diff options
Diffstat (limited to 'tests')
126 files changed, 4676 insertions, 3749 deletions
diff --git a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini index 4de44cbb3..7a9d0390d 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -21,6 +21,7 @@ SQEntries=32 SSITSize=1024 activity=0 backComSize=5 +cachePorts=200 choiceCtrBits=2 choicePredictorSize=8192 clock=500 @@ -35,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -52,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -74,8 +77,18 @@ renameToFetchDelay=1 renameToIEWDelay=2 renameToROBDelay=1 renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 squashWidth=8 system=system +tracer=system.cpu.tracer trapLatency=13 wbDepth=1 wbWidth=8 @@ -85,21 +98,21 @@ 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 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -107,12 +120,10 @@ 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 @@ -121,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -128,11 +143,11 @@ 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 @@ -206,11 +221,11 @@ 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 @@ -218,11 +233,11 @@ 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 @@ -248,11 +263,11 @@ 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 @@ -260,21 +275,21 @@ 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 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -282,12 +297,10 @@ 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 @@ -296,23 +309,27 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -320,12 +337,10 @@ 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 @@ -343,6 +358,9 @@ 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=gzip input.log 1 @@ -366,7 +384,7 @@ 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/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt index 21eca8681..0a81b23fb 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/00.gzip/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 65796417 # Number of BTB hits -global.BPredUnit.BTBLookups 73152793 # Number of BTB lookups -global.BPredUnit.RASInCorrect 162 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 4224786 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 70143727 # Number of conditional branches predicted -global.BPredUnit.lookups 75959317 # Number of BP lookups -global.BPredUnit.usedRAS 1707904 # Number of times the RAS was used to get a target. -host_inst_rate 95235 # Simulator instruction rate (inst/s) -host_mem_usage 154544 # Number of bytes of host memory used -host_seconds 5938.47 # Real time elapsed on the host -host_tick_rate 31305923 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 11533351 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 9283325 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 125815870 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 42503953 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 65676436 # Number of BTB hits +global.BPredUnit.BTBLookups 73156986 # Number of BTB lookups +global.BPredUnit.RASInCorrect 166 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 4207318 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 70088985 # Number of conditional branches predicted +global.BPredUnit.lookups 76017379 # Number of BP lookups +global.BPredUnit.usedRAS 1692882 # Number of times the RAS was used to get a target. +host_inst_rate 211348 # Simulator instruction rate (inst/s) +host_mem_usage 182448 # Number of bytes of host memory used +host_seconds 2675.93 # Real time elapsed on the host +host_tick_rate 60738573 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 16721732 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 11866335 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 126743752 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 43041597 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 565552443 # Number of instructions simulated -sim_seconds 0.185909 # Number of seconds simulated -sim_ticks 185909249000 # Number of ticks simulated +sim_seconds 0.162532 # Number of seconds simulated +sim_ticks 162531946000 # Number of ticks simulated system.cpu.commit.COM:branches 62547159 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 21750592 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 20242536 # 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 363164843 +system.cpu.commit.COM:committed_per_cycle.samples 315316083 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 150226418 4136.59% - 1 99566964 2741.65% - 2 34056070 937.76% - 3 10333475 284.54% - 4 20301573 559.02% - 5 15829471 435.88% - 6 8882909 244.60% - 7 2217371 61.06% - 8 21750592 598.92% + 0 101801168 3228.54% + 1 100686280 3193.19% + 2 36605446 1160.91% + 3 9846862 312.29% + 4 9756830 309.43% + 5 22230548 705.02% + 6 12726034 403.60% + 7 1420379 45.05% + 8 20242536 641.98% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,72 @@ system.cpu.commit.COM:loads 115049510 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 154862033 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 4224164 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 4206693 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 601856963 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 17 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 52370845 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 60367294 # The number of squashed insts skipped by commit system.cpu.committedInsts 565552443 # Number of Instructions Simulated system.cpu.committedInsts_total 565552443 # Number of Instructions Simulated -system.cpu.cpi 0.657443 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.657443 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 115591547 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 3246.088003 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2434.144734 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 115095381 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 1610598500 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.004292 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 496166 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 273177 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 542787500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.001929 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 222989 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 39451321 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 3474.707454 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 2824.359825 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 38691611 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 2639770000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.019257 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 759710 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 502007 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 727846000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.006532 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 257703 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 427.272727 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 0 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 319.928337 # Average number of references to valid blocks. -system.cpu.dcache.blocked_no_mshrs 1210 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 2 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 517000 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked +system.cpu.cpi 0.574772 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.574772 # CPI: Total CPI of All Threads +system.cpu.dcache.LoadLockedReq_accesses 1 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.LoadLockedReq_hits 1 # number of LoadLockedReq hits +system.cpu.dcache.ReadReq_accesses 111194484 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 32074.811872 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5025.209404 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 110978275 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 6934863000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.001944 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 216209 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 901354 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 1086495500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.001944 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 216209 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 37821041 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 31690.076841 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5379.514968 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 37483812 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 10686812923 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.008916 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 337229 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 1630280 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 1814128453 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.008916 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 337229 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 500 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 1750 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 314.126008 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 1 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 4 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 500 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 7000 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 155042868 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 3384.385481 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 2643.342307 # average overall mshr miss latency -system.cpu.dcache.demand_hits 153786992 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 4250368500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.008100 # miss rate for demand accesses -system.cpu.dcache.demand_misses 1255876 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 775184 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1270633500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.003100 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 480692 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 149015525 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 31840.379452 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5241.100093 # average overall mshr miss latency +system.cpu.dcache.demand_hits 148462087 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 17621675923 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.003714 # miss rate for demand accesses +system.cpu.dcache.demand_misses 553438 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 2531634 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 2900623953 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.003714 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 553438 # 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 155042868 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 3384.385481 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 2643.342307 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 149015525 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 31840.379452 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5241.100093 # 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 153786992 # number of overall hits -system.cpu.dcache.overall_miss_latency 4250368500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.008100 # miss rate for overall accesses -system.cpu.dcache.overall_misses 1255876 # number of overall misses -system.cpu.dcache.overall_mshr_hits 775184 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1270633500 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.003100 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 480692 # number of overall MSHR misses +system.cpu.dcache.overall_hits 148462087 # number of overall hits +system.cpu.dcache.overall_miss_latency 17621675923 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.003714 # miss rate for overall accesses +system.cpu.dcache.overall_misses 553438 # number of overall misses +system.cpu.dcache.overall_mshr_hits 2531634 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 2900623953 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.003714 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 553438 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +120,104 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 476596 # number of replacements -system.cpu.dcache.sampled_refs 480692 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 468780 # number of replacements +system.cpu.dcache.sampled_refs 472876 # 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 4095.610639 # Cycle average of tags in use -system.cpu.dcache.total_refs 153786992 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 28323000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 338024 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 44010110 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 636 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 3910489 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 686828869 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 203536444 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 106139742 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 8653682 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 1958 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 9478548 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 75959317 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 65390933 # Number of cache lines fetched -system.cpu.fetch.Cycles 182129217 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 2901518 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 693889852 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 4411999 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.204291 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 65390933 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 67504321 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.866206 # Number of inst fetches per cycle +system.cpu.dcache.tagsinuse 4095.312024 # Cycle average of tags in use +system.cpu.dcache.total_refs 148542650 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 41060000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 334093 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 42961711 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 654 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 4159669 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 688665550 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 143212697 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 123677184 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 9747531 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 1998 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 5464492 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 162979892 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 162933690 # DTB hits +system.cpu.dtb.misses 46202 # DTB misses +system.cpu.dtb.read_accesses 122208199 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 122186821 # DTB read hits +system.cpu.dtb.read_misses 21378 # DTB read misses +system.cpu.dtb.write_accesses 40771693 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 40746869 # DTB write hits +system.cpu.dtb.write_misses 24824 # DTB write misses +system.cpu.fetch.Branches 76017379 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 65923007 # Number of cache lines fetched +system.cpu.fetch.Cycles 196871509 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 1349795 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 697858274 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 4233156 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.233854 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 65923007 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 67369318 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.146836 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 371818526 +system.cpu.fetch.rateDist.samples 325063615 system.cpu.fetch.rateDist.min_value 0 - 0 255080243 6860.34% - 1 9944321 267.45% - 2 12043396 323.91% - 3 10077209 271.02% - 4 7005486 188.41% - 5 3160802 85.01% - 6 3551742 95.52% - 7 3151910 84.77% - 8 67803417 1823.56% + 0 194115151 5971.61% + 1 10367448 318.94% + 2 15852914 487.69% + 3 14602370 449.22% + 4 12321515 379.05% + 5 14794025 455.11% + 6 6009823 184.88% + 7 3340187 102.75% + 8 53660182 1650.76% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 65390933 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5347.983454 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4573.991031 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 65389966 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 5171500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000015 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 967 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 75 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 4080000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_accesses 65922920 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7890.798226 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5470.620843 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 65922018 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 7117500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000014 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 902 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 87 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 4934500 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000014 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 892 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses 902 # 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 73307.136771 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 73084.277162 # 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 65390933 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5347.983454 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4573.991031 # average overall mshr miss latency -system.cpu.icache.demand_hits 65389966 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 5171500 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000015 # miss rate for demand accesses -system.cpu.icache.demand_misses 967 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 75 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 4080000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_accesses 65922920 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7890.798226 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5470.620843 # average overall mshr miss latency +system.cpu.icache.demand_hits 65922018 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 7117500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000014 # miss rate for demand accesses +system.cpu.icache.demand_misses 902 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 87 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 4934500 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.000014 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 892 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses 902 # 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 65390933 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5347.983454 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4573.991031 # average overall mshr miss latency +system.cpu.icache.overall_accesses 65922920 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7890.798226 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5470.620843 # 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 65389966 # number of overall hits -system.cpu.icache.overall_miss_latency 5171500 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000015 # miss rate for overall accesses -system.cpu.icache.overall_misses 967 # number of overall misses -system.cpu.icache.overall_mshr_hits 75 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 4080000 # number of overall MSHR miss cycles +system.cpu.icache.overall_hits 65922018 # number of overall hits +system.cpu.icache.overall_miss_latency 7117500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000014 # miss rate for overall accesses +system.cpu.icache.overall_misses 902 # number of overall misses +system.cpu.icache.overall_mshr_hits 87 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 4934500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.000014 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 892 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses 902 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -215,81 +229,81 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 33 # number of replacements -system.cpu.icache.sampled_refs 892 # Sample count of references to valid blocks. +system.cpu.icache.replacements 32 # number of replacements +system.cpu.icache.sampled_refs 902 # 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 761.711791 # Cycle average of tags in use -system.cpu.icache.total_refs 65389966 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 770.534444 # Cycle average of tags in use +system.cpu.icache.total_refs 65922018 # 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 2468 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 67136036 # Number of branches executed -system.cpu.iew.EXEC:nop 41949449 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.608660 # Inst execution rate -system.cpu.iew.EXEC:refs 164353457 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 41112797 # Number of stores executed +system.cpu.idleCycles 190397 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 67319692 # Number of branches executed +system.cpu.iew.EXEC:nop 42991424 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.842347 # Inst execution rate +system.cpu.iew.EXEC:refs 163918711 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 41167815 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 478961290 # num instructions consuming a value -system.cpu.iew.WB:count 594114153 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.812310 # average fanout of values written-back +system.cpu.iew.WB:consumers 490977460 # num instructions consuming a value +system.cpu.iew.WB:count 595732364 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.805927 # 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 389064913 # num instructions producing a value -system.cpu.iew.WB:rate 1.597861 # insts written-back per cycle -system.cpu.iew.WB:sent 594699658 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 4485637 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 10981 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 125815870 # Number of dispatched load instructions +system.cpu.iew.WB:producers 395691865 # num instructions producing a value +system.cpu.iew.WB:rate 1.832664 # insts written-back per cycle +system.cpu.iew.WB:sent 596897738 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 4671822 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 211982 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 126743752 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 22 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 6586227 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 42503953 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 654225210 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 123240660 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 4346710 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 598129643 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 518 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewDispSquashedInsts 3268805 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 43041597 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 662373944 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 122750896 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 6416858 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 598879902 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 1310 # 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 8653682 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 4417 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 2 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 9747531 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 36871 # 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 2615 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 7105932 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 1847 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.cacheBlocked 104 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 10085062 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 15402 # 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 296430 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 5860 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 10766360 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 2691430 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 296430 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 519296 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 3966341 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.521044 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.521044 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 602476353 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 28955 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 5897 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 11694242 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 3229074 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 28955 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 540642 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 4131180 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.739821 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.739821 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 605296760 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist - (null) 0 0.00% # Type of FU issued - IntAlu 435905994 72.35% # Type of FU issued - IntMult 6492 0.00% # Type of FU issued + No_OpClass 0 0.00% # Type of FU issued + IntAlu 438526639 72.45% # Type of FU issued + IntMult 6526 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 27 0.00% # Type of FU issued + FloatAdd 29 0.00% # Type of FU issued FloatCmp 5 0.00% # Type of FU issued FloatCvt 5 0.00% # Type of FU issued FloatMult 4 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 124769613 20.71% # Type of FU issued - MemWrite 41794213 6.94% # Type of FU issued + MemRead 124781721 20.61% # Type of FU issued + MemWrite 41981831 6.94% # 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 3485464 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.005785 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 6717566 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.011098 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist - (null) 0 0.00% # attempts to use FU when none available - IntAlu 2980889 85.52% # attempts to use FU when none available - IntMult 104 0.00% # attempts to use FU when none available + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 5391256 80.26% # attempts to use FU when none available + IntMult 67 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 FloatCmp 0 0.00% # attempts to use FU when none available @@ -297,80 +311,105 @@ 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 331227 9.50% # attempts to use FU when none available - MemWrite 173244 4.97% # attempts to use FU when none available + MemRead 838838 12.49% # attempts to use FU when none available + MemWrite 487405 7.26% # 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 371818526 +system.cpu.iq.ISSUE:issued_per_cycle.samples 325063615 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 125625601 3378.68% - 1 89616652 2410.23% - 2 55904072 1503.53% - 3 46310572 1245.52% - 4 27240019 732.62% - 5 12675210 340.90% - 6 11517465 309.76% - 7 2752555 74.03% - 8 176380 4.74% + 0 85796359 2639.37% + 1 67542387 2077.82% + 2 80092036 2463.89% + 3 31532999 970.06% + 4 32045835 985.83% + 5 15660373 481.76% + 6 10783606 331.74% + 7 1095697 33.71% + 8 514323 15.82% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.620351 # Inst issue rate -system.cpu.iq.iqInstsAdded 612275739 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 602476353 # Number of instructions issued +system.cpu.iq.ISSUE:rate 1.862087 # Inst issue rate +system.cpu.iq.iqInstsAdded 619382498 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 605296760 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 22 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 42659982 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 2623 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 52509739 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 11652 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 5 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 21979774 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 481584 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 6174.721472 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2416.099471 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 455285 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 162389000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.054609 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 26299 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 63541000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.054609 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 26299 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 338024 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 338024 # number of Writeback hits +system.cpu.iq.iqSquashedOperandsExamined 28327252 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 65923045 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 65923007 # ITB hits +system.cpu.itb.misses 38 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 256667 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4174.217956 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2174.217956 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 1071384000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 256667 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 558050000 # 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 256667 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 217111 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4357.993028 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2357.993028 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 30930 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 811375500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.857538 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 186181 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 439013500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.857538 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 186181 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 80592 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4188.374777 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2188.374777 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 337549500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 80592 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 176365500 # 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 80592 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 334093 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses +system.cpu.l2cache.Writeback_misses 334093 # number of Writeback misses +system.cpu.l2cache.Writeback_mshr_miss_rate 1 # mshr miss rate for Writeback accesses +system.cpu.l2cache.Writeback_mshr_misses 334093 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 30.164987 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 4.206809 # 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 481584 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 6174.721472 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2416.099471 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 455285 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 162389000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.054609 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 26299 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 473778 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4251.480192 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2251.480192 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 30930 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 1882759500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.934716 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 442848 # 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 63541000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.054609 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 26299 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 997063500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.934716 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 442848 # 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 819608 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 6174.721472 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2416.099471 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 473778 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4251.480192 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2251.480192 # 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 793309 # number of overall hits -system.cpu.l2cache.overall_miss_latency 162389000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.032087 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 26299 # number of overall misses +system.cpu.l2cache.overall_hits 30930 # number of overall hits +system.cpu.l2cache.overall_miss_latency 1882759500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.934716 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 442848 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 63541000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.032087 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 26299 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 997063500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.934716 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 442848 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -382,31 +421,31 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.l2cache.replacements 931 # number of replacements -system.cpu.l2cache.sampled_refs 26299 # Sample count of references to valid blocks. +system.cpu.l2cache.replacements 14218 # number of replacements +system.cpu.l2cache.sampled_refs 15715 # 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 25071.267749 # Cycle average of tags in use -system.cpu.l2cache.total_refs 793309 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 8150.643180 # Cycle average of tags in use +system.cpu.l2cache.total_refs 66110 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.writebacks 904 # number of writebacks -system.cpu.numCycles 371818526 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 11517489 # Number of cycles rename is blocking +system.cpu.l2cache.writebacks 0 # number of writebacks +system.cpu.numCycles 325063615 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 11040699 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 463854889 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 32462126 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 206624315 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 21712 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 889109667 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 674900294 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 515718683 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 111518348 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 8653682 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 33504424 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 51863794 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 268 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 59569309 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 24 # count of temporary serializing insts renamed -system.cpu.timesIdled 32 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 31586100 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 150557156 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 290380 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 895272473 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 679363424 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 518606333 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 116560800 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 9747531 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 37157112 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 54751444 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 317 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 27 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 72001269 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 25 # count of temporary serializing insts renamed +system.cpu.timesIdled 103 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/config.ini index e7acc71a6..e21c42f32 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=gzip input.log 1 @@ -53,7 +67,7 @@ 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/long/00.gzip/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/m5stats.txt index 5453dc099..c668a0459 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/00.gzip/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 963880 # Simulator instruction rate (inst/s) -host_mem_usage 148548 # Number of bytes of host memory used -host_seconds 624.41 # Real time elapsed on the host -host_tick_rate 481939681 # Simulator tick rate (ticks/s) +host_inst_rate 2906348 # Simulator instruction rate (inst/s) +host_mem_usage 174252 # Number of bytes of host memory used +host_seconds 207.08 # Real time elapsed on the host +host_tick_rate 1453183573 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 601856965 # Number of instructions simulated -sim_seconds 0.300928 # Number of seconds simulated -sim_ticks 300928482000 # Number of ticks simulated +sim_insts 601856964 # Number of instructions simulated +sim_seconds 0.300931 # Number of seconds simulated +sim_ticks 300930958000 # Number of ticks simulated +system.cpu.dtb.accesses 153970296 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 153965363 # DTB hits +system.cpu.dtb.misses 4933 # DTB misses +system.cpu.dtb.read_accesses 114516673 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 114514042 # DTB read hits +system.cpu.dtb.read_misses 2631 # DTB read misses +system.cpu.dtb.write_accesses 39453623 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 39451321 # DTB write hits +system.cpu.dtb.write_misses 2302 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 601861917 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 601861897 # ITB hits +system.cpu.itb.misses 20 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 601856965 # number of cpu cycles simulated -system.cpu.num_insts 601856965 # Number of instructions executed -system.cpu.num_refs 154862034 # Number of memory references +system.cpu.numCycles 601861917 # number of cpu cycles simulated +system.cpu.num_insts 601856964 # Number of instructions executed +system.cpu.num_refs 154866966 # Number of memory references system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/alpha/tru64/simple-timing/config.ini b/tests/long/00.gzip/ref/alpha/tru64/simple-timing/config.ini index 16b6c6fda..21fbe2323 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/00.gzip/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/00.gzip/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/00.gzip/ref/alpha/tru64/simple-timing/m5stats.txt index eaccc0729..b76b4e6c1 100644 --- a/tests/long/00.gzip/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/00.gzip/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1799420 # Simulator instruction rate (inst/s) -host_mem_usage 199568 # Number of bytes of host memory used -host_seconds 334.47 # Real time elapsed on the host -host_tick_rate 2297009943 # Simulator tick rate (ticks/s) +host_inst_rate 1730291 # Simulator instruction rate (inst/s) +host_mem_usage 181616 # Number of bytes of host memory used +host_seconds 347.84 # Real time elapsed on the host +host_tick_rate 2208778962 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 601856965 # Number of instructions simulated -sim_seconds 0.768288 # Number of seconds simulated -sim_ticks 768287940000 # Number of ticks simulated +sim_insts 601856964 # Number of instructions simulated +sim_seconds 0.768293 # Number of seconds simulated +sim_ticks 768292872000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 114514042 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 23626.361612 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 21626.361612 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 451299 # number of replacements system.cpu.dcache.sampled_refs 455395 # 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 4094.970134 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4094.968001 # Cycle average of tags in use system.cpu.dcache.total_refs 153509968 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 342925000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 343385000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 325723 # number of writebacks -system.cpu.icache.ReadReq_accesses 601856966 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 153970296 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 153965363 # DTB hits +system.cpu.dtb.misses 4933 # DTB misses +system.cpu.dtb.read_accesses 114516673 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 114514042 # DTB read hits +system.cpu.dtb.read_misses 2631 # DTB read misses +system.cpu.dtb.write_accesses 39453623 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 39451321 # DTB write hits +system.cpu.dtb.write_misses 2302 # DTB write misses +system.cpu.icache.ReadReq_accesses 601861898 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 601856171 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 601861103 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 19875000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000001 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 795 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000001 # ms system.cpu.icache.ReadReq_mshr_misses 795 # 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 757051.787421 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 757057.991195 # 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 601856966 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 601861898 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 23000 # average overall mshr miss latency -system.cpu.icache.demand_hits 601856171 # number of demand (read+write) hits +system.cpu.icache.demand_hits 601861103 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 19875000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000001 # miss rate for demand accesses system.cpu.icache.demand_misses 795 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 795 # nu 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 601856966 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 601861898 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 23000 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 601856171 # number of overall hits +system.cpu.icache.overall_hits 601861103 # number of overall hits system.cpu.icache.overall_miss_latency 19875000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000001 # miss rate for overall accesses system.cpu.icache.overall_misses 795 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 24 # number of replacements system.cpu.icache.sampled_refs 795 # 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 673.685789 # Cycle average of tags in use -system.cpu.icache.total_refs 601856171 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 673.685273 # Cycle average of tags in use +system.cpu.icache.total_refs 601861103 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 601861918 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 601861898 # ITB hits +system.cpu.itb.misses 20 # ITB misses system.cpu.l2cache.ReadExReq_accesses 254163 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 13394 # number of replacements system.cpu.l2cache.sampled_refs 14881 # 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 8423.446687 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 8423.428104 # Cycle average of tags in use system.cpu.l2cache.total_refs 52084 # 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 768287940000 # number of cpu cycles simulated -system.cpu.num_insts 601856965 # Number of instructions executed -system.cpu.num_refs 154862034 # Number of memory references +system.cpu.numCycles 768292872000 # number of cpu cycles simulated +system.cpu.num_insts 601856964 # Number of instructions executed +system.cpu.num_refs 154866966 # Number of memory references system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/sparc/linux/o3-timing/config.ini b/tests/long/00.gzip/ref/sparc/linux/o3-timing/config.ini index 1ce1e7585..470af89eb 100644 --- a/tests/long/00.gzip/ref/sparc/linux/o3-timing/config.ini +++ b/tests/long/00.gzip/ref/sparc/linux/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/00.gzip/ref/sparc/linux/o3-timing/m5stats.txt b/tests/long/00.gzip/ref/sparc/linux/o3-timing/m5stats.txt index 47c1d93f0..51c499e27 100644 --- a/tests/long/00.gzip/ref/sparc/linux/o3-timing/m5stats.txt +++ b/tests/long/00.gzip/ref/sparc/linux/o3-timing/m5stats.txt @@ -1,122 +1,122 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 183168209 # Number of BTB hits -global.BPredUnit.BTBLookups 207693172 # Number of BTB lookups +global.BPredUnit.BTBHits 183932235 # Number of BTB hits +global.BPredUnit.BTBLookups 208089812 # Number of BTB lookups global.