7 791772 88.46% - 8 3893678 435.02% + 0 33945527 5556.35% + 1 9263496 1516.29% + 2 5234944 856.88% + 3 3369457 551.53% + 4 2068681 338.61% + 5 1423240 232.96% + 6 1205139 197.26% + 7 784481 128.41% + 8 3798224 621.71% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,70 @@ system.cpu.commit.COM:loads 20379399 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 35224018 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 359967 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 359791 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 88340672 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 4583 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 21665941 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 8215609 # The number of squashed insts skipped by commit system.cpu.committedInsts 79591756 # Number of Instructions Simulated system.cpu.committedInsts_total 79591756 # Number of Instructions Simulated -system.cpu.cpi 14.205014 # CPI: Cycles Per Instruction -system.cpu.cpi_total 14.205014 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 19540231 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 4453.766964 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 3237.815878 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 19382637 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 701886951 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.008065 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 157594 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 95950 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 199591922 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.003155 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 61644 # number of ReadReq MSHR misses +system.cpu.cpi 11.483501 # CPI: Cycles Per Instruction +system.cpu.cpi_total 11.483501 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 19669616 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 4470.389268 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 3240.793422 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 19511676 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 706053281 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.008030 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 157940 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 96341 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 199629634 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.003132 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 61599 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 14613377 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 4830.124895 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 3999.409028 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 13942631 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 3239786953 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.045899 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 670746 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 527274 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 573803212 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_avg_miss_latency 9707.501078 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 9477.511675 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 13569879 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 10129757960 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.071407 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 1043498 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 900030 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 1359719645 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.009818 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 143472 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 3332.672727 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 3759.399862 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 162.470348 # Average number of references to valid blocks. +system.cpu.dcache.WriteReq_mshr_misses 143468 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 3321.963636 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 3975 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 161.320715 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 110 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 125901 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 366594 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 473312202 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 1 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 365416 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 3975 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 34153608 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 4758.521747 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 3770.525625 # average overall mshr miss latency -system.cpu.dcache.demand_hits 33325268 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 3941673904 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.024253 # miss rate for demand accesses -system.cpu.dcache.demand_misses 828340 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 623224 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 773395134 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.006006 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 205116 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 34282993 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 9019.034891 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 7604.096607 # average overall mshr miss latency +system.cpu.dcache.demand_hits 33081555 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 10835811241 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.035045 # miss rate for demand accesses +system.cpu.dcache.demand_misses 1201438 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 996371 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 1559349279 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.005982 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 205067 # 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 34153608 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 4758.521747 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 3770.525625 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 34282993 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 9019.034891 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 7604.096607 # 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 33325268 # number of overall hits -system.cpu.dcache.overall_miss_latency 3941673904 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.024253 # miss rate for overall accesses -system.cpu.dcache.overall_misses 828340 # number of overall misses -system.cpu.dcache.overall_mshr_hits 623224 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 773395134 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.006006 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 205116 # number of overall MSHR misses +system.cpu.dcache.overall_hits 33081555 # number of overall hits +system.cpu.dcache.overall_miss_latency 10835811241 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.035045 # miss rate for overall accesses +system.cpu.dcache.overall_misses 1201438 # number of overall misses +system.cpu.dcache.overall_mshr_hits 996371 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 1559349279 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.005982 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 205067 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +118,92 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 201020 # number of replacements -system.cpu.dcache.sampled_refs 205116 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 200971 # number of replacements +system.cpu.dcache.sampled_refs 205067 # 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 4057.039034 # Cycle average of tags in use -system.cpu.dcache.total_refs 33325268 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 27784000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 147771 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 11948269 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 95198 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 3558048 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 131593428 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 51674084 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 25481309 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 4702945 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 281359 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 401531 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 27047110 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 22733117 # Number of cache lines fetched -system.cpu.fetch.Cycles 51481541 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 159026 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 148267180 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 3966980 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.287100 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 22733117 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 18080227 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.573826 # Number of inst fetches per cycle +system.cpu.dcache.tagsinuse 4063.517542 # Cycle average of tags in use +system.cpu.dcache.total_refs 33081555 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 17025000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 147753 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 13116101 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 95141 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 3521692 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 99189601 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 29616630 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 18020228 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 1276894 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 291919 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 340231 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 15617287 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 13002150 # Number of cache lines fetched +system.cpu.fetch.Cycles 31529148 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 124397 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 100725428 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 547316 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.250397 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 13002150 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 9796371 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.614964 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 94208138 +system.cpu.fetch.rateDist.samples 62370084 system.cpu.fetch.rateDist.min_value 0 - 0 65459635 6948.41% - 1 1687117 179.08% - 2 1748812 185.63% - 3 1938924 205.81% - 4 6981531 741.08% - 5 6100701 647.58% - 6 758078 80.47% - 7 1979150 210.08% - 8 7554190 801.86% + 0 43843090 7029.51% + 1 1383259 221.78% + 2 1262238 202.38% + 3 1426265 228.68% + 4 3918105 628.20% + 5 1724208 276.45% + 6 613107 98.30% + 7 1031700 165.42% + 8 7168112 1149.29% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 22733116 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 3345.551905 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 2359.548288 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 22631700 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 339292492 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.004461 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 101416 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 13878 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 206550138 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.003851 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 87538 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 13002150 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 3387.778909 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 2412.580892 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 12899943 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 346254719 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.007861 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 102207 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 14535 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 211515792 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.006743 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 87672 # 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 3731.567010 # average number of cycles each access was blocked -system.cpu.icache.avg_refs 258.538675 # Average number of references to valid blocks. +system.cpu.icache.avg_blocked_cycles_no_targets 5804 # average number of cycles each access was blocked +system.cpu.icache.avg_refs 147.140366 # 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 97 # number of cycles access was blocked +system.cpu.icache.blocked_no_targets 1 # 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 361962 # number of cycles access was blocked +system.cpu.icache.blocked_cycles_no_targets 5804 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 22733116 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 3345.551905 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 2359.548288 # average overall mshr miss latency -system.cpu.icache.demand_hits 22631700 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 339292492 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.004461 # miss rate for demand accesses -system.cpu.icache.demand_misses 101416 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 13878 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 206550138 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.003851 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 87538 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 13002150 