diff options
Diffstat (limited to 'tests/quick/00.hello')
30 files changed, 962 insertions, 883 deletions
diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini index f112ef506..f145eee43 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload +children=dcache fuPool icache l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -86,6 +86,7 @@ smtROBPolicy=Partitioned smtROBThreshold=100 squashWidth=8 system=system +tracer=system.cpu.tracer trapLatency=13 wbDepth=1 wbWidth=8 @@ -95,12 +96,9 @@ icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -118,12 +116,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=20 trace_addr=0 @@ -139,11 +135,11 @@ FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUL [system.cpu.fuPool.FUList0] type=FUDesc -children=opList0 +children=opList count=6 -opList=system.cpu.fuPool.FUList0.opList0 +opList=system.cpu.fuPool.FUList0.opList -[system.cpu.fuPool.FUList0.opList0] +[system.cpu.fuPool.FUList0.opList] type=OpDesc issueLat=1 opClass=IntAlu @@ -217,11 +213,11 @@ opLat=24 [system.cpu.fuPool.FUList4] type=FUDesc -children=opList0 +children=opList count=0 -opList=system.cpu.fuPool.FUList4.opList0 +opList=system.cpu.fuPool.FUList4.opList -[system.cpu.fuPool.FUList4.opList0] +[system.cpu.fuPool.FUList4.opList] type=OpDesc issueLat=1 opClass=MemRead @@ -229,11 +225,11 @@ opLat=1 [system.cpu.fuPool.FUList5] type=FUDesc -children=opList0 +children=opList count=0 -opList=system.cpu.fuPool.FUList5.opList0 +opList=system.cpu.fuPool.FUList5.opList -[system.cpu.fuPool.FUList5.opList0] +[system.cpu.fuPool.FUList5.opList] type=OpDesc issueLat=1 opClass=MemWrite @@ -259,11 +255,11 @@ opLat=1 [system.cpu.fuPool.FUList7] type=FUDesc -children=opList0 +children=opList count=1 -opList=system.cpu.fuPool.FUList7.opList0 +opList=system.cpu.fuPool.FUList7.opList -[system.cpu.fuPool.FUList7.opList0] +[system.cpu.fuPool.FUList7.opList] type=OpDesc issueLat=3 opClass=IprAccess @@ -271,12 +267,9 @@ opLat=3 [system.cpu.icache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -294,12 +287,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=20 trace_addr=0 @@ -310,12 +301,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -333,12 +321,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -356,6 +342,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt index 2ac86dd84..02095a557 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/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 522 # Number of BTB hits -global.BPredUnit.BTBLookups 1584 # Number of BTB lookups -global.BPredUnit.RASInCorrect 57 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 422 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 1088 # Number of conditional branches predicted -global.BPredUnit.lookups 1837 # Number of BP lookups -global.BPredUnit.usedRAS 241 # Number of times the RAS was used to get a target. -host_inst_rate 39303 # Simulator instruction rate (inst/s) -host_mem_usage 153768 # Number of bytes of host memory used -host_seconds 0.14 # Real time elapsed on the host -host_tick_rate 32016268 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 17 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 127 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 1874 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1142 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 543 # Number of BTB hits +global.BPredUnit.BTBLookups 1720 # Number of BTB lookups +global.BPredUnit.RASInCorrect 59 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 423 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 1175 # Number of conditional branches predicted +global.BPredUnit.lookups 2025 # Number of BP lookups +global.BPredUnit.usedRAS 277 # Number of times the RAS was used to get a target. +host_inst_rate 29843 # Simulator instruction rate (inst/s) +host_mem_usage 154572 # Number of bytes of host memory used +host_seconds 0.19 # Real time elapsed on the host +host_tick_rate 22095832 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 31 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 133 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 1967 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1200 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5623 # Number of instructions simulated -sim_seconds 0.000005 # Number of seconds simulated -sim_ticks 4589500 # Number of ticks simulated +sim_seconds 0.000004 # Number of seconds simulated +sim_ticks 4170500 # Number of ticks simulated system.cpu.commit.COM:branches 862 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 104 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 105 # 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 8521 +system.cpu.commit.COM:committed_per_cycle.samples 7614 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 6200 7276.14% - 1 1160 1361.34% - 2 469 550.40% - 3 177 207.72% - 4 131 153.74% - 5 98 115.01% - 6 109 127.92% - 7 73 85.67% - 8 104 122.05% + 0 5315 6980.56% + 1 1182 1552.40% + 2 399 524.03% + 3 192 252.17% + 4 125 164.17% + 5 99 130.02% + 6 130 170.74% + 7 67 88.00% + 8 105 137.90% 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 979 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 1791 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 350 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 349 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 5640 # 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 3571 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 3957 # The number of squashed insts skipped by commit system.cpu.committedInsts 5623 # Number of Instructions Simulated system.cpu.committedInsts_total 5623 # Number of Instructions Simulated -system.cpu.cpi 1.636315 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.636315 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 1470 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 5932.330827 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5380 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 1337 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 789000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.090476 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 133 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 33 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 538000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.068027 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 100 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 812 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 4504.373178 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5116.438356 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 469 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 1545000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.422414 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 343 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 270 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 373500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.089901 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 73 # number of WriteReq MSHR misses +system.cpu.cpi 1.483372 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.483372 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 1487 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 8188.118812 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5495.049505 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 1386 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 827000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.067922 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 101 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 34 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 555000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.067922 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 101 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 561 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 18316.091954 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5068.965517 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 474 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 1593500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.155080 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 87 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 251 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 441000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.155080 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 87 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 10.439306 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 10.770115 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 2282 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 4903.361345 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5268.786127 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1806 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 2334000 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.208589 # miss rate for demand accesses -system.cpu.dcache.demand_misses 476 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 303 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 911500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.075811 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 173 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 2048 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 12875 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5297.872340 # average overall mshr miss latency +system.cpu.dcache.demand_hits 1860 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 2420500 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.091797 # miss rate for demand accesses +system.cpu.dcache.demand_misses 188 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 285 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 996000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.091797 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 188 # 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 2282 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 4903.361345 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5268.786127 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 2048 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 12875 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5297.872340 # 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 1806 # number of overall hits -system.cpu.dcache.overall_miss_latency 2334000 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.208589 # miss rate for overall accesses -system.cpu.dcache.overall_misses 476 # number of overall misses -system.cpu.dcache.overall_mshr_hits 303 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 911500 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.075811 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 173 # number of overall MSHR misses +system.cpu.dcache.overall_hits 1860 # number of overall hits +system.cpu.dcache.overall_miss_latency 2420500 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.091797 # miss rate for overall accesses +system.cpu.dcache.overall_misses 188 # number of overall misses +system.cpu.dcache.overall_mshr_hits 285 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 996000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.091797 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 188 # 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 @@ -119,91 +119,91 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 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 0 # number of replacements -system.cpu.dcache.sampled_refs 173 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 174 # 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 112.669258 # Cycle average of tags in use -system.cpu.dcache.total_refs 1806 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 112.600183 # Cycle average of tags in use +system.cpu.dcache.total_refs 1874 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 389 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 75 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 143 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 10466 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 6230 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 1855 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 679 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 228 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:BlockedCycles 391 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 82 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 164 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 11387 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 5174 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 2002 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 726 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 244 # Number of squashed instructions handled by decode system.cpu.decode.DECODE:UnblockCycles 48 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 1837 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 1469 # Number of cache lines fetched -system.cpu.fetch.Cycles 3456 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 267 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 11417 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 455 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.199652 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 1469 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 763 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.240843 # Number of inst fetches per cycle +system.cpu.fetch.Branches 2025 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 1529 # Number of cache lines fetched +system.cpu.fetch.Cycles 3690 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 212 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 12463 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 457 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.242777 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 1529 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 820 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.494185 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 9201 +system.cpu.fetch.rateDist.samples 8341 system.cpu.fetch.rateDist.min_value 0 - 0 7216 7842.63% - 1 168 182.59% - 2 148 160.85% - 3 136 147.81% - 4 214 232.58% - 5 138 149.98% - 6 177 192.37% - 7 95 103.25% - 8 909 987.94% + 0 6181 7410.38% + 1 173 207.41% + 2 174 208.61% + 3 151 181.03% + 4 219 262.56% + 5 157 188.23% + 6 179 214.60% + 7 102 122.29% + 8 1005 1204.89% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 1469 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5381.818182 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4530.448718 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1139 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 1776000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.224643 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 330 # number of ReadReq misses +system.cpu.icache.ReadReq_accesses 1511 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 5621.019108 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4464.968153 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 1197 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 1765000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.207809 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 314 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_hits 