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 83686538 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 256168234 # Number of conditional branches predicted -global.BPredUnit.lookups 256168234 # Number of BP lookups +global.BPredUnit.condIncorrect 84447535 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 256528366 # Number of conditional branches predicted +global.BPredUnit.lookups 256528366 # Number of BP lookups global.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. -host_inst_rate 108517 # Simulator instruction rate (inst/s) -host_mem_usage 202532 # Number of bytes of host memory used -host_seconds 13726.13 # Real time elapsed on the host -host_tick_rate 80131991 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 457134527 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 154100032 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 745124340 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 301027499 # Number of stores inserted to the mem dependence unit. +host_inst_rate 100069 # Simulator instruction rate (inst/s) +host_mem_usage 184776 # Number of bytes of host memory used +host_seconds 14046.38 # Real time elapsed on the host +host_tick_rate 78132380 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 458856790 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 141228058 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 745627925 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 302069201 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 1489514761 # Number of instructions simulated -sim_seconds 1.099902 # Number of seconds simulated -sim_ticks 1099901861500 # Number of ticks simulated +sim_insts 1405610550 # Number of instructions simulated +sim_seconds 1.097477 # Number of seconds simulated +sim_ticks 1097476890500 # Number of ticks simulated system.cpu.commit.COM:branches 86246390 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 9028629 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 9005633 # 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 1956850179 +system.cpu.commit.COM:committed_per_cycle.samples 1955398373 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 1082285235 5530.75% - 1 575067444 2938.74% - 2 119112331 608.69% - 3 121687931 621.86% - 4 26918285 137.56% - 5 9398970 48.03% - 6 9197638 47.00% - 7 4153716 21.23% - 8 9028629 46.14% + 0 1080294174 5524.68% + 1 576226777 2946.85% + 2 118746551 607.28% + 3 121516054 621.44% + 4 26673737 136.41% + 5 9328411 47.71% + 6 9370387 47.92% + 7 4236649 21.67% + 8 9005633 46.06% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist -system.cpu.commit.COM:count 1489514761 # Number of instructions committed -system.cpu.commit.COM:loads 402511688 # Number of loads committed +system.cpu.commit.COM:count 1489528973 # Number of instructions committed +system.cpu.commit.COM:loads 402516086 # Number of loads committed system.cpu.commit.COM:membars 51356 # Number of memory barriers committed -system.cpu.commit.COM:refs 569359656 # Number of memory references committed +system.cpu.commit.COM:refs 569373868 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 83686538 # The number of times a branch was mispredicted -system.cpu.commit.commitCommittedInsts 1489514761 # The number of committed instructions -system.cpu.commit.commitNonSpecStalls 2243499 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 1386494932 # The number of squashed insts skipped by commit -system.cpu.committedInsts 1489514761 # Number of Instructions Simulated -system.cpu.committedInsts_total 1489514761 # Number of Instructions Simulated -system.cpu.cpi 1.476859 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.476859 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 432423106 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 21577.217813 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4456.675710 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 432175035 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 5352682000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.000574 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 248071 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 707847 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 1105572000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.000574 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 248071 # number of ReadReq MSHR misses +system.cpu.commit.branchMispredicts 84447535 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 1489528973 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 2243501 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 1399558822 # The number of squashed insts skipped by commit +system.cpu.committedInsts 1405610550 # Number of Instructions Simulated +system.cpu.committedInsts_total 1405610550 # Number of Instructions Simulated +system.cpu.cpi 1.561566 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.561566 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 422711123 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 22402.386533 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4523.374198 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 422473917 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 5313980500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000561 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 237206 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 708416 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 1072971500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000561 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 237206 # number of ReadReq MSHR misses system.cpu.dcache.SwapReq_accesses 1326 # number of SwapReq accesses(hits+misses) -system.cpu.dcache.SwapReq_avg_miss_latency 7012.500000 # average SwapReq miss latency -system.cpu.dcache.SwapReq_avg_mshr_miss_latency 5012.500000 # average SwapReq mshr miss latency +system.cpu.dcache.SwapReq_avg_miss_latency 7025 # average SwapReq miss latency +system.cpu.dcache.SwapReq_avg_mshr_miss_latency 5025 # average SwapReq mshr miss latency system.cpu.dcache.SwapReq_hits 1286 # number of SwapReq hits -system.cpu.dcache.SwapReq_miss_latency 280500 # number of SwapReq miss cycles +system.cpu.dcache.SwapReq_miss_latency 281000 # number of SwapReq miss cycles system.cpu.dcache.SwapReq_miss_rate 0.030166 # miss rate for SwapReq accesses system.cpu.dcache.SwapReq_misses 40 # number of SwapReq misses -system.cpu.dcache.SwapReq_mshr_miss_latency 200500 # number of SwapReq MSHR miss cycles +system.cpu.dcache.SwapReq_mshr_miss_latency 201000 # number of SwapReq MSHR miss cycles system.cpu.dcache.SwapReq_mshr_miss_rate 0.030166 # mshr miss rate for SwapReq accesses system.cpu.dcache.SwapReq_mshr_misses 40 # number of SwapReq MSHR misses -system.cpu.dcache.WriteReq_accesses 165036365 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 45516.173877 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5913.886312 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 164687129 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 15895886500 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.002116 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 349236 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 1810277 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 2065342000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.002116 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 349236 # number of WriteReq MSHR misses +system.cpu.dcache.WriteReq_accesses 165053813 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 45668.908621 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5916.368381 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 164707389 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 15820806000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.002099 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 346424 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 1802643 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 2049572000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.002099 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 346424 # 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 1139.085750 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 1145.843097 # 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 597459471 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 35573.948573 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5308.683809 # average overall mshr miss latency -system.cpu.dcache.demand_hits 596862164 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 21248568500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.001000 # miss rate for demand accesses -system.cpu.dcache.demand_misses 597307 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 2518124 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 3170914000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.001000 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 597307 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 587764936 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 36212.645854 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5350.210750 # average overall mshr miss latency +system.cpu.dcache.demand_hits 587181306 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 21134786500 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000993 # miss rate for demand accesses +system.cpu.dcache.demand_misses 583630 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 2511059 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 3122543500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.000993 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 583630 # 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 597459471 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 35573.948573 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5308.683809 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 587764936 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 36212.645854 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5350.210750 # 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 596862164 # number of overall hits -system.cpu.dcache.overall_miss_latency 21248568500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.001000 # miss rate for overall accesses -system.cpu.dcache.overall_misses 597307 # number of overall misses -system.cpu.dcache.overall_mshr_hits 2518124 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 3170914000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.001000 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 597307 # number of overall MSHR misses +system.cpu.dcache.overall_hits 587181306 # number of overall hits +system.cpu.dcache.overall_miss_latency 21134786500 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000993 # miss rate for overall accesses +system.cpu.dcache.overall_misses 583630 # number of overall misses +system.cpu.dcache.overall_mshr_hits 2511059 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 3122543500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.000993 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 583630 # 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 @@ -128,89 +128,89 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 519953 # number of replacements -system.cpu.dcache.sampled_refs 524049 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 508412 # number of replacements +system.cpu.dcache.sampled_refs 512508 # 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 4095.788106 # Cycle average of tags in use -system.cpu.dcache.total_refs 596936748 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 72857000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 346070 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 407153301 # Number of cycles decode is blocked -system.cpu.decode.DECODE:DecodedInsts 3453639261 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 763587746 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 783418811 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 242953531 # Number of cycles decode is squashing -system.cpu.decode.DECODE:UnblockCycles 2690321 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 256168234 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 355186488 # Number of cache lines fetched -system.cpu.fetch.Cycles 1201174807 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 10202313 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 3743631874 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 91259594 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.116450 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 355186488 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 183168209 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.701803 # Number of inst fetches per cycle +system.cpu.dcache.tagsinuse 4095.762102 # Cycle average of tags in use +system.cpu.dcache.total_refs 587253754 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 80526000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 343259 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 406688141 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 3452580675 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 760521931 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 785512506 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 239555254 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 2675795 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 256528366 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 355016142 # Number of cache lines fetched +system.cpu.fetch.Cycles 1201036760 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 10894008 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 3738352844 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 89458561 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.116872 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 355016142 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 183932235 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.703158 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 2199803710 +system.cpu.fetch.rateDist.samples 2194953627 system.cpu.fetch.rateDist.min_value 0 - 0 1353815392 6154.26% - 1 255570605 1161.79% - 2 82946121 377.06% - 3 38413739 174.62% - 4 83998079 381.84% - 5 40983172 186.30% - 6 33041033 150.20% - 7 20511116 93.24% - 8 290524453 1320.68% + 0 1348933053 6145.61% + 1 256313247 1167.74% + 2 82698191 376.77% + 3 38326183 174.61% + 4 84519360 385.06% + 5 41105906 187.27% + 6 32923583 150.00% + 7 20556634 93.65% + 8 289577470 1319.29% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 355186427 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7448.556625 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5296.447076 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 355185076 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 10063000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_accesses 355016079 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7452.363368 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5292.836041 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 355014725 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 10090500 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000004 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 1351 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 61 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 7155500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_misses 1354 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 63 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 7166500 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000004 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 1351 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses 1354 # 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 262905.311621 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 262196.990399 # 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 355186427 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7448.556625 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5296.447076 # average overall mshr miss latency -system.cpu.icache.demand_hits 355185076 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 10063000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_accesses 355016079 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7452.363368 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5292.836041 # average overall mshr miss latency +system.cpu.icache.demand_hits 355014725 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 10090500 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000004 # miss rate for demand accesses -system.cpu.icache.demand_misses 1351 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 61 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 7155500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_misses 1354 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 63 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 7166500 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.000004 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 1351 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses 1354 # 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 355186427 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7448.556625 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5296.447076 # average overall mshr miss latency +system.cpu.icache.overall_accesses 355016079 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7452.363368 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5292.836041 # 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 355185076 # number of overall hits -system.cpu.icache.overall_miss_latency 10063000 # number of overall miss cycles +system.cpu.icache.overall_hits 355014725 # number of overall hits +system.cpu.icache.overall_miss_latency 10090500 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000004 # miss rate for overall accesses -system.cpu.icache.overall_misses 1351 # number of overall misses -system.cpu.icache.overall_mshr_hits 61 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 7155500 # number of overall MSHR miss cycles +system.cpu.icache.overall_misses 1354 # number of overall misses +system.cpu.icache.overall_mshr_hits 63 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 7166500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.000004 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 1351 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses 1354 # 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 @@ -222,183 +222,183 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 207 # number of replacements -system.cpu.icache.sampled_refs 1351 # Sample count of references to valid blocks. +system.cpu.icache.replacements 208 # number of replacements +system.cpu.icache.sampled_refs 1354 # 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 1040.211796 # Cycle average of tags in use -system.cpu.icache.total_refs 355185076 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1042.348080 # Cycle average of tags in use +system.cpu.icache.total_refs 355014725 # 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 8497 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 126707080 # Number of branches executed -system.cpu.iew.EXEC:nop 0 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.003361 # Inst execution rate -system.cpu.iew.EXEC:refs 760962527 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 208093186 # Number of stores executed +system.cpu.idleCycles 94965 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 128778452 # Number of branches executed +system.cpu.iew.EXEC:nop 354384689 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.865881 # Inst execution rate +system.cpu.iew.EXEC:refs 753461994 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 210026063 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1493645383 # num instructions consuming a value -system.cpu.iew.WB:count 2165444744 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.962819 # average fanout of values written-back +system.cpu.iew.WB:consumers 1497813793 # num instructions consuming a value +system.cpu.iew.WB:count 1867109874 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.963032 # 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 1438109572 # num instructions producing a value -system.cpu.iew.WB:rate 0.984381 # insts written-back per cycle -system.cpu.iew.WB:sent 2178310152 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 91514542 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 458290 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 745124340 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 21362312 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 17090675 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 301027499 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 2876000922 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 552869341 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 140121943 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 2207196457 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 56098 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 1442442170 # num instructions producing a value +system.cpu.iew.WB:rate 0.850638 # insts written-back per cycle +system.cpu.iew.WB:sent 1877161047 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 91327681 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 454443 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 745627925 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 21367021 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 17089542 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 302069201 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 2889153048 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 543435931 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 103575555 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 1900567912 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 61243 # 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 8365 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 242953531 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 87287 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 9772 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 239555254 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 95884 # 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 119737756 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 85786 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 119997179 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 80650 # 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 10100571 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 31 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 342612652 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 134179531 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 10100571 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 1514083 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 90000459 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.677113 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.677113 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 2347318400 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 5250080 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 6 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 343111839 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 135211419 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 5250080 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 1516982 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 89810699 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.640383 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.640383 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 2004143467 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist - No_OpClass 351441317 14.97% # Type of FU issued - IntAlu 1181231771 50.32% # Type of FU issued + No_OpClass 0 0.00% # Type of FU issued + IntAlu 1186366605 59.20% # Type of FU issued IntMult 0 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 3000185 0.13% # Type of FU issued + FloatAdd 3003253 0.15% # 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 586473179 24.98% # Type of FU issued - MemWrite 225171948 9.59% # Type of FU issued + MemRead 584611723 29.17% # Type of FU issued + MemWrite 230161886 11.48% # 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 3997880 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.001703 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 6010355 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.002999 # 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 155579 3.89% # attempts to use FU when none available + IntAlu 143340 2.38% # 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 244024 6.10% # attempts to use FU when none available + FloatAdd 241345 4.02% # attempts to use FU when none available FloatCmp 0 0.00% # attempts to use FU when none available FloatCvt 0 0.00% # attempts to use FU when none available 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 3267233 81.72% # attempts to use FU when none available - MemWrite 331044 8.28% # attempts to use FU when none available + MemRead 5244225 87.25% # attempts to use FU when none available + MemWrite 381445 6.35% # attempts to use FU when none available IprAccess 0 0.00% # attempts to use FU when none available InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 2199803710 +system.cpu.iq.ISSUE:issued_per_cycle.samples 2194953627 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 993478594 4516.21% - 1 570157916 2591.86% - 2 321116547 1459.75% - 3 178901320 813.26% - 4 92584833 420.88% - 5 34984610 159.04% - 6 7286511 33.12% - 7 1105050 5.02% - 8 188329 0.86% + 0 1076765226 4905.64% + 1 582878371 2655.54% + 2 298125643 1358.23% + 3 159003575 724.41% + 4 52530250 239.32% + 5 16707223 76.12% + 6 8404252 38.29% + 7 392238 1.79% + 8 146849 0.67% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.067058 # Inst issue rate -system.cpu.iq.iqInstsAdded 2854330173 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 2347318400 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 21670749 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 1311892803 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 993660 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 19427250 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 1293606933 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadExReq_accesses 275979 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4897.575540 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2897.575540 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 1351628000 # number of ReadExReq miss cycles +system.cpu.iq.ISSUE:rate 0.913069 # Inst issue rate +system.cpu.iq.iqInstsAdded 2513084593 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 2004143467 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 21683766 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 1087893079 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 3817087 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 19440265 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 1299740082 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 275303 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4888.651776 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2888.651776 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 1345860500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_misses 275979 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 799670000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 275303 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 795254500 # 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 275979 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 249421 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4201.208939 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2201.208939 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 64300 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 777732000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.742203 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 185121 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 407490000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.742203 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 185121 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 73301 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4221.136137 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2221.136137 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 309413500 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_mshr_misses 275303 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 238559 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4206.099871 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2206.099871 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 56424 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 766078000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.763480 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 182135 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 401808000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.763480 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 182135 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 71169 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4205.419494 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2205.419494 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 299295500 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_misses 73301 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 162811500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 71169 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 156957500 # 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 73301 # number of UpgradeReq MSHR misses -system.cpu.l2cache.Writeback_accesses 346070 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_mshr_misses 71169 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 343259 # number of Writeback accesses(hits+misses) system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses -system.cpu.l2cache.Writeback_misses 346070 # number of Writeback misses +system.cpu.l2cache.Writeback_misses 343259 # number of Writeback misses system.cpu.l2cache.Writeback_mshr_miss_rate 1 # mshr miss rate for Writeback accesses -system.cpu.l2cache.Writeback_mshr_misses 346070 # number of Writeback MSHR misses +system.cpu.l2cache.Writeback_mshr_misses 343259 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 4.935065 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 4.652891 # 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 525400 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4618.000434 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2618.000434 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 64300 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 2129360000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.877617 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 461100 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 513862 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4616.884693 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2616.884693 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 56424 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 2111938500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.890196 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 457438 # 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 1207160000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.877617 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 461100 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 1197062500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.890196 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 457438 # 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 525400 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4618.000434 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2618.000434 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 513862 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4616.884693 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2616.884693 # 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 64300 # number of overall hits -system.cpu.l2cache.overall_miss_latency 2129360000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.877617 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 461100 # number of overall misses +system.cpu.l2cache.overall_hits 56424 # number of overall hits +system.cpu.l2cache.overall_miss_latency 2111938500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.890196 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 457438 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 1207160000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.877617 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 461100 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 1197062500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.890196 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 457438 # 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 @@ -411,31 +411,31 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 19390 # number of replacements -system.cpu.l2cache.sampled_refs 20790 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 20786 # 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 8555.838166 # Cycle average of tags in use -system.cpu.l2cache.total_refs 102600 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 8527.413561 # Cycle average of tags in use +system.cpu.l2cache.total_refs 96715 # 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 2199803710 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 12980165 # Number of cycles rename is blocking -system.cpu.rename.RENAME:CommittedMaps 1244762261 # Number of HB maps that are committed -system.cpu.rename.RENAME:FullRegisterEvents 11 # Number of times there has been no free registers -system.cpu.rename.RENAME:IQFullEvents 40711 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 826156851 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 20049545 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 4942866473 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 3108910588 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 2431469653 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 720639508 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 242953531 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 28416809 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 1186707392 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 368656846 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 21929426 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 159084902 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 21683995 # 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.numCycles 2194953627 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 13000888 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 1244771057 # Number of HB maps that are committed +system.cpu.rename.RENAME:FullRegisterEvents 9 # Number of times there has been no free registers +system.cpu.rename.RENAME:IQFullEvents 47407 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 822770114 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 20101500 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 4935577703 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 3109070263 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 2428488542 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 723045080 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 239555254 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 28402170 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 1183717485 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 368180121 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 21968418 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 159248004 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 21723083 # count of temporary serializing insts renamed +system.cpu.timesIdled 35 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 19 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/sparc/linux/o3-timing/stdout b/tests/long/00.gzip/ref/sparc/linux/o3-timing/stdout index 0785768bd..dc3199e5a 100644 --- a/tests/long/00.gzip/ref/sparc/linux/o3-timing/stdout +++ b/tests/long/00.gzip/ref/sparc/linux/o3-timing/stdout @@ -36,9 +36,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 12:23:15 -M5 started Sun Aug 12 12:23:18 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 22:51:35 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/00.gzip/sparc/linux/o3-timing tests/run.py long/00.gzip/sparc/linux/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 1099901861500 because target called exit() +Exiting @ tick 1097476890500 because target called exit() diff --git a/tests/long/00.gzip/ref/sparc/linux/simple-atomic/config.ini b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/config.ini index 144c9c7fe..c0e8863c5 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=gzip input.log 1 @@ -53,7 +67,7 @@ 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/long/00.gzip/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/m5stats.txt index bdafc8603..09530dafb 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 723585 # Simulator instruction rate (inst/s) -host_mem_usage 149576 # Number of bytes of host memory used -host_seconds 2058.52 # Real time elapsed on the host -host_tick_rate 361792205 # Simulator tick rate (ticks/s) +host_inst_rate 1870525 # Simulator instruction rate (inst/s) +host_mem_usage 176480 # Number of bytes of host memory used +host_seconds 796.31 # Real time elapsed on the host +host_tick_rate 935265227 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 1489514860 # Number of instructions simulated -sim_seconds 0.744757 # Number of seconds simulated -sim_ticks 744757429500 # Number of ticks simulated +sim_insts 1489514761 # Number of instructions simulated +sim_seconds 0.744760 # Number of seconds simulated +sim_ticks 744759833500 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 1489514860 # number of cpu cycles simulated -system.cpu.num_insts 1489514860 # Number of instructions executed -system.cpu.num_refs 569359656 # Number of memory references +system.cpu.numCycles 1489519668 # number of cpu cycles simulated +system.cpu.num_insts 1489514761 # Number of instructions executed +system.cpu.num_refs 569364430 # Number of memory references system.cpu.workload.PROG:num_syscalls 19 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/sparc/linux/simple-atomic/stdout b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/stdout index b335083d4..d033c7748 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-atomic/stdout +++ b/tests/long/00.gzip/ref/sparc/linux/simple-atomic/stdout @@ -36,9 +36,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 13:02:31 -M5 started Tue May 15 13:02:33 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 22:51:35 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/00.gzip/sparc/linux/simple-atomic tests/run.py long/00.gzip/sparc/linux/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 744757429500 because target called exit() +Exiting @ tick 744759833500 because target called exit() diff --git a/tests/long/00.gzip/ref/sparc/linux/simple-timing/config.ini b/tests/long/00.gzip/ref/sparc/linux/simple-timing/config.ini index 8f0821576..86d8c5b0f 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-timing/config.ini +++ b/tests/long/00.gzip/ref/sparc/linux/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/00.gzip/ref/sparc/linux/simple-timing/m5stats.txt b/tests/long/00.gzip/ref/sparc/linux/simple-timing/m5stats.txt index e732be59f..2a33edee7 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/long/00.gzip/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1190065 # Simulator instruction rate (inst/s) -host_mem_usage 201788 # Number of bytes of host memory used -host_seconds 1251.63 # Real time elapsed on the host -host_tick_rate 1654548560 # Simulator tick rate (ticks/s) +host_inst_rate 1120793 # Simulator instruction rate (inst/s) +host_mem_usage 183848 # Number of bytes of host memory used +host_seconds 1328.98 # Real time elapsed on the host +host_tick_rate 1558243449 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 1489514860 # Number of instructions simulated -sim_seconds 2.070875 # Number of seconds simulated -sim_ticks 2070875212000 # Number of ticks simulated +sim_insts 1489514761 # Number of instructions simulated +sim_seconds 2.070880 # Number of seconds simulated +sim_ticks 2070879986000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 402511688 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 23237.213149 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 21237.213149 # average ReadReq mshr miss latency @@ -86,14 +86,14 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 449136 # number of replacements system.cpu.dcache.sampled_refs 453232 # 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 4095.520244 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4095.519446 # Cycle average of tags in use system.cpu.dcache.total_refs 568906424 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 358125000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 358580000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 316447 # number of writebacks -system.cpu.icache.ReadReq_accesses 1489514861 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses 1489519635 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 24978.142077 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 22978.142077 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1489513763 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 1489518537 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 27426000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000001 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 1098 # number of ReadReq misses @@ -102,16 +102,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000001 # ms system.cpu.icache.ReadReq_mshr_misses 1098 # 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 1356569.911658 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 1356574.259563 # 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 1489514861 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 1489519635 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 24978.142077 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 22978.142077 # average overall mshr miss latency -system.cpu.icache.demand_hits 1489513763 # number of demand (read+write) hits +system.cpu.icache.demand_hits 1489518537 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 27426000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000001 # miss rate for demand accesses system.cpu.icache.demand_misses 1098 # number of demand (read+write) misses @@ -122,11 +122,11 @@ system.cpu.icache.demand_mshr_misses 1098 # nu 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 1489514861 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 1489519635 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 