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 3387.778909 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 2412.580892 # average overall mshr miss latency +system.cpu.icache.demand_hits 12899943 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 346254719 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.007861 # miss rate for demand accesses +system.cpu.icache.demand_misses 102207 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 14535 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 211515792 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.006743 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 87672 # 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 22733116 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 3345.551905 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 2359.548288 # average overall mshr miss latency +system.cpu.icache.overall_accesses 13002150 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 3387.778909 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 2412.580892 # 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 22631700 # number of overall hits -system.cpu.icache.overall_miss_latency 339292492 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.004461 # miss rate for overall accesses -system.cpu.icache.overall_misses 101416 # number of overall misses -system.cpu.icache.overall_mshr_hits 13878 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 206550138 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.003851 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 87538 # number of overall MSHR misses +system.cpu.icache.overall_hits 12899943 # number of overall hits +system.cpu.icache.overall_miss_latency 346254719 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.007861 # miss rate for overall accesses +system.cpu.icache.overall_misses 102207 # number of overall misses +system.cpu.icache.overall_mshr_hits 14535 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 211515792 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.006743 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 87672 # 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 @@ -215,80 +215,80 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 85490 # number of replacements -system.cpu.icache.sampled_refs 87537 # Sample count of references to valid blocks. +system.cpu.icache.replacements 85624 # number of replacements +system.cpu.icache.sampled_refs 87671 # 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 1835.330854 # Cycle average of tags in use -system.cpu.icache.total_refs 22631700 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1862.743229 # Cycle average of tags in use +system.cpu.icache.total_refs 12899943 # 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 1036393877 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 14379719 # Number of branches executed -system.cpu.iew.EXEC:nop 9265977 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.989418 # Inst execution rate -system.cpu.iew.EXEC:refs 43156162 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 15338261 # Number of stores executed +system.cpu.idleCycles 851621931 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 14377755 # Number of branches executed +system.cpu.iew.EXEC:nop 9220461 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.335296 # Inst execution rate +system.cpu.iew.EXEC:refs 36382036 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 15204952 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 46157981 # num instructions consuming a value -system.cpu.iew.WB:count 86105601 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.741496 # average fanout of values written-back +system.cpu.iew.WB:consumers 46748099 # num instructions consuming a value +system.cpu.iew.WB:count 82847738 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.736514 # 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 34225955 # num instructions producing a value -system.cpu.iew.WB:rate 0.913993 # insts written-back per cycle -system.cpu.iew.WB:sent 86171133 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 389534 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 3213991 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 28863760 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 4784 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 1402526 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 16312214 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 110003367 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 27817901 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 453087 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 93211232 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 28742 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 34430613 # num instructions producing a value +system.cpu.iew.WB:rate 1.328325 # insts written-back per cycle +system.cpu.iew.WB:sent 82914162 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 396555 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 4917376 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 22199501 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 4762 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 311974 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 16236124 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 96553237 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 21177084 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 433562 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 83282498 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 37202 # 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 12962 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 4702945 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 194395 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 1528 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 6922047 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 1365052 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 5008 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 11594 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 1276894 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 204710 # 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 98563 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 1300046 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 1230 # 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 3825 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 1528 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 8484361 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 1467595 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 3825 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 102872 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 286662 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.070398 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.070398 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 93664319 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 27684 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 1255 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 1820102 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 1391505 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 27684 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 103251 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 293304 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.087081 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.087081 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 83716060 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 0 0.00% # Type of FU issued - IntAlu 49995908 53.38% # Type of FU issued - IntMult 43196 0.05% # Type of FU issued + IntAlu 46816661 55.92% # Type of FU issued + IntMult 44502 0.05% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 123595 0.13% # Type of FU issued + FloatAdd 125345 0.15% # Type of FU issued FloatCmp 86 0.00% # Type of FU issued - FloatCvt 122386 0.13% # Type of FU issued + FloatCvt 122997 0.15% # Type of FU issued FloatMult 51 0.00% # Type of FU issued - FloatDiv 37853 0.04% # Type of FU issued + FloatDiv 37854 0.05% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 27919833 29.81% # Type of FU issued - MemWrite 15421411 16.46% # Type of FU issued + MemRead 21285503 25.43% # Type of FU issued + MemWrite 15283061 18.26% # 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 1229792 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.013130 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 1123822 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.013424 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available - IntAlu 83895 6.82% # attempts to use FU when none available + IntAlu 98385 8.75% # 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 @@ -297,84 +297,84 @@ 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 589327 47.92% # attempts to use FU when none available - MemWrite 556570 45.26% # attempts to use FU when none available + MemRead 476117 42.37% # attempts to use FU when none available + MemWrite 549320 48.88% # 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 94208138 +system.cpu.iq.ISSUE:issued_per_cycle.samples 62370084 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 54322746 5766.25% - 1 13333515 1415.33% - 2 10626230 1127.95% - 3 8813553 935.54% - 4 4440243 471.32% - 5 1597603 169.58% - 6 685526 72.77% - 7 334234 35.48% - 8 54488 5.78% + 0 25315225 4058.87% + 1 13800975 2212.76% + 2 10743054 1722.47% + 3 5596398 897.29% + 4 4388925 703.69% + 5 1495414 239.76% + 6 664039 106.47% + 7 305653 49.01% + 8 60401 9.68% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.994227 # Inst issue rate -system.cpu.iq.iqInstsAdded 100732606 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 93664319 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 4784 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 20911338 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 73995 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 201 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 16334966 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 292646 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 3929.598028 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2043.469607 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 122985 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 666699531 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.579748 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 169661 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 346697097 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.579748 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 169661 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 147771 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 147307 # number of Writeback hits -system.cpu.l2cache.Writeback_miss_rate 0.003140 # miss rate for Writeback accesses -system.cpu.l2cache.Writeback_misses 464 # number of Writeback misses -system.cpu.l2cache.Writeback_mshr_miss_rate 0.003140 # mshr miss rate for Writeback accesses -system.cpu.l2cache.Writeback_mshr_misses 464 # number of Writeback MSHR misses +system.cpu.iq.ISSUE:rate 1.342247 # Inst issue rate +system.cpu.iq.iqInstsAdded 87328014 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 83716060 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 4762 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 7507881 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 113500 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 179 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 6033024 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 292729 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 7766.621627 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2997.837795 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 123055 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1317793758 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.579628 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 169674 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 508655130 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.579628 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 169674 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 147753 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 147285 # number of Writeback hits +system.cpu.l2cache.Writeback_miss_rate 0.003167 # miss rate for Writeback accesses +system.cpu.l2cache.Writeback_misses 468 # number of Writeback misses +system.cpu.l2cache.Writeback_mshr_miss_rate 0.003167 # mshr miss rate for Writeback accesses +system.cpu.l2cache.Writeback_mshr_misses 468 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 1.593139 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 1.593300 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 292646 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 3929.598028 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2043.469607 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 122985 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 666699531 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.579748 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 169661 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 292729 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 7766.621627 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2997.837795 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 123055 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1317793758 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.579628 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 169674 # 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 346697097 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.579748 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 169661 