18 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 1413500 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.212389 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 312 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_miss_latency 1402000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.207809 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 314 # 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 3.650641 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 3.812102 # Average number of references to valid blocks. system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 1469 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5381.818182 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4530.448718 # average overall mshr miss latency -system.cpu.icache.demand_hits 1139 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 1776000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.224643 # miss rate for demand accesses -system.cpu.icache.demand_misses 330 # number of demand (read+write) misses +system.cpu.icache.demand_accesses 1511 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 5621.019108 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4464.968153 # average overall mshr miss latency +system.cpu.icache.demand_hits 1197 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 1765000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.207809 # miss rate for demand accesses +system.cpu.icache.demand_misses 314 # number of demand (read+write) misses system.cpu.icache.demand_mshr_hits 18 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 1413500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.212389 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 312 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_miss_latency 1402000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.207809 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 314 # 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 1469 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5381.818182 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4530.448718 # average overall mshr miss latency +system.cpu.icache.overall_accesses 1511 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 5621.019108 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4464.968153 # 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 1139 # number of overall hits -system.cpu.icache.overall_miss_latency 1776000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.224643 # miss rate for overall accesses -system.cpu.icache.overall_misses 330 # number of overall misses +system.cpu.icache.overall_hits 1197 # number of overall hits +system.cpu.icache.overall_miss_latency 1765000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.207809 # miss rate for overall accesses +system.cpu.icache.overall_misses 314 # number of overall misses system.cpu.icache.overall_mshr_hits 18 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 1413500 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.212389 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 312 # number of overall MSHR misses +system.cpu.icache.overall_mshr_miss_latency 1402000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.207809 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 314 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -216,76 +216,76 @@ system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.icache.replacements 0 # number of replacements -system.cpu.icache.sampled_refs 312 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 314 # 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 165.921810 # Cycle average of tags in use -system.cpu.icache.total_refs 1139 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 167.838424 # Cycle average of tags in use +system.cpu.icache.total_refs 1197 # 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 2474 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 1144 # Number of branches executed -system.cpu.iew.EXEC:nop 40 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.835018 # Inst execution rate -system.cpu.iew.EXEC:refs 2519 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 977 # Number of stores executed +system.cpu.idleCycles 1997 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 1159 # Number of branches executed +system.cpu.iew.EXEC:nop 43 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.933581 # Inst execution rate +system.cpu.iew.EXEC:refs 2561 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 971 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 5193 # num instructions consuming a value -system.cpu.iew.WB:count 7387 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.742923 # average fanout of values written-back +system.cpu.iew.WB:consumers 5329 # num instructions consuming a value +system.cpu.iew.WB:count 7480 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.739351 # 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 3858 # num instructions producing a value -system.cpu.iew.WB:rate 0.802848 # insts written-back per cycle -system.cpu.iew.WB:sent 7452 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 373 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 3940 # num instructions producing a value +system.cpu.iew.WB:rate 0.896775 # insts written-back per cycle +system.cpu.iew.WB:sent 7559 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 402 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 4 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 1874 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 22 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 302 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 1142 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 9228 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 1542 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 285 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 7683 # Number of executed instructions +system.cpu.iew.iewDispLoadInsts 1967 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 23 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 240 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 1200 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 9614 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 1590 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 364 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 7787 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 679 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 726 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 50 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 4 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 48 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 3 # 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 63 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 70 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 1 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 895 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 330 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 63 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 262 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 111 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.611129 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.611129 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 7968 # Type of FU issued +system.cpu.iew.lsq.thread.0.squashedLoads 988 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 388 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 70 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 287 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 115 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.674140 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.674140 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8151 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist - No_OpClass 2 0.03% # Type of FU issued - IntAlu 5314 66.69% # Type of FU issued + No_OpClass 2 0.02% # Type of FU issued + IntAlu 5422 66.52% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 2 0.03% # Type of FU issued + FloatAdd 2 0.02% # Type of FU issued FloatCmp 0 0.00% # Type of FU issued FloatCvt 0 0.00% # Type of FU issued FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 1659 20.82% # Type of FU issued - MemWrite 990 12.42% # Type of FU issued + MemRead 1720 21.10% # Type of FU issued + MemWrite 1004 12.32% # 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 105 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.013178 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 104 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.012759 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist No_OpClass 0 0.00% # attempts to use FU when none available IntAlu 0 0.00% # attempts to use FU when none available @@ -297,77 +297,96 @@ 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 70 66.67% # attempts to use FU when none available - MemWrite 35 33.33% # attempts to use FU when none available + MemRead 70 67.31% # attempts to use FU when none available + MemWrite 34 32.69% # 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 9201 +system.cpu.iq.ISSUE:issued_per_cycle.samples 8341 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 5952 6468.86% - 1 1111 1207.48% - 2 928 1008.59% - 3 433 470.60% - 4 378 410.82% - 5 251 272.80% - 6 111 120.64% - 7 27 29.34% - 8 10 10.87% + 0 5104 6119.17% + 1 1084 1299.60% + 2 829 993.89% + 3 533 639.01% + 4 366 438.80% + 5 258 309.32% + 6 126 151.06% + 7 28 33.57% + 8 13 15.59% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.865993 # Inst issue rate -system.cpu.iq.iqInstsAdded 9166 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 7968 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 22 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 3154 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.ISSUE:rate 0.977221 # Inst issue rate +system.cpu.iq.iqInstsAdded 9548 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 8151 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 23 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 3578 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedInstsIssued 22 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 5 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 2035 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 483 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4644.927536 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2467.908903 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 2243500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 483 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 1192000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 483 # number of ReadReq MSHR misses +system.cpu.iq.iqSquashedNonSpecRemoved 6 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 2360 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 73 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 3643.835616 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2643.835616 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 266000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 73 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 193000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 73 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 415 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 3406.779661 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2406.779661 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 2 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1407000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.995181 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 413 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 994000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.995181 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 413 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 3392.857143 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2392.857143 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 47500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 33500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 14 # number of UpgradeReq MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked 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 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.005013 # 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 483 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4644.927536 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2467.908903 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 2243500 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 483 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 488 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 3442.386831 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2442.386831 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 2 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1673000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.995902 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 486 # 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 1192000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 483 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 1187000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.995902 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 486 # 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 483 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4644.927536 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2467.908903 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 488 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 3442.386831 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2442.386831 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 2243500 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 483 # number of overall misses +system.cpu.l2cache.overall_hits 2 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1673000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.995902 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 486 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 1192000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 483 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 1187000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.995902 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 486 # 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 @@ -380,29 +399,29 @@ 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 483 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 399 # 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 278.204751 # Cycle average of tags in use -system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 223.758944 # Cycle average of tags in use +system.cpu.l2cache.total_refs 2 # 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 9201 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 15 # Number of cycles rename is blocking +system.cpu.numCycles 8341 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 14 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 4051 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 6382 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 70 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 12837 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 10018 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 