24978.142077 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 22978.142077 # 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 1489513763 # number of overall hits +system.cpu.icache.overall_hits 1489518537 # number of overall hits system.cpu.icache.overall_miss_latency 27426000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000001 # miss rate for overall accesses system.cpu.icache.overall_misses 1098 # number of overall misses @@ -148,8 +148,8 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 115 # number of replacements system.cpu.icache.sampled_refs 1098 # 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 891.566276 # Cycle average of tags in use -system.cpu.icache.total_refs 1489513763 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 891.566024 # Cycle average of tags in use +system.cpu.icache.total_refs 1489518537 # 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 @@ -234,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 18201 # number of replacements system.cpu.l2cache.sampled_refs 19574 # 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 8449.172652 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 8449.165713 # Cycle average of tags in use system.cpu.l2cache.total_refs 62289 # 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 2070875212000 # number of cpu cycles simulated -system.cpu.num_insts 1489514860 # Number of instructions executed -system.cpu.num_refs 569359656 # Number of memory references +system.cpu.numCycles 2070879986000 # number of cpu cycles simulated +system.cpu.num_insts 1489514761 # Number of instructions executed +system.cpu.num_refs 569364430 # Number of memory references system.cpu.workload.PROG:num_syscalls 19 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/00.gzip/ref/sparc/linux/simple-timing/stdout b/tests/long/00.gzip/ref/sparc/linux/simple-timing/stdout index 6d07eec7c..51f82ab6b 100644 --- a/tests/long/00.gzip/ref/sparc/linux/simple-timing/stdout +++ b/tests/long/00.gzip/ref/sparc/linux/simple-timing/stdout @@ -36,9 +36,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 12:23:15 -M5 started Sun Aug 12 16:24:16 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:04:52 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/00.gzip/sparc/linux/simple-timing tests/run.py long/00.gzip/sparc/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 2070875212000 because target called exit() +Exiting @ tick 2070879986000 because target called exit() diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/config.ini b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/config.ini index 9cdc13914..b261bdc1f 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=mcf mcf.in diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/m5stats.txt index ed8482fb4..88a38e809 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1151751 # Simulator instruction rate (inst/s) -host_mem_usage 150484 # Number of bytes of host memory used -host_seconds 211.71 # Real time elapsed on the host -host_tick_rate 575874246 # Simulator tick rate (ticks/s) +host_inst_rate 1759086 # Simulator instruction rate (inst/s) +host_mem_usage 176892 # Number of bytes of host memory used +host_seconds 138.61 # Real time elapsed on the host +host_tick_rate 881692154 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 243840172 # Number of instructions simulated -sim_seconds 0.121920 # Number of seconds simulated -sim_ticks 121920085500 # Number of ticks simulated +sim_insts 243829010 # Number of instructions simulated +sim_seconds 0.122213 # Number of seconds simulated +sim_ticks 122212687000 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 243840172 # number of cpu cycles simulated -system.cpu.num_insts 243840172 # Number of instructions executed -system.cpu.num_refs 105125191 # Number of memory references +system.cpu.numCycles 244425375 # number of cpu cycles simulated +system.cpu.num_insts 243829010 # Number of instructions executed +system.cpu.num_refs 105710359 # Number of memory references system.cpu.workload.PROG:num_syscalls 428 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/stdout b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/stdout index 448df62f5..0f3bf1970 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-atomic/stdout +++ b/tests/long/10.mcf/ref/sparc/linux/simple-atomic/stdout @@ -21,9 +21,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 21 2007 21:15:48 -M5 started Fri Jun 22 01:58:18 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:27:01 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/10.mcf/sparc/linux/simple-atomic tests/run.py long/10.mcf/sparc/linux/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 121920085500 because target called exit() +Exiting @ tick 122212687000 because target called exit() diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-timing/config.ini b/tests/long/10.mcf/ref/sparc/linux/simple-timing/config.ini index 5a68a6d2e..6e51c357c 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-timing/config.ini +++ b/tests/long/10.mcf/ref/sparc/linux/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-timing/m5stats.txt b/tests/long/10.mcf/ref/sparc/linux/simple-timing/m5stats.txt index e657db2a6..7fd034515 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/long/10.mcf/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1064489 # Simulator instruction rate (inst/s) -host_mem_usage 202188 # Number of bytes of host memory used -host_seconds 229.07 # Real time elapsed on the host -host_tick_rate 1583716497 # Simulator tick rate (ticks/s) +host_inst_rate 1059302 # Simulator instruction rate (inst/s) +host_mem_usage 184256 # Number of bytes of host memory used +host_seconds 230.18 # Real time elapsed on the host +host_tick_rate 1578613892 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 243840172 # Number of instructions simulated -sim_seconds 0.362779 # Number of seconds simulated -sim_ticks 362778959000 # Number of ticks simulated +sim_insts 243829010 # Number of instructions simulated +sim_seconds 0.363364 # Number of seconds simulated +sim_ticks 363364127000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 82219469 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 13897.517462 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 11897.517462 # average ReadReq mshr miss latency @@ -86,14 +86,14 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 935407 # number of replacements system.cpu.dcache.sampled_refs 939503 # 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 3565.606162 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 3566.459969 # Cycle average of tags in use system.cpu.dcache.total_refs 104185688 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 134193588000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 134193645000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 94807 # number of writebacks -system.cpu.icache.ReadReq_accesses 243840173 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses 244425341 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 24972.696246 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 22972.696246 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 243839294 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 244424462 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 21951000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000004 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 879 # number of ReadReq misses @@ -102,16 +102,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000004 # ms system.cpu.icache.ReadReq_mshr_misses 879 # 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 277405.340159 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 278071.060296 # 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 243840173 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 244425341 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 24972.696246 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 22972.696246 # average overall mshr miss latency -system.cpu.icache.demand_hits 243839294 # number of demand (read+write) hits +system.cpu.icache.demand_hits 244424462 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 21951000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000004 # miss rate for demand accesses system.cpu.icache.demand_misses 879 # number of demand (read+write) misses @@ -122,11 +122,11 @@ system.cpu.icache.demand_mshr_misses 879 # nu 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 243840173 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 244425341 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 24972.696246 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 22972.696246 # 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 243839294 # number of overall hits +system.cpu.icache.overall_hits 244424462 # number of overall hits system.cpu.icache.overall_miss_latency 21951000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000004 # miss rate for overall accesses system.cpu.icache.overall_misses 879 # number of overall misses @@ -148,8 +148,8 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 25 # number of replacements system.cpu.icache.sampled_refs 879 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 716.749422 # Cycle average of tags in use -system.cpu.icache.total_refs 243839294 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 716.846544 # Cycle average of tags in use +system.cpu.icache.total_refs 244424462 # 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 @@ -234,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 829 # number of replacements system.cpu.l2cache.sampled_refs 11345 # 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 8098.685225 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 8106.936507 # Cycle average of tags in use system.cpu.l2cache.total_refs 553407 # 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 362778959000 # number of cpu cycles simulated -system.cpu.num_insts 243840172 # Number of instructions executed -system.cpu.num_refs 105125191 # Number of memory references +system.cpu.numCycles 363364127000 # number of cpu cycles simulated +system.cpu.num_insts 243829010 # Number of instructions executed +system.cpu.num_refs 105710359 # Number of memory references system.cpu.workload.PROG:num_syscalls 428 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/10.mcf/ref/sparc/linux/simple-timing/stdout b/tests/long/10.mcf/ref/sparc/linux/simple-timing/stdout index c0328c6cb..300700c18 100644 --- a/tests/long/10.mcf/ref/sparc/linux/simple-timing/stdout +++ b/tests/long/10.mcf/ref/sparc/linux/simple-timing/stdout @@ -21,9 +21,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 12:23:15 -M5 started Sun Aug 12 16:47:12 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:29:20 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/10.mcf/sparc/linux/simple-timing tests/run.py long/10.mcf/sparc/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 362778959000 because target called exit() +Exiting @ tick 363364127000 because target called exit() diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini index 24e6c40a6..895539fc6 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/30.eon/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt index ce15a47de..373ebcd68 100644 --- a/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/30.eon/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 38073438 # Number of BTB hits -global.BPredUnit.BTBLookups 45542237 # Number of BTB lookups -global.BPredUnit.RASInCorrect 1066 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 5897861 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 35152227 # Number of conditional branches predicted -global.BPredUnit.lookups 62262084 # Number of BP lookups -global.BPredUnit.usedRAS 12565322 # Number of times the RAS was used to get a target. -host_inst_rate 169929 # Simulator instruction rate (inst/s) -host_mem_usage 207944 # Number of bytes of host memory used -host_seconds 2210.19 # Real time elapsed on the host -host_tick_rate 59827386 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 71764383 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 51661369 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 124318593 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 91863744 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 36861570 # Number of BTB hits +global.BPredUnit.BTBLookups 45954115 # Number of BTB lookups +global.BPredUnit.RASInCorrect 1137 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 5797485 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 35586107 # Number of conditional branches predicted +global.BPredUnit.lookups 62816866 # Number of BP lookups +global.BPredUnit.usedRAS 12584281 # Number of times the RAS was used to get a target. +host_inst_rate 159982 # Simulator instruction rate (inst/s) +host_mem_usage 190068 # Number of bytes of host memory used +host_seconds 2347.61 # Real time elapsed on the host +host_tick_rate 55593251 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 72605768 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 52678550 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 125601766 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 92855490 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 375574833 # Number of instructions simulated -sim_seconds 0.132230 # Number of seconds simulated -sim_ticks 132229900500 # Number of ticks simulated +sim_seconds 0.130511 # Number of seconds simulated +sim_ticks 130511349000 # Number of ticks simulated system.cpu.commit.COM:branches 44587535 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 12177812 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 13042688 # 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 249309209 +system.cpu.commit.COM:committed_per_cycle.samples 245378648 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 114305349 4584.88% - 1 51380693 2060.92% - 2 21363734 856.92% - 3 20883024 837.64% - 4 12699516 509.39% - 5 8486510 340.40% - 6 4833732 193.89% - 7 3178839 127.51% - 8 12177812 488.46% + 0 113059928 4607.57% + 1 50147502 2043.68% + 2 19710557 803.27% + 3 20862995 850.24% + 4 12236933 498.70% + 5 8068065 328.80% + 6 4872414 198.57% + 7 3377566 137.65% + 8 13042688 531.53% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,72 +43,72 @@ system.cpu.commit.COM:loads 100651996 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 174183399 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 5893662 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 5793282 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 398664608 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 215 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 93436434 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 97412298 # The number of squashed insts skipped by commit system.cpu.committedInsts 375574833 # Number of Instructions Simulated system.cpu.committedInsts_total 375574833 # Number of Instructions Simulated -system.cpu.cpi 0.704145 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.704145 # CPI: Total CPI of All Threads +system.cpu.cpi 0.694992 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.694992 # CPI: Total CPI of All Threads system.cpu.dcache.LoadLockedReq_accesses 1 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.LoadLockedReq_hits 1 # number of LoadLockedReq hits -system.cpu.dcache.ReadReq_accesses 96516428 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 11350.662589 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5775.739042 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 96515447 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 11135000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_accesses 96463931 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 11260.913706 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5745.177665 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 96462946 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 11092000 # number of ReadReq miss cycles system.cpu.dcache.ReadReq_miss_rate 0.000010 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 981 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 512 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 5666000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_misses 985 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 503 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 5659000 # number of ReadReq MSHR miss cycles system.cpu.dcache.ReadReq_mshr_miss_rate 0.000010 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 981 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 73513288 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 23676.737160 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6083.836858 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 73509978 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 78370000 # number of WriteReq miss cycles +system.cpu.dcache.ReadReq_mshr_misses 985 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 73513272 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 23662.839879 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6056.042296 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 73509962 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 78324000 # number of WriteReq miss cycles system.cpu.dcache.WriteReq_miss_rate 0.000045 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 3310 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 7442 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 20137500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_hits 7458 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 20045500 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.000045 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 3310 # 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 40714.928400 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 40702.353448 # 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 170029716 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 20858.774179 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 6013.400140 # average overall mshr miss latency -system.cpu.dcache.demand_hits 170025425 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 89505000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_accesses 169977203 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 20818.626310 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5984.749709 # average overall mshr miss latency +system.cpu.dcache.demand_hits 169972908 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 89416000 # number of demand (read+write) miss cycles system.cpu.dcache.demand_miss_rate 0.000025 # miss rate for demand accesses -system.cpu.dcache.demand_misses 4291 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 7954 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 25803500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_misses 4295 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 7961 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 25704500 # number of demand (read+write) MSHR miss cycles system.cpu.dcache.demand_mshr_miss_rate 0.000025 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 4291 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses 4295 # 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 170029716 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 20858.774179 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 6013.400140 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 169977203 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 20818.626310 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5984.749709 # 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 170025425 # number of overall hits -system.cpu.dcache.overall_miss_latency 89505000 # number of overall miss cycles +system.cpu.dcache.overall_hits 169972908 # number of overall hits +system.cpu.dcache.overall_miss_latency 89416000 # number of overall miss cycles system.cpu.dcache.overall_miss_rate 0.000025 # miss rate for overall accesses -system.cpu.dcache.overall_misses 4291 # number of overall misses -system.cpu.dcache.overall_mshr_hits 7954 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 25803500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_misses 4295 # number of overall misses +system.cpu.dcache.overall_mshr_hits 7961 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 25704500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_miss_rate 0.000025 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 4291 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses 4295 # 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 @@ -123,89 +123,101 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 780 # number of replacements system.cpu.dcache.sampled_refs 4176 # 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 3294.806600 # Cycle average of tags in use -system.cpu.dcache.total_refs 170025541 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 3295.577155 # Cycle average of tags in use +system.cpu.dcache.total_refs 169973028 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 635 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 14093330 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 4329 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 11426166 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 530907169 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 132358480 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 102072460 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 15149848 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 12784 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 784940 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 62262084 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 64149519 # Number of cache lines fetched -system.cpu.fetch.Cycles 169628877 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 1267942 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 544672632 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 6256256 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.235432 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 64149519 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 50638760 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 2.059573 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BlockedCycles 10379369 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 4333 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 11455632 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 536109933 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 132797558 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 101446828 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 15642913 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 12797 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 754894 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 185890093 # DTB accesses +system.cpu.dtb.acv 14625 # DTB access violations +system.cpu.dtb.hits 185845750 # DTB hits +system.cpu.dtb.misses 44343 # DTB misses +system.cpu.dtb.read_accesses 105156938 # DTB read accesses +system.cpu.dtb.read_acv 14625 # DTB read access violations +system.cpu.dtb.read_hits 105114144 # DTB read hits +system.cpu.dtb.read_misses 42794 # DTB read misses +system.cpu.dtb.write_accesses 80733155 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 80731606 # DTB write hits +system.cpu.dtb.write_misses 1549 # DTB write misses +system.cpu.fetch.Branches 62816866 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 64526365 # Number of cache lines fetched +system.cpu.fetch.Cycles 169349894 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 1380085 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 550063393 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 6176073 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.240658 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 64526365 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 49445851 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.107348 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 264459058 +system.cpu.fetch.rateDist.samples 261021562 system.cpu.fetch.rateDist.min_value 0 - 0 158979701 6011.51% - 1 11898103 449.90% - 2 12511338 473.09% - 3 6558243 247.99% - 4 15951093 603.16% - 5 8933216 337.79% - 6 6667977 252.14% - 7 4076286 154.14% - 8 38883101 1470.29% + 0 156198329 5984.12% + 1 10474114 401.27% + 2 12009483 460.10% + 3 7031360 269.38% + 4 15051020 576.62% + 5 10018831 383.83% + 6 6809824 260.89% + 7 4109754 157.45% + 8 39318847 1506.34% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 64149331 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7193.164363 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5001.152074 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 64145425 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 28096500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000061 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 3906 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 188 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 19534500 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000061 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 3906 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 64526174 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7182.389131 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 4988.079979 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 64522273 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 28018500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000060 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 3901 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 191 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 19458500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000060 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 3901 # 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 16422.279826 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 16539.931556 # 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 64149331 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7193.164363 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5001.152074 # average overall mshr miss latency -system.cpu.icache.demand_hits 64145425 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 28096500 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000061 # miss rate for demand accesses -system.cpu.icache.demand_misses 3906 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 188 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 19534500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000061 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 3906 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 64526174 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7182.389131 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 4988.079979 # average overall mshr miss latency +system.cpu.icache.demand_hits 64522273 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 28018500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000060 # miss rate for demand accesses +system.cpu.icache.demand_misses 3901 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 191 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 19458500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000060 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 3901 # 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 64149331 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7193.164363 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5001.152074 # average overall mshr miss latency +system.cpu.icache.overall_accesses 64526174 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7182.389131 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 4988.079979 # 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 64145425 # number of overall hits -system.cpu.icache.overall_miss_latency 28096500 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000061 # miss rate for overall accesses -system.cpu.icache.overall_misses 3906 # number of overall misses -system.cpu.icache.overall_mshr_hits 188 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 19534500 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000061 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 3906 # number of overall MSHR misses +system.cpu.icache.overall_hits 64522273 # number of overall hits +system.cpu.icache.overall_miss_latency 28018500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000060 # miss rate for overall accesses +system.cpu.icache.overall_misses 3901 # number of overall misses +system.cpu.icache.overall_mshr_hits 191 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 19458500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000060 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 3901 # 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 @@ -217,144 +229,148 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 1984 # number of replacements -system.cpu.icache.sampled_refs 3906 # Sample count of references to valid blocks. +system.cpu.icache.replacements 1979 # number of replacements +system.cpu.icache.sampled_refs 3901 # 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 1827.150129 # Cycle average of tags in use -system.cpu.icache.total_refs 64145425 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1827.041992 # Cycle average of tags in use +system.cpu.icache.total_refs 64522273 # 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 557628 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 51104102 # Number of branches executed -system.cpu.iew.EXEC:nop 27319155 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.584545 # Inst execution rate -system.cpu.iew.EXEC:refs 191326029 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 79588041 # Number of stores executed +system.cpu.idleCycles 787561 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 51184181 # Number of branches executed +system.cpu.iew.EXEC:nop 27521515 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.613810 # Inst execution rate +system.cpu.iew.EXEC:refs 192783461 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 80743835 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 282498519 # num instructions consuming a value -system.cpu.iew.WB:count 414521159 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.706139 # average fanout of values written-back +system.cpu.iew.WB:consumers 284447545 # num instructions consuming a value +system.cpu.iew.WB:count 417188655 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.706015 # 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 199483248 # num instructions producing a value -system.cpu.iew.WB:rate 1.567430 # insts written-back per cycle -system.cpu.iew.WB:sent 415435713 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 6236762 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 2781988 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 124318593 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 240 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 6814163 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 91863744 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 492099709 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 111737988 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 8739319 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 419047233 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 168412 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 200824371 # num instructions producing a value +system.cpu.iew.WB:rate 1.598292 # insts written-back per cycle +system.cpu.iew.WB:sent 418096768 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 6170690 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 1426561 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 125601766 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 239 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 6545178 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 92855490 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 496077841 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 112039626 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 9995558 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 421239213 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 59610 # 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 50946 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 15149848 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 506738 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 24612 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 15642913 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 326804 # 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 8219638 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 31016 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 8473702 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 35459 # 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 502753 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 178119 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 23666597 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 18332341 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 502753 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 955669 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 5281093 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.420162 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.420162 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 427786552 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 574238 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 176007 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 24949770 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 19324087 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 574238 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 908757 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 5261933 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.438865 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.438865 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 431234771 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 33581 0.01% # Type of FU issued - IntAlu 166519693 38.93% # Type of FU issued - IntMult 2147905 0.50% # Type of FU issued + IntAlu 167547165 38.85% # Type of FU issued + IntMult 2148252 0.50% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 35254026 8.24% # Type of FU issued - FloatCmp 7817685 1.83% # Type of FU issued - FloatCvt 2969947 0.69% # Type of FU issued - FloatMult 16787400 3.92% # Type of FU issued - FloatDiv 1570522 0.37% # Type of FU issued + FloatAdd 34932915 8.10% # Type of FU issued + FloatCmp 7864913 1.82% # Type of FU issued + FloatCvt 2933513 0.68% # Type of FU issued + FloatMult 16766961 3.89% # Type of FU issued + FloatDiv 1572145 0.36% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 113248293 26.47% # Type of FU issued - MemWrite 81437500 19.04% # Type of FU issued + MemRead 114624584 26.58% # Type of FU issued + MemWrite 82810742 19.20% # 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 9448608 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.022087 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 10914524 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.025310 # 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 17181 0.18% # attempts to use FU when none available + IntAlu 15305 0.14% # 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 604 0.01% # attempts to use FU when none available - FloatCmp 32516 0.34% # attempts to use FU when none available - FloatCvt 8012 0.08% # attempts to use FU when none available - FloatMult 2137313 22.62% # attempts to use FU when none available - FloatDiv 917798 9.71% # attempts to use FU when none available + FloatAdd 41564 0.38% # attempts to use FU when none available + FloatCmp 31641 0.29% # attempts to use FU when none available + FloatCvt 9732 0.09% # attempts to use FU when none available + FloatMult 2290427 20.99% # attempts to use FU when none available + FloatDiv 1536693 14.08% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 5261958 55.69% # attempts to use FU when none available - MemWrite 1073226 11.36% # attempts to use FU when none available + MemRead 5500856 50.40% # attempts to use FU when none available + MemWrite 1488306 13.64% # 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 264459058 +system.cpu.iq.ISSUE:issued_per_cycle.samples 261021562 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 94473273 3572.32% - 1 57538428 2175.70% - 2 41283183 1561.04% - 3 28951087 1094.73% - 4 22152944 837.67% - 5 11939207 451.46% - 6 5137200 194.25% - 7 2172402 82.15% - 8 811334 30.68% + 0 92982852 3562.27% + 1 54227475 2077.51% + 2 40411704 1548.21% + 3 29929713 1146.64% + 4 23083699 884.36% + 5 11888091 455.44% + 6 5433351 208.16% + 7 2498024 95.70% + 8 566653 21.71% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.617591 # Inst issue rate -system.cpu.iq.iqInstsAdded 464780314 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 427786552 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 240 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 88460147 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 742026 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 25 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 67499517 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadExReq_accesses 3199 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4646.764614 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2646.764614 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 14865000 # number of ReadExReq miss cycles +system.cpu.iq.ISSUE:rate 1.652104 # Inst issue rate +system.cpu.iq.iqInstsAdded 468556087 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 431234771 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 239 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 92147793 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 947116 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 24 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 68967166 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 64526661 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 64526365 # ITB hits +system.cpu.itb.misses 296 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 3195 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4623.317684 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2623.317684 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 14771500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_misses 3199 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 8467000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 3195 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 8381500 # 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 3199 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 4883 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4356.375525 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2356.375525 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 601 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 18654000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.876920 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 4282 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 10090000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.876920 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 4282 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 117 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4482.905983 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2482.905983 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 524500 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_mshr_misses 3195 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 4882 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4343.436699 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2343.436699 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 593 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 18629000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.878533 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 4289 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 10051000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.878533 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 4289 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 121 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4487.603306 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2487.603306 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 543000 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_misses 117 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 290500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 121 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 301000 # 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 117 # number of UpgradeReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 121 # number of UpgradeReq MSHR misses system.cpu.l2cache.Writeback_accesses 635 # number of Writeback accesses(hits+misses) system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses system.cpu.l2cache.Writeback_misses 635 # number of Writeback misses @@ -362,38 +378,38 @@ system.cpu.l2cache.Writeback_mshr_miss_rate 1 # system.cpu.l2cache.Writeback_mshr_misses 635 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 0.139496 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.137476 # 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 8082 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4480.550729 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2480.550729 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 601 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 33519000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.925637 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 7481 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 8077 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4462.920898 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2462.920898 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 593 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 33400500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.926582 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 7484 # 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 18557000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.925637 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 7481 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 18432500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.926582 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 7484 # 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 8082 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4480.550729 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2480.550729 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 8077 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4462.920898 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2462.920898 # 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 601 # number of overall hits -system.cpu.l2cache.overall_miss_latency 33519000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.925637 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 7481 # number of overall misses +system.cpu.l2cache.overall_hits 593 # number of overall hits +system.cpu.l2cache.overall_miss_latency 33400500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.926582 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 7484 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 18557000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.925637 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 7481 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 18432500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.926582 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 7484 # 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 @@ -406,30 +422,30 @@ 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 6 # number of replacements -system.cpu.l2cache.sampled_refs 4165 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 4168 # 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 3521.188558 # Cycle average of tags in use -system.cpu.l2cache.total_refs 581 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 3522.085649 # Cycle average of tags in use +system.cpu.l2cache.total_refs 573 # 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 264459058 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 6942912 # Number of cycles rename is blocking +system.cpu.numCycles 261021562 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 4632657 