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 508655130 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.579628 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 169674 # 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 440417 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 3918.880417 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2043.469607 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 440482 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 7745.258419 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2997.837795 # 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 270292 # number of overall hits -system.cpu.l2cache.overall_miss_latency 666699531 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.386282 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 170125 # number of overall misses +system.cpu.l2cache.overall_hits 270340 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1317793758 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.386263 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 170142 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 346697097 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.385228 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 169661 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 508655130 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.385201 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 169674 # 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 @@ -386,32 +386,32 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 136892 # number of replacements -system.cpu.l2cache.sampled_refs 169660 # Sample count of references to valid blocks. +system.cpu.l2cache.replacements 136905 # number of replacements +system.cpu.l2cache.sampled_refs 169673 # 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 30349.297230 # Cycle average of tags in use -system.cpu.l2cache.total_refs 270292 # Total number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 625483000 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.writebacks 115938 # number of writebacks -system.cpu.numCycles 94208138 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 7563765 # Number of cycles rename is blocking +system.cpu.l2cache.tagsinuse 30821.723437 # Cycle average of tags in use +system.cpu.l2cache.total_refs 270340 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 468003000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 115935 # number of writebacks +system.cpu.numCycles 62370084 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 8787185 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 52546881 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 87866 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 52361095 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 3315491 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 3509 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 154857350 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 130101763 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 82913656 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 25182526 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 4702945 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 3542613 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 30366775 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 855194 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 4773 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 6398047 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 4771 # count of temporary serializing insts renamed -system.cpu.timesIdled 275758 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 113083 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 30263464 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 3026568 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 587 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 118807787 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 98380136 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 59048113 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 17777635 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 1276894 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 3354217 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 6501232 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 910689 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 4741 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 5955323 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 4739 # count of temporary serializing insts renamed +system.cpu.timesIdled 280733 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 4583 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/stderr b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/stderr index eb1796ead..f33d007a7 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/stderr +++ b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/stderr @@ -1,2 +1,2 @@ -0: system.remote_gdb.listener: listening for remote gdb on port 7000 warn: Entering event queue @ 0. Starting simulation... +warn: Increasing stack size by one page. diff --git a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini index 9ae62655d..567f53165 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini @@ -1,48 +1,7 @@ [root] type=Root children=system -checkpoint= -clock=1000000000000 -max_tick=0 -output_file=cout -progress_interval=0 - -[exetrace] -intel_format=false -legion_lockstep=false -pc_symbol=true -print_cpseq=false -print_cycle=true -print_data=true -print_effaddr=true -print_fetchseq=false -print_iregs=false -print_opclass=true -print_thread=true -speculative=true -trace_system=client - -[serialize] -count=10 -cycle=0 -dir=cpt.%012d -period=0 - -[stats] -descriptions=true -dump_cycle=0 -dump_period=0 -dump_reset=false -ignore_events= -mysql_db= -mysql_host= -mysql_password= -mysql_user= -project_name=test -simulation_name=test -simulation_sample=0 -text_compat=true -text_file=m5stats.txt +dummy=0 [system] type=System @@ -70,6 +29,7 @@ commitToFetchDelay=1 commitToIEWDelay=1 commitToRenameDelay=1 commitWidth=8 +cpu_id=0 decodeToFetchDelay=1 decodeToRenameDelay=1 decodeWidth=8 @@ -155,7 +115,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -331,7 +291,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -388,7 +348,7 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=bzip2 input.source 1 -cwd=build/ALPHA_SE/tests/fast/long/60.bzip2/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/60.bzip2/alpha/tru64/o3-timing egid=100 env= euid=100 diff --git a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.out b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.out index 690cc5723..bf1cbf0ac 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.out +++ b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.out @@ -1,9 +1,6 @@ [root] type=Root -clock=1000000000000 -max_tick=0 -progress_interval=0 -output_file=cout +dummy=0 [system.physmem] type=PhysicalMemory @@ -31,7 +28,7 @@ executable=/dist/m5/cpu2000/binaries/alpha/tru64/bzip2 input=cin output=cout env= -cwd=build/ALPHA_SE/tests/fast/long/60.bzip2/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/60.bzip2/alpha/tru64/o3-timing system=system uid=100 euid=100 @@ -173,6 +170,7 @@ type=DerivO3CPU clock=1 phase=0 numThreads=1 +cpu_id=0 activity=0 workload=system.cpu.workload checker=null @@ -253,7 +251,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -291,7 +289,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -367,39 +365,3 @@ clock=1000 width=64 responder_set=false -[stats] -descriptions=true -project_name=test -simulation_name=test -simulation_sample=0 -text_file=m5stats.txt -text_compat=true -mysql_db= -mysql_user= -mysql_password= -mysql_host= -events_start=-1 -dump_reset=false -dump_cycle=0 -dump_period=0 -ignore_events= - -[exetrace] -speculative=true -print_cycle=true -print_opclass=true -print_thread=true -print_effaddr=true -print_data=true -print_iregs=false -print_fetchseq=false -print_cpseq=false -print_reg_delta=false -pc_symbol=true -intel_format=false -legion_lockstep=false -trace_system=client - -[statsreset] -reset_cycle=0 - diff --git a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt index bc6866525..3521e50a1 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/60.bzip2/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 1060300638 # Number of BTB hits -global.BPredUnit.BTBLookups 1075264664 # Number of BTB lookups +global.BPredUnit.BTBHits 929108954 # Number of BTB hits +global.BPredUnit.BTBLookups 938262248 # Number of BTB lookups global.BPredUnit.RASInCorrect 132 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 20658855 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 1028649695 # Number of conditional branches predicted -global.BPredUnit.lookups 1098978166 # Number of BP lookups -global.BPredUnit.usedRAS 20738311 # Number of times the RAS was used to get a target. -host_inst_rate 28281 # Simulator instruction rate (inst/s) -host_mem_usage 1256892 # Number of bytes of host memory used -host_seconds 61385.49 # Real time elapsed on the host -host_tick_rate 405833 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 114920109 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 60881817 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 938731548 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 389309694 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.condIncorrect 21205625 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 887467305 # Number of conditional branches predicted +global.BPredUnit.lookups 962390884 # Number of BP lookups +global.BPredUnit.usedRAS 21400461 # Number of times the RAS was used to get a target. +host_inst_rate 41899 # Simulator instruction rate (inst/s) +host_mem_usage 150980 # Number of bytes of host memory used +host_seconds 41434.26 # Real time elapsed on the host +host_tick_rate 599461 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 138710917 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 68670490 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 815007661 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 388931456 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 1736043781 # Number of instructions simulated -sim_seconds 0.024912 # Number of seconds simulated -sim_ticks 24912272090 # Number of ticks simulated +sim_seconds 0.024838 # Number of seconds simulated +sim_ticks 24838210102 # Number of ticks simulated system.cpu.commit.COM:branches 214632552 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 72343657 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 66487461 # 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 5678957793 +system.cpu.commit.COM:committed_per_cycle.samples 7112101736 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 5103057521 8985.90% - 1 193842571 341.33% - 2 126727829 223.15% - 3 63255233 111.39% - 4 47590442 83.80% - 5 34302037 60.40% - 6 22774532 40.10% - 7 15063971 26.53% - 8 72343657 127.39% + 0 6522703166 9171.27% + 1 208562151 293.25% + 2 123042509 173.00% + 3 62023833 87.21% + 4 51435586 72.32% + 5 40600313 57.09% + 6 22309158 31.37% + 7 14937559 21.00% + 8 66487461 93.48% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,70 @@ system.cpu.commit.COM:loads 445666361 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 606571343 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 20658355 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 21205131 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 1819780126 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 29 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 3012390712 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 2701603860 # The number of squashed insts skipped by commit system.cpu.committedInsts 1736043781 # Number of Instructions Simulated system.cpu.committedInsts_total 1736043781 # Number of Instructions Simulated -system.cpu.cpi 14.350025 # CPI: Cycles Per Instruction -system.cpu.cpi_total 14.350025 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 466176479 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 5764.172372 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5678.042412 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 454097633 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 69624550394 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.025910 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 12078846 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 4784670 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 41416640690 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.015647 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 7294176 # number of ReadReq MSHR misses +system.cpu.cpi 14.307364 # CPI: Cycles Per Instruction +system.cpu.cpi_total 14.307364 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 489384352 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 5253.286413 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5452.839977 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 474368420 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 78882991559 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.030683 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 15015932 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 7713263 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 39820285465 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.014922 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 7302669 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 160728502 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 11148.179412 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 14223.476157 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 157574910 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 35156809407 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.019621 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 3153592 