7477 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 1754 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 679 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 101 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 3426 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 270 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:IdleCycles 5339 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 71 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 13891 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 10852 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 8114 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 1888 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 726 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 102 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 4063 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 272 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 380 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 20 # count of temporary serializing insts renamed -system.cpu.timesIdled 26 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:skidInsts 382 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 21 # count of temporary serializing insts renamed +system.cpu.timesIdled 3 # 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/quick/00.hello/ref/alpha/linux/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout index 142cb9695..22c3e0435 100644 --- a/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 21 2007 21:25:27 -M5 started Fri Jun 22 00:04:38 2007 +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:12 2007 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/linux/o3-timing tests/run.py quick/00.hello/alpha/linux/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 4589500 because target called exit() +Exiting @ tick 4170500 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini index e4dfe86d3..d025afdec 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=tracer workload clock=500 cpu_id=0 defer_registration=false @@ -25,11 +25,15 @@ phase=0 progress_interval=0 simulate_stalls=false system=system +tracer=system.cpu.tracer width=1 workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/m5stats.txt index f1c7bd968..f87ad2cd6 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/m5stats.txt @@ -1,8 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 93019 # Simulator instruction rate (inst/s) -host_seconds 0.06 # Real time elapsed on the host -host_tick_rate 46199079 # Simulator tick rate (ticks/s) +host_inst_rate 109073 # Simulator instruction rate (inst/s) +host_mem_usage 148564 # Number of bytes of host memory used +host_seconds 0.05 # Real time elapsed on the host +host_tick_rate 54123810 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5642 # Number of instructions simulated sim_seconds 0.000003 # Number of seconds simulated diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout index 58fc0e374..0bec3d18f 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/simple-atomic/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 10 2007 14:06:20 -M5 started Sun Jun 10 14:22:34 2007 -M5 executing on iceaxe -command line: /Users/nate/build/outgoing/build/ALPHA_SE/m5.debug -d /Users/nate/build/outgoing/build/ALPHA_SE/tests/debug/quick/00.hello/alpha/linux/simple-atomic tests/run.py quick/00.hello/alpha/linux/simple-atomic +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:12 2007 +M5 executing on zizzer.eecs.umich.edu +command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/linux/simple-atomic tests/run.py quick/00.hello/alpha/linux/simple-atomic Global frequency set at 1000000000000 ticks per second Exiting @ tick 2820500 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini index 47315cc1d..5ae318852 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus workload +children=dcache icache l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false @@ -24,17 +24,16 @@ max_loads_any_thread=0 phase=0 progress_interval=0 system=system +tracer=system.cpu.tracer workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -52,12 +51,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -68,11 +65,9 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.icache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -90,12 +85,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -106,11 +99,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=10000 lifo=false @@ -128,12 +119,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -151,6 +140,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt index 1b70f10b3..db7224c2e 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt @@ -1,12 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 54390 # Simulator instruction rate (inst/s) -host_seconds 0.10 # Real time elapsed on the host -host_tick_rate 126525357 # Simulator tick rate (ticks/s) +host_inst_rate 65923 # Simulator instruction rate (inst/s) +host_mem_usage 154180 # Number of bytes of host memory used +host_seconds 0.09 # Real time elapsed on the host +host_tick_rate 155349854 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5642 # Number of instructions simulated sim_seconds 0.000013 # Number of seconds simulated -sim_ticks 13168000 # Number of ticks simulated +sim_ticks 13359000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 979 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 14000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 13000 # average ReadReq mshr miss latency @@ -20,13 +21,13 @@ system.cpu.dcache.ReadReq_mshr_misses 92 # nu system.cpu.dcache.WriteReq_accesses 812 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 14000 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 13000 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 739 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 1022000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.089901 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 73 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_miss_latency 949000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.089901 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 73 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_hits 725 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 1218000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.107143 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 87 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_miss_latency 1131000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.107143 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 87 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_refs 9.854545 # Average number of references to valid blocks. @@ -38,14 +39,14 @@ system.cpu.dcache.cache_copies 0 # nu system.cpu.dcache.demand_accesses 1791 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 13000 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1626 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 2310000 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.092127 # miss rate for demand accesses -system.cpu.dcache.demand_misses 165 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 1612 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 2506000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.099944 # miss rate for demand accesses +system.cpu.dcache.demand_misses 179 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 2145000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.092127 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 165 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 2327000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.099944 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 179 # 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 @@ -53,14 +54,14 @@ system.cpu.dcache.overall_accesses 1791 # nu system.cpu.dcache.overall_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 13000 # 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 1626 # number of overall hits -system.cpu.dcache.overall_miss_latency 2310000 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.092127 # miss rate for overall accesses -system.cpu.dcache.overall_misses 165 # number of overall misses +system.cpu.dcache.overall_hits 1612 # number of overall hits +system.cpu.dcache.overall_miss_latency 2506000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.099944 # miss rate for overall accesses +system.cpu.dcache.overall_misses 179 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 2145000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.092127 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 165 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 2327000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.099944 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 179 # 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 @@ -75,18 +76,18 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 165 # 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 103.640117 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 103.895955 # Cycle average of tags in use system.cpu.dcache.total_refs 1626 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 5643 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 13960.288809 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 12960.288809 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_avg_miss_latency 13992.779783 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 12992.779783 # average ReadReq mshr miss latency system.cpu.icache.ReadReq_hits 5366 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 3867000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_latency 3876000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.049087 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 277 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_miss_latency 3590000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 3599000 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.049087 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 277 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked @@ -98,29 +99,29 @@ system.cpu.icache.blocked_cycles_no_mshrs 0 # n 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 5643 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 13960.288809 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 12960.288809 # average overall mshr miss latency +system.cpu.icache.demand_avg_miss_latency 13992.779783 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 12992.779783 # average overall mshr miss latency system.cpu.icache.demand_hits 5366 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 3867000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency 3876000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.049087 # miss rate for demand accesses system.cpu.icache.demand_misses 277 # number of demand (read+write) misses system.cpu.icache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 3590000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 3599000 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.049087 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 277 # 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 5643 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 13960.288809 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 12960.288809 # average overall mshr miss latency +system.cpu.icache.overall_avg_miss_latency 13992.779783 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 12992.779783 # 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 5366 # number of overall hits -system.cpu.icache.overall_miss_latency 3867000 # number of overall miss cycles +system.cpu.icache.overall_miss_latency 3876000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.049087 # miss rate for overall accesses system.cpu.icache.overall_misses 277 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 3590000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 3599000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.049087 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 277 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles @@ -137,53 +138,72 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 277 # 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 129.241810 # Cycle average of tags in use +system.cpu.icache.tagsinuse 129.745202 # Cycle average of tags in use system.cpu.icache.total_refs 5366 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 441 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 13000 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_accesses 73 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 12000 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 876000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 73 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 803000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 73 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 369 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 12000 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 11000 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 5733000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 441 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4851000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 441 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_hits 1 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 4416000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.997290 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 368 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 4048000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.997290 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 368 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 12000 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 11000 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 168000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 154000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 14 # number of UpgradeReq MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked 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 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.002825 # 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 441 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.demand_accesses 442 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 11000 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 5733000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses +system.cpu.l2cache.demand_hits 1 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 5292000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.997738 # miss rate for demand accesses system.cpu.l2cache.demand_misses 441 # 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 4851000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.997738 # mshr miss rate for demand accesses system.cpu.l2cache.demand_mshr_misses 441 # 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 441 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.overall_accesses 442 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 11000 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 5733000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses +system.cpu.l2cache.overall_hits 1 # number of overall hits +system.cpu.l2cache.overall_miss_latency 5292000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.997738 # miss rate for overall accesses system.cpu.l2cache.overall_misses 