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 259532351 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 1128496 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 136398173 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 4996172 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 682131973 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 517993086 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 334891535 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 98637930 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 15149848 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 6975590 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 75359184 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 354605 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 37909 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 15667924 # count of insts added to the skid buffer +system.cpu.rename.RENAME:IQFullEvents 371371 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 136793870 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 4480722 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 687103591 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 521769627 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 337207883 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 98011455 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 15642913 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 5589343 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 77675532 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 351324 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 37944 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 12960882 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 253 # count of temporary serializing insts renamed -system.cpu.timesIdled 375 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 442 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 215 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/30.eon/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/30.eon/ref/alpha/tru64/simple-atomic/config.ini index 58022eaf1..bfc3d0e40 100644 --- a/tests/long/30.eon/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/30.eon/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=eon chair.control.cook chair.camera chair.surfaces chair.cook.ppm ppm pixels_out.cook @@ -53,7 +67,7 @@ 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/long/30.eon/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/30.eon/ref/alpha/tru64/simple-atomic/m5stats.txt index 2e2beec40..e32cacf16 100644 --- a/tests/long/30.eon/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/30.eon/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 828868 # Simulator instruction rate (inst/s) -host_mem_usage 151076 # Number of bytes of host memory used -host_seconds 480.97 # Real time elapsed on the host -host_tick_rate 414433819 # Simulator tick rate (ticks/s) +host_inst_rate 2526947 # Simulator instruction rate (inst/s) +host_mem_usage 181828 # Number of bytes of host memory used +host_seconds 157.77 # Real time elapsed on the host +host_tick_rate 1263471125 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 398664597 # Number of instructions simulated +sim_insts 398664595 # Number of instructions simulated sim_seconds 0.199332 # Number of seconds simulated -sim_ticks 199332298000 # Number of ticks simulated +sim_ticks 199332411500 # Number of ticks simulated +system.cpu.dtb.accesses 168275274 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 168275218 # DTB hits +system.cpu.dtb.misses 56 # DTB misses +system.cpu.dtb.read_accesses 94754510 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 94754489 # DTB read hits +system.cpu.dtb.read_misses 21 # DTB read misses +system.cpu.dtb.write_accesses 73520764 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 73520729 # DTB write hits +system.cpu.dtb.write_misses 35 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 398664824 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 398664651 # ITB hits +system.cpu.itb.misses 173 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 398664597 # number of cpu cycles simulated -system.cpu.num_insts 398664597 # Number of instructions executed -system.cpu.num_refs 174183399 # Number of memory references +system.cpu.numCycles 398664824 # number of cpu cycles simulated +system.cpu.num_insts 398664595 # Number of instructions executed +system.cpu.num_refs 174183453 # Number of memory references system.cpu.workload.PROG:num_syscalls 215 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/30.eon/ref/alpha/tru64/simple-timing/config.ini b/tests/long/30.eon/ref/alpha/tru64/simple-timing/config.ini index 2f7931c5a..f30cc2238 100644 --- a/tests/long/30.eon/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/30.eon/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/30.eon/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/30.eon/ref/alpha/tru64/simple-timing/m5stats.txt index 5d80e04f0..9be74e08a 100644 --- a/tests/long/30.eon/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/30.eon/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1477024 # Simulator instruction rate (inst/s) -host_mem_usage 207136 # Number of bytes of host memory used -host_seconds 269.91 # Real time elapsed on the host -host_tick_rate 2101151515 # Simulator tick rate (ticks/s) +host_inst_rate 1404632 # Simulator instruction rate (inst/s) +host_mem_usage 189192 # Number of bytes of host memory used +host_seconds 283.82 # Real time elapsed on the host +host_tick_rate 1998169503 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 398664611 # Number of instructions simulated +sim_insts 398664609 # Number of instructions simulated sim_seconds 0.567124 # Number of seconds simulated -sim_ticks 567123959000 # Number of ticks simulated +sim_ticks 567124013000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 94754490 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 24216.842105 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 22216.842105 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 764 # number of replacements system.cpu.dcache.sampled_refs 4152 # 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 3289.454030 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 3289.453852 # Cycle average of tags in use system.cpu.dcache.total_refs 168271068 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 625 # number of writebacks -system.cpu.icache.ReadReq_accesses 398664612 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 168275276 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 168275220 # DTB hits +system.cpu.dtb.misses 56 # DTB misses +system.cpu.dtb.read_accesses 94754511 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 94754490 # DTB read hits +system.cpu.dtb.read_misses 21 # DTB read misses +system.cpu.dtb.write_accesses 73520765 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 73520730 # DTB write hits +system.cpu.dtb.write_misses 35 # DTB write misses +system.cpu.icache.ReadReq_accesses 398664666 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 23471.004628 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 21471.004628 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 398660939 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 398660993 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 86209000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000009 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 3673 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000009 # ms system.cpu.icache.ReadReq_mshr_misses 3673 # 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 108538.235502 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 108538.250204 # 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 398664612 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 398664666 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 23471.004628 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 21471.004628 # average overall mshr miss latency -system.cpu.icache.demand_hits 398660939 # number of demand (read+write) hits +system.cpu.icache.demand_hits 398660993 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 86209000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000009 # miss rate for demand accesses system.cpu.icache.demand_misses 3673 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 3673 # nu 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 398664612 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 398664666 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 23471.004628 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 21471.004628 # 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 398660939 # number of overall hits +system.cpu.icache.overall_hits 398660993 # number of overall hits system.cpu.icache.overall_miss_latency 86209000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000009 # miss rate for overall accesses system.cpu.icache.overall_misses 3673 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 1769 # number of replacements system.cpu.icache.sampled_refs 3673 # 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 1795.369888 # Cycle average of tags in use -system.cpu.icache.total_refs 398660939 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1795.369803 # Cycle average of tags in use +system.cpu.icache.total_refs 398660993 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 398664839 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 398664666 # ITB hits +system.cpu.itb.misses 173 # ITB misses system.cpu.l2cache.ReadExReq_accesses 3202 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 6 # number of replacements system.cpu.l2cache.sampled_refs 3981 # 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 3355.056948 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 3355.056761 # Cycle average of tags in use system.cpu.l2cache.total_refs 510 # 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 567123959000 # number of cpu cycles simulated -system.cpu.num_insts 398664611 # Number of instructions executed -system.cpu.num_refs 174183401 # Number of memory references +system.cpu.numCycles 567124013000 # number of cpu cycles simulated +system.cpu.num_insts 398664609 # Number of instructions executed +system.cpu.num_refs 174183455 # Number of memory references system.cpu.workload.PROG:num_syscalls 215 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/config.ini index 1b858fca2..9054cf093 100644 --- a/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=perlbmk -I. -I lib lgred.makerand.pl @@ -53,7 +67,7 @@ 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/long/40.perlbmk/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/m5stats.txt index 0f58a9003..3a5a57719 100644 --- a/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/40.perlbmk/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 855891 # Simulator instruction rate (inst/s) -host_mem_usage 151228 # Number of bytes of host memory used -host_seconds 2347.25 # Real time elapsed on the host -host_tick_rate 427945543 # Simulator tick rate (ticks/s) +host_inst_rate 2579952 # Simulator instruction rate (inst/s) +host_mem_usage 180972 # Number of bytes of host memory used +host_seconds 778.69 # Real time elapsed on the host +host_tick_rate 1290253991 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2008987607 # Number of instructions simulated -sim_seconds 1.004494 # Number of seconds simulated -sim_ticks 1004493803000 # Number of ticks simulated +sim_insts 2008987605 # Number of instructions simulated +sim_seconds 1.004711 # Number of seconds simulated +sim_ticks 1004710587000 # Number of ticks simulated +system.cpu.dtb.accesses 722298387 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 721864922 # DTB hits +system.cpu.dtb.misses 433465 # DTB misses +system.cpu.dtb.read_accesses 511488910 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 511070026 # DTB read hits +system.cpu.dtb.read_misses 418884 # DTB read misses +system.cpu.dtb.write_accesses 210809477 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 210794896 # DTB write hits +system.cpu.dtb.write_misses 14581 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2009421175 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2009421070 # ITB hits +system.cpu.itb.misses 105 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 2008987607 # number of cpu cycles simulated -system.cpu.num_insts 2008987607 # Number of instructions executed -system.cpu.num_refs 722390435 # Number of memory references +system.cpu.numCycles 2009421175 # number of cpu cycles simulated +system.cpu.num_insts 2008987605 # Number of instructions executed +system.cpu.num_refs 722823898 # Number of memory references system.cpu.workload.PROG:num_syscalls 39 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/config.ini b/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/config.ini index 31abd8f36..7ccc4388b 100644 --- a/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/m5stats.txt index ea21ed74e..4725fc27c 100644 --- a/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/40.perlbmk/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1536320 # Simulator instruction rate (inst/s) -host_mem_usage 206288 # Number of bytes of host memory used -host_seconds 1307.66 # Real time elapsed on the host -host_tick_rate 2116487900 # Simulator tick rate (ticks/s) +host_inst_rate 1524477 # Simulator instruction rate (inst/s) +host_mem_usage 188336 # Number of bytes of host memory used +host_seconds 1317.82 # Real time elapsed on the host +host_tick_rate 2100501698 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2008987607 # Number of instructions simulated -sim_seconds 2.767652 # Number of seconds simulated -sim_ticks 2767652365000 # Number of ticks simulated +sim_insts 2008987605 # Number of instructions simulated +sim_seconds 2.768086 # Number of seconds simulated +sim_ticks 2768085828000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 511070026 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 24898.959808 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 22898.959808 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 1526048 # number of replacements system.cpu.dcache.sampled_refs 1530144 # 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 4095.361611 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4095.361643 # Cycle average of tags in use system.cpu.dcache.total_refs 720334778 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 795826000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 795905000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 74589 # number of writebacks -system.cpu.icache.ReadReq_accesses 2008987608 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 722298387 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 721864922 # DTB hits +system.cpu.dtb.misses 433465 # DTB misses +system.cpu.dtb.read_accesses 511488910 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 511070026 # DTB read hits +system.cpu.dtb.read_misses 418884 # DTB read misses +system.cpu.dtb.write_accesses 210809477 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 210794896 # DTB write hits +system.cpu.dtb.write_misses 14581 # DTB write misses +system.cpu.icache.ReadReq_accesses 2009421071 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 15691.959230 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 13691.959230 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 2008977012 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 2009410475 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 166272000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000005 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 10596 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000005 # ms system.cpu.icache.ReadReq_mshr_misses 10596 # 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 189597.679502 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 189638.587675 # 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 2008987608 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 2009421071 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 15691.959230 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 13691.959230 # average overall mshr miss latency -system.cpu.icache.demand_hits 2008977012 # number of demand (read+write) hits +system.cpu.icache.demand_hits 2009410475 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 166272000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000005 # miss rate for demand accesses system.cpu.icache.demand_misses 10596 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 10596 # nu 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 2008987608 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 2009421071 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 15691.959230 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 13691.959230 # 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 2008977012 # number of overall hits +system.cpu.icache.overall_hits 2009410475 # number of overall hits system.cpu.icache.overall_miss_latency 166272000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000005 # miss rate for overall accesses system.cpu.icache.overall_misses 10596 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 9046 # number of replacements system.cpu.icache.sampled_refs 10596 # 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 1478.559322 # Cycle average of tags in use -system.cpu.icache.total_refs 2008977012 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1478.559335 # Cycle average of tags in use +system.cpu.icache.total_refs 2009410475 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2009421176 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2009421071 # ITB hits +system.cpu.itb.misses 105 # ITB misses system.cpu.l2cache.ReadExReq_accesses 71952 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 1412930 # number of replacements system.cpu.l2cache.sampled_refs 1445479 # 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 31165.183060 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 31165.186472 # Cycle average of tags in use system.cpu.l2cache.total_refs 22612 # 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 2767652365000 # number of cpu cycles simulated -system.cpu.num_insts 2008987607 # Number of instructions executed -system.cpu.num_refs 722390435 # Number of memory references +system.cpu.numCycles 2768085828000 # number of cpu cycles simulated +system.cpu.num_insts 2008987605 # Number of instructions executed +system.cpu.num_refs 722823898 # Number of memory references system.cpu.workload.PROG:num_syscalls 39 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini index 2052b6302..dffb46ac1 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt index 3ea341d47..b4b0c54a3 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/50.vortex/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 7542290 # Number of BTB hits -global.BPredUnit.BTBLookups 13308941 # Number of BTB lookups -global.BPredUnit.RASInCorrect 34250 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 454073 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 9847799 # Number of conditional branches predicted -global.BPredUnit.lookups 15155323 # Number of BP lookups -global.BPredUnit.usedRAS 1795531 # Number of times the RAS was used to get a target. -host_inst_rate 196409 # Simulator instruction rate (inst/s) -host_mem_usage 211144 # Number of bytes of host memory used -host_seconds 405.24 # Real time elapsed on the host -host_tick_rate 57107000 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 11563356 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 10718994 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 21578903 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 15738647 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 8001673 # Number of BTB hits +global.BPredUnit.BTBLookups 14256966 # Number of BTB lookups +global.BPredUnit.RASInCorrect 35545 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 455902 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 10551273 # Number of conditional branches predicted +global.BPredUnit.lookups 16246333 # Number of BP lookups +global.BPredUnit.usedRAS 1941036 # Number of times the RAS was used to get a target. +host_inst_rate 173213 # Simulator instruction rate (inst/s) +host_mem_usage 193376 # Number of bytes of host memory used +host_seconds 459.50 # Real time elapsed on the host +host_tick_rate 54150958 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 12304370 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 10964244 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 22974359 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 16298386 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 79591756 # Number of instructions simulated -sim_seconds 0.023142 # Number of seconds simulated -sim_ticks 23141799000 # Number of ticks simulated +sim_seconds 0.024882 # Number of seconds simulated +sim_ticks 24882469000 # Number of ticks simulated system.cpu.commit.COM:branches 13754477 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 3510282 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 3430644 # 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 45393667 +system.cpu.commit.COM:committed_per_cycle.samples 48501675 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 16854505 3712.96% - 1 10816662 2382.86% - 2 5010201 1103.72% - 3 3353080 738.67% - 4 2515867 554.23% - 5 1511689 333.02% - 6 1009468 222.38% - 7 811913 178.86% - 8 3510282 773.30% + 0 19715966 4065.01% + 1 10943165 2256.24% + 2 5093030 1050.07% + 3 3475751 716.62% + 4 2505421 516.56% + 5 1522534 313.91% + 6 1001460 206.48% + 7 813704 167.77% + 8 3430644 707.32% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,72 +43,72 @@ system.cpu.commit.COM:loads 20379399 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 35224018 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 357583 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 360143 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 88340672 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 4583 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 5444219 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 8051078 # The number of squashed insts skipped by commit system.cpu.committedInsts 79591756 # Number of Instructions Simulated system.cpu.committedInsts_total 79591756 # Number of Instructions Simulated -system.cpu.cpi 0.581499 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.581499 # CPI: Total CPI of All Threads -system.cpu.dcache.LoadLockedReq_accesses 43 # number of LoadLockedReq accesses(hits+misses) -system.cpu.dcache.LoadLockedReq_hits 43 # number of LoadLockedReq hits -system.cpu.dcache.ReadReq_accesses 19849413 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 15478.106634 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4237.239017 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 19787819 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 953358500 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.003103 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 61594 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 85223 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 260988500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.003103 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 61594 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 13805554 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 30519.673214 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5295.405245 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 13655731 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 4572549000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.010852 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 149823 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 807823 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 793373500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.010852 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 149823 # number of WriteReq MSHR misses +system.cpu.cpi 0.625230 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.625230 # CPI: Total CPI of All Threads +system.cpu.dcache.LoadLockedReq_accesses 44 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.LoadLockedReq_hits 44 # number of LoadLockedReq hits +system.cpu.dcache.ReadReq_accesses 20377695 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 15251.726884 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 4211.460009 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 20316168 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 938393000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.003019 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 61527 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 82932 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 259118500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.003019 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 61527 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 13807431 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 30521.435580 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5307.053083 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 13657610 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 4572752000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.010851 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 149821 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 805946 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 795108000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.010851 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 149821 # 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 163.116342 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 165.739033 # 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 33654967 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 26137.479484 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 4987.120241 # average overall mshr miss latency -system.cpu.dcache.demand_hits 33443550 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 5525907500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.006282 # miss rate for demand accesses -system.cpu.dcache.demand_misses 211417 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 893046 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1054362000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.006282 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 211417 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 34185126 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 26076.163484 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 4988.107292 # average overall mshr miss latency +system.cpu.dcache.demand_hits 33973778 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 5511145000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.006182 # miss rate for demand accesses +system.cpu.dcache.demand_misses 211348 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 888878 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 1054226500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.006182 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 211348 # 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 33654967 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 26137.479484 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 4987.120241 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 34185126 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 26076.163484 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 4988.107292 # 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 33443550 # number of overall hits -system.cpu.dcache.overall_miss_latency 5525907500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.006282 # miss rate for overall accesses -system.cpu.dcache.overall_misses 211417 # number of overall misses -system.cpu.dcache.overall_mshr_hits 893046 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1054362000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.006282 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 211417 # number of overall MSHR misses +system.cpu.dcache.overall_hits 33973778 # number of overall hits +system.cpu.dcache.overall_miss_latency 5511145000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.006182 # miss rate for overall accesses +system.cpu.dcache.overall_misses 211348 # number of overall misses +system.cpu.dcache.overall_mshr_hits 888878 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 1054226500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.006182 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 211348 # 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 @@ -120,92 +120,104 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 200972 # number of replacements -system.cpu.dcache.sampled_refs 205068 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 200926 # number of replacements +system.cpu.dcache.sampled_refs 205022 # 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 4079.963353 # Cycle average of tags in use -system.cpu.dcache.total_refs 33449942 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 119008000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.tagsinuse 4080.923075 # Cycle average of tags in use +system.cpu.dcache.total_refs 33980148 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 120631000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 147761 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 971695 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 97371 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 3417858 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 96162354 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 25952342 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 18439987 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 888885 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 288762 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 29644 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 15155323 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 12535185 # Number of cache lines fetched -system.cpu.fetch.Cycles 31179449 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 131701 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 97686537 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 470452 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.327452 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 12535185 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 9337821 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 2.110656 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BlockedCycles 953936 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 96699 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 3650405 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 101647473 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 27934130 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 19589260 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 1261472 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 284553 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 24350 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 36627778 # DTB accesses +system.cpu.dtb.acv 37 # DTB access violations +system.cpu.dtb.hits 36455125 # DTB hits +system.cpu.dtb.misses 172653 # DTB misses +system.cpu.dtb.read_accesses 21565019 # DTB read accesses +system.cpu.dtb.read_acv 35 # DTB read access violations +system.cpu.dtb.read_hits 21407076 # DTB read hits +system.cpu.dtb.read_misses 157943 # DTB read misses +system.cpu.dtb.write_accesses 15062759 # DTB write accesses +system.cpu.dtb.write_acv 2 # DTB write access violations +system.cpu.dtb.write_hits 15048049 # DTB write hits +system.cpu.dtb.write_misses 14710 # DTB write misses +system.cpu.fetch.Branches 16246333 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 13375683 # Number of cache lines fetched +system.cpu.fetch.Cycles 33194597 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 152184 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 103251284 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 572846 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.326473 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 13375683 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 9942709 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.074854 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 46282553 +system.cpu.fetch.rateDist.samples 49763148 system.cpu.fetch.rateDist.min_value 0 - 0 27638291 5971.64% - 1 1733920 374.64% - 2 1408099 304.24% - 3 1707036 368.83% - 4 3689148 797.09% - 5 1739866 375.92% - 6 655334 141.59% - 7 1059487 228.92% - 8 6651372 1437.12% + 0 29969634 6022.46% + 1 1857821 373.33% + 2 1524433 306.34% + 3 1786134 358.93% + 4 3977224 799.23% + 5 1866445 375.07% + 6 698149 140.29% + 7 1110284 223.11% + 8 6973024 1401.24% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 12534294 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 4593.252212 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 2552.911039 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 12448414 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 394468500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.006852 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 85880 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 891 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 219244000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.006852 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 85880 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 13374854 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 4582.447586 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 2544.287368 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 13289333 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 391895500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.006394 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 85521 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 829 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 217590000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.006394 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 85521 # 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 144.958009 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 155.392629 # 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 12534294 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 4593.252212 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 2552.911039 # average overall mshr miss latency -system.cpu.icache.demand_hits 12448414 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 394468500 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.006852 # miss rate for demand accesses -system.cpu.icache.demand_misses 85880 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 891 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 219244000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.006852 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 85880 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 13374854 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 4582.447586 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 2544.287368 # average overall mshr miss latency +system.cpu.icache.demand_hits 13289333 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 391895500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.006394 # miss rate for demand accesses +system.cpu.icache.demand_misses 85521 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 829 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 217590000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.006394 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 85521 # 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 12534294 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 4593.252212 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 2552.911039 # average overall mshr miss latency +system.cpu.icache.overall_accesses 13374854 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 4582.447586 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 2544.287368 # 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 12448414 # number of overall hits -system.cpu.icache.overall_miss_latency 394468500 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.006852 # miss rate for overall accesses -system.cpu.icache.overall_misses 85880 # number of overall misses -system.cpu.icache.overall_mshr_hits 891 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 219244000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.006852 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 85880 # number of overall MSHR misses +system.cpu.icache.overall_hits 13289333 # number of overall hits +system.cpu.icache.overall_miss_latency 391895500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.006394 # miss rate for overall accesses +system.cpu.icache.overall_misses 85521 # number of overall misses +system.cpu.icache.overall_mshr_hits 829 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 217590000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.006394 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 85521 # 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 @@ -217,80 +229,80 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 83828 # number of replacements -system.cpu.icache.sampled_refs 85876 # Sample count of references to valid blocks. +system.cpu.icache.replacements 83473 # number of replacements +system.cpu.icache.sampled_refs 85521 # 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 1919.939531 # Cycle average of tags in use -system.cpu.icache.total_refs 12448414 # Total number of references to valid blocks. -system.cpu.icache.warmup_cycle 20180672000 # Cycle when the warmup percentage was hit. +system.cpu.icache.tagsinuse 1922.769682 # Cycle average of tags in use +system.cpu.icache.total_refs 13289333 # Total number of references to valid blocks. +system.cpu.icache.warmup_cycle 21643859000 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.idleCycles 779486 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 14215317 # Number of branches executed -system.cpu.iew.EXEC:nop 9054056 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.776804 # Inst execution rate -system.cpu.iew.EXEC:refs 36085022 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 15098216 # Number of stores executed +system.cpu.idleCycles 1231826 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 14739683 # Number of branches executed +system.cpu.iew.EXEC:nop 9380523 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.704450 # Inst execution rate +system.cpu.iew.EXEC:refs 36969776 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 15295559 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 41423091 # num instructions consuming a value -system.cpu.iew.WB:count 81970056 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.763712 # average fanout of values written-back +system.cpu.iew.WB:consumers 42405904 # num instructions consuming a value +system.cpu.iew.WB:count 84333016 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.765386 # 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 31635305 # num instructions producing a value -system.cpu.iew.WB:rate 1.771079 # insts written-back per cycle -system.cpu.iew.WB:sent 82027383 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 388269 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 17461 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 21578903 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 4692 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 341214 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 15738647 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 93782111 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 20986806 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 455724 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 82235016 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 2252 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 32456867 # num instructions producing a value +system.cpu.iew.WB:rate 1.694688 # insts written-back per cycle +system.cpu.iew.WB:sent 84566644 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 400717 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 20492 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 22974359 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 4987 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 359590 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 16298386 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 98827714 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 21674217 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 545926 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 84818805 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 2571 # 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 122 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 888885 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 3197 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 174 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 1261472 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 3172 # 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 937737 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 950 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 945093 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 1085 # 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 19015 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 1226 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 1199504 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 894028 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 19015 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 105591 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 282678 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.719692 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.719692 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 82690740 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 19531 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 1312 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 2594960 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 1453767 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 19531 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 108348 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 292369 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.599412 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.599412 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 85364731 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 0 0.00% # Type of FU issued - IntAlu 46107608 55.76% # Type of FU issued - IntMult 43061 0.05% # Type of FU issued + IntAlu 47879047 56.09% # Type of FU issued + IntMult 43747 0.05% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 119602 0.14% # Type of FU issued - FloatCmp 87 0.00% # Type of FU issued - FloatCvt 120853 0.15% # Type of FU issued + FloatAdd 121378 0.14% # Type of FU issued + FloatCmp 86 0.00% # Type of FU issued + FloatCvt 121979 0.14% # Type of FU issued FloatMult 50 0.00% # Type of FU issued - FloatDiv 37774 0.05% # Type of FU issued + FloatDiv 38527 0.05% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 21079728 25.49% # Type of FU issued - MemWrite 15181977 18.36% # Type of FU issued + MemRead 21782176 25.52% # Type of FU issued + MemWrite 15377741 18.01% # 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 974009 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.011779 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 969096 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.011352 # 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 90058 9.25% # attempts to use FU when none available + IntAlu 95806 9.89% # 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 @@ -299,62 +311,66 @@ 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 437339 44.90% # attempts to use FU when none available - MemWrite 446612 45.85% # attempts to use FU when none available + MemRead 442018 45.61% # attempts to use FU when none available + MemWrite 431272 44.50% # 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 46282553 +system.cpu.iq.ISSUE:issued_per_cycle.samples 49763148 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 12550048 2711.62% - 1 12875827 2782.00% - 2 7785024 1682.06% - 3 4673558 1009.79% - 4 4500672 972.43% - 5 2074677 448.26% - 6 1137561 245.79% - 7 458736 99.12% - 8 226450 48.93% + 0 14890253 2992.22% + 1 13307982 2674.26% + 2 8090593 1625.82% + 3 4789845 