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 1270515 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 26783900812 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.011716 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 1883077 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 972.020892 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 2881.979981 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 66.650940 # Average number of references to valid blocks. -system.cpu.dcache.blocked_no_mshrs 659829 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 896062 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 641367573 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 2582432746 # number of cycles access was blocked +system.cpu.dcache.WriteReq_avg_miss_latency 8690.039906 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 14121.575874 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 155407108 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 46243126214 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.033108 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 5321394 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 3438755 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 26585829481 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.011713 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 1882639 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 985.727671 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 3841.099983 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 68.563354 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 637482 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 65141 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 628383647 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 250213094 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 626904981 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 6878.830546 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 7431.476663 # average overall mshr miss latency -system.cpu.dcache.demand_hits 611672543 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 104781359801 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.024298 # miss rate for demand accesses -system.cpu.dcache.demand_misses 15232438 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 6055185 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 68200541502 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.014639 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 9177253 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 650112854 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 6152.535381 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 7229.601331 # average overall mshr miss latency +system.cpu.dcache.demand_hits 629775528 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 125126117773 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.031283 # miss rate for demand accesses +system.cpu.dcache.demand_misses 20337326 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 11152018 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 66406114946 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.014129 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 9185308 # 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 626904981 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 6878.830546 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 7431.476663 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 650112854 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 6152.535381 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 7229.601331 # 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 611672543 # number of overall hits -system.cpu.dcache.overall_miss_latency 104781359801 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.024298 # miss rate for overall accesses -system.cpu.dcache.overall_misses 15232438 # number of overall misses -system.cpu.dcache.overall_mshr_hits 6055185 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 68200541502 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.014639 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 9177253 # number of overall MSHR misses +system.cpu.dcache.overall_hits 629775528 # number of overall hits +system.cpu.dcache.overall_miss_latency 125126117773 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.031283 # miss rate for overall accesses +system.cpu.dcache.overall_misses 20337326 # number of overall misses +system.cpu.dcache.overall_mshr_hits 11152018 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 66406114946 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.014129 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 9185308 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,91 +118,91 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 9173157 # number of replacements -system.cpu.dcache.sampled_refs 9177253 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 9181212 # number of replacements +system.cpu.dcache.sampled_refs 9185308 # 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 4093.061614 # Cycle average of tags in use -system.cpu.dcache.total_refs 611672543 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 39716000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 2244715 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 3168036062 # Number of cycles decode is blocked +system.cpu.dcache.tagsinuse 4093.052798 # Cycle average of tags in use +system.cpu.dcache.total_refs 629775528 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 39780000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 2244995 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 5295615421 # Number of cycles decode is blocked system.cpu.decode.DECODE:BranchMispred 511 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 48557069 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 6641345328 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 1298412925 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 1202046298 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 501929792 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 1629 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 10462509 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 1098978166 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 541280485 # Number of cache lines fetched -system.cpu.fetch.Cycles 1955627258 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 11328270 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 7938391391 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 242391708 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.177803 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 541280485 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 1081038949 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.284345 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BranchResolved 51642597 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 5750899999 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 834310560 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 972356636 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 417727902 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 1635 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 9819120 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 962390884 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 341574441 # Number of cache lines fetched +system.cpu.fetch.Cycles 1454523625 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 5354005 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 6616091478 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 145044249 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.127810 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 341574441 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 950509415 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.878651 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 6180887586 +system.cpu.fetch.rateDist.samples 7529829639 system.cpu.fetch.rateDist.min_value 0 - 0 4766540797 7711.74% - 1 80764415 130.67% - 2 63598055 102.89% - 3 58203597 94.17% - 4 424384465 686.61% - 5 69131012 111.85% - 6 94422767 152.77% - 7 44649271 72.24% - 8 579193207 937.07% + 0 6416880458 8521.95% + 1 35027129 46.52% + 2 21417088 28.44% + 3 34363919 45.64% + 4 372287950 494.42% + 5 53476407 71.02% + 6 32781145 43.54% + 7 26846633 35.65% + 8 536748910 712.83% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 541280484 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5378.819380 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4616.750831 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 541279194 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 6938677 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000002 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 1290 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 387 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 4168926 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000002 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_accesses 341574441 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 5436.849282 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4708.305648 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 341573187 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 6817809 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000004 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 1254 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 351 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 4251600 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000003 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 903 # 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 4207.523810 # average number of cycles each access was blocked -system.cpu.icache.avg_refs 599423.249169 # Average number of references to valid blocks. +system.cpu.icache.avg_blocked_cycles_no_targets 4779 # average number of cycles each access was blocked +system.cpu.icache.avg_refs 378264.880399 # 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 21 # number of cycles access was blocked +system.cpu.icache.blocked_no_targets 1 # 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 88358 # number of cycles access was blocked +system.cpu.icache.blocked_cycles_no_targets 4779 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 541280484 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5378.819380 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4616.750831 # average overall mshr miss latency -system.cpu.icache.demand_hits 541279194 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 6938677 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000002 # miss rate for demand accesses -system.cpu.icache.demand_misses 1290 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 387 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 4168926 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000002 # mshr miss rate for demand accesses +system.cpu.icache.demand_accesses 341574441 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 5436.849282 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4708.305648 # average overall mshr miss latency +system.cpu.icache.demand_hits 341573187 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 6817809 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000004 # miss rate for demand accesses +system.cpu.icache.demand_misses 1254 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 351 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 4251600 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000003 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 903 # 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 541280484 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5378.819380 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4616.750831 # average overall mshr miss latency +system.cpu.icache.overall_accesses 341574441 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 5436.849282 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4708.305648 # 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 541279194 # number of overall hits -system.cpu.icache.overall_miss_latency 6938677 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000002 # miss rate for overall accesses -system.cpu.icache.overall_misses 1290 # number of overall misses -system.cpu.icache.overall_mshr_hits 387 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 4168926 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000002 # mshr miss rate for overall accesses +system.cpu.icache.overall_hits 341573187 # number of overall hits +system.cpu.icache.overall_miss_latency 6817809 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000004 # miss rate for overall accesses +system.cpu.icache.overall_misses 1254 # number of overall misses +system.cpu.icache.overall_mshr_hits 351 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 4251600 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000003 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 903 # 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 @@ -218,77 +218,77 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 1 # number of replacements system.cpu.icache.sampled_refs 903 # 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 716.132429 # Cycle average of tags in use -system.cpu.icache.total_refs 541279194 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 719.119159 # Cycle average of tags in use +system.cpu.icache.total_refs 341573187 # 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 18731384505 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 250098653 # Number of branches executed -system.cpu.iew.EXEC:nop 147895912 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.440971 # Inst execution rate -system.cpu.iew.EXEC:refs 918923683 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 