441 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.l2cache.overall_mshr_miss_latency 4851000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.997738 # mshr miss rate for overall accesses system.cpu.l2cache.overall_mshr_misses 441 # 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 @@ -197,14 +217,14 @@ 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 441 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 354 # 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 232.802947 # Cycle average of tags in use -system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 179.464793 # Cycle average of tags in use +system.cpu.l2cache.total_refs 1 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 13168000 # number of cpu cycles simulated +system.cpu.numCycles 13359000 # number of cpu cycles simulated system.cpu.num_insts 5642 # Number of instructions executed system.cpu.num_refs 1792 # Number of memory references system.cpu.workload.PROG:num_syscalls 17 # Number of system calls diff --git a/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout index 501ba5063..d25a0624e 100644 --- a/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/linux/simple-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 10 2007 14:06:20 -M5 started Sun Jun 10 14:22:35 2007 -M5 executing on iceaxe -command line: /Users/nate/build/outgoing/build/ALPHA_SE/m5.debug -d /Users/nate/build/outgoing/build/ALPHA_SE/tests/debug/quick/00.hello/alpha/linux/simple-timing tests/run.py quick/00.hello/alpha/linux/simple-timing +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:13 2007 +M5 executing on zizzer.eecs.umich.edu +command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/linux/simple-timing tests/run.py quick/00.hello/alpha/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 13168000 because target called exit() +Exiting @ tick 13359000 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini index 36a50c983..ca7690f17 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload +children=dcache fuPool icache l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -86,6 +86,7 @@ smtROBPolicy=Partitioned smtROBThreshold=100 squashWidth=8 system=system +tracer=system.cpu.tracer trapLatency=13 wbDepth=1 wbWidth=8 @@ -95,12 +96,9 @@ icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -118,12 +116,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=20 trace_addr=0 @@ -139,11 +135,11 @@ FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUL [system.cpu.fuPool.FUList0] type=FUDesc -children=opList0 +children=opList count=6 -opList=system.cpu.fuPool.FUList0.opList0 +opList=system.cpu.fuPool.FUList0.opList -[system.cpu.fuPool.FUList0.opList0] +[system.cpu.fuPool.FUList0.opList] type=OpDesc issueLat=1 opClass=IntAlu @@ -217,11 +213,11 @@ opLat=24 [system.cpu.fuPool.FUList4] type=FUDesc -children=opList0 +children=opList count=0 -opList=system.cpu.fuPool.FUList4.opList0 +opList=system.cpu.fuPool.FUList4.opList -[system.cpu.fuPool.FUList4.opList0] +[system.cpu.fuPool.FUList4.opList] type=OpDesc issueLat=1 opClass=MemRead @@ -229,11 +225,11 @@ opLat=1 [system.cpu.fuPool.FUList5] type=FUDesc -children=opList0 +children=opList count=0 -opList=system.cpu.fuPool.FUList5.opList0 +opList=system.cpu.fuPool.FUList5.opList -[system.cpu.fuPool.FUList5.opList0] +[system.cpu.fuPool.FUList5.opList] type=OpDesc issueLat=1 opClass=MemWrite @@ -259,11 +255,11 @@ opLat=1 [system.cpu.fuPool.FUList7] type=FUDesc -children=opList0 +children=opList count=1 -opList=system.cpu.fuPool.FUList7.opList0 +opList=system.cpu.fuPool.FUList7.opList -[system.cpu.fuPool.FUList7.opList0] +[system.cpu.fuPool.FUList7.opList] type=OpDesc issueLat=3 opClass=IprAccess @@ -271,12 +267,9 @@ opLat=3 [system.cpu.icache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -294,12 +287,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=20 trace_addr=0 @@ -310,12 +301,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -333,12 +321,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -356,6 +342,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt index d400dcd22..f575843e4 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 132 # Number of BTB hits -global.BPredUnit.BTBLookups 584 # Number of BTB lookups -global.BPredUnit.RASInCorrect 28 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 208 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 376 # Number of conditional branches predicted -global.BPredUnit.lookups 738 # Number of BP lookups -global.BPredUnit.usedRAS 140 # Number of times the RAS was used to get a target. -host_inst_rate 39805 # Simulator instruction rate (inst/s) -host_mem_usage 153128 # Number of bytes of host memory used -host_seconds 0.06 # Real time elapsed on the host -host_tick_rate 34110715 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 8 # Number of conflicting loads. +global.BPredUnit.BTBHits 146 # Number of BTB hits +global.BPredUnit.BTBLookups 613 # Number of BTB lookups +global.BPredUnit.RASInCorrect 32 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 212 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 393 # Number of conditional branches predicted +global.BPredUnit.lookups 777 # Number of BP lookups +global.BPredUnit.usedRAS 153 # Number of times the RAS was used to get a target. +host_inst_rate 24407 # Simulator instruction rate (inst/s) +host_mem_usage 153952 # Number of bytes of host memory used +host_seconds 0.10 # Real time elapsed on the host +host_tick_rate 19202153 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 7 # Number of conflicting loads. memdepunit.memDep.conflictingStores 7 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 608 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 357 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 635 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 367 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2387 # Number of instructions simulated sim_seconds 0.000002 # Number of seconds simulated -sim_ticks 2055000 # Number of ticks simulated +sim_ticks 1884000 # Number of ticks simulated system.cpu.commit.COM:branches 396 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 41 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 33 # 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 3910 +system.cpu.commit.COM:committed_per_cycle.samples 3543 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 2950 7544.76% - 1 266 680.31% - 2 336 859.34% - 3 131 335.04% - 4 76 194.37% - 5 65 166.24% - 6 27 69.05% - 7 18 46.04% - 8 41 104.86% + 0 2580 7281.96% + 1 265 747.95% + 2 337 951.17% + 3 138 389.50% + 4 67 189.11% + 5 69 194.75% + 6 32 90.32% + 7 22 62.09% + 8 33 93.14% 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 415 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 709 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 128 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 131 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 2576 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 4 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 978 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 1118 # The number of squashed insts skipped by commit system.cpu.committedInsts 2387 # Number of Instructions Simulated system.cpu.committedInsts_total 2387 # Number of Instructions Simulated -system.cpu.cpi 1.723083 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.723083 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 514 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 5391.304348 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4669.491525 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 445 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 372000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.134241 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 69 # number of ReadReq misses +system.cpu.cpi 1.578969 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.578969 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 518 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 6583.333333 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4891.666667 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 458 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 395000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.115830 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 60 # number of ReadReq misses system.cpu.dcache.ReadReq_mshr_hits 10 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 275500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.114786 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 59 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 294 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 5669.014085 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5020 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 223 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 402500 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.241497 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 71 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 46 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 125500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.085034 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 25 # number of WriteReq MSHR misses +system.cpu.dcache.ReadReq_mshr_miss_latency 293500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.115830 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 60 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 239 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 14216.216216 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5202.702703 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 202 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 526000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.154812 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 37 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 55 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 192500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.154812 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 37 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 7.952381 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 7.905882 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 808 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 5532.142857 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 4773.809524 # average overall mshr miss latency -system.cpu.dcache.demand_hits 668 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 774500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.173267 # miss rate for demand accesses -system.cpu.dcache.demand_misses 140 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 56 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 401000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.103960 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 84 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 757 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 9494.845361 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5010.309278 # average overall mshr miss latency +system.cpu.dcache.demand_hits 660 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 921000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.128137 # miss rate for demand accesses +system.cpu.dcache.demand_misses 97 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 65 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 486000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.128137 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 97 # 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 808 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 5532.142857 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 4773.809524 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 757 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 9494.845361 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5010.309278 # 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 668 # number of overall hits -system.cpu.dcache.overall_miss_latency 774500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.173267 # miss rate for overall accesses -system.cpu.dcache.overall_misses 140 # number of overall misses -system.cpu.dcache.overall_mshr_hits 56 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 401000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.103960 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 84 # number of overall MSHR misses +system.cpu.dcache.overall_hits 660 # number of overall hits +system.cpu.dcache.overall_miss_latency 921000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.128137 # miss rate for overall accesses +system.cpu.dcache.overall_misses 97 # number of overall misses +system.cpu.dcache.overall_mshr_hits 65 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 486000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.128137 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 97 # 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 @@ -119,89 +119,90 @@ system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 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 0 # number of replacements -system.cpu.dcache.sampled_refs 84 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 85 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 51.873008 # Cycle average of tags in use -system.cpu.dcache.total_refs 668 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 51.399169 # Cycle average of tags in use +system.cpu.dcache.total_refs 672 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 95 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 81 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 123 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 4033 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 3045 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 771 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 202 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 298 # Number of squashed instructions handled by decode -system.cpu.fetch.Branches 738 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 654 # Number of cache lines fetched -system.cpu.fetch.Cycles 1444 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 120 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 4685 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 218 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.179431 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 654 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 272 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.139071 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BlockedCycles 87 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 83 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 125 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 4218 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 2648 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 808 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 225 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 304 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 1 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 777 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 686 # Number of cache lines fetched +system.cpu.fetch.Cycles 1528 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 107 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 4951 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 223 