962.53% + 4 4747984 954.12% + 5 2061711 414.30% + 6 1164817 234.07% + 7 463069 93.05% + 8 246894 49.61% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.786650 # Inst issue rate -system.cpu.iq.iqInstsAdded 84723363 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 82690740 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 4692 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 4940751 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 53730 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 109 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 3594449 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadExReq_accesses 143476 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4086.446514 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2086.446514 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 586307000 # number of ReadExReq miss cycles +system.cpu.iq.ISSUE:rate 1.715421 # Inst issue rate +system.cpu.iq.iqInstsAdded 89442204 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 85364731 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 4987 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 9646731 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 49535 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 404 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 6611614 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 13401083 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 13375683 # ITB hits +system.cpu.itb.misses 25400 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 143495 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4092.480574 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2092.480574 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 587250500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_misses 143476 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 299355000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 143495 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 300260500 # 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 143476 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 147467 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4144.894478 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2144.894478 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 98804 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 201703000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.329992 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 48663 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 104377000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.329992 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 48663 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 6368 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4226.366206 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2231.626884 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 26913500 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_mshr_misses 143495 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 147048 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4140.515824 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2140.515824 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 98388 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 201477500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.330912 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 48660 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 104157500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.330912 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 48660 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 6344 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4240.542245 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2242.591425 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 26902000 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_misses 6368 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 14211000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 6344 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 14227000 # 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 6368 # number of UpgradeReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 6344 # number of UpgradeReq MSHR misses system.cpu.l2cache.Writeback_accesses 147761 # number of Writeback accesses(hits+misses) system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses system.cpu.l2cache.Writeback_misses 147761 # number of Writeback misses @@ -362,38 +378,38 @@ system.cpu.l2cache.Writeback_mshr_miss_rate 1 # system.cpu.l2cache.Writeback_mshr_misses 147761 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 2.459748 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 2.449354 # 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 290943 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4101.249616 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2101.249616 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 98804 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 788010000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.660401 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 192139 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 290543 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4104.644688 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2104.644688 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 98388 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 788728000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.661365 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 192155 # 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 403732000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.660401 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 192139 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 404418000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.661365 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 192155 # 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 290943 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4101.249616 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2101.249616 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 290543 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4104.644688 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2104.644688 # 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 98804 # number of overall hits -system.cpu.l2cache.overall_miss_latency 788010000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.660401 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 192139 # number of overall misses +system.cpu.l2cache.overall_hits 98388 # number of overall hits +system.cpu.l2cache.overall_miss_latency 788728000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.661365 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 192155 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 403732000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.660401 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 192139 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 404418000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.661365 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 192155 # 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 @@ -405,31 +421,31 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.l2cache.replacements 25941 # number of replacements +system.cpu.l2cache.replacements 25943 # number of replacements system.cpu.l2cache.sampled_refs 41849 # 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 4585.524484 # Cycle average of tags in use -system.cpu.l2cache.total_refs 102938 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 4581.530519 # Cycle average of tags in use +system.cpu.l2cache.total_refs 102503 # 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 46282553 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 249890 # Number of cycles rename is blocking +system.cpu.numCycles 49763148 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 263435 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 52546881 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 36341 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 26244762 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 565515 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 115161809 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 95469817 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 57208765 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 18176186 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 888885 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 649163 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 4661884 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 73667 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 4695 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 1420326 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 4693 # count of temporary serializing insts renamed -system.cpu.timesIdled 518 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 34724 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 28245765 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 545942 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 121486902 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 100840274 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 60680951 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 19296581 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 1261472 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 621968 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 8134070 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 73927 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 5255 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 1395173 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 5253 # count of temporary serializing insts renamed +system.cpu.timesIdled 678 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 4583 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/config.ini index 5339d79af..4745ee94c 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=vortex lendian.raw @@ -53,7 +67,7 @@ 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/long/50.vortex/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/m5stats.txt index 16fb6367e..f06392b4f 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 840697 # Simulator instruction rate (inst/s) -host_mem_usage 152968 # Number of bytes of host memory used -host_seconds 105.08 # Real time elapsed on the host -host_tick_rate 420346781 # Simulator tick rate (ticks/s) +host_inst_rate 2496642 # Simulator instruction rate (inst/s) +host_mem_usage 184388 # Number of bytes of host memory used +host_seconds 35.38 # Real time elapsed on the host +host_tick_rate 1249741953 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 88340674 # Number of instructions simulated -sim_seconds 0.044170 # Number of seconds simulated -sim_ticks 44170336500 # Number of ticks simulated +sim_insts 88340673 # Number of instructions simulated +sim_seconds 0.044221 # Number of seconds simulated +sim_ticks 44221003000 # Number of ticks simulated +system.cpu.dtb.accesses 34987415 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 34890015 # DTB hits +system.cpu.dtb.misses 97400 # DTB misses +system.cpu.dtb.read_accesses 20366786 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 20276638 # DTB read hits +system.cpu.dtb.read_misses 90148 # DTB read misses +system.cpu.dtb.write_accesses 14620629 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 14613377 # DTB write hits +system.cpu.dtb.write_misses 7252 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 88442007 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 88438073 # ITB hits +system.cpu.itb.misses 3934 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 88340674 # number of cpu cycles simulated -system.cpu.num_insts 88340674 # Number of instructions executed -system.cpu.num_refs 35224019 # Number of memory references +system.cpu.numCycles 88442007 # number of cpu cycles simulated +system.cpu.num_insts 88340673 # Number of instructions executed +system.cpu.num_refs 35321418 # Number of memory references system.cpu.workload.PROG:num_syscalls 4583 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/smred.msg b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/smred.msg index 327142d7c..472b08431 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/smred.msg +++ b/tests/long/50.vortex/ref/alpha/tru64/simple-atomic/smred.msg @@ -134,7 +134,7 @@ DB Handle Chunk's StackPtr = 20797 DB[ 1] LOADED; Handles= 20797 - KERNEL in CORE[ 1] Restored @ 40054800 + KERNEL in CORE[ 1] Restored @ 4005c800 OPEN File ./input/lendian.wnv *Status = 0 diff --git a/tests/long/50.vortex/ref/alpha/tru64/simple-timing/config.ini b/tests/long/50.vortex/ref/alpha/tru64/simple-timing/config.ini index 878ba709b..99534f902 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/50.vortex/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/50.vortex/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/50.vortex/ref/alpha/tru64/simple-timing/m5stats.txt index b10e7249f..42618bd93 100644 --- a/tests/long/50.vortex/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/50.vortex/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1495977 # Simulator instruction rate (inst/s) -host_mem_usage 209700 # Number of bytes of host memory used -host_seconds 59.05 # Real time elapsed on the host -host_tick_rate 2185213288 # Simulator tick rate (ticks/s) +host_inst_rate 1453070 # Simulator instruction rate (inst/s) +host_mem_usage 191752 # Number of bytes of host memory used +host_seconds 60.80 # Real time elapsed on the host +host_tick_rate 2124138006 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 88340674 # Number of instructions simulated -sim_seconds 0.129042 # Number of seconds simulated -sim_ticks 129042205000 # Number of ticks simulated +sim_insts 88340673 # Number of instructions simulated +sim_seconds 0.129140 # Number of seconds simulated +sim_ticks 129139604000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 20276638 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 20958.331276 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 18958.331276 # average ReadReq mshr miss latency @@ -76,53 +76,65 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 200247 # number of replacements system.cpu.dcache.sampled_refs 204343 # 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 4080.920336 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4080.930479 # Cycle average of tags in use system.cpu.dcache.total_refs 34685672 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 737102000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 737173000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 147714 # number of writebacks -system.cpu.icache.ReadReq_accesses 88340675 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 34987415 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 34890015 # DTB hits +system.cpu.dtb.misses 97400 # DTB misses +system.cpu.dtb.read_accesses 20366786 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 20276638 # DTB read hits +system.cpu.dtb.read_misses 90148 # DTB read misses +system.cpu.dtb.write_accesses 14620629 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 14613377 # DTB write hits +system.cpu.dtb.write_misses 7252 # DTB write misses +system.cpu.icache.ReadReq_accesses 88438074 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 14131.456382 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 12131.456382 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 88264239 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 88361638 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 1080152000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.000865 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.000864 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 76436 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 927280000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.000865 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate 0.000864 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 76436 # 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 1154.746965 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 1156.021220 # 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 88340675 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 88438074 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 14131.456382 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 12131.456382 # average overall mshr miss latency -system.cpu.icache.demand_hits 88264239 # number of demand (read+write) hits +system.cpu.icache.demand_hits 88361638 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 1080152000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.000865 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.000864 # miss rate for demand accesses system.cpu.icache.demand_misses 76436 # 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 927280000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.000865 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate 0.000864 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 76436 # 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 88340675 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 88438074 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 14131.456382 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 12131.456382 # 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 88264239 # number of overall hits +system.cpu.icache.overall_hits 88361638 # number of overall hits system.cpu.icache.overall_miss_latency 1080152000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.000865 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.000864 # miss rate for overall accesses system.cpu.icache.overall_misses 76436 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.icache.overall_mshr_miss_latency 927280000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.000865 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate 0.000864 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 76436 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 74391 # number of replacements system.cpu.icache.sampled_refs 76436 # 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 1876.903920 # Cycle average of tags in use -system.cpu.icache.total_refs 88264239 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1876.941758 # Cycle average of tags in use +system.cpu.icache.total_refs 88361638 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 88442008 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 88438074 # ITB hits +system.cpu.itb.misses 3934 # ITB misses system.cpu.l2cache.ReadExReq_accesses 143578 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 24953 # number of replacements system.cpu.l2cache.sampled_refs 40841 # 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 4393.051484 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 4393.054480 # Cycle average of tags in use system.cpu.l2cache.total_refs 93692 # 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 129042205000 # number of cpu cycles simulated -system.cpu.num_insts 88340674 # Number of instructions executed -system.cpu.num_refs 35224019 # Number of memory references +system.cpu.numCycles 129139604000 # number of cpu cycles simulated +system.cpu.num_insts 88340673 # Number of instructions executed +system.cpu.num_refs 35321418 # Number of memory references system.cpu.workload.PROG:num_syscalls 4583 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/sparc/linux/simple-atomic/config.ini b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/config.ini index da377104f..dcd40ebc7 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=vortex bendian.raw @@ -53,7 +67,7 @@ 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/long/50.vortex/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/m5stats.txt index 9dd2e7465..c76c08dcd 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 672762 # Simulator instruction rate (inst/s) -host_mem_usage 151516 # Number of bytes of host memory used -host_seconds 202.52 # Real time elapsed on the host -host_tick_rate 336380340 # Simulator tick rate (ticks/s) +host_inst_rate 1682182 # Simulator instruction rate (inst/s) +host_mem_usage 185356 # Number of bytes of host memory used +host_seconds 80.93 # Real time elapsed on the host +host_tick_rate 842064489 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 136246936 # Number of instructions simulated -sim_seconds 0.068123 # Number of seconds simulated -sim_ticks 68123467500 # Number of ticks simulated +sim_insts 136141055 # Number of instructions simulated +sim_seconds 0.068150 # Number of seconds simulated +sim_ticks 68149604500 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 136246936 # number of cpu cycles simulated -system.cpu.num_insts 136246936 # Number of instructions executed -system.cpu.num_refs 58111522 # Number of memory references +system.cpu.numCycles 136299210 # number of cpu cycles simulated +system.cpu.num_insts 136141055 # Number of instructions executed +system.cpu.num_refs 58160249 # Number of memory references system.cpu.workload.PROG:num_syscalls 1946 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/sparc/linux/simple-atomic/stdout b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/stdout index 13addb638..6a817bd73 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-atomic/stdout +++ b/tests/long/50.vortex/ref/sparc/linux/simple-atomic/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 16:40:43 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:33:10 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/50.vortex/sparc/linux/simple-atomic tests/run.py long/50.vortex/sparc/linux/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 68123467500 because target called exit() +Exiting @ tick 68149604500 because target called exit() diff --git a/tests/long/50.vortex/ref/sparc/linux/simple-timing/config.ini b/tests/long/50.vortex/ref/sparc/linux/simple-timing/config.ini index 5f9deac8a..1069d2547 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-timing/config.ini +++ b/tests/long/50.vortex/ref/sparc/linux/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/50.vortex/ref/sparc/linux/simple-timing/m5stats.txt b/tests/long/50.vortex/ref/sparc/linux/simple-timing/m5stats.txt index e924e185b..2bb84bd57 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/long/50.vortex/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1128502 # Simulator instruction rate (inst/s) -host_mem_usage 210664 # Number of bytes of host memory used -host_seconds 120.73 # Real time elapsed on the host -host_tick_rate 1658768570 # Simulator tick rate (ticks/s) +host_inst_rate 960220 # Simulator instruction rate (inst/s) +host_mem_usage 192724 # Number of bytes of host memory used +host_seconds 141.78 # Real time elapsed on the host +host_tick_rate 1412855280 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 136246936 # Number of instructions simulated -sim_seconds 0.200268 # Number of seconds simulated -sim_ticks 200267857000 # Number of ticks simulated +sim_insts 136141055 # Number of instructions simulated +sim_seconds 0.200317 # Number of seconds simulated +sim_ticks 200316584000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 37231301 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 21199.169030 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 19199.169030 # average ReadReq mshr miss latency @@ -86,53 +86,53 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 146582 # number of replacements system.cpu.dcache.sampled_refs 150678 # 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 4089.106244 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4089.107113 # Cycle average of tags in use system.cpu.dcache.total_refs 57960843 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 584597000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 584680000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 107279 # number of writebacks -system.cpu.icache.ReadReq_accesses 136246937 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses 136295664 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 13638.549063 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 11638.549063 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 136059913 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 136108640 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 2550736000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.001373 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.001372 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 187024 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 2176688000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.001373 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate 0.001372 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 187024 # 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 727.499749 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 727.760287 # 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 136246937 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 136295664 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 13638.549063 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 11638.549063 # average overall mshr miss latency -system.cpu.icache.demand_hits 136059913 # number of demand (read+write) hits +system.cpu.icache.demand_hits 136108640 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 2550736000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.001373 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.001372 # miss rate for demand accesses system.cpu.icache.demand_misses 187024 # 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 2176688000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.001373 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate 0.001372 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 187024 # 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 136246937 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 136295664 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 13638.549063 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 11638.549063 # 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 136059913 # number of overall hits +system.cpu.icache.overall_hits 136108640 # number of overall hits system.cpu.icache.overall_miss_latency 2550736000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.001373 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.001372 # miss rate for overall accesses system.cpu.icache.overall_misses 187024 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.icache.overall_mshr_miss_latency 2176688000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.001373 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate 0.001372 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 187024 # 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 @@ -148,9 +148,9 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 184976 # number of replacements system.cpu.icache.sampled_refs 187024 # 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 2006.859894 # Cycle average of tags in use -system.cpu.icache.total_refs 136059913 # Total number of references to valid blocks. -system.cpu.icache.warmup_cycle 142624255000 # Cycle when the warmup percentage was hit. +system.cpu.icache.tagsinuse 2006.864278 # Cycle average of tags in use +system.cpu.icache.total_refs 136108640 # Total number of references to valid blocks. +system.cpu.icache.warmup_cycle 142656863000 # 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.ReadExReq_accesses 105189 # number of ReadExReq accesses(hits+misses) @@ -234,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 22010 # number of replacements system.cpu.l2cache.sampled_refs 36485 # 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 6146.860431 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 6146.948797 # Cycle average of tags in use system.cpu.l2cache.total_refs 193951 # 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 200267857000 # number of cpu cycles simulated -system.cpu.num_insts 136246936 # Number of instructions executed -system.cpu.num_refs 58111522 # Number of memory references +system.cpu.numCycles 200316584000 # number of cpu cycles simulated +system.cpu.num_insts 136141055 # Number of instructions executed +system.cpu.num_refs 58160249 # Number of memory references system.cpu.workload.PROG:num_syscalls 1946 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/50.vortex/ref/sparc/linux/simple-timing/stdout b/tests/long/50.vortex/ref/sparc/linux/simple-timing/stdout index 862e98203..e6db66f3d 100644 --- a/tests/long/50.vortex/ref/sparc/linux/simple-timing/stdout +++ b/tests/long/50.vortex/ref/sparc/linux/simple-timing/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 12:23:15 -M5 started Sun Aug 12 16:52:13 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:34:32 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/50.vortex/sparc/linux/simple-timing tests/run.py long/50.vortex/sparc/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 200267857000 because target called exit() +Exiting @ tick 200316584000 because target called exit() diff --git a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini index 105e8c6e2..e0dba3f8d 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -21,6 +21,7 @@ SQEntries=32 SSITSize=1024 activity=0 backComSize=5 +cachePorts=200 choiceCtrBits=2 choicePredictorSize=8192 clock=500 @@ -35,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -52,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -74,8 +77,18 @@ renameToFetchDelay=1 renameToIEWDelay=2 renameToROBDelay=1 renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 squashWidth=8 system=system +tracer=system.cpu.tracer trapLatency=13 wbDepth=1 wbWidth=8 @@ -85,21 +98,21 @@ 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 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -107,12 +120,10 @@ 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 @@ -121,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -128,11 +143,11 @@ 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 @@ -206,11 +221,11 @@ 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 @@ -218,11 +233,11 @@ 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 @@ -248,11 +263,11 @@ 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 @@ -260,21 +275,21 @@ 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 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -282,12 +297,10 @@ 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 @@ -296,23 +309,27 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache -adaptive_compression=false +addr_range=0:18446744073709551615 assoc=2 block_size=64 -compressed_bus=false -compression_latency=0 +cpu_side_filter_ranges= hash_delay=1 latency=1000 lifo=false max_miss_count=0 +mem_side_filter_ranges= mshrs=10 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 @@ -320,12 +337,10 @@ 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 @@ -343,6 +358,9 @@ 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=bzip2 input.source 1 @@ -366,7 +384,7 @@ 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/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt index dccb62bee..57430d61b 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/60.bzip2/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 236329759 # Number of BTB hits -global.BPredUnit.BTBLookups 244099867 # Number of BTB lookups -global.BPredUnit.RASInCorrect 116 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 19342549 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 203388054 # Number of conditional branches predicted -global.BPredUnit.lookups 265702680 # Number of BP lookups -global.BPredUnit.usedRAS 19620183 # Number of times the RAS was used to get a target. -host_inst_rate 104740 # Simulator instruction rate (inst/s) -host_mem_usage 154596 # Number of bytes of host memory used -host_seconds 16574.74 # Real time elapsed on the host -host_tick_rate 38540500 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 53067106 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 26767467 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 497279728 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 174034666 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 295839321 # Number of BTB hits +global.BPredUnit.BTBLookups 304173613 # Number of BTB lookups +global.BPredUnit.RASInCorrect 120 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 19407214 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 254124044 # Number of conditional branches predicted +global.BPredUnit.lookups 329654644 # Number of BP lookups +global.BPredUnit.usedRAS 23321143 # Number of times the RAS was used to get a target. +host_inst_rate 153530 # Simulator instruction rate (inst/s) +host_mem_usage 182552 # Number of bytes of host memory used +host_seconds 11307.49 # Real time elapsed on the host +host_tick_rate 57851122 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 71970991 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 36581423 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 594992654 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 221743675 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 1736043781 # Number of instructions simulated -sim_seconds 0.638799 # Number of seconds simulated -sim_ticks 638798750000 # Number of ticks simulated +sim_seconds 0.654151 # Number of seconds simulated +sim_ticks 654151113500 # Number of ticks simulated system.cpu.commit.COM:branches 214632552 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 60317471 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 63247574 # 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 1240430038 +system.cpu.commit.COM:committed_per_cycle.samples 1235798441 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 616961832 4973.77% - 1 236071207 1903.14% - 2 130159070 1049.31% - 3 77572840 625.37% - 4 40072787 323.06% - 5 42334502 341.29% - 6 22413470 180.69% - 7 14526859 117.11% - 8 60317471 486.26% + 0 591538606 4786.69% + 1 262725137 2125.95% + 2 125553765 1015.97% + 3 79229995 641.12% + 4 49991526 404.53% + 5 29482834 238.57% + 6 23306420 188.59% + 7 10722584 86.77% + 8 63247574 511.80% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,70 +43,80 @@ system.cpu.commit.COM:loads 445666361 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 606571343 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 19342064 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 19406708 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 1819780126 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 29 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 213160886 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 476380119 # The number of squashed insts skipped by commit system.cpu.committedInsts 1736043781 # Number of Instructions Simulated system.cpu.committedInsts_total 1736043781 # Number of Instructions Simulated -system.cpu.cpi 0.735925 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.735925 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 460303357 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 3955.169300 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2868.381634 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 451791924 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 33664158500 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.018491 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 8511433 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 1219244 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 20916781000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.015842 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 7292189 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 160728502 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 6699.535635 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 8433.632873 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 157310932 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 22896132000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.021263 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 3417570 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 1533904 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 15886147500 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.011720 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 1883666 # number of WriteReq MSHR misses -system.cpu.dcache.avg_blocked_cycles_no_mshrs 1092.259997 # average number of cycles each access was blocked -system.cpu.dcache.avg_blocked_cycles_no_targets 571.397227 # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 66.381046 # Average number of references to valid blocks. -system.cpu.dcache.blocked_no_mshrs 62416 # number of cycles access was blocked -system.cpu.dcache.blocked_no_targets 56970 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_mshrs 68174500 # number of cycles access was blocked -system.cpu.dcache.blocked_cycles_no_targets 32552500 # number of cycles access was blocked +system.cpu.cpi 0.753611 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.753611 # CPI: Total CPI of All Threads +system.cpu.dcache.LoadLockedReq_accesses 3 # number of LoadLockedReq accesses(hits+misses) +system.cpu.dcache.LoadLockedReq_avg_miss_latency 7500 # average LoadLockedReq miss latency +system.cpu.dcache.LoadLockedReq_avg_mshr_miss_latency 5500 # average LoadLockedReq mshr miss latency +system.cpu.dcache.LoadLockedReq_hits 2 # number of LoadLockedReq hits +system.cpu.dcache.LoadLockedReq_miss_latency 7500 # number of LoadLockedReq miss cycles +system.cpu.dcache.LoadLockedReq_miss_rate 0.333333 # miss rate for LoadLockedReq accesses +system.cpu.dcache.LoadLockedReq_misses 1 # number of LoadLockedReq misses +system.cpu.dcache.LoadLockedReq_mshr_miss_latency 5500 # number of LoadLockedReq MSHR miss cycles +system.cpu.dcache.LoadLockedReq_mshr_miss_rate 0.333333 # mshr miss rate for LoadLockedReq accesses +system.cpu.dcache.LoadLockedReq_mshr_misses 1 # number of LoadLockedReq MSHR misses +system.cpu.dcache.ReadReq_accesses 511433561 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 6211.231687 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 3240.921493 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 504159044 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 45183710500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.014224 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 7274517 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 1442446 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 23576138500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.014224 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 7274517 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 158840549 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 13691.838043 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 7367.789283 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 156591934 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 30787672401 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.014156 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 2248615 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 1887953 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 16567321498 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.014156 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 2248615 # number of WriteReq MSHR misses +system.cpu.dcache.avg_blocked_cycles_no_mshrs 1521.266534 # average number of cycles each access was blocked +system.cpu.dcache.avg_blocked_cycles_no_targets 1667.900476 # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 72.179758 # Average number of references to valid blocks. +system.cpu.dcache.blocked_no_mshrs 34791 # number of cycles access was blocked +system.cpu.dcache.blocked_no_targets 65110 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_mshrs 52926384 # number of cycles access was blocked +system.cpu.dcache.blocked_cycles_no_targets 108597000 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 621031859 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 4741.409697 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 4010.844602 # average overall mshr miss latency -system.cpu.dcache.demand_hits 609102856 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 56560290500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.019208 # miss rate for demand accesses -system.cpu.dcache.demand_misses 11929003 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 2753148 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 36802928500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.014775 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 9175855 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 670274110 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 7977.562728 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 4215.363181 # average overall mshr miss latency +system.cpu.dcache.demand_hits 660750978 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 75971382901 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.014208 # miss rate for demand accesses +system.cpu.dcache.demand_misses 9523132 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 3330399 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 40143459998 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.014208 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 9523132 # 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 621031859 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 4741.409697 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 4010.844602 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 670274110 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 7977.562728 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 4215.363181 # 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 609102856 # number of overall hits -system.cpu.dcache.overall_miss_latency 56560290500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.019208 # miss rate for overall accesses -system.cpu.dcache.overall_misses 11929003 # number of overall misses -system.cpu.dcache.overall_mshr_hits 2753148 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 36802928500 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.014775 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 9175855 # number of overall MSHR misses +system.cpu.dcache.overall_hits 660750978 # number of overall hits +system.cpu.dcache.overall_miss_latency 75971382901 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.014208 # miss rate for overall accesses +system.cpu.dcache.overall_misses 9523132 # number of overall misses +system.cpu.dcache.overall_mshr_hits 3330399 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 40143459998 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.014208 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 9523132 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.dcache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -118,92 +128,104 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 9171759 # number of replacements -system.cpu.dcache.sampled_refs 9175855 # Sample count of references to valid blocks. +system.cpu.dcache.replacements 9155187 # number of replacements +system.cpu.dcache.sampled_refs 9159283 # 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 4081.309726 # Cycle average of tags in use -system.cpu.dcache.total_refs 609102856 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 8881811000 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 2245633 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 27333658 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 501 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 42431183 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 2163062948 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 823856490 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 388659524 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 37167487 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 1638 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 580367 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 265702680 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 277957843 # Number of cache lines fetched -system.cpu.fetch.Cycles 672748425 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 10624598 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 2197044125 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 19810424 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.207971 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 277957843 