177016651 # Number of stores executed +system.cpu.idleCycles 17308380464 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 264199071 # Number of branches executed +system.cpu.iew.EXEC:nop 130726584 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.347587 # Inst execution rate +system.cpu.iew.EXEC:refs 833351854 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 181613826 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1839076786 # num instructions consuming a value -system.cpu.iew.WB:count 2471794731 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.797100 # average fanout of values written-back +system.cpu.iew.WB:consumers 1860973502 # num instructions consuming a value +system.cpu.iew.WB:count 2467010272 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.791148 # 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 1465928228 # num instructions producing a value -system.cpu.iew.WB:rate 0.399909 # insts written-back per cycle -system.cpu.iew.WB:sent 2475054397 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 21956654 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 2471410228 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 938731548 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 45 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 111073783 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 389309694 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 4831881465 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 741907032 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 286170200 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 2725595031 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 1536928 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 1472305742 # num instructions producing a value +system.cpu.iew.WB:rate 0.327632 # insts written-back per cycle +system.cpu.iew.WB:sent 2471732034 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 22834368 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 4630364405 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 815007661 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 46 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 31860417 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 388931456 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 4520549939 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 651738028 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 279876672 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 2617267318 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 2938028 # 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 161620 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 501929792 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 6153373 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 8 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 233590575 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 41593346 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 516978 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 161905 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 417727902 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 6385903 # 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 122063096 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 39544757 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 151090 # 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 47985 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 8 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 493065187 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 228404712 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 47985 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 726441 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 21230213 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.069686 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.069686 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 3011765231 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 4644371 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 12 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 369341300 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 228026474 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 4644371 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 832035 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 22002333 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.069894 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.069894 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 2897143990 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 0 0.00% # Type of FU issued - IntAlu 1970711875 65.43% # Type of FU issued - IntMult 679 0.00% # Type of FU issued + IntAlu 1942173026 67.04% # Type of FU issued + IntMult 100 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 206 0.00% # Type of FU issued + FloatAdd 210 0.00% # Type of FU issued FloatCmp 15 0.00% # Type of FU issued - FloatCvt 146 0.00% # Type of FU issued - FloatMult 12 0.00% # Type of FU issued + FloatCvt 140 0.00% # Type of FU issued + FloatMult 13 0.00% # Type of FU issued FloatDiv 24 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 862446019 28.64% # Type of FU issued - MemWrite 178606255 5.93% # Type of FU issued + MemRead 770673405 26.60% # Type of FU issued + MemWrite 184297057 6.36% # 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 11307551 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.003754 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 12298143 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.004245 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist (null) 0 0.00% # attempts to use FU when none available - IntAlu 509990 4.51% # attempts to use FU when none available + IntAlu 765509 6.22% # 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 @@ -297,84 +297,84 @@ 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 9173598 81.13% # attempts to use FU when none available - MemWrite 1623963 14.36% # attempts to use FU when none available + MemRead 9714303 78.99% # attempts to use FU when none available + MemWrite 1818331 14.79% # 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 6180887586 +system.cpu.iq.ISSUE:issued_per_cycle.samples 7529829639 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 4878979324 7893.65% - 1 360055339 582.53% - 2 481197713 778.53% - 3 280796976 454.30% - 4 94854448 153.46% - 5 50760526 82.12% - 6 26723872 43.24% - 7 6795220 10.99% - 8 724168 1.17% + 0 6294390011 8359.27% + 1 325228389 431.92% + 2 480486573 638.11% + 3 243738023 323.70% + 4 97825007 129.92% + 5 51561666 68.48% + 6 27659179 36.73% + 7 6861374 9.11% + 8 2079417 2.76% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.487271 # Inst issue rate -system.cpu.iq.iqInstsAdded 4683985508 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 3011765231 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 45 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 2916477755 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 6096386 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 16 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 3050829124 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 9178154 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 7336.712513 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2076.036854 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 7008989 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 15914539999 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.236340 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 2169165 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4503266483 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.236340 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 2169165 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 2244715 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 2215400 # number of Writeback hits -system.cpu.l2cache.Writeback_miss_rate 0.013060 # miss rate for Writeback accesses -system.cpu.l2cache.Writeback_misses 29315 # number of Writeback misses -system.cpu.l2cache.Writeback_mshr_miss_rate 0.013060 # mshr miss rate for Writeback accesses -system.cpu.l2cache.Writeback_mshr_misses 29315 # number of Writeback MSHR misses +system.cpu.iq.ISSUE:rate 0.384756 # Inst issue rate +system.cpu.iq.iqInstsAdded 4389823309 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 2897143990 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 46 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 2623608231 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 10330579 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 17 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 2673985156 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 9186210 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 7225.224344 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2102.004971 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 7015727 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 15682226609 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.236276 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 2170483 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 4562366056 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.236276 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 2170483 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 2244995 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 2215762 # number of Writeback hits +system.cpu.l2cache.Writeback_miss_rate 0.013021 # miss rate for Writeback accesses +system.cpu.l2cache.Writeback_misses 29233 # number of Writeback misses +system.cpu.l2cache.Writeback_mshr_miss_rate 0.013021 # mshr miss rate for Writeback accesses +system.cpu.l2cache.Writeback_mshr_misses 29233 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 4.252507 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 4.253196 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 9178154 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 7336.712513 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2076.036854 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 7008989 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 15914539999 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.236340 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 2169165 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 9186210 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 7225.224344 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2102.004971 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 7015727 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 15682226609 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.236276 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 2170483 # 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 4503266483 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.236340 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 2169165 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 4562366056 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.236276 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 2170483 # 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 11422869 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 7238.883228 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2076.036854 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 11431205 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 7129.205138 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2102.004971 # 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 9224389 # number of overall hits -system.cpu.l2cache.overall_miss_latency 15914539999 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.192463 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 2198480 # number of overall misses +system.cpu.l2cache.overall_hits 9231489 # number of overall hits +system.cpu.l2cache.overall_miss_latency 15682226609 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.192431 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 2199716 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 4503266483 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.189897 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 2169165 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 4562366056 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.189874 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 2170483 # 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 @@ -386,32 +386,32 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 2136397 # number of replacements -system.cpu.l2cache.sampled_refs 2169165 # Sample count of references to valid blocks. +system.cpu.l2cache.replacements 2137715 # number of replacements +system.cpu.l2cache.sampled_refs 2170483 # 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 32623.472165 # Cycle average of tags in use -system.cpu.l2cache.total_refs 9224389 # Total number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 520424000 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.writebacks 1039341 # number of writebacks -system.cpu.numCycles 6180887586 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 2894504060 # Number of cycles rename is blocking +system.cpu.l2cache.tagsinuse 32622.966749 # Cycle average of tags in use +system.cpu.l2cache.total_refs 9231489 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 513093000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 1039675 # number of writebacks +system.cpu.numCycles 7529829639 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 5035061268 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 1376202963 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 6511750 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 1451413065 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 266047107 