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.206155 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 686 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 299 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.313611 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 4113 +system.cpu.fetch.rateDist.samples 3769 system.cpu.fetch.rateDist.min_value 0 - 0 3325 8084.12% - 1 32 77.80% - 2 80 194.51% - 3 50 121.57% - 4 99 240.70% - 5 52 126.43% - 6 39 94.82% - 7 35 85.10% - 8 401 974.96% + 0 2929 7771.29% + 1 36 95.52% + 2 88 233.48% + 3 54 143.27% + 4 108 286.55% + 5 55 145.93% + 6 40 106.13% + 7 42 111.44% + 8 417 1106.39% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 654 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5298.507463 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4556.451613 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 453 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 1065000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.307339 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 201 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 15 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 847500 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.284404 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_accesses 676 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 5629.032258 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4489.247312 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 490 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 1047000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.275148 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 186 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 10 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 835000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.275148 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 186 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 2.435484 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 2.634409 # Average number of references to valid blocks. system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 654 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5298.507463 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4556.451613 # average overall mshr miss latency -system.cpu.icache.demand_hits 453 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 1065000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.307339 # miss rate for demand accesses -system.cpu.icache.demand_misses 201 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 15 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 847500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.284404 # mshr miss rate for demand accesses +system.cpu.icache.demand_accesses 676 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 5629.032258 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4489.247312 # average overall mshr miss latency +system.cpu.icache.demand_hits 490 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 1047000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.275148 # miss rate for demand accesses +system.cpu.icache.demand_misses 186 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 10 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 835000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.275148 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 186 # 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 654 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5298.507463 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4556.451613 # average overall mshr miss latency +system.cpu.icache.overall_accesses 676 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 5629.032258 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4489.247312 # 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 453 # number of overall hits -system.cpu.icache.overall_miss_latency 1065000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.307339 # miss rate for overall accesses -system.cpu.icache.overall_misses 201 # number of overall misses -system.cpu.icache.overall_mshr_hits 15 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 847500 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.284404 # mshr miss rate for overall accesses +system.cpu.icache.overall_hits 490 # number of overall hits +system.cpu.icache.overall_miss_latency 1047000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.275148 # miss rate for overall accesses +system.cpu.icache.overall_misses 186 # number of overall misses +system.cpu.icache.overall_mshr_hits 10 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 835000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.275148 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 186 # 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 @@ -217,59 +218,59 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 186 # 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 106.293956 # Cycle average of tags in use -system.cpu.icache.total_refs 453 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 104.691657 # Cycle average of tags in use +system.cpu.icache.total_refs 490 # 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 2992 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 501 # Number of branches executed -system.cpu.iew.EXEC:nop 234 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.726477 # Inst execution rate -system.cpu.iew.EXEC:refs 878 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 333 # Number of stores executed +system.cpu.idleCycles 998 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 516 # Number of branches executed +system.cpu.iew.EXEC:nop 242 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.810295 # Inst execution rate +system.cpu.iew.EXEC:refs 894 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 334 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1652 # num instructions consuming a value -system.cpu.iew.WB:count 2914 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.799637 # average fanout of values written-back +system.cpu.iew.WB:consumers 1725 # num instructions consuming a value +system.cpu.iew.WB:count 2987 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.794203 # 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 1321 # num instructions producing a value -system.cpu.iew.WB:rate 0.708485 # insts written-back per cycle -system.cpu.iew.WB:sent 2931 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 135 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 1370 # num instructions producing a value +system.cpu.iew.WB:rate 0.792518 # insts written-back per cycle +system.cpu.iew.WB:sent 3007 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 146 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 0 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 608 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 7 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 179 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 357 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 3571 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 545 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 87 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 2988 # Number of executed instructions +system.cpu.iew.iewDispLoadInsts 635 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 6 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 92 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 367 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 3711 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 560 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 111 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 3054 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 202 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 225 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 22 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.forwLoads 24 # Number of loads that had data forwarded from stores system.cpu.iew.lsq.thread.0.ignoredResponses 0 # 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 10 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 12 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 193 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 63 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 10 # Number of memory order violations +system.cpu.iew.lsq.thread.0.squashedLoads 220 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 73 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 12 # Number of memory order violations system.cpu.iew.predictedNotTakenIncorrect 98 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 37 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.580355 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.580355 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 3075 # Type of FU issued +system.cpu.iew.predictedTakenIncorrect 48 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.633324 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.633324 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 3165 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 0 0.00% # Type of FU issued - IntAlu 2178 70.83% # Type of FU issued + IntAlu 2243 70.87% # Type of FU issued IntMult 1 0.03% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 0 0.00% # Type of FU issued @@ -278,16 +279,16 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 561 18.24% # Type of FU issued - MemWrite 335 10.89% # Type of FU issued + MemRead 581 18.36% # Type of FU issued + MemWrite 340 10.74% # 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 35 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.011382 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate 0.011058 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist No_OpClass 0 0.00% # attempts to use FU when none available - IntAlu 2 5.71% # attempts to use FU when none available + IntAlu 1 2.86% # attempts to use FU when none available IntMult 0 0.00% # attempts to use FU when none available IntDiv 0 0.00% # attempts to use FU when none available FloatAdd 0 0.00% # attempts to use FU when none available @@ -297,41 +298,60 @@ system.cpu.iq.ISSUE:fu_full.start_dist FloatDiv 0 0.00% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available MemRead 12 34.29% # attempts to use FU when none available - MemWrite 21 60.00% # attempts to use FU when none available + MemWrite 22 62.86% # attempts to use FU when none available IprAccess 0 0.00% # attempts to use FU when none available InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 4113 +system.cpu.iq.ISSUE:issued_per_cycle.samples 3769 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 2848 6924.39% - 1 479 1164.60% - 2 276 671.04% - 3 213 517.87% - 4 158 384.15% - 5 86 209.09% - 6 34 82.66% - 7 13 31.61% - 8 6 14.59% + 0 2469 6550.81% + 1 494 1310.69% + 2 274 726.98% + 3 234 620.85% + 4 152 403.29% + 5 87 230.83% + 6 40 106.13% + 7 14 37.15% + 8 5 13.27% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.747629 # Inst issue rate -system.cpu.iq.iqInstsAdded 3330 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 3075 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 7 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 790 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedNonSpecRemoved 3 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 409 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 270 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4509.259259 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2388.888889 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 1217500 # number of ReadReq miss cycles +system.cpu.iq.ISSUE:rate 0.839745 # Inst issue rate +system.cpu.iq.iqInstsAdded 3463 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 3165 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 6 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 947 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 1 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 2 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 468 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 25 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 3720 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2720 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 93000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 25 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 68000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 25 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 246 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 3357.723577 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2357.723577 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_miss_latency 826000 # number of ReadReq miss cycles system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 270 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 645000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_misses 246 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 580000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 270 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 246 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 13 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 3230.769231 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2230.769231 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 42000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 13 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 29000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 13 # number of UpgradeReq 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 0 # Average number of references to valid blocks. @@ -340,32 +360,32 @@ system.cpu.l2cache.blocked_no_targets 0 # nu system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 270 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4509.259259 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2388.888889 # average overall mshr miss latency +system.cpu.l2cache.demand_accesses 271 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 3391.143911 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2391.143911 # average overall mshr miss latency system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 1217500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 919000 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 270 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses 271 # 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 645000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 648000 # number of demand (read+write) MSHR miss cycles system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 270 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses 271 # 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 270 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4509.259259 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2388.888889 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 271 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 3391.143911 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2391.143911 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 1217500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 919000 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 270 # number of overall misses +system.cpu.l2cache.overall_misses 271 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 645000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 