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 255949942 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.719668 # Number of inst fetches per cycle +system.cpu.dcache.tagsinuse 4084.725965 # Cycle average of tags in use +system.cpu.dcache.total_refs 661114830 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 6949550000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 2245528 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 23691683 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 575 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 51434078 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 2685033161 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 684622025 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 525046007 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 72503589 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 1687 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 2438727 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 758263361 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 743549453 # DTB hits +system.cpu.dtb.misses 14713908 # DTB misses +system.cpu.dtb.read_accesses 558500359 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 549711515 # DTB read hits +system.cpu.dtb.read_misses 8788844 # DTB read misses +system.cpu.dtb.write_accesses 199763002 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 193837938 # DTB write hits +system.cpu.dtb.write_misses 5925064 # DTB write misses +system.cpu.fetch.Branches 329654644 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 338459974 # Number of cache lines fetched +system.cpu.fetch.Cycles 875922763 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 8905677 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 2732615549 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 26330328 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.251971 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 338459974 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 319160464 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.088673 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 1277597526 +system.cpu.fetch.rateDist.samples 1308302031 system.cpu.fetch.rateDist.min_value 0 - 0 882806946 6909.90% - 1 27356477 214.12% - 2 16416749 128.50% - 3 27123610 212.30% - 4 80197027 627.72% - 5 46838848 366.62% - 6 25144427 196.81% - 7 24073126 188.42% - 8 147640316 1155.61% + 0 770839278 5891.91% + 1 46037022 351.88% + 2 31884256 243.71% + 3 48862894 373.48% + 4 119031598 909.82% + 5 67260927 514.11% + 6 45605029 348.58% + 7 40088084 306.41% + 8 138692943 1060.10% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 277957843 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5447.729673 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 4641.891892 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 277956896 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 5159000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_accesses 338459894 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7804.756637 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5448.008850 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 338458990 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 7055500 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000003 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 947 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 59 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 4122000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_misses 904 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 80 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 4925000 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000003 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 888 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses 904 # 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 313014.522523 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 374401.537611 # 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 277957843 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5447.729673 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 4641.891892 # average overall mshr miss latency -system.cpu.icache.demand_hits 277956896 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 5159000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_accesses 338459894 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7804.756637 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5448.008850 # average overall mshr miss latency +system.cpu.icache.demand_hits 338458990 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 7055500 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000003 # miss rate for demand accesses -system.cpu.icache.demand_misses 947 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 59 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 4122000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_misses 904 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 80 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 4925000 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.000003 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 888 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses 904 # 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 277957843 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5447.729673 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 4641.891892 # average overall mshr miss latency +system.cpu.icache.overall_accesses 338459894 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7804.756637 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5448.008850 # 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 277956896 # number of overall hits -system.cpu.icache.overall_miss_latency 5159000 # number of overall miss cycles +system.cpu.icache.overall_hits 338458990 # number of overall hits +system.cpu.icache.overall_miss_latency 7055500 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000003 # miss rate for overall accesses -system.cpu.icache.overall_misses 947 # number of overall misses -system.cpu.icache.overall_mshr_hits 59 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 4122000 # number of overall MSHR miss cycles +system.cpu.icache.overall_misses 904 # number of overall misses +system.cpu.icache.overall_mshr_hits 80 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 4925000 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.000003 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 888 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses 904 # 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 @@ -216,79 +238,79 @@ 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 1 # number of replacements -system.cpu.icache.sampled_refs 888 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 904 # 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 691.554117 # Cycle average of tags in use -system.cpu.icache.total_refs 277956896 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 710.981871 # Cycle average of tags in use +system.cpu.icache.total_refs 338458990 # 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 973 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 231142223 # Number of branches executed -system.cpu.iew.EXEC:nop 101615397 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.460942 # Inst execution rate -system.cpu.iew.EXEC:refs 650877785 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 168419462 # Number of stores executed +system.cpu.idleCycles 287621 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 270496646 # Number of branches executed +system.cpu.iew.EXEC:nop 123104849 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.690527 # Inst execution rate +system.cpu.iew.EXEC:refs 759555990 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 199980185 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1210814193 # num instructions consuming a value -system.cpu.iew.WB:count 1847797148 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.819076 # average fanout of values written-back +system.cpu.iew.WB:consumers 1477074275 # num instructions consuming a value +system.cpu.iew.WB:count 2172910283 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.814315 # 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 991749121 # num instructions producing a value -system.cpu.iew.WB:rate 1.446306 # insts written-back per cycle -system.cpu.iew.WB:sent 1849274792 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 20085867 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 1985372 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 497279728 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 38 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 27992821 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 174034666 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 2032941045 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 482458323 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 14098084 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 1866495371 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 77 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 1202803999 # num instructions producing a value +system.cpu.iew.WB:rate 1.660863 # insts written-back per cycle +system.cpu.iew.WB:sent 2193655848 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 21011443 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 889547 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 594992654 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 42 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 23236593 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 221743675 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 2499789620 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 559575805 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 40783059 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 2211719338 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 12131 # 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 1402 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 37167487 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 36044 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 5627 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 72503589 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 62383 # 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 409084 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.0.forwLoads 20784106 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 401249 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.cacheBlocked 123404 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.0.forwLoads 36795200 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 338162 # 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 306932 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 3 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 51613367 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 13129684 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 306932 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 672336 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 19413531 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.358835 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.358835 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 1880593455 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 340968 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 5 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 149326293 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 60838693 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 340968 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 705259 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 20306184 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.326944 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.326944 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 2252502397 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist - (null) 0 0.00% # Type of FU issued - IntAlu 1224165146 65.09% # Type of FU issued - IntMult 78 0.00% # Type of FU issued + No_OpClass 0 0.00% # Type of FU issued + IntAlu 1478322730 65.63% # Type of FU issued + IntMult 88 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 199 0.00% # Type of FU issued - FloatCmp 15 0.00% # Type of FU issued - FloatCvt 141 0.00% # Type of FU issued - FloatMult 13 0.00% # Type of FU issued + FloatAdd 219 0.00% # Type of FU issued + FloatCmp 16 0.00% # Type of FU issued + FloatCvt 143 0.00% # Type of FU issued + FloatMult 14 0.00% # Type of FU issued FloatDiv 24 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 487297898 25.91% # Type of FU issued - MemWrite 169129941 8.99% # Type of FU issued + MemRead 570745758 25.34% # Type of FU issued + MemWrite 203433405 9.03% # 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 14841221 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.007892 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 16701897 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.007415 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist - (null) 0 0.00% # attempts to use FU when none available - IntAlu 753308 5.08% # attempts to use FU when none available + No_OpClass 0 0.00% # attempts to use FU when none available + IntAlu 2428134 14.54% # attempts to use FU when none available IntMult 0 0.00% # attempts to use FU when none available IntDiv 0 0.00% # attempts to use FU when none available FloatAdd 0 0.00% # attempts to use FU when none available @@ -297,84 +319,105 @@ 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 10126775 68.23% # attempts to use FU when none available - MemWrite 3961138 26.69% # attempts to use FU when none available + MemRead 10594349 63.43% # attempts to use FU when none available + MemWrite 3679414 22.03% # 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 1277597526 +system.cpu.iq.ISSUE:issued_per_cycle.samples 1308302031 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 550473495 4308.66% - 1 242915598 1901.35% - 2 174612702 1366.73% - 3 111937959 876.16% - 4 91216702 713.97% - 5 63235343 494.96% - 6 32411117 253.69% - 7 9228529 72.23% - 8 1566081 12.26% + 0 464994121 3554.18% + 1 246274545 1882.40% + 2 221057021 1689.65% + 3 136661440 1044.57% + 4 111222535 850.13% + 5 73372650 560.82% + 6 42938124 328.20% + 7 9505404 72.65% + 8 2276191 17.40% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.471976 # Inst issue rate -system.cpu.iq.iqInstsAdded 1931325610 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 1880593455 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 38 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 179510503 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 87058 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 9 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 101093002 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadReq_accesses 9176743 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 5323.405393 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2210.600583 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 7008183 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 11544124000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.236310 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 2168560 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 4793820000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.236310 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 2168560 # number of ReadReq MSHR misses -system.cpu.l2cache.Writeback_accesses 2245633 # number of Writeback accesses(hits+misses) -system.cpu.l2cache.Writeback_hits 2216502 # number of Writeback hits -system.cpu.l2cache.Writeback_miss_rate 0.012972 # miss rate for Writeback accesses -system.cpu.l2cache.Writeback_misses 29131 # number of Writeback misses -system.cpu.l2cache.Writeback_mshr_miss_rate 0.012972 # mshr miss rate for Writeback accesses -system.cpu.l2cache.Writeback_mshr_misses 29131 # number of Writeback MSHR misses +system.cpu.iq.ISSUE:rate 1.721699 # Inst issue rate +system.cpu.iq.iqInstsAdded 2376684729 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 2252502397 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 42 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 628382514 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 968135 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 13 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 253289566 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 338460010 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 338459974 # ITB hits +system.cpu.itb.misses 36 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 1884766 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 5021.667411 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 3021.667411 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 9464668000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 1884766 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 5695136000 # 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 1884766 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 7275421 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4312.514661 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2312.514661 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 5169531 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 9081681500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.289453 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 2105890 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 4869901500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.289453 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 2105890 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 363856 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4839.580768 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2839.786894 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 1760910500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 363856 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 1033273500 # 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 363856 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 2245528 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses +system.cpu.l2cache.Writeback_misses 2245528 # number of Writeback misses +system.cpu.l2cache.Writeback_mshr_miss_rate 1 # mshr miss rate for Writeback accesses +system.cpu.l2cache.Writeback_mshr_misses 2245528 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 4.253830 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 4.195595 # 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 9176743 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 5323.405393 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2210.600583 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 7008183 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 11544124000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.236310 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 2168560 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 9160187 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4647.443804 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2647.443804 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 5169531 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 18546349500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.435652 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 3990656 # 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 4793820000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.236310 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 2168560 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 10565037500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.435652 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 3990656 # 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 11422376 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 5252.842188 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2210.600583 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 9160187 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4647.443804 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2647.443804 # 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 9224685 # number of overall hits -system.cpu.l2cache.overall_miss_latency 11544124000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.192402 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 2197691 # number of overall misses +system.cpu.l2cache.overall_hits 5169531 # number of overall hits +system.cpu.l2cache.overall_miss_latency 18546349500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.435652 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 3990656 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 4793820000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.189852 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 2168560 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 10565037500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.435652 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 3990656 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -386,32 +429,32 @@ system.cpu.l2cache.prefetcher.num_hwpf_issued 0 system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.l2cache.replacements 2135792 # number of replacements -system.cpu.l2cache.sampled_refs 2168560 # Sample count of references to valid blocks. +system.cpu.l2cache.replacements 1375756 # number of replacements +system.cpu.l2cache.sampled_refs 1398753 # 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 31406.160078 # Cycle average of tags in use -system.cpu.l2cache.total_refs 9224685 # Total number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 53019662000 # Cycle when the warmup percentage was hit. -system.cpu.l2cache.writebacks 1039396 # number of writebacks -system.cpu.numCycles 1277597526 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 16292159 # Number of cycles rename is blocking +system.cpu.l2cache.tagsinuse 18802.772660 # Cycle average of tags in use +system.cpu.l2cache.total_refs 5868601 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 505903232000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 0 # number of writebacks +system.cpu.numCycles 1308302031 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 9337867 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 1376202963 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 4365074 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 834284464 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 6221923 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:ROBFullEvents 448 # Number of times rename has blocked due to ROB full -system.cpu.rename.RENAME:RenameLookups 2711841153 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 2114466649 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 1591248178 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 378627043 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 37167487 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 11225904 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 215045215 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 469 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 45 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 21611838 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 43 # count of temporary serializing insts renamed -system.cpu.timesIdled 27 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 3445352 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 700444810 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 8719596 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 7541 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 3393542048 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 2622643652 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 1968531188 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 511623131 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 72503589 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 14392125 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 592328225 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 509 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 48 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 29038158 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 46 # count of temporary serializing insts renamed +system.cpu.timesIdled 379 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 29 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/config.ini index ab96f2ec5..378e34da6 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=bzip2 input.source 1 @@ -53,7 +67,7 @@ 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/long/60.bzip2/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/m5stats.txt index 4bc7b8152..ac280ef36 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/60.bzip2/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 918892 # Simulator instruction rate (inst/s) -host_mem_usage 148632 # Number of bytes of host memory used -host_seconds 1980.41 # Real time elapsed on the host -host_tick_rate 459446111 # Simulator tick rate (ticks/s) +host_inst_rate 2729023 # Simulator instruction rate (inst/s) +host_mem_usage 174164 # Number of bytes of host memory used +host_seconds 666.82 # Real time elapsed on the host +host_tick_rate 1369458693 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 1819780129 # Number of instructions simulated -sim_seconds 0.909890 # Number of seconds simulated -sim_ticks 909890064000 # Number of ticks simulated +sim_insts 1819780127 # Number of instructions simulated +sim_seconds 0.913189 # Number of seconds simulated +sim_ticks 913189263000 # Number of ticks simulated +system.cpu.dtb.accesses 611922547 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 605324165 # DTB hits +system.cpu.dtb.misses 6598382 # DTB misses +system.cpu.dtb.read_accesses 449492741 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 444595663 # DTB read hits +system.cpu.dtb.read_misses 4897078 # DTB read misses +system.cpu.dtb.write_accesses 162429806 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 160728502 # DTB write hits +system.cpu.dtb.write_misses 1701304 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 1826378527 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 1826378509 # ITB hits +system.cpu.itb.misses 18 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 1819780129 # number of cpu cycles simulated -system.cpu.num_insts 1819780129 # Number of instructions executed -system.cpu.num_refs 606571345 # Number of memory references +system.cpu.numCycles 1826378527 # number of cpu cycles simulated +system.cpu.num_insts 1819780127 # Number of instructions executed +system.cpu.num_refs 613169725 # Number of memory references system.cpu.workload.PROG:num_syscalls 29 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/config.ini b/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/config.ini index ef8186c31..9095d9dfe 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/m5stats.txt index 6f7531c90..a6eb50453 100644 --- a/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/60.bzip2/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1593285 # Simulator instruction rate (inst/s) -host_mem_usage 199472 # Number of bytes of host memory used -host_seconds 1142.16 # Real time elapsed on the host -host_tick_rate 2268225007 # Simulator tick rate (ticks/s) +host_inst_rate 1514723 # Simulator instruction rate (inst/s) +host_mem_usage 181532 # Number of bytes of host memory used +host_seconds 1201.39 # Real time elapsed on the host +host_tick_rate 2161875158 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 1819780129 # Number of instructions simulated -sim_seconds 2.590667 # Number of seconds simulated -sim_ticks 2590666806000 # Number of ticks simulated +sim_insts 1819780127 # Number of instructions simulated +sim_seconds 2.597265 # Number of seconds simulated +sim_ticks 2597265186000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 444595663 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 16451.345769 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 14451.345769 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 9107638 # number of replacements system.cpu.dcache.sampled_refs 9111734 # 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 4079.283777 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 4079.325443 # Cycle average of tags in use system.cpu.dcache.total_refs 596212431 # Total number of references to valid blocks. -system.cpu.dcache.warmup_cycle 40727264000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.warmup_cycle 40727877000 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 2244708 # number of writebacks -system.cpu.icache.ReadReq_accesses 1819780130 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 611922547 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 605324165 # DTB hits +system.cpu.dtb.misses 6598382 # DTB misses +system.cpu.dtb.read_accesses 449492741 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 444595663 # DTB read hits +system.cpu.dtb.read_misses 4897078 # DTB read misses +system.cpu.dtb.write_accesses 162429806 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 160728502 # DTB write hits +system.cpu.dtb.write_misses 1701304 # DTB write misses +system.cpu.icache.ReadReq_accesses 1826378510 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1819779328 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 1826377708 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 20050000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000000 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 802 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000000 # ms system.cpu.icache.ReadReq_mshr_misses 802 # 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 2269051.531172 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 2277278.937656 # 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 1819780130 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 1826378510 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 23000 # average overall mshr miss latency -system.cpu.icache.demand_hits 1819779328 # number of demand (read+write) hits +system.cpu.icache.demand_hits 1826377708 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 20050000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000000 # miss rate for demand accesses system.cpu.icache.demand_misses 802 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 802 # nu 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 1819780130 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 1826378510 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 23000 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 1819779328 # number of overall hits +system.cpu.icache.overall_hits 1826377708 # number of overall hits system.cpu.icache.overall_miss_latency 20050000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000000 # miss rate for overall accesses system.cpu.icache.overall_misses 802 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 1 # number of replacements system.cpu.icache.sampled_refs 802 # 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 611.417495 # Cycle average of tags in use -system.cpu.icache.total_refs 1819779328 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 611.506832 # Cycle average of tags in use +system.cpu.icache.total_refs 1826377708 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 1826378528 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 1826378510 # ITB hits +system.cpu.itb.misses 18 # ITB misses system.cpu.l2cache.ReadExReq_accesses 1889320 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 1367767 # number of replacements system.cpu.l2cache.sampled_refs 1390767 # 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 18546.386002 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 18552.565433 # Cycle average of tags in use system.cpu.l2cache.total_refs 5824390 # Total number of references to valid blocks. -system.cpu.l2cache.warmup_cycle 2030116907000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.warmup_cycle 2034930554000 # 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 2590666806000 # number of cpu cycles simulated -system.cpu.num_insts 1819780129 # Number of instructions executed -system.cpu.num_refs 606571345 # Number of memory references +system.cpu.numCycles 2597265186000 # number of cpu cycles simulated +system.cpu.num_insts 1819780127 # Number of instructions executed +system.cpu.num_refs 613169725 # Number of memory references system.cpu.workload.PROG:num_syscalls 29 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini index 752831326..10ff9c3eb 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt index f4a8bde29..0262f8e2d 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 13022932 # Number of BTB hits -global.BPredUnit.BTBLookups 16938031 # Number of BTB lookups -global.BPredUnit.RASInCorrect 1193 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 1944645 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 14588431 # Number of conditional branches predicted -global.BPredUnit.lookups 19441115 # Number of BP lookups -global.BPredUnit.usedRAS 1715741 # Number of times the RAS was used to get a target. -host_inst_rate 140839 # Simulator instruction rate (inst/s) -host_mem_usage 205524 # Number of bytes of host memory used -host_seconds 597.70 # Real time elapsed on the host -host_tick_rate 68085854 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 17320747 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 5158870 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 33916617 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 10592327 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.BTBHits 13010658 # Number of BTB hits +global.BPredUnit.BTBLookups 16925459 # Number of BTB lookups +global.BPredUnit.RASInCorrect 1191 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1944478 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 14575632 # Number of conditional branches predicted +global.BPredUnit.lookups 19422613 # Number of BP lookups +global.BPredUnit.usedRAS 1713685 # Number of times the RAS was used to get a target. +host_inst_rate 134486 # Simulator instruction rate (inst/s) +host_mem_usage 187512 # Number of bytes of host memory used +host_seconds 625.94 # Real time elapsed on the host +host_tick_rate 64866574 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 17216912 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 5017487 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 33831723 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 10556967 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 84179709 # Number of instructions simulated -sim_seconds 0.040695 # Number of seconds simulated -sim_ticks 40694900000 # Number of ticks simulated +sim_seconds 0.040602 # Number of seconds simulated +sim_ticks 40602361500 # Number of ticks simulated system.cpu.commit.COM:branches 10240685 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 2814383 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 2830089 # 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 73372540 +system.cpu.commit.COM:committed_per_cycle.samples 73220545 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 36054158 4913.85% - 1 18224800 2483.87% - 2 7501822 1022.43% - 3 3901009 531.67% - 4 2128189 290.05% - 5 1274528 173.71% - 6 744433 101.46% - 7 729218 99.39% - 8 2814383 383.57% + 0 35958705 4911.01% + 1 18165534 2480.93% + 2 7495163 1023.64% + 3 3905368 533.37% + 4 2115499 288.92% + 5 1290804 176.29% + 6 741318 101.24% + 7 718065 98.07% + 8 2830089 386.52% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,72 +43,72 @@ system.cpu.commit.COM:loads 20034413 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 26537108 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 1932230 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 1932029 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 91903055 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 389 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 55717434 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 55442802 # The number of squashed insts skipped by commit system.cpu.committedInsts 84179709 # Number of Instructions Simulated system.cpu.committedInsts_total 84179709 # Number of Instructions Simulated -system.cpu.cpi 0.966851 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.966851 # CPI: Total CPI of All Threads +system.cpu.cpi 0.964650 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.964650 # CPI: Total CPI of All Threads system.cpu.dcache.LoadLockedReq_accesses 7 # number of LoadLockedReq accesses(hits+misses) system.cpu.dcache.LoadLockedReq_hits 7 # number of LoadLockedReq hits -system.cpu.dcache.ReadReq_accesses 23356209 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 9066 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5569 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 23355709 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 4533000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.000021 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 500 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 123 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 2784500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.000021 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 500 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 6495002 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 24564.959569 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5850.134771 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 6493147 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 45568000 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.000286 # miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_misses 1855 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 6101 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 10852000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.000286 # mshr miss rate for WriteReq accesses -system.cpu.dcache.WriteReq_mshr_misses 1855 # number of WriteReq MSHR misses +system.cpu.dcache.ReadReq_accesses 23305151 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 8854.743083 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5500 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 23304645 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 4480500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000022 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 506 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 115 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 2783000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000022 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 506 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 6494991 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 24985.167206 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5885.922330 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 6493137 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 46322500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.000285 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 1854 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 6112 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 10912500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.000285 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 1854 # 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 13325.436607 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 13302.637946 # 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 29851211 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 21274.309979 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5790.445860 # average overall mshr miss latency -system.cpu.dcache.demand_hits 29848856 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 50101000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_accesses 29800142 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 21526.694915 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5803.177966 # average overall mshr miss latency +system.cpu.dcache.demand_hits 29797782 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 50803000 # number of demand (read+write) miss cycles system.cpu.dcache.demand_miss_rate 0.000079 # miss rate for demand accesses -system.cpu.dcache.demand_misses 2355 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 6224 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 13636500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_misses 2360 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 6227 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 13695500 # number of demand (read+write) MSHR miss cycles system.cpu.dcache.demand_mshr_miss_rate 0.000079 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 2355 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses 2360 # 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 29851211 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 21274.309979 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5790.445860 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 29800142 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 21526.694915 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5803.177966 # 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 29848856 # number of overall hits -system.cpu.dcache.overall_miss_latency 50101000 # number of overall miss cycles +system.cpu.dcache.overall_hits 29797782 # number of overall hits +system.cpu.dcache.overall_miss_latency 50803000 # number of overall miss cycles system.cpu.dcache.overall_miss_rate 0.000079 # miss rate for overall accesses -system.cpu.dcache.overall_misses 2355 # number of overall misses -system.cpu.dcache.overall_mshr_hits 6224 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 13636500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_misses 2360 # number of overall misses +system.cpu.dcache.overall_mshr_hits 6227 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 13695500 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_miss_rate 0.000079 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 2355 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses 2360 # 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 @@ -120,92 +120,104 @@ system.cpu.dcache.prefetcher.num_hwpf_issued 0 system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.dcache.replacements 160 # number of replacements +system.cpu.dcache.replacements 159 # number of replacements system.cpu.dcache.sampled_refs 2240 # 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 1458.130010 # Cycle average of tags in use -system.cpu.dcache.total_refs 29848978 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 1459.011880 # Cycle average of tags in use +system.cpu.dcache.total_refs 29797909 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. -system.cpu.dcache.writebacks 106 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 3820626 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 12575 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 3037417 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 162462210 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 39463165 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 29936850 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 8016661 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 44953 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 151900 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 19441115 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 19217268 # Number of cache lines fetched -system.cpu.fetch.Cycles 50163624 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 510483 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 167309935 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 2078673 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.238866 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 19217268 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 14738673 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 2.055677 # Number of inst fetches per cycle +system.cpu.dcache.writebacks 105 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 3766232 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 12611 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 3034294 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 162205348 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 39405972 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 29900475 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 7983383 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 45169 