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 3125053 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 8501370508 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 6112671585 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 4584914520 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 1056218413 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 501929792 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 276756270 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 3208711557 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 65986 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 49 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 1117979447 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 47 # count of temporary serializing insts renamed -system.cpu.timesIdled 7293390 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 12523289 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 970889170 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 234469237 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 2022618 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 7453165021 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 5328451425 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 4004220538 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 843247999 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 417727902 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 262813407 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 2628017575 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 89893 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 51 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 1009480859 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 49 # count of temporary serializing insts renamed +system.cpu.timesIdled 6494671 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 29 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/stderr b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/stderr index cdd59eda7..d0a887867 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/stderr +++ b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/stderr @@ -1,2 +1,3 @@ -0: system.remote_gdb.listener: listening for remote gdb on port 7006 warn: Entering event queue @ 0. Starting simulation... +warn: Increasing stack size by one page. +warn: Increasing stack size by one page. diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini index 5604f880f..9795f2e42 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini @@ -1,11 +1,7 @@ [root] type=Root children=system -checkpoint= -clock=1000000000000 -max_tick=0 -output_file=cout -progress_interval=0 +dummy=0 [system] type=System @@ -33,6 +29,7 @@ commitToFetchDelay=1 commitToIEWDelay=1 commitToRenameDelay=1 commitWidth=8 +cpu_id=0 decodeToFetchDelay=1 decodeToRenameDelay=1 decodeWidth=8 @@ -118,7 +115,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -294,7 +291,7 @@ split=false split_size=0 store_compressed=false subblock_size=0 -tgts_per_mshr=5 +tgts_per_mshr=20 trace_addr=0 two_queue=false write_buffers=8 @@ -351,11 +348,11 @@ port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cp [system.cpu.workload] type=LiveProcess cmd=twolf smred -cwd=build/ALPHA_SE/tests/fast/long/70.twolf/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/70.twolf/alpha/tru64/o3-timing egid=100 env= euid=100 -executable=/home/gblack/m5/dist/m5/cpu2000/binaries/alpha/tru64/twolf +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf gid=100 input=cin output=cout diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.out b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.out index a78c52d7f..504c6e888 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.out +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.out @@ -1,9 +1,6 @@ [root] type=Root -clock=1000000000000 -max_tick=0 -progress_interval=0 -output_file=cout +dummy=0 [system.physmem] type=PhysicalMemory @@ -27,11 +24,11 @@ responder_set=false [system.cpu.workload] type=LiveProcess cmd=twolf smred -executable=/home/gblack/m5/dist/m5/cpu2000/binaries/alpha/tru64/twolf +executable=/dist/m5/cpu2000/binaries/alpha/tru64/twolf input=cin output=cout env= -cwd=build/ALPHA_SE/tests/fast/long/70.twolf/alpha/linux/o3-timing +cwd=build/ALPHA_SE/tests/fast/long/70.twolf/alpha/tru64/o3-timing system=system uid=100 euid=100 @@ -173,6 +170,7 @@ type=DerivO3CPU clock=1 phase=0 numThreads=1 +cpu_id=0 activity=0 workload=system.cpu.workload checker=null @@ -253,7 +251,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null @@ -291,7 +289,7 @@ assoc=2 block_size=64 latency=1 mshrs=10 -tgts_per_mshr=5 +tgts_per_mshr=20 write_buffers=8 prioritizeRequests=false protocol=null diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt index c77face31..dba9e1470 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/70.twolf/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 11848811 # Number of BTB hits -global.BPredUnit.BTBLookups 15227898 # Number of BTB lookups -global.BPredUnit.RASInCorrect 1227 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 2015952 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 12943595 # Number of conditional branches predicted -global.BPredUnit.lookups 17560137 # Number of BP lookups -global.BPredUnit.usedRAS 1685355 # Number of times the RAS was used to get a target. -host_inst_rate 110871 # Simulator instruction rate (inst/s) -host_mem_usage 184176 # Number of bytes of host memory used -host_seconds 759.26 # Real time elapsed on the host -host_tick_rate 138735 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 9867030 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 3328836 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 29553768 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 9396457 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 13130842 # Number of BTB hits +global.BPredUnit.BTBLookups 17054746 # Number of BTB lookups +global.BPredUnit.RASInCorrect 1205 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1949700 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 14620230 # Number of conditional branches predicted +global.BPredUnit.lookups 19607486 # Number of BP lookups +global.BPredUnit.usedRAS 1766776 # Number of times the RAS was used to get a target. +host_inst_rate 70212 # Simulator instruction rate (inst/s) +host_mem_usage 153248 # Number of bytes of host memory used +host_seconds 1198.94 # Real time elapsed on the host +host_tick_rate 95357 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 19046664 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 5327434 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 34568849 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 10915344 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 84179709 # Number of instructions simulated -sim_seconds 0.000105 # Number of seconds simulated -sim_ticks 105335101 # Number of ticks simulated +sim_seconds 0.000114 # Number of seconds simulated +sim_ticks 114327081 # Number of ticks simulated system.cpu.commit.COM:branches 10240685 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 3300349 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 2895131 # 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 65617496 +system.cpu.commit.COM:committed_per_cycle.samples 73926385 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 32041205 4883.03% - 1 13628356 2076.94% - 2 7878182 1200.62% - 3 3859920 588.25% - 4 2040157 310.92% - 5 1456623 221.99% - 6 796888 121.44% - 7 615816 93.85% - 8 3300349 502.97% + 0 37511035 5074.11% + 1 16507127 2232.91% + 2 8529257 1153.75% + 3 3749717 507.22% + 4 1879220 254.20% + 5 1361115 184.12% + 6 851721 115.21% + 7 642062 86.85% + 8 2895131 391.62% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,70 @@ system.cpu.commit.COM:loads 20034413 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 26537108 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 2003468 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 1937238 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 91903055 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 389 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 39205061 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 58539227 # The number of squashed insts skipped by commit system.cpu.committedInsts 84179709 # Number of Instructions Simulated system.cpu.committedInsts_total 84179709 # Number of Instructions Simulated -system.cpu.cpi 1.251312 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.251312 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 23022109 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 5495.207331 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4910.485944 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 23021236 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 4797316 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.000038 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 873 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 375 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 2445422 # number of ReadReq MSHR miss cycles +system.cpu.cpi 1.358131 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.358131 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 23376895 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 5393.890593 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4863.252964 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 23375917 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 5275225 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000042 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 978 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 472 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 2460806 # number of ReadReq MSHR miss cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000022 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 498 # number of ReadReq MSHR misses +system.cpu.dcache.ReadReq_mshr_misses 506 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 6501103 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 4880.722363 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 4578.932720 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 6495178 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 28918280 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.000911 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 5925 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 4186 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 7962764 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_avg_miss_latency 6579.789722 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6507.873418 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 6492638 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 55697920 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.001302 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 8465 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 6727 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 11310684 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.000267 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 1739 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 2807.125000 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 3125.260571 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 13194.641931 # Average number of references to valid blocks. -system.cpu.dcache.blocked_no_mshrs 8 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 875 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 22457 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 2734603 # number of cycles access was blocked +system.cpu.dcache.WriteReq_mshr_misses 1738 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 2809.444444 # 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 13310.407754 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 9 # 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 25285 # 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 29523212 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 4959.634598 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 4652.742959 # average overall mshr miss latency -system.cpu.dcache.demand_hits 29516414 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 33715596 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.000230 # miss rate for demand accesses -system.cpu.dcache.demand_misses 6798 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 4561 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 10408186 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.000076 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 2237 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 29877998 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 6456.967595 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 6137.027629 # average overall mshr miss latency +system.cpu.dcache.demand_hits 29868555 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 60973145 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000316 # miss rate for demand accesses +system.cpu.dcache.demand_misses 9443 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 7199 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 13771490 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.000075 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 2244 # 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 29523212 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 4959.634598 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 4652.742959 # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_uncacheable_latency no value # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 29516414 # number of overall hits -system.cpu.dcache.overall_miss_latency 33715596 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.000230 # miss rate for overall accesses -system.cpu.dcache.overall_misses 6798 # number of overall misses -system.cpu.dcache.overall_mshr_hits 