648000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 270 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses 271 # 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 @@ -378,28 +398,28 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 270 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 233 # 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 158.313436 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 129.636467 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks -system.cpu.numCycles 4113 # number of cpu cycles simulated +system.cpu.numCycles 3769 # number of cpu cycles simulated system.cpu.rename.RENAME:CommittedMaps 1768 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 3116 # Number of cycles rename is idle +system.cpu.rename.RENAME:IdleCycles 2724 # Number of cycles rename is idle system.cpu.rename.RENAME:LSQFullEvents 1 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 4416 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 3886 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 2777 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 700 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 202 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 6 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 1009 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 89 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 9 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 55 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 7 # count of temporary serializing insts renamed -system.cpu.timesIdled 8 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:RenameLookups 4613 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 4068 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 2909 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 733 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 225 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 7 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 1141 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 80 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 8 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 52 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 6 # count of temporary serializing insts renamed +system.cpu.timesIdled 2 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout index c276fcaea..79e638bb8 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 21 2007 21:25:27 -M5 started Fri Jun 22 00:04:44 2007 +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:13 2007 M5 executing on zizzer.eecs.umich.edu command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/o3-timing tests/run.py quick/00.hello/alpha/tru64/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 2055000 because target called exit() +Exiting @ tick 1884000 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini index 61db8446a..16ea738bc 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=tracer workload clock=500 cpu_id=0 defer_registration=false @@ -25,11 +25,15 @@ phase=0 progress_interval=0 simulate_stalls=false system=system +tracer=system.cpu.tracer width=1 workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt index 29351d427..dfc8b7f6b 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,8 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 111994 # Simulator instruction rate (inst/s) -host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 55017079 # Simulator tick rate (ticks/s) +host_inst_rate 34280 # Simulator instruction rate (inst/s) +host_mem_usage 147884 # Number of bytes of host memory used +host_seconds 0.08 # Real time elapsed on the host +host_tick_rate 17043200 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2578 # Number of instructions simulated sim_seconds 0.000001 # Number of seconds simulated diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout index f76500526..6e78c47eb 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 10 2007 14:06:20 -M5 started Sun Jun 10 14:22:37 2007 -M5 executing on iceaxe -command line: /Users/nate/build/outgoing/build/ALPHA_SE/m5.debug -d /Users/nate/build/outgoing/build/ALPHA_SE/tests/debug/quick/00.hello/alpha/tru64/simple-atomic tests/run.py quick/00.hello/alpha/tru64/simple-atomic +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:14 2007 +M5 executing on zizzer.eecs.umich.edu +command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-atomic tests/run.py quick/00.hello/alpha/tru64/simple-atomic Global frequency set at 1000000000000 ticks per second Exiting @ tick 1288500 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini index 5a336ab13..a9adf07b9 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus workload +children=dcache icache l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false @@ -24,17 +24,16 @@ max_loads_any_thread=0 phase=0 progress_interval=0 system=system +tracer=system.cpu.tracer workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -52,12 +51,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -68,11 +65,9 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.icache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -90,12 +85,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -106,11 +99,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=10000 lifo=false @@ -128,12 +119,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -151,6 +140,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt index 621520fa3..56479827d 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,12 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 51133 # Simulator instruction rate (inst/s) -host_seconds 0.05 # Real time elapsed on the host -host_tick_rate 127514531 # Simulator tick rate (ticks/s) +host_inst_rate 43962 # Simulator instruction rate (inst/s) +host_mem_usage 153564 # Number of bytes of host memory used +host_seconds 0.06 # Real time elapsed on the host +host_tick_rate 112042683 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2578 # Number of instructions simulated -sim_seconds 0.000006 # Number of seconds simulated -sim_ticks 6472000 # Number of ticks simulated +sim_seconds 0.000007 # Number of seconds simulated +sim_ticks 6615000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 415 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 14000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 13000 # average ReadReq mshr miss latency @@ -20,13 +21,13 @@ system.cpu.dcache.ReadReq_mshr_misses 55 # nu system.cpu.dcache.WriteReq_accesses 294 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 14000 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 13000 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 267 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 378000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.091837 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 27 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_miss_latency 351000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.091837 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 27 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_hits 256 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 532000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.129252 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 38 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_miss_latency 494000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.129252 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 38 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_refs 7.646341 # Average number of references to valid blocks. @@ -38,14 +39,14 @@ system.cpu.dcache.cache_copies 0 # nu system.cpu.dcache.demand_accesses 709 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 13000 # average overall mshr miss latency -system.cpu.dcache.demand_hits 627 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1148000 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.115656 # miss rate for demand accesses -system.cpu.dcache.demand_misses 82 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 616 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 1302000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.131171 # miss rate for demand accesses +system.cpu.dcache.demand_misses 93 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1066000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.115656 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 82 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 1209000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.131171 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 93 # 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 @@ -53,14 +54,14 @@ system.cpu.dcache.overall_accesses 709 # nu system.cpu.dcache.overall_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 13000 # 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 627 # number of overall hits -system.cpu.dcache.overall_miss_latency 1148000 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.115656 # miss rate for overall accesses -system.cpu.dcache.overall_misses 82 # number of overall misses +system.cpu.dcache.overall_hits 616 # number of overall hits +system.cpu.dcache.overall_miss_latency 1302000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.131171 # miss rate for overall accesses +system.cpu.dcache.overall_misses 93 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1066000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.115656 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 82 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 1209000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.131171 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 93 # 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 @@ -75,7 +76,7 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 82 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 50.002941 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 50.044147 # Cycle average of tags in use system.cpu.dcache.total_refs 627 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks @@ -137,20 +138,38 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 163 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 86.067224 # Cycle average of tags in use +system.cpu.icache.tagsinuse 86.205303 # Cycle average of tags in use system.cpu.icache.total_refs 2416 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 245 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 13000 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_accesses 27 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 12000 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 324000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 27 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 297000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 27 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 218 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 12000 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 11000 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 3185000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency 2616000 # number of ReadReq miss cycles system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 245 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 2695000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_misses 218 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 2398000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 245 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 218 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 11 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 12000 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 11000 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 132000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 11 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 121000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 11 # number of UpgradeReq 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 0 # Average number of references to valid blocks. @@ -160,10 +179,10 @@ system.cpu.l2cache.blocked_cycles_no_mshrs 0 # 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 245 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 11000 # average overall mshr miss latency system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 3185000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 2940000 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses system.cpu.l2cache.demand_misses 245 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits @@ -174,11 +193,11 @@ system.cpu.l2cache.fast_writes 0 # nu 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 245 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 11000 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 3185000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 2940000 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses system.cpu.l2cache.overall_misses 245 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits @@ -197,14 +216,14 @@ 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 245 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 207 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 136.108021 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 109.774164 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 6472000 # number of cpu cycles simulated +system.cpu.numCycles 6615000 # number of cpu cycles simulated system.cpu.num_insts 2578 # Number of instructions executed system.cpu.num_refs 710 # Number of memory references system.cpu.workload.PROG:num_syscalls 4 # Number of system calls diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout index 1c6780cf0..47fca6faf 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 10 2007 14:06:20 -M5 started Sun Jun 10 14:22:37 2007 -M5 executing on iceaxe -command line: /Users/nate/build/outgoing/build/ALPHA_SE/m5.debug -d /Users/nate/build/outgoing/build/ALPHA_SE/tests/debug/quick/00.hello/alpha/tru64/simple-timing tests/run.py quick/00.hello/alpha/tru64/simple-timing +M5 compiled Aug 3 2007 03:56:47 +M5 started Fri Aug 3 04:17:14 2007 +M5 executing on zizzer.eecs.umich.edu +command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-timing tests/run.py quick/00.hello/alpha/tru64/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 6472000 because target called exit() +Exiting @ tick 6615000 because target called exit() diff --git a/tests/quick/00.hello/ref/mips/linux/simple-atomic/config.ini b/tests/quick/00.hello/ref/mips/linux/simple-atomic/config.ini index ea3ba751b..c6807e6a7 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/mips/linux/simple-atomic/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=tracer workload clock=500 cpu_id=0 defer_registration=false @@ -25,11 +25,15 @@ phase=0 progress_interval=0 simulate_stalls=false system=system +tracer=system.cpu.tracer width=1 workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello @@ -53,7 +57,7 @@ bus_id=0 clock=1000 responder_set=false width=64 -port=system.physmem.port system.cpu.icache_port system.cpu.dcache_port +port=system.physmem.port[0] system.cpu.icache_port system.cpu.dcache_port [system.physmem] type=PhysicalMemory diff --git a/tests/quick/00.hello/ref/mips/linux/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/mips/linux/simple-atomic/m5stats.txt index 6a0c251b5..98d540d90 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/mips/linux/simple-atomic/m5stats.txt @@ -1,9 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 535701 # Simulator