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 147867 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 31800987 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 31340580 # DTB hits +system.cpu.dtb.misses 460407 # DTB misses +system.cpu.dtb.read_accesses 24617799 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 24158583 # DTB read hits +system.cpu.dtb.read_misses 459216 # DTB read misses +system.cpu.dtb.write_accesses 7183188 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 7181997 # DTB write hits +system.cpu.dtb.write_misses 1191 # DTB write misses +system.cpu.fetch.Branches 19422613 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 19195045 # Number of cache lines fetched +system.cpu.fetch.Cycles 50102609 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 509210 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 167066208 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 2080138 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.239183 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 19195045 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 14724343 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.057366 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 81389202 +system.cpu.fetch.rateDist.samples 81203929 system.cpu.fetch.rateDist.min_value 0 - 0 50442849 6197.73% - 1 3127409 384.25% - 2 2013333 247.37% - 3 3501649 430.24% - 4 4585592 563.42% - 5 1499931 184.29% - 6 2042041 250.90% - 7 1854540 227.86% - 8 12321858 1513.94% + 0 50296438 6193.84% + 1 3127485 385.14% + 2 2009190 247.43% + 3 3499443 430.95% + 4 4580392 564.06% + 5 1498651 184.55% + 6 2040206 251.24% + 7 1851037 227.95% + 8 12301087 1514.84% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 19216915 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 5291.898608 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 3156.958250 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 19206855 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 53236500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_accesses 19194697 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 5285.401314 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 3152.011551 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 19184655 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 53076000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000523 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 10060 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 353 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 31759000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_misses 10042 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 348 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 31652500 # number of ReadReq MSHR miss cycles system.cpu.icache.ReadReq_mshr_miss_rate 0.000523 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 10060 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses 10042 # 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 1909.230119 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 1910.441645 # 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 19216915 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 5291.898608 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 3156.958250 # average overall mshr miss latency -system.cpu.icache.demand_hits 19206855 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 53236500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_accesses 19194697 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 5285.401314 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 3152.011551 # average overall mshr miss latency +system.cpu.icache.demand_hits 19184655 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 53076000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000523 # miss rate for demand accesses -system.cpu.icache.demand_misses 10060 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 353 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 31759000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_misses 10042 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 348 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 31652500 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate 0.000523 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 10060 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses 10042 # 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 19216915 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 5291.898608 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 3156.958250 # average overall mshr miss latency +system.cpu.icache.overall_accesses 19194697 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 5285.401314 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 3152.011551 # 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 19206855 # number of overall hits -system.cpu.icache.overall_miss_latency 53236500 # number of overall miss cycles +system.cpu.icache.overall_hits 19184655 # number of overall hits +system.cpu.icache.overall_miss_latency 53076000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000523 # miss rate for overall accesses -system.cpu.icache.overall_misses 10060 # number of overall misses -system.cpu.icache.overall_mshr_hits 353 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 31759000 # number of overall MSHR miss cycles +system.cpu.icache.overall_misses 10042 # number of overall misses +system.cpu.icache.overall_mshr_hits 348 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 31652500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate 0.000523 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 10060 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses 10042 # 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 @@ -217,183 +229,187 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 8146 # number of replacements -system.cpu.icache.sampled_refs 10060 # Sample count of references to valid blocks. +system.cpu.icache.replacements 8129 # number of replacements +system.cpu.icache.sampled_refs 10042 # 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 1551.624399 # Cycle average of tags in use -system.cpu.icache.total_refs 19206855 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1547.586704 # Cycle average of tags in use +system.cpu.icache.total_refs 19184655 # 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 435727 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 12761226 # Number of branches executed -system.cpu.iew.EXEC:nop 12552336 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.247935 # Inst execution rate -system.cpu.iew.EXEC:refs 31899012 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 7188094 # Number of stores executed +system.cpu.idleCycles 554685 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 12760718 # Number of branches executed +system.cpu.iew.EXEC:nop 12520368 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.249722 # Inst execution rate +system.cpu.iew.EXEC:refs 31851627 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 7184817 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 90808493 # num instructions consuming a value -system.cpu.iew.WB:count 99646578 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.722903 # average fanout of values written-back +system.cpu.iew.WB:consumers 90693698 # num instructions consuming a value +system.cpu.iew.WB:count 99568419 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.723301 # 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 65645732 # num instructions producing a value -system.cpu.iew.WB:rate 1.224322 # insts written-back per cycle -system.cpu.iew.WB:sent 100573545 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 2105709 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 285403 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 33916617 # Number of dispatched load instructions +system.cpu.iew.WB:producers 65598879 # num instructions producing a value +system.cpu.iew.WB:rate 1.226153 # insts written-back per cycle +system.cpu.iew.WB:sent 100495413 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 2106580 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 285272 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 33831723 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 429 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 1714541 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 10592327 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 147619094 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 24710918 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 2203361 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 101568426 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 132795 # Number of times the IQ has become full, causing a stall +system.cpu.iew.iewDispSquashedInsts 1731846 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 10556967 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 147344437 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 24666810 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2188087 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 101482299 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 133099 # 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 9 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 8016661 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 165683 # Number of cycles IEW is unblocking +system.cpu.iew.iewLSQFullEvents 12 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 7983383 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 165893 # 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 838013 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 1487 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 843499 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 1537 # 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 249026 # Number of memory ordering violations -system.cpu.iew.lsq.thread.0.rescheduledLoads 9801 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 13882204 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 4089632 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 249026 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 202527 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 1903182 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 1.034286 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.034286 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 103771787 # Type of FU issued +system.cpu.iew.lsq.thread.0.memOrderViolation 250644 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 9811 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 13797310 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 4054272 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 250644 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 202889 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 1903691 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 1.036646 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.036646 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 103670386 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 7 0.00% # Type of FU issued - IntAlu 64228940 61.89% # Type of FU issued - IntMult 473017 0.46% # Type of FU issued + IntAlu 64195239 61.92% # Type of FU issued + IntMult 473046 0.46% # Type of FU issued IntDiv 0 0.00% # Type of FU issued - FloatAdd 2790055 2.69% # Type of FU issued - FloatCmp 115633 0.11% # Type of FU issued - FloatCvt 2376207 2.29% # Type of FU issued - FloatMult 305676 0.29% # Type of FU issued - FloatDiv 755062 0.73% # Type of FU issued - FloatSqrt 323 0.00% # Type of FU issued - MemRead 25409003 24.49% # Type of FU issued - MemWrite 7317864 7.05% # Type of FU issued + FloatAdd 2788829 2.69% # Type of FU issued + FloatCmp 115617 0.11% # Type of FU issued + FloatCvt 2372095 2.29% # Type of FU issued + FloatMult 305683 0.29% # Type of FU issued + FloatDiv 755148 0.73% # Type of FU issued + FloatSqrt 322 0.00% # Type of FU issued + MemRead 25353594 24.46% # Type of FU issued + MemWrite 7310806 7.05% # 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 1978136 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.019062 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 1973729 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.019039 # 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 311313 15.74% # attempts to use FU when none available + IntAlu 311847 15.80% # 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 546 0.03% # attempts to use FU when none available + FloatAdd 478 0.02% # attempts to use FU when none available FloatCmp 0 0.00% # attempts to use FU when none available - FloatCvt 3483 0.18% # attempts to use FU when none available - FloatMult 2460 0.12% # attempts to use FU when none available - FloatDiv 833660 42.14% # attempts to use FU when none available + FloatCvt 2917 0.15% # attempts to use FU when none available + FloatMult 2390 0.12% # attempts to use FU when none available + FloatDiv 832522 42.18% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 753551 38.09% # attempts to use FU when none available - MemWrite 73123 3.70% # attempts to use FU when none available + MemRead 750992 38.05% # attempts to use FU when none available + MemWrite 72583 3.68% # 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 81389202 +system.cpu.iq.ISSUE:issued_per_cycle.samples 81203929 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 35308856 4338.27% - 1 18677963 2294.89% - 2 11652538 1431.71% - 3 6999702 860.03% - 4 4887440 600.50% - 5 2229546 273.94% - 6 1377818 169.29% - 7 217468 26.72% - 8 37871 4.65% + 0 35188418 4333.34% + 1 18662979 2298.29% + 2 11625415 1431.63% + 3 6937118 854.28% + 4 4927347 606.79% + 5 2234432 275.16% + 6 1373348 169.12% + 7 215389 26.52% + 8 39483 4.86% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.275007 # Inst issue rate -system.cpu.iq.iqInstsAdded 135066329 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 103771787 # Number of instructions issued +system.cpu.iq.ISSUE:rate 1.276667 # Inst issue rate +system.cpu.iq.iqInstsAdded 134823640 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 103670386 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 429 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 50270340 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 231965 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 50027749 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 225448 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 40 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 47066497 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadExReq_accesses 1741 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4485.353245 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2485.353245 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 7809000 # number of ReadExReq miss cycles +system.cpu.iq.iqSquashedOperandsExamined 46827412 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 19195118 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 19195045 # ITB hits +system.cpu.itb.misses 73 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 1735 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4523.342939 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2523.342939 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 7848000 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_misses 1741 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 4327000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 1735 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 4378000 # 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 1741 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 10559 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4274.193548 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2274.193548 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 7149 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 14575000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.322947 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 1735 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 10547 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4263.929619 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2263.929619 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 7137 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 14540000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.323315 # miss rate for ReadReq accesses system.cpu.l2cache.ReadReq_misses 3410 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 7755000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.322947 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_miss_latency 7720000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.323315 # mshr miss rate for ReadReq accesses system.cpu.l2cache.ReadReq_mshr_misses 3410 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 118 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4500 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2500 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 531000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_accesses 123 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4430.894309 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2430.894309 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 545000 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_misses 118 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 295000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 123 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 299000 # 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 118 # number of UpgradeReq MSHR misses -system.cpu.l2cache.Writeback_accesses 106 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_mshr_misses 123 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 105 # number of Writeback accesses(hits+misses) system.cpu.l2cache.Writeback_miss_rate 1 # miss rate for Writeback accesses -system.cpu.l2cache.Writeback_misses 106 # number of Writeback misses +system.cpu.l2cache.Writeback_misses 105 # number of Writeback misses system.cpu.l2cache.Writeback_mshr_miss_rate 1 # mshr miss rate for Writeback accesses -system.cpu.l2cache.Writeback_mshr_misses 106 # number of Writeback MSHR misses +system.cpu.l2cache.Writeback_mshr_misses 105 # number of Writeback MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.l2cache.avg_refs 2.172948 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 2.172603 # 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 12300 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4345.563968 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2345.563968 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 7149 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 22384000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.418780 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 5151 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 12282 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4351.409135 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2351.409135 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 7137 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 22388000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.418906 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 5145 # 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 12082000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.418780 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 5151 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 12098000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.418906 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 5145 # 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 12300 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4345.563968 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2345.563968 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 12282 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4351.409135 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2351.409135 # 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 7149 # number of overall hits -system.cpu.l2cache.overall_miss_latency 22384000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.418780 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 5151 # number of overall misses +system.cpu.l2cache.overall_hits 7137 # number of overall hits +system.cpu.l2cache.overall_miss_latency 22388000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.418906 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 5145 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 12082000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.418780 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 5151 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 12098000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.418906 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 5145 # 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 @@ -406,30 +422,30 @@ 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 3290 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 3285 # 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 2252.890734 # Cycle average of tags in use -system.cpu.l2cache.total_refs 7149 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 2248.754865 # Cycle average of tags in use +system.cpu.l2cache.total_refs 7137 # 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 81389202 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 1683934 # Number of cycles rename is blocking +system.cpu.numCycles 81203929 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 1670922 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 68427361 # Number of HB maps that are committed -system.cpu.rename.RENAME:IQFullEvents 1032549 # Number of times rename has blocked due to IQ full -system.cpu.rename.RENAME:IdleCycles 40751116 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 970163 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 202965992 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 157380306 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 115963922 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 28805465 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 8016661 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 2127274 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 47536561 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 4752 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 464 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 4689522 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 453 # count of temporary serializing insts renamed -system.cpu.timesIdled 283 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:IQFullEvents 1021107 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 40689840 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 938076 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 202669964 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 157140698 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 115798524 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 28770212 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 7983383 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 2084846 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 47371163 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 4726 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 465 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 4645791 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 454 # count of temporary serializing insts renamed +system.cpu.timesIdled 325 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 389 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/config.ini b/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/config.ini index 3cb797e6a..8fbd6f60b 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=twolf smred @@ -53,7 +67,7 @@ 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/long/70.twolf/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/m5stats.txt index acfa7c9dd..127e45547 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 935813 # Simulator instruction rate (inst/s) -host_mem_usage 150648 # Number of bytes of host memory used -host_seconds 98.21 # Real time elapsed on the host -host_tick_rate 467904361 # Simulator tick rate (ticks/s) +host_inst_rate 2451408 # Simulator instruction rate (inst/s) +host_mem_usage 179100 # Number of bytes of host memory used +host_seconds 37.49 # Real time elapsed on the host +host_tick_rate 1225693454 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 91903057 # Number of instructions simulated +sim_insts 91903056 # Number of instructions simulated sim_seconds 0.045952 # Number of seconds simulated -sim_ticks 45951528000 # Number of ticks simulated +sim_ticks 45951567500 # Number of ticks simulated +system.cpu.dtb.accesses 26497334 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 26497301 # DTB hits +system.cpu.dtb.misses 33 # DTB misses +system.cpu.dtb.read_accesses 19996208 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 19996198 # DTB read hits +system.cpu.dtb.read_misses 10 # DTB read misses +system.cpu.dtb.write_accesses 6501126 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 6501103 # DTB write hits +system.cpu.dtb.write_misses 23 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 91903136 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 91903089 # ITB hits +system.cpu.itb.misses 47 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 91903057 # number of cpu cycles simulated -system.cpu.num_insts 91903057 # Number of instructions executed -system.cpu.num_refs 26537109 # Number of memory references +system.cpu.numCycles 91903136 # number of cpu cycles simulated +system.cpu.num_insts 91903056 # Number of instructions executed +system.cpu.num_refs 26537141 # Number of memory references system.cpu.workload.PROG:num_syscalls 389 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/alpha/tru64/simple-timing/config.ini b/tests/long/70.twolf/ref/alpha/tru64/simple-timing/config.ini index 56cac7865..da35f8268 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/long/70.twolf/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/70.twolf/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/long/70.twolf/ref/alpha/tru64/simple-timing/m5stats.txt index 1f35acc4a..beacdcee0 100644 --- a/tests/long/70.twolf/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/long/70.twolf/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1713530 # Simulator instruction rate (inst/s) -host_mem_usage 204416 # Number of bytes of host memory used -host_seconds 53.63 # Real time elapsed on the host -host_tick_rate 2211088665 # Simulator tick rate (ticks/s) +host_inst_rate 1574277 # Simulator instruction rate (inst/s) +host_mem_usage 186464 # Number of bytes of host memory used +host_seconds 58.38 # Real time elapsed on the host +host_tick_rate 2031398471 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 91903057 # Number of instructions simulated +sim_insts 91903056 # Number of instructions simulated sim_seconds 0.118590 # Number of seconds simulated -sim_ticks 118589598000 # Number of ticks simulated +sim_ticks 118589630000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 19996198 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 24316.455696 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 22316.455696 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 157 # number of replacements system.cpu.dcache.sampled_refs 2222 # 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 1441.457790 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 1441.457531 # Cycle average of tags in use system.cpu.dcache.total_refs 26495079 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 104 # number of writebacks -system.cpu.icache.ReadReq_accesses 91903058 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 26497334 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 26497301 # DTB hits +system.cpu.dtb.misses 33 # DTB misses +system.cpu.dtb.read_accesses 19996208 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 19996198 # DTB read hits +system.cpu.dtb.read_misses 10 # DTB read misses +system.cpu.dtb.write_accesses 6501126 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 6501103 # DTB write hits +system.cpu.dtb.write_misses 23 # DTB write misses +system.cpu.icache.ReadReq_accesses 91903090 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 16695.887192 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 14695.887192 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 91894548 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 91894580 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 142082000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000093 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 8510 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000093 # ms system.cpu.icache.ReadReq_mshr_misses 8510 # 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 10798.419271 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 10798.423032 # 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 91903058 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 91903090 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 16695.887192 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 14695.887192 # average overall mshr miss latency -system.cpu.icache.demand_hits 91894548 # number of demand (read+write) hits +system.cpu.icache.demand_hits 91894580 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 142082000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000093 # miss rate for demand accesses system.cpu.icache.demand_misses 8510 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 8510 # nu 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 91903058 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 91903090 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 16695.887192 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 14695.887192 # 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 91894548 # number of overall hits +system.cpu.icache.overall_hits 91894580 # number of overall hits system.cpu.icache.overall_miss_latency 142082000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000093 # miss rate for overall accesses system.cpu.icache.overall_misses 8510 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 6681 # number of replacements system.cpu.icache.sampled_refs 8510 # 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 1418.474486 # Cycle average of tags in use -system.cpu.icache.total_refs 91894548 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1418.474247 # Cycle average of tags in use +system.cpu.icache.total_refs 91894580 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 91903137 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 91903090 # ITB hits +system.cpu.itb.misses 47 # ITB misses system.cpu.l2cache.ReadExReq_accesses 1748 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -224,14 +240,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 2955 # 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 2014.752255 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 2014.751911 # Cycle average of tags in use system.cpu.l2cache.total_refs 5916 # 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 118589598000 # number of cpu cycles simulated -system.cpu.num_insts 91903057 # Number of instructions executed -system.cpu.num_refs 26537109 # Number of memory references +system.cpu.numCycles 118589630000 # number of cpu cycles simulated +system.cpu.num_insts 91903056 # Number of instructions executed +system.cpu.num_refs 26537141 # Number of memory references system.cpu.workload.PROG:num_syscalls 389 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/sparc/linux/simple-atomic/config.ini b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/config.ini index 3dcf027c2..aad9a4c07 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=twolf smred @@ -53,7 +67,7 @@ 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/long/70.twolf/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/m5stats.txt index c41d3b35f..655a20772 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 673586 # Simulator instruction rate (inst/s) -host_mem_usage 150548 # Number of bytes of host memory used -host_seconds 287.17 # Real time elapsed on the host -host_tick_rate 336792536 # Simulator tick rate (ticks/s) +host_inst_rate 1618953 # Simulator instruction rate (inst/s) +host_mem_usage 181044 # Number of bytes of host memory used +host_seconds 119.48 # Real time elapsed on the host +host_tick_rate 809478979 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 193435973 # Number of instructions simulated +sim_insts 193435005 # Number of instructions simulated sim_seconds 0.096718 # Number of seconds simulated -sim_ticks 96717986000 # Number of ticks simulated +sim_ticks 96718067000 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 193435973 # number of cpu cycles simulated -system.cpu.num_insts 193435973 # Number of instructions executed -system.cpu.num_refs 76732959 # Number of memory references +system.cpu.numCycles 193436135 # number of cpu cycles simulated +system.cpu.num_insts 193435005 # Number of instructions executed +system.cpu.num_refs 76733003 # Number of memory references system.cpu.workload.PROG:num_syscalls 396 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/sparc/linux/simple-atomic/stdout b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/stdout index f878587c3..6b3948164 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-atomic/stdout +++ b/tests/long/70.twolf/ref/sparc/linux/simple-atomic/stdout @@ -18,11 +18,11 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 13:02:31 -M5 started Tue May 15 16:48:51 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:36:54 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-atomic tests/run.py long/70.twolf/sparc/linux/simple-atomic Couldn't unlink build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-atomic/smred.sav Couldn't unlink build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-atomic/smred.sv2 Global frequency set at 1000000000000 ticks per second -Exiting @ tick 96717986000 because target called exit() +Exiting @ tick 96718067000 because target called exit() diff --git a/tests/long/70.twolf/ref/sparc/linux/simple-timing/config.ini b/tests/long/70.twolf/ref/sparc/linux/simple-timing/config.ini index 1e251ac7c..8769743d0 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-timing/config.ini +++ b/tests/long/70.twolf/ref/sparc/linux/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/long/70.twolf/ref/sparc/linux/simple-timing/m5stats.txt b/tests/long/70.twolf/ref/sparc/linux/simple-timing/m5stats.txt index 7c9f3f182..bb82b8cc2 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/long/70.twolf/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1154889 # Simulator instruction rate (inst/s) -host_mem_usage 206344 # Number of bytes of host memory used -host_seconds 167.49 # Real time elapsed on the host -host_tick_rate 1614378740 # Simulator tick rate (ticks/s) +host_inst_rate 1002711 # Simulator instruction rate (inst/s) +host_mem_usage 188412 # Number of bytes of host memory used +host_seconds 192.91 # Real time elapsed on the host +host_tick_rate 1401662479 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 193435973 # Number of instructions simulated +sim_insts 193435005 # Number of instructions simulated sim_seconds 0.270398 # Number of seconds simulated -sim_ticks 270397855000 # Number of ticks simulated +sim_ticks 270397899000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 57734138 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -86,14 +86,14 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 26 # number of replacements system.cpu.dcache.sampled_refs 1585 # 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 1237.402461 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 1237.402352 # Cycle average of tags in use system.cpu.dcache.total_refs 76731373 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 23 # number of writebacks -system.cpu.icache.ReadReq_accesses 193435974 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses 193436018 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 16510.596674 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 14510.596674 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 193423706 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 193423750 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 202552000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000063 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 12268 # number of ReadReq misses @@ -102,16 +102,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000063 # ms system.cpu.icache.ReadReq_mshr_misses 12268 # 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 15766.523150 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 15766.526736 # 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 193435974 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 193436018 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 16510.596674 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 14510.596674 # average overall mshr miss latency -system.cpu.icache.demand_hits 193423706 # number of demand (read+write) hits +system.cpu.icache.demand_hits 193423750 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 202552000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000063 # miss rate for demand accesses system.cpu.icache.demand_misses 12268 # number of demand (read+write) misses @@ -122,11 +122,11 @@ system.cpu.icache.demand_mshr_misses 12268 # nu 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 193435974 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 193436018 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 16510.596674 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 14510.596674 # 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 193423706 # number of overall hits +system.cpu.icache.overall_hits 193423750 # number of overall hits system.cpu.icache.overall_miss_latency 202552000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000063 # miss rate for overall accesses system.cpu.icache.overall_misses 12268 # number of overall misses @@ -148,8 +148,8 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 10342 # number of replacements system.cpu.icache.sampled_refs 12268 # 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 1591.726914 # Cycle average of tags in use -system.cpu.icache.total_refs 193423706 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 1591.726789 # Cycle average of tags in use +system.cpu.icache.total_refs 193423750 # 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 @@ -234,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 4062 # 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 2649.703709 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 2649.703495 # Cycle average of tags in use system.cpu.l2cache.total_refs 8679 # 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 270397855000 # number of cpu cycles simulated -system.cpu.num_insts 193435973 # Number of instructions executed -system.cpu.num_refs 76732959 # Number of memory references +system.cpu.numCycles 270397899000 # number of cpu cycles simulated +system.cpu.num_insts 193435005 # Number of instructions executed +system.cpu.num_refs 76733003 # Number of memory references system.cpu.workload.PROG:num_syscalls 396 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/long/70.twolf/ref/sparc/linux/simple-timing/stdout b/tests/long/70.twolf/ref/sparc/linux/simple-timing/stdout index c89e9c783..656615235 100644 --- a/tests/long/70.twolf/ref/sparc/linux/simple-timing/stdout +++ b/tests/long/70.twolf/ref/sparc/linux/simple-timing/stdout @@ -18,11 +18,11 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 12:23:15 -M5 started Sun Aug 12 16:55:52 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:48:17 +M5 started Tue Aug 14 23:38:54 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-timing tests/run.py long/70.twolf/sparc/linux/simple-timing Couldn't unlink build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-timing/smred.sav Couldn't unlink build/SPARC_SE/tests/fast/long/70.twolf/sparc/linux/simple-timing/smred.sv2 Global frequency set at 1000000000000 ticks per second -Exiting @ tick 270397855000 because target called exit() +Exiting @ tick 270397899000 because target called exit() diff --git a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/config.ini b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/config.ini index d0738b960..7369c8a0c 100644 --- a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/config.ini +++ b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/config.ini @@ -34,8 +34,8 @@ symbolfile= [system.bridge] type=Bridge delay=100 -fix_partial_write_a=false -fix_partial_write_b=true +filter_ranges_a= +filter_ranges_b= nack_delay=8 req_size_a=16 req_size_b=16 @@ -47,7 +47,7 @@ side_b=system.membus.port[2] [system.cpu] type=AtomicSimpleCPU -children=dtb itb +children=dtb itb tracer clock=1 cpu_id=0 defer_registration=false @@ -67,6 +67,7 @@ profile=0 progress_interval=0 simulate_stalls=false system=system +tracer=system.cpu.tracer width=1 dcache_port=system.membus.port[10] icache_port=system.membus.port[9] @@ -79,6 +80,9 @@ size=64 type=SparcITB size=64 +[system.cpu.tracer] +type=ExeTracer + [system.disk0] type=MmDisk children=image @@ -149,7 +153,7 @@ clock=2 responder_set=false width=64 default=system.membus.responder.pio -port=system.t1000.iob.pio system.t1000.htod.pio system.bridge.side_b system.physmem.port system.physmem2.port system.rom.port system.nvram.port system.hypervisor_desc.port system.partition_desc.port system.cpu.icache_port system.cpu.dcache_port +port=system.t1000.iob.pio system.t1000.htod.pio system.bridge.side_b system.physmem.port[0] system.physmem2.port[0] system.rom.port[0] system.nvram.port[0] system.hypervisor_desc.port[0] system.partition_desc.port[0] system.cpu.icache_port system.cpu.dcache_port [system.membus.responder] type=IsaFake @@ -419,7 +423,7 @@ pio_addr=1099255906296 pio_latency=2 platform=system.t1000 system=system -time=2009 1 1 0 0 0 3 1 +time=Thu Jan 1 00:00:00 2009 pio=system.membus.port[1] [system.t1000.hvuart] diff --git a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/console.system.t1000.pconsole b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/console.system.t1000.pconsole index a31449664..f90a96e24 100644 --- a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/console.system.t1000.pconsole +++ b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/console.system.t1000.pconsole @@ -1,48 +1,48 @@ -cpu - -Sun Fire T2000, No Keyboard -Copyright 2006 Sun Microsystems, Inc. All rights reserved. -OpenBoot 4.23.0, 256 MB memory available, Serial #1122867. -[saidi obp #30] -Ethernet address 0:80:3:de:ad:3, Host ID: 80112233. - - - -Boot device: /virtual-devices/disk@0 File and args: -vV -Loading ufs-file-system package 1.4 04 Aug 1995 13:02:54. -FCode UFS Reader 1.12 00/07/17 15:48:16. -Loading: /platform/SUNW,Sun-Fire-T2000/ufsboot -Loading: /platform/sun4v/ufsboot -device path '/virtual-devices@100/disk@0:a' -The boot filesystem is logging. -The ufs log is empty and will not be used. -standalone = `kernel/sparcv9/unix', args = `-v' -|Elf64 client -Size: /-\|/-\|0x76e40+/-\|/-\|/-\|/-\0x1c872+|/-\0x3123a Bytes -modpath: /platform/sun4v/kernel /kernel /usr/kernel -|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-module /platform/sun4v/kernel/sparcv9/unix: text at [0x1000000, 0x1076e3f] data at 0x1800000 -module misc/sparcv9/krtld: text at [0x1076e40, 0x108f737] data at 0x184dab0 -module /platform/sun4v/kernel/sparcv9/genunix: text at [0x108f738, 0x11dd437] data at 0x18531c0 -module /platform/sun4v/kernel/misc/sparcv9/platmod: text at [0x11dd438, 0x11dd43f] data at 0x18a4be0 -module /platform/sun4v/kernel/cpu/sparcv9/SUNW,UltraSPARC-T1: text at [0x11dd440, 0x11e06ff] data at 0x18a5300 -\
SunOS Release 5.10 Version Generic_118822-23 64-bit -Copyright 1983-2005 Sun Microsystems, Inc. All rights reserved. -Use is subject to license terms. -|/-\|/-\|/-\|/-\|/-Ethernet address = 0:80:3:de:ad:3 -\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/mem = 262144K (0x10000000) -avail mem = 237879296 -root nexus = Sun Fire T2000 -pseudo0 at root -pseudo0 is /pseudo -scsi_vhci0 at root -scsi_vhci0 is /scsi_vhci -virtual-device: hsimd0 -hsimd0 is /virtual-devices@100/disk@0 -root on /virtual-devices@100/disk@0:a fstype ufs -pseudo-device: dld0 -dld0 is /pseudo/dld@0 -cpu0: UltraSPARC-T1 (cpuid 0 clock 5 MHz) -iscsi0 at root -iscsi0 is /iscsi -Hostname: unknown -Loading M5 readfile script... +cpu
+
+Sun Fire T2000, No Keyboard
+Copyright 2006 Sun Microsystems, Inc. All rights reserved.