4561 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 10408186 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.000076 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 2237 # number of overall MSHR misses +system.cpu.dcache.overall_accesses 29877998 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 6456.967595 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 6137.027629 # 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 29868555 # number of overall hits +system.cpu.dcache.overall_miss_latency 60973145 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000316 # miss rate for overall accesses +system.cpu.dcache.overall_misses 9443 # number of overall misses +system.cpu.dcache.overall_mshr_hits 7199 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 13771490 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.000075 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 2244 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +118,92 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 158 # number of replacements -system.cpu.dcache.sampled_refs 2237 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 160 # number of replacements +system.cpu.dcache.sampled_refs 2244 # 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 1400.647488 # Cycle average of tags in use -system.cpu.dcache.total_refs 29516414 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 1415.957077 # Cycle average of tags in use +system.cpu.dcache.total_refs 29868555 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 105 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 2047370 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 12661 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 2829477 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 146297095 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 36266329 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 27223403 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 6075840 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 45354 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 80395 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 17560137 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 17576948 # Number of cache lines fetched -system.cpu.fetch.Cycles 45711428 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 479088 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 150837354 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 2061309 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.244934 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 17576948 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 13534166 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 2.103924 # Number of inst fetches per cycle +system.cpu.dcache.writebacks 106 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 5155486 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 12562 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 3109369 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 165294506 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 40322652 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 28299602 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 8350763 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 41264 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 148646 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 19607486 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 19380281 # Number of cache lines fetched +system.cpu.fetch.Cycles 48705122 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 491925 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 170506876 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 2058666 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.238310 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 19380281 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 14897618 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.072348 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 71693337 +system.cpu.fetch.rateDist.samples 82277149 system.cpu.fetch.rateDist.min_value 0 - 0 43559639 6075.83% - 1 2788432 388.94% - 2 2133609 297.60% - 3 3200202 446.37% - 4 4098889 571.73% - 5 1363717 190.22% - 6 1885995 263.06% - 7 1651845 230.40% - 8 11011009 1535.85% + 0 52952312 6435.85% + 1 3129610 380.37% + 2 1369966 166.51% + 3 2017219 245.17% + 4 3854384 468.46% + 5 1357405 164.98% + 6 1550178 188.41% + 7 1288552 156.61% + 8 14757523 1793.64% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 17576948 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 3407.568545 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 2506.978423 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 17563424 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 46083957 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000769 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 13524 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 3467 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 25212682 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000572 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 10057 # number of ReadReq MSHR misses -system.cpu.icache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked -system.cpu.icache.avg_blocked_cycles_no_targets 3513.269231 # average number of cycles each access was blocked -system.cpu.icache.avg_refs 1746.387988 # Average number of references to valid blocks. +system.cpu.icache.ReadReq_accesses 19380281 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 3416.377011 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 2534.518183 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 19366483 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 47139170 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000712 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 13798 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 3761 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 25438959 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000518 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 10037 # 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 1929.509116 # 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 26 # 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 91345 # 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 17576948 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 3407.568545 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 2506.978423 # average overall mshr miss latency -system.cpu.icache.demand_hits 17563424 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 46083957 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000769 # miss rate for demand accesses -system.cpu.icache.demand_misses 13524 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 3467 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 25212682 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000572 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 10057 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 19380281 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 3416.377011 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 2534.518183 # average overall mshr miss latency +system.cpu.icache.demand_hits 19366483 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 47139170 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000712 # miss rate for demand accesses +system.cpu.icache.demand_misses 13798 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 3761 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 25438959 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000518 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 10037 # 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 17576948 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 3407.568545 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 2506.978423 # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_uncacheable_latency no value # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 17563424 # number of overall hits -system.cpu.icache.overall_miss_latency 46083957 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000769 # miss rate for overall accesses -system.cpu.icache.overall_misses 13524 # number of overall misses -system.cpu.icache.overall_mshr_hits 3467 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 25212682 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000572 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 10057 # number of overall MSHR misses +system.cpu.icache.overall_accesses 19380281 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 3416.377011 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 2534.518183 # 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 19366483 # number of overall hits +system.cpu.icache.overall_miss_latency 47139170 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000712 # miss rate for overall accesses +system.cpu.icache.overall_misses 13798 # number of overall misses +system.cpu.icache.overall_mshr_hits 3761 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 25438959 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000518 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 10037 # 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 @@ -215,162 +215,162 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated 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 8145 # number of replacements -system.cpu.icache.sampled_refs 10057 # Sample count of references to valid blocks. +system.cpu.icache.replacements 8123 # number of replacements +system.cpu.icache.sampled_refs 10037 # 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 1487.085502 # Cycle average of tags in use -system.cpu.icache.total_refs 17563424 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1498.249784 # Cycle average of tags in use +system.cpu.icache.total_refs 19366483 # 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 33641765 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 12581618 # Number of branches executed -system.cpu.iew.EXEC:nop 11617565 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.388001 # Inst execution rate -system.cpu.iew.EXEC:refs 31473535 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 7134398 # Number of stores executed +system.cpu.idleCycles 32049933 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 12923262 # Number of branches executed +system.cpu.iew.EXEC:nop 13162253 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.241494 # Inst execution rate +system.cpu.iew.EXEC:refs 31990682 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 7220394 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 88408054 # num instructions consuming a value -system.cpu.iew.WB:count 97920299 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.731090 # average fanout of values written-back +system.cpu.iew.WB:consumers 91915926 # num instructions consuming a value +system.cpu.iew.WB:count 100065162 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.718590 # 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 64634219 # num instructions producing a value -system.cpu.iew.WB:rate 1.365821 # insts written-back per cycle -system.cpu.iew.WB:sent 98494929 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 2154192 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 104376 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 29553768 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 436 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 2191495 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 9396457 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 131107086 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 24339137 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 2193063 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 99510422 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 16363 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 66049838 # num instructions producing a value +system.cpu.iew.WB:rate 1.216196 # insts written-back per cycle +system.cpu.iew.WB:sent 100916733 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 2084205 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 596692 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 34568849 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 437 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 864110 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 10915344 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 150440832 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 24770288 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2226727 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 102146587 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 177017 # 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 879 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 6075840 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 34734 # Number of cycles IEW is unblocking -system.cpu.iew.lsq.thread.0.blockedLoads 9915 # Number of blocked loads due to partial load-store forwarding -system.cpu.iew.lsq.thread.0.cacheBlocked 36009 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 941599 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 3004 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.iewLSQFullEvents 827 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 8350763 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 211777 # 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 3149 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 865223 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 1107 # 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 23070 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 9915 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 9519355 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 2893762 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 