instruction rate (inst/s) -host_mem_usage 148368 # Number of bytes of host memory used -host_seconds 0.01 # Real time elapsed on the host -host_tick_rate 257653061 # Simulator tick rate (ticks/s) +host_inst_rate 25511 # Simulator instruction rate (inst/s) +host_mem_usage 149560 # Number of bytes of host memory used +host_seconds 0.22 # Real time elapsed on the host +host_tick_rate 12728361 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5657 # Number of instructions simulated sim_seconds 0.000003 # Number of seconds simulated diff --git a/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout b/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout index 7fb23e5a5..3919c7c81 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout @@ -6,8 +6,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 12:54:05 -M5 started Tue May 15 12:54:07 2007 +M5 compiled Aug 3 2007 04:06:41 +M5 started Fri Aug 3 04:31:09 2007 M5 executing on zizzer.eecs.umich.edu command line: build/MIPS_SE/m5.fast -d build/MIPS_SE/tests/fast/quick/00.hello/mips/linux/simple-atomic tests/run.py quick/00.hello/mips/linux/simple-atomic Global frequency set at 1000000000000 ticks per second diff --git a/tests/quick/00.hello/ref/mips/linux/simple-timing/config.ini b/tests/quick/00.hello/ref/mips/linux/simple-timing/config.ini index a5d4e6583..c52036289 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/mips/linux/simple-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus workload +children=dcache icache l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false @@ -24,17 +24,16 @@ max_loads_any_thread=0 phase=0 progress_interval=0 system=system +tracer=system.cpu.tracer workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -44,7 +43,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=10000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -52,12 +51,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -68,11 +65,9 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.icache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -82,7 +77,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=10000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -90,12 +85,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -106,11 +99,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=10000 lifo=false @@ -120,7 +111,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=100000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -128,12 +119,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -151,6 +140,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello @@ -174,7 +166,7 @@ bus_id=0 clock=1000 responder_set=false width=64 -port=system.physmem.port system.cpu.l2cache.mem_side +port=system.physmem.port[0] system.cpu.l2cache.mem_side [system.physmem] type=PhysicalMemory diff --git a/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt index 41bb7c8b7..985175cad 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/mips/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 273338 # Simulator instruction rate (inst/s) -host_mem_usage 153844 # Number of bytes of host memory used -host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 633390216 # Simulator tick rate (ticks/s) +host_inst_rate 45085 # Simulator instruction rate (inst/s) +host_mem_usage 155088 # Number of bytes of host memory used +host_seconds 0.13 # Real time elapsed on the host +host_tick_rate 101545982 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 5657 # Number of instructions simulated -sim_seconds 0.000013 # Number of seconds simulated -sim_ticks 13362000 # Number of ticks simulated +sim_seconds 0.000014 # Number of seconds simulated +sim_ticks 13544000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 1130 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 14000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 13000 # average ReadReq mshr miss latency @@ -21,13 +21,13 @@ system.cpu.dcache.ReadReq_mshr_misses 82 # nu system.cpu.dcache.WriteReq_accesses 924 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 14000 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 13000 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 874 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 700000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.054113 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 50 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_miss_latency 650000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.054113 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 50 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_hits 860 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 896000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.069264 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 64 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_miss_latency 832000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.069264 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 64 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_refs 14.560606 # Average number of references to valid blocks. @@ -39,14 +39,14 @@ system.cpu.dcache.cache_copies 0 # nu system.cpu.dcache.demand_accesses 2054 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency 13000 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1922 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1848000 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.064265 # miss rate for demand accesses -system.cpu.dcache.demand_misses 132 # number of demand (read+write) misses +system.cpu.dcache.demand_hits 1908 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 2044000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.071081 # miss rate for demand accesses +system.cpu.dcache.demand_misses 146 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1716000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.064265 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 132 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 1898000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.071081 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 146 # 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 @@ -54,14 +54,14 @@ system.cpu.dcache.overall_accesses 2054 # nu system.cpu.dcache.overall_avg_miss_latency 14000 # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency 13000 # 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 1922 # number of overall hits -system.cpu.dcache.overall_miss_latency 1848000 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.064265 # miss rate for overall accesses -system.cpu.dcache.overall_misses 132 # number of overall misses +system.cpu.dcache.overall_hits 1908 # number of overall hits +system.cpu.dcache.overall_miss_latency 2044000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.071081 # miss rate for overall accesses +system.cpu.dcache.overall_misses 146 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1716000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.064265 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 132 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 1898000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.071081 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 146 # 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 @@ -76,7 +76,7 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 132 # 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 85.283494 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 85.440937 # Cycle average of tags in use system.cpu.dcache.total_refs 1922 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks @@ -138,34 +138,52 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 13 # number of replacements system.cpu.icache.sampled_refs 303 # 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 136.309471 # Cycle average of tags in use +system.cpu.icache.tagsinuse 136.727640 # Cycle average of tags in use system.cpu.icache.total_refs 5355 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 435 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 13000 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_accesses 50 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 12000 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 600000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 50 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 550000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 50 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 385 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 12000 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 11000 # average ReadReq mshr miss latency system.cpu.l2cache.ReadReq_hits 2 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 5629000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.995402 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 433 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4763000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.995402 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 433 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_miss_latency 4596000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.994805 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 383 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 4213000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.994805 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 383 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 12000 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 11000 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 168000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 154000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 14 # number of UpgradeReq MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.004619 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.005420 # 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 435 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 11000 # average overall mshr miss latency system.cpu.l2cache.demand_hits 2 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 5629000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 5196000 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate 0.995402 # miss rate for demand accesses system.cpu.l2cache.demand_misses 433 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits @@ -176,11 +194,11 @@ system.cpu.l2cache.fast_writes 0 # nu 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 435 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 11000 # 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 2 # number of overall hits -system.cpu.l2cache.overall_miss_latency 5629000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 5196000 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate 0.995402 # miss rate for overall accesses system.cpu.l2cache.overall_misses 433 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits @@ -199,14 +217,14 @@ 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 433 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 369 # 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 222.872415 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 184.077317 # Cycle average of tags in use system.cpu.l2cache.total_refs 2 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 13362000 # number of cpu cycles simulated +system.cpu.numCycles 13544000 # number of cpu cycles simulated system.cpu.num_insts 5657 # Number of instructions executed system.cpu.num_refs 2055 # Number of memory references system.cpu.workload.PROG:num_syscalls 13 # Number of system calls diff --git a/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout b/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout index 6b688641a..c24f82c4f 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout +++ b/tests/quick/00.hello/ref/mips/linux/simple-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 12:54:05 -M5 started Tue May 15 12:54:07 2007 +M5 compiled Aug 3 2007 04:06:41 +M5 started Fri Aug 3 04:31:10 2007 M5 executing on zizzer.eecs.umich.edu command line: build/MIPS_SE/m5.fast -d build/MIPS_SE/tests/fast/quick/00.hello/mips/linux/simple-timing tests/run.py quick/00.hello/mips/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 13362000 because target called exit() +Exiting @ tick 13544000 because target called exit() diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/config.ini b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/config.ini index 0e142e6ce..d7237a4af 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=tracer workload clock=500 cpu_id=0 defer_registration=false @@ -25,11 +25,15 @@ phase=0 progress_interval=0 simulate_stalls=false system=system +tracer=system.cpu.tracer width=1 workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello @@ -53,7 +57,7 @@ bus_id=0 clock=1000 responder_set=false width=64 -port=system.physmem.port system.cpu.icache_port system.cpu.dcache_port +port=system.physmem.port[0] system.cpu.icache_port system.cpu.dcache_port [system.physmem] type=PhysicalMemory diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/m5stats.txt index 8e0baaf8b..ab2e76d2a 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,9 +1,9 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 439375 # Simulator instruction rate (inst/s) -host_mem_usage 149124 # Number of bytes of host memory used -host_seconds 0.01 # Real time elapsed on the host -host_tick_rate 211870315 # Simulator tick rate (ticks/s) +host_inst_rate 15625 # Simulator instruction rate (inst/s) +host_mem_usage 149968 # Number of bytes of host memory used +host_seconds 0.31 # Real time elapsed on the host +host_tick_rate 7799892 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 4863 # Number of instructions simulated sim_seconds 0.000002 # Number of seconds simulated diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout index 9e1770f92..40d1acccc 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout @@ -5,8 +5,8 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 13:02:31 -M5 started Tue May 15 17:00:05 2007 +M5 compiled Aug 3 2007 04:11:25 +M5 started Fri Aug 3 04:31:18 2007 M5 executing on zizzer.eecs.umich.edu command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/quick/00.hello/sparc/linux/simple-atomic tests/run.py quick/00.hello/sparc/linux/simple-atomic Global frequency set at 1000000000000 ticks per second diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-timing/config.ini b/tests/quick/00.hello/ref/sparc/linux/simple-timing/config.ini index fdb2bc3c9..4a945c9a3 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/sparc/linux/simple-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus workload +children=dcache icache l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false @@ -24,17 +24,16 @@ max_loads_any_thread=0 phase=0 progress_interval=0 system=system +tracer=system.cpu.tracer workload=system.cpu.workload dcache_port=system.cpu.dcache.cpu_side icache_port=system.cpu.icache.cpu_side [system.cpu.dcache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -44,7 +43,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=10000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -52,12 +51,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=262144 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -68,11 +65,9 @@ mem_side=system.cpu.toL2Bus.port[1] [system.cpu.icache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=1000 lifo=false @@ -82,7 +77,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=10000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -90,12 +85,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=131072 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -106,11 +99,9 @@ mem_side=system.cpu.toL2Bus.port[0] [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 hash_delay=1 latency=10000 lifo=false @@ -120,7 +111,7 @@ prefetch_access=false prefetch_cache_check_push=true prefetch_data_accesses_only=false prefetch_degree=1 -prefetch_latency=10 +prefetch_latency=100000 prefetch_miss=false prefetch_past_page=false prefetch_policy=none @@ -128,12 +119,10 @@ prefetch_serial_squash=false prefetch_use_cpu_id=true prefetcher_size=100 prioritizeRequests=false -protocol=Null repl=Null size=2097152 split=false split_size=0 -store_compressed=false subblock_size=0 tgts_per_mshr=5 trace_addr=0 @@ -151,6 +140,9 @@ responder_set=false width=64 port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=hello @@ -174,7 +166,7 @@ bus_id=0 clock=1000 responder_set=false width=64 -port=system.physmem.port system.cpu.l2cache.mem_side +port=system.physmem.port[0] system.cpu.l2cache.mem_side [system.physmem] type=PhysicalMemory diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/sparc/linux/simple-timing/m5stats.txt index 839307810..7810c3335 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,33 +1,33 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 239687 # Simulator instruction rate (inst/s) -host_mem_usage 154512 # Number of bytes of host memory used -host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 542234464 # Simulator tick rate (ticks/s) +host_inst_rate 36222 # Simulator instruction rate (inst/s) +host_mem_usage 155556 # Number of bytes of host memory used +host_seconds 0.13 # Real time elapsed on the host +host_tick_rate 84966253 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 4863 # Number of instructions simulated sim_seconds 0.000011 # Number of seconds simulated -sim_ticks 11221000 # Number of ticks simulated +sim_ticks 11443000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 608 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 13796.296296 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 12796.296296 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_avg_miss_latency 13962.962963 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 12962.962963 # average ReadReq mshr miss latency system.cpu.dcache.ReadReq_hits 554 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 745000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_latency 754000 # number of ReadReq miss cycles system.cpu.dcache.ReadReq_miss_rate 0.088816 # miss rate for ReadReq accesses system.cpu.dcache.ReadReq_misses 54 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_miss_latency 691000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency 700000 # number of ReadReq MSHR miss cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.088816 # mshr miss rate for ReadReq accesses system.cpu.dcache.ReadReq_mshr_misses 54 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 661 # number of WriteReq accesses(hits+misses) system.cpu.dcache.WriteReq_avg_miss_latency 14000 # average WriteReq miss latency system.cpu.dcache.WriteReq_avg_mshr_miss_latency 13000 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 577 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 1176000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.127080 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 84 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_miss_latency 1092000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.127080 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 84 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_hits 562 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 1386000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.149773 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 99 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_miss_latency 1287000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.149773 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 99 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_refs 8.195652 # Average number of references to valid blocks. @@ -37,31 +37,31 @@ system.cpu.dcache.blocked_cycles_no_mshrs 0 # n 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 1269 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 13920.289855 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 12920.289855 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1131 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1921000 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.108747 # miss rate for demand accesses -system.cpu.dcache.demand_misses 138 # number of demand (read+write) misses +system.cpu.dcache.demand_avg_miss_latency 13986.928105 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 12986.928105 # average overall mshr miss latency +system.cpu.dcache.demand_hits 1116 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 2140000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.120567 # miss rate for demand accesses +system.cpu.dcache.demand_misses 153 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1783000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.108747 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 138 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_miss_latency 1987000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.120567 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 153 # 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 1269 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 13920.289855 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 12920.289855 # average overall mshr miss latency +system.cpu.dcache.overall_avg_miss_latency 13986.928105 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 12986.928105 # 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 1131 # number of overall hits -system.cpu.dcache.overall_miss_latency 1921000 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.108747 # miss rate for overall accesses -system.cpu.dcache.overall_misses 138 # number of overall misses +system.cpu.dcache.overall_hits 1116 # number of overall hits +system.cpu.dcache.overall_miss_latency 2140000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.120567 # miss rate for overall accesses +system.cpu.dcache.overall_misses 153 # number of overall misses system.cpu.dcache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1783000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.108747 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 138 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_miss_latency 1987000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.120567 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 153 # 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 @@ -76,18 +76,18 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 138 # 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 83.705022 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 83.865949 # Cycle average of tags in use system.cpu.dcache.total_refs 1131 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks system.cpu.icache.ReadReq_accesses 4864 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 13914.062500 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 12914.062500 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_avg_miss_latency 13984.375000 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 12984.375000 # average ReadReq mshr miss latency system.cpu.icache.ReadReq_hits 4608 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 3562000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_latency 3580000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.052632 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 256 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_miss_latency 3306000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency 3324000 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.052632 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 256 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked @@ -99,29 +99,29 @@ system.cpu.icache.blocked_cycles_no_mshrs 0 # n 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 4864 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 13914.062500 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 12914.062500 # average overall mshr miss latency +system.cpu.icache.demand_avg_miss_latency 13984.375000 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 12984.375000 # average overall mshr miss latency system.cpu.icache.demand_hits 4608 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 3562000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency 3580000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.052632 # miss rate for demand accesses system.cpu.icache.demand_misses 256 # number of demand (read+write) misses system.cpu.icache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 3306000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 3324000 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.052632 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 256 # 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 4864 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 13914.062500 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 12914.062500 # average overall mshr miss latency +system.cpu.icache.overall_avg_miss_latency 13984.375000 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 12984.375000 # 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 4608 # number of overall hits -system.cpu.icache.overall_miss_latency 3562000 # number of overall miss cycles +system.cpu.icache.overall_miss_latency 3580000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.052632 # miss rate for overall accesses system.cpu.icache.overall_misses 256 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 3306000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 3324000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.052632 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 256 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles @@ -138,53 +138,72 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 256 # 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 114.172725 # Cycle average of tags in use +system.cpu.icache.tagsinuse 114.646434 # Cycle average of tags in use system.cpu.icache.total_refs 4608 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles -system.cpu.l2cache.ReadReq_accesses 391 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 13000 # average ReadReq miss latency +system.cpu.l2cache.ReadExReq_accesses 84 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 12000 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 1008000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 84 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 924000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 84 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 310 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 12000 # average ReadReq miss latency system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 11000 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 5083000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 391 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4301000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 391 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_hits 3 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 3684000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.990323 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 307 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 3377000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.990323 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 307 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 15 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 12000 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 11000 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 180000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 15 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 165000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 15 # number of UpgradeReq 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 0 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.010274 # 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 391 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.demand_accesses 394 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency 11000 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 5083000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses +system.cpu.l2cache.demand_hits 3 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 4692000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.992386 # miss rate for demand accesses system.cpu.l2cache.demand_misses 391 # 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 4301000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_miss_rate 0.992386 # mshr miss rate for demand accesses system.cpu.l2cache.demand_mshr_misses 391 # 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 391 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 13000 # average overall miss latency +system.cpu.l2cache.overall_accesses 394 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 12000 # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency 11000 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 5083000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses +system.cpu.l2cache.overall_hits 3 # number of overall hits +system.cpu.l2cache.overall_miss_latency 4692000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.992386 # miss rate for overall accesses system.cpu.l2cache.overall_misses 391 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.l2cache.overall_mshr_miss_latency 4301000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_miss_rate 0.992386 # mshr miss rate for overall accesses system.cpu.l2cache.overall_mshr_misses 391 # 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 @@ -198,14 +217,14 @@ 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 391 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 292 # 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 196.304892 # Cycle average of tags in use -system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 133.135118 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 11221000 # number of cpu cycles simulated +system.cpu.numCycles 11443000 # number of cpu cycles simulated system.cpu.num_insts 4863 # Number of instructions executed system.cpu.num_refs 1269 # Number of memory references system.cpu.workload.PROG:num_syscalls 11 # Number of system calls diff --git a/tests/quick/00.hello/ref/sparc/linux/simple-timing/stdout b/tests/quick/00.hello/ref/sparc/linux/simple-timing/stdout index 65bf4abca..1b34d79bb 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-timing/stdout +++ b/tests/quick/00.hello/ref/sparc/linux/simple-timing/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 13:02:31 -M5 started Tue May 15 17:00:05 2007 +M5 compiled Aug 3 2007 04:11:25 +M5 started Fri Aug 3 04:31:19 2007 M5 executing on zizzer.eecs.umich.edu command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/quick/00.hello/sparc/linux/simple-timing tests/run.py quick/00.hello/sparc/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 11221000 because target called exit() +Exiting @ tick 11443000 because target called exit() |