23070 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 196104 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 1958088 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.799161 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.799161 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 101703485 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 167324 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 9618 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 14534436 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 4412649 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 167324 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 194984 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 1889221 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.736306 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.736306 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 104373314 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist (null) 7 0.00% # Type of FU issued - IntAlu 62578225 61.53% # Type of FU issued - IntMult 472394 0.46% # Type of FU issued + IntAlu 64752207 62.04% # Type of FU issued + IntMult 471285 0.45% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 2776755 2.73% # Type of FU issued - FloatCmp 115486 0.11% # Type of FU issued - FloatCvt 2376016 2.34% # Type of FU issued - FloatMult 302348 0.30% # Type of FU issued - FloatDiv 754954 0.74% # Type of FU issued - FloatSqrt 321 0.00% # Type of FU issued - MemRead 25019338 24.60% # Type of FU issued - MemWrite 7307641 7.19% # Type of FU issued + FloatAdd 2789912 2.67% # Type of FU issued + FloatCmp 115515 0.11% # Type of FU issued + FloatCvt 2364267 2.27% # Type of FU issued + FloatMult 305289 0.29% # Type of FU issued + FloatDiv 755087 0.72% # Type of FU issued + FloatSqrt 324 0.00% # Type of FU issued + MemRead 25418322 24.35% # Type of FU issued + MemWrite 7401099 7.09% # 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 1392706 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.013694 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 1952486 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.018707 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist -(null) 0 0.00% # attempts to use FU when none available -IntAlu 193189 13.87% # 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 1883 0.14% # attempts to use FU when none available -FloatCmp 96 0.01% # attempts to use FU when none available -FloatCvt 2836 0.20% # attempts to use FU when none available -FloatMult 2464 0.18% # attempts to use FU when none available -FloatDiv 659899 47.38% # attempts to use FU when none available -FloatSqrt 0 0.00% # attempts to use FU when none available -MemRead 465101 33.40% # attempts to use FU when none available -MemWrite 67238 4.83% # 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 + (null) 0 0.00% # attempts to use FU when none available + IntAlu 163325 8.36% # 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 1017 0.05% # attempts to use FU when none available + FloatCmp 0 0.00% # attempts to use FU when none available + FloatCvt 12505 0.64% # attempts to use FU when none available + FloatMult 2432 0.12% # attempts to use FU when none available + FloatDiv 905685 46.39% # attempts to use FU when none available + FloatSqrt 0 0.00% # attempts to use FU when none available + MemRead 774173 39.65% # attempts to use FU when none available + MemWrite 93349 4.78% # 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 71693337 +system.cpu.iq.ISSUE:issued_per_cycle.samples 82277149 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 27977053 3902.32% - 1 15408153 2149.18% - 2 12854527 1792.99% - 3 7056557 984.27% - 4 4494209 626.87% - 5 2427532 338.60% - 6 1097338 153.06% - 7 305661 42.63% - 8 72307 10.09% + 0 35738506 4343.67% + 1 18264427 2219.87% + 2 12740961 1548.54% + 3 6961052 846.05% + 4 4806764 584.22% + 5 2441659 296.76% + 6 994924 120.92% + 7 291934 35.48% + 8 36922 4.49% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.418590 # Inst issue rate -system.cpu.iq.iqInstsAdded 119489085 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 101703485 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 436 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 34413373 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 132312 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 47 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 28441004 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 12293 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 3855.809345 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2071.040418 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 7221 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 19556665 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.412593 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 5072 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 10504317 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.412593 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 5072 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 105 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 105 # number of Writeback hits -system.cpu.l2cache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked -system.cpu.l2cache.avg_blocked_cycles_no_targets no value # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 1.444401 # Average number of references to valid blocks. +system.cpu.iq.ISSUE:rate 1.268558 # Inst issue rate +system.cpu.iq.iqInstsAdded 137278142 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 104373314 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 437 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 52505275 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 293840 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 48 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 49588547 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadReq_accesses 12278 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4378.207161 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2293.937242 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 7195 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 22254427 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.413993 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 5083 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 11660083 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.413993 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 5083 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 106 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 106 # number of Writeback hits +system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked +system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked +system.cpu.l2cache.avg_refs 1.436356 # Average number of references to valid blocks. system.cpu.l2cache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 12293 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 3855.809345 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2071.040418 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 7221 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 19556665 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.412593 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 5072 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 12278 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4378.207161 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2293.937242 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 7195 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 22254427 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.413993 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 5083 # 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 10504317 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.412593 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 5072 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 11660083 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.413993 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 5083 # 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 12398 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 3855.809345 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2071.040418 # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no value # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 7326 # number of overall hits -system.cpu.l2cache.overall_miss_latency 19556665 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.409098 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 5072 # number of overall misses +system.cpu.l2cache.overall_accesses 12384 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4378.207161 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2293.937242 # 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 7301 # number of overall hits +system.cpu.l2cache.overall_miss_latency 22254427 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.410449 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 5083 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 10504317 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.409098 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 5072 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 11660083 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.410449 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 5083 # 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 @@ -383,31 +383,31 @@ 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 5072 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 5083 # 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 3261.872945 # Cycle average of tags in use -system.cpu.l2cache.total_refs 7326 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 3292.223620 # Cycle average of tags in use +system.cpu.l2cache.total_refs 7301 # 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 71693337 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 812700 # Number of cycles rename is blocking +system.cpu.numCycles 82277149 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 2387077 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 68427361 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 369396 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 37208342 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 772307 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 122 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 182866276 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 141908898 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 104156212 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 26334995 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 6075840 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 1200845 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 35728851 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 60615 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 555 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 2896644 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 544 # count of temporary serializing insts renamed -system.cpu.timesIdled 10380 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 1473927 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 41553511 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 1059964 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 61 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 206590907 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 160246119 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 117849091 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 27232157 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 8350763 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 2654523 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 49421730 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 99118 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 461 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 5497153 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 451 # count of temporary serializing insts renamed +system.cpu.timesIdled 10204 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 389 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/smred.out b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/smred.out index 00387ae5c..98777e0af 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/smred.out +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/smred.out @@ -66,7 +66,7 @@ The rand generator seed was at utemp() : 1 I T fds Wire Penalty P_lim Epct binC rowC acc s/p early FDs MRs 1 500 0 929 592 160 30.0 1.0 3.0 84.2 34.7 0.0 0 40 2 491 0 876 106 726 0.0 0.8 2.5 80.0 18.5 0.0 0 46 - 3 482 0 822 273 372 0.0 0.5 1.5 80.8 21.2 0.0 0 46 + 3 482 0 822 273 372 0.0 0.5 1.5 80.8 21.3 0.0 0 46 4 474 0 826 53 247 0.0 0.5 0.9 65.0 21.9 0.0 0 48 5 465 8 987 73 190 0.0 0.5 0.5 50.0 38.3 0.0 0 46 6 457 8 851 67 226 0.0 0.5 0.5 53.8 42.9 0.0 0 52 @@ -103,7 +103,7 @@ The rand generator seed was at utemp() : 1 37 264 4 875 106 133 0.0 0.5 0.5 31.7 55.3 0.0 0 52 38 260 8 1023 145 149 0.0 0.6 0.5 28.7 65.0 0.0 0 52 39 255 8 801 151 173 0.0 0.9 0.5 41.7 41.2 0.0 0 48 - 40 251 8 741 104 159 0.0 0.8 0.5 36.2 47.5 0.0 0 48 + 40 251 8 741 104 159 0.0 0.8 0.5 36.3 47.5 0.0 0 48 41 246 8 828 108 149 0.0 0.5 0.5 34.6 50.9 0.0 0 50 42 242 8 947 128 132 0.0 0.7 0.5 34.2 39.0 0.0 0 50 43 238 8 917 101 142 0.0 0.8 0.5 34.4 50.9 0.0 0 48 diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/stderr b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/stderr index eb1796ead..f33d007a7 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/stderr +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/stderr @@ -1,2 +1,2 @@ -0: system.remote_gdb.listener: listening for remote gdb on port 7000 warn: Entering event queue @ 0. Starting simulation... +warn: Increasing stack size by one page. |