+OpenBoot 4.23.0, 256 MB memory available, Serial #1122867.
+[saidi obp #30]
+Ethernet address 0:80:3:de:ad:3, Host ID: 80112233.
+
+
+
+Boot device: /virtual-devices/disk@0 File and args: -vV
+Loading ufs-file-system package 1.4 04 Aug 1995 13:02:54.
+FCode UFS Reader 1.12 00/07/17 15:48:16.
+Loading: /platform/SUNW,Sun-Fire-T2000/ufsboot
+Loading: /platform/sun4v/ufsboot
+device path '/virtual-devices@100/disk@0:a'
+The boot filesystem is logging.
+The ufs log is empty and will not be used.
+standalone = `kernel/sparcv9/unix', args = `-v'
+|Elf64 client
+Size: /-\|/-\|0x76e40+/-\|/-\|/-\|/-\0x1c872+|/-\0x3123a Bytes
+modpath: /platform/sun4v/kernel /kernel /usr/kernel
+|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-module /platform/sun4v/kernel/sparcv9/unix: text at [0x1000000, 0x1076e3f] data at 0x1800000
+module misc/sparcv9/krtld: text at [0x1076e40, 0x108f737] data at 0x184dab0
+module /platform/sun4v/kernel/sparcv9/genunix: text at [0x108f738, 0x11dd437] data at 0x18531c0
+module /platform/sun4v/kernel/misc/sparcv9/platmod: text at [0x11dd438, 0x11dd43f] data at 0x18a4be0
+module /platform/sun4v/kernel/cpu/sparcv9/SUNW,UltraSPARC-T1: text at [0x11dd440, 0x11e06ff] data at 0x18a5300
+\
SunOS Release 5.10 Version Generic_118822-23 64-bit
+Copyright 1983-2005 Sun Microsystems, Inc. All rights reserved.
+Use is subject to license terms.
+|/-\|/-\|/-\|/-\|/-Ethernet address = 0:80:3:de:ad:3
+\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/-\|/mem = 262144K (0x10000000)
+avail mem = 237879296
+root nexus = Sun Fire T2000
+pseudo0 at root
+pseudo0 is /pseudo
+scsi_vhci0 at root
+scsi_vhci0 is /scsi_vhci
+virtual-device: hsimd0
+hsimd0 is /virtual-devices@100/disk@0
+root on /virtual-devices@100/disk@0:a fstype ufs
+pseudo-device: dld0
+dld0 is /pseudo/dld@0
+cpu0: UltraSPARC-T1 (cpuid 0 clock 5 MHz)
+iscsi0 at root
+iscsi0 is /iscsi
+Hostname: unknown
+Loading M5 readfile script...
diff --git a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/m5stats.txt b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/m5stats.txt index 5229bd3a6..34b89818c 100644 --- a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/m5stats.txt +++ b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/m5stats.txt @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 584673 # Simulator instruction rate (inst/s) -host_mem_usage 374168 # Number of bytes of host memory used -host_seconds 3820.23 # Real time elapsed on the host -host_tick_rate 584723 # Simulator tick rate (ticks/s) +host_inst_rate 1839897 # Simulator instruction rate (inst/s) +host_mem_usage 481416 # Number of bytes of host memory used +host_seconds 1211.57 # Real time elapsed on the host +host_tick_rate 1843707 # Simulator tick rate (ticks/s) sim_freq 2000000000 # Frequency of simulated ticks -sim_insts 2233583679 # Number of instructions simulated +sim_insts 2229160714 # Number of instructions simulated sim_seconds 1.116889 # Number of seconds simulated sim_ticks 2233777512 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles @@ -13,7 +13,7 @@ system.cpu.kern.inst.arm 0 # nu system.cpu.kern.inst.quiesce 0 # number of quiesce instructions executed system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles system.cpu.numCycles 2233777513 # number of cpu cycles simulated -system.cpu.num_insts 2233583679 # Number of instructions executed +system.cpu.num_insts 2229160714 # Number of instructions executed system.cpu.num_refs 547951940 # Number of memory references ---------- End Simulation Statistics ---------- diff --git a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stderr b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stderr index cf3ec3bba..4c0b4aee0 100644 --- a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stderr +++ b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stderr @@ -3,8 +3,12 @@ Warning: rounding error > tolerance Warning: rounding error > tolerance 0.002000 rounded to 0 warn: No kernel set for full system simulation. Assuming you know what you're doing... +Warning: rounding error > tolerance + 0.002000 rounded to 0 Listening for t1000 connection on port 3456 Listening for t1000 connection on port 3457 +Warning: rounding error > tolerance + 0.002000 rounded to 0 0: system.remote_gdb.listener: listening for remote gdb on port 7000 warn: Entering event queue @ 0. Starting simulation... warn: Ignoring write to SPARC ERROR regsiter diff --git a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stdout b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stdout index ef048f157..4c8cf9392 100644 --- a/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stdout +++ b/tests/long/80.solaris-boot/ref/sparc/solaris/t1000-simple-atomic/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 17:08:10 -M5 started Tue May 15 17:08:12 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 21 2007 14:42:25 +M5 started Tue Aug 21 14:44:56 2007 +M5 executing on nacho command line: build/SPARC_FS/m5.fast -d build/SPARC_FS/tests/fast/long/80.solaris-boot/sparc/solaris/t1000-simple-atomic tests/run.py long/80.solaris-boot/sparc/solaris/t1000-simple-atomic Global frequency set at 2000000000 ticks per second Exiting @ tick 2233777512 because m5_exit instruction encountered 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 1a19512dc..f58899eb3 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 tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt index 35d6ad747..ce1ae8d6f 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 538 # Number of BTB hits -global.BPredUnit.BTBLookups 1681 # Number of BTB lookups +global.BPredUnit.BTBHits 562 # Number of BTB hits +global.BPredUnit.BTBLookups 1725 # Number of BTB lookups global.BPredUnit.RASInCorrect 51 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 412 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 1149 # Number of conditional branches predicted -global.BPredUnit.lookups 1984 # Number of BP lookups -global.BPredUnit.usedRAS 275 # Number of times the RAS was used to get a target. -host_inst_rate 62494 # Simulator instruction rate (inst/s) -host_mem_usage 196896 # Number of bytes of host memory used -host_seconds 0.09 # Real time elapsed on the host -host_tick_rate 50069310 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 10 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 121 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 1979 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1190 # Number of stores inserted to the mem dependence unit. +global.BPredUnit.condIncorrect 409 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 1184 # Number of conditional branches predicted +global.BPredUnit.lookups 2029 # Number of BP lookups +global.BPredUnit.usedRAS 277 # Number of times the RAS was used to get a target. +host_inst_rate 9351 # Simulator instruction rate (inst/s) +host_mem_usage 180452 # Number of bytes of host memory used +host_seconds 0.60 # Real time elapsed on the host +host_tick_rate 7988790 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 23 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 124 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 2030 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1236 # 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 4515000 # Number of ticks simulated +sim_ticks 4806000 # Number of ticks simulated system.cpu.commit.COM:branches 862 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 81 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 85 # 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 8177 +system.cpu.commit.COM:committed_per_cycle.samples 8660 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 5854 7159.10% - 1 1205 1473.65% - 2 403 492.85% - 3 188 229.91% - 4 133 162.65% - 5 98 119.85% - 6 110 134.52% - 7 105 128.41% - 8 81 99.06% + 0 6353 7336.03% + 1 1192 1376.44% + 2 402 464.20% + 3 185 213.63% + 4 132 152.42% + 5 93 107.39% + 6 110 127.02% + 7 108 124.71% + 8 85 98.15% 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 339 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 336 # 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 4015 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 4234 # 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 1.584030 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.584030 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 1516 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 10550 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 6350 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 1416 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 1055000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.065963 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 100 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 32 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 635000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.065963 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 100 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 533 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 26660.919540 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5781.609195 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 446 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 2319500 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate 0.163227 # miss rate for WriteReq accesses +system.cpu.cpi 1.680420 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.680420 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 1535 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 10443.877551 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 6357.142857 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 1437 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 1023500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.063844 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 98 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 31 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 623000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.063844 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 98 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 529 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 27385.057471 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5839.080460 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 442 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 2382500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.164461 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 87 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 279 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 503000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate 0.163227 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_hits 283 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 508000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.164461 # 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 10.843931 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 11.141176 # 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 2049 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 18045.454545 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 6085.561497 # average overall mshr miss latency -system.cpu.dcache.demand_hits 1862 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 3374500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.091264 # miss rate for demand accesses -system.cpu.dcache.demand_misses 187 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 311 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 1138000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.091264 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 187 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 2064 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 18410.810811 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 6113.513514 # average overall mshr miss latency +system.cpu.dcache.demand_hits 1879 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 3406000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.089632 # miss rate for demand accesses +system.cpu.dcache.demand_misses 185 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 314 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 1131000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.089632 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 185 # 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 2049 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 18045.454545 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 6085.561497 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 2064 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 18410.810811 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 6113.513514 # 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 1862 # number of overall hits -system.cpu.dcache.overall_miss_latency 3374500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.091264 # miss rate for overall accesses -system.cpu.dcache.overall_misses 187 # number of overall misses -system.cpu.dcache.overall_mshr_hits 311 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 1138000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.091264 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 187 # number of overall MSHR misses +system.cpu.dcache.overall_hits 1879 # number of overall hits +system.cpu.dcache.overall_miss_latency 3406000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.089632 # miss rate for overall accesses +system.cpu.dcache.overall_misses 185 # number of overall misses +system.cpu.dcache.overall_mshr_hits 314 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 1131000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.089632 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 185 # 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 +119,103 @@ 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 170 # 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 111.683956 # Cycle average of tags in use -system.cpu.dcache.total_refs 1876 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 109.245747 # Cycle average of tags in use +system.cpu.dcache.total_refs 1894 # 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 428 # 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 164 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 11204 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 5725 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 1989 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 729 # Number of cycles decode is squashing +system.cpu.decode.DECODE:BranchMispred 80 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 168 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 11542 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 6127 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 2070 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 788 # Number of cycles decode is squashing system.cpu.decode.DECODE:SquashedInsts 235 # Number of squashed instructions handled by decode system.cpu.decode.DECODE:UnblockCycles 36 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 1984 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 1520 # Number of cache lines fetched -system.cpu.fetch.Cycles 3641 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 230 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 12195 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 444 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.222746 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 1520 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 813 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.369148 # Number of inst fetches per cycle +system.cpu.dtb.accesses 2656 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 2596 # DTB hits +system.cpu.dtb.misses 60 # DTB misses +system.cpu.dtb.read_accesses 1652 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 1615 # DTB read hits +system.cpu.dtb.read_misses 37 # DTB read misses +system.cpu.dtb.write_accesses 1004 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 981 # DTB write hits +system.cpu.dtb.write_misses 23 # DTB write misses +system.cpu.fetch.Branches 2029 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 1542 # Number of cache lines fetched +system.cpu.fetch.Cycles 3746 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 226 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 12519 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 469 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.214732 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 1542 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 839 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.324902 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 8907 +system.cpu.fetch.rateDist.samples 9449 system.cpu.fetch.rateDist.min_value 0 - 0 6787 7619.85% - 1 178 199.84% - 2 167 187.49% - 3 149 167.28% - 4 210 235.77% - 5 157 176.27% - 6 180 202.09% - 7 101 113.39% - 8 978 1098.01% + 0 7275 7699.23% + 1 181 191.55% + 2 174 184.15% + 3 146 154.51% + 4 219 231.77% + 5 159 168.27% + 6 189 200.02% + 7 101 106.89% + 8 1005 1063.60% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 1497 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7812.101911 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5500 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 1183 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 2453000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.209753 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 314 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 23 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 1727000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.209753 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 314 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 1520 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7745.954693 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5443.365696 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 1211 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 2393500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.203289 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 309 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 22 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 1682000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.203289 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 309 # 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 3.767516 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 3.919094 # 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 1497 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7812.101911 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5500 # average overall mshr miss latency -system.cpu.icache.demand_hits 1183 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 2453000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.209753 # miss rate for demand accesses -system.cpu.icache.demand_misses 314 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 23 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 1727000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.209753 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 314 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 1520 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7745.954693 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5443.365696 # average overall mshr miss latency +system.cpu.icache.demand_hits 1211 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 2393500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.203289 # miss rate for demand accesses +system.cpu.icache.demand_misses 309 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 22 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 1682000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.203289 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 309 # 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 1497 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7812.101911 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5500 # average overall mshr miss latency +system.cpu.icache.overall_accesses 1520 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7745.954693 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5443.365696 # 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 1183 # number of overall hits -system.cpu.icache.overall_miss_latency 2453000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.209753 # miss rate for overall accesses -system.cpu.icache.overall_misses 314 # number of overall misses -system.cpu.icache.overall_mshr_hits 23 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 1727000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.209753 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 314 # number of overall MSHR misses +system.cpu.icache.overall_hits 1211 # number of overall hits +system.cpu.icache.overall_miss_latency 2393500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.203289 # miss rate for overall accesses +system.cpu.icache.overall_misses 309 # number of overall misses +system.cpu.icache.overall_mshr_hits 22 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 1682000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.203289 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 309 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -216,61 +228,61 @@ system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.icache.replacements 0 # number of replacements -system.cpu.icache.sampled_refs 314 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 309 # 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 165.376334 # Cycle average of tags in use -system.cpu.icache.total_refs 1183 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 164.253671 # Cycle average of tags in use +system.cpu.icache.total_refs 1211 # 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 88946 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 1172 # Number of branches executed -system.cpu.iew.EXEC:nop 45 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.880207 # Inst execution rate -system.cpu.iew.EXEC:refs 2591 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 974 # Number of stores executed +system.cpu.idleCycles 110443 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 1199 # Number of branches executed +system.cpu.iew.EXEC:nop 72 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.848450 # Inst execution rate +system.cpu.iew.EXEC:refs 2660 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 1006 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 5292 # num instructions consuming a value -system.cpu.iew.WB:count 7505 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.745276 # average fanout of values written-back +system.cpu.iew.WB:consumers 5426 # num instructions consuming a value +system.cpu.iew.WB:count 7664 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.742905 # 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 3944 # num instructions producing a value -system.cpu.iew.WB:rate 0.842596 # insts written-back per cycle -system.cpu.iew.WB:sent 7591 # cumulative count of insts sent to commit +system.cpu.iew.WB:producers 4031 # num instructions producing a value +system.cpu.iew.WB:rate 0.811091 # insts written-back per cycle +system.cpu.iew.WB:sent 7781 # cumulative count of insts sent to commit system.cpu.iew.branchMispredicts 401 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 4 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 1979 # Number of dispatched load instructions +system.cpu.iew.iewDispLoadInsts 2030 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 23 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 194 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 1190 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 9672 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 1617 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 358 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 7840 # Number of executed instructions +system.cpu.iew.iewDispSquashedInsts 173 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 1236 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 9996 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 1654 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 366 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 8017 # 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 729 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 788 # 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 47 # Number of loads that had data forwarded from stores +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 66 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 68 # 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 1000 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 378 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 66 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 294 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 107 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.631301 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.631301 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 8198 # Type of FU issued +system.cpu.iew.lsq.thread.0.squashedLoads 1051 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 424 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 68 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 295 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 106 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.595089 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.595089 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8383 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 2 0.02% # Type of FU issued - IntAlu 5452 66.50% # Type of FU issued + IntAlu 5559 66.31% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 2 0.02% # Type of FU issued @@ -279,16 +291,16 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 1744 21.27% # Type of FU issued - MemWrite 997 12.16% # Type of FU issued + MemRead 1786 21.31% # Type of FU issued + MemWrite 1033 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 102 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.012442 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate 0.012167 # 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 + IntAlu 1 0.98% # 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 @@ -297,96 +309,100 @@ 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 67 65.69% # attempts to use FU when none available + MemRead 66 64.71% # attempts to use FU when none available MemWrite 35 34.31% # 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 8907 +system.cpu.iq.ISSUE:issued_per_cycle.samples 9449 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 5630 6320.87% - 1 1096 1230.49% - 2 792 889.19% - 3 582 653.42% - 4 464 520.94% - 5 200 224.54% - 6 99 111.15% - 7 30 33.68% - 8 14 15.72% + 0 6104 6459.94% + 1 1119 1184.25% + 2 811 858.29% + 3 592 626.52% + 4 460 486.82% + 5 212 224.36% + 6 105 111.12% + 7 32 33.87% + 8 14 14.82% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.920400 # Inst issue rate -system.cpu.iq.iqInstsAdded 9604 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 8198 # Number of instructions issued +system.cpu.iq.ISSUE:rate 0.887184 # Inst issue rate +system.cpu.iq.iqInstsAdded 9901 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 8383 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 23 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 3664 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 22 # Number of squashed instructions issued +system.cpu.iq.iqSquashedInstsExamined 3948 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 23 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 6 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 2365 # 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 4486.301370 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2486.301370 # average ReadExReq mshr miss latency +system.cpu.iq.iqSquashedOperandsExamined 2574 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 1572 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 1542 # ITB hits +system.cpu.itb.misses 30 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 72 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 4548.611111 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2548.611111 # average ReadExReq mshr miss latency system.cpu.l2cache.ReadExReq_miss_latency 327500 # 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 181500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 72 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 183500 # 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 414 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4450.242718 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2450.242718 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 2 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 1833500 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.995169 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 412 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 1009500 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.995169 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 412 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4214.285714 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2214.285714 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 59000 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_mshr_misses 72 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 407 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4400.246305 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2400.246305 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 1 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1786500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.997543 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 406 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 974500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.997543 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 406 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 15 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4266.666667 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2266.666667 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 64000 # 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 31000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 15 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 34000 # 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.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 0.005025 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.002558 # 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 487 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4455.670103 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2455.670103 # average overall mshr miss latency -system.cpu.l2cache.demand_hits 2 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 2161000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.995893 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 485 # number of demand (read+write) misses +system.cpu.l2cache.demand_accesses 479 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4422.594142 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2422.594142 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 1 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 2114000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.997912 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 478 # 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 1191000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.995893 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 485 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 1158000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.997912 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 478 # 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 487 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4455.670103 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2455.670103 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 479 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4422.594142 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2422.594142 # 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 2161000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.995893 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 485 # number of overall misses +system.cpu.l2cache.overall_hits 1 # number of overall hits +system.cpu.l2cache.overall_miss_latency 2114000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.997912 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 478 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 1191000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.995893 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 485 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 1158000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.997912 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 478 # 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 @@ -399,29 +415,29 @@ 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 398 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 391 # 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 221.319862 # Cycle average of tags in use -system.cpu.l2cache.total_refs 2 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 218.025629 # 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.numCycles 8907 # number of cpu cycles simulated +system.cpu.numCycles 9449 # number of cpu cycles simulated system.cpu.rename.RENAME:BlockCycles 50 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 4051 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 5884 # Number of cycles rename is idle +system.cpu.rename.RENAME:IdleCycles 6291 # 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 13715 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 10735 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 8030 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 1846 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 729 # Number of cycles rename is squashing +system.cpu.rename.RENAME:RenameLookups 14101 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 11035 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 8205 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 1922 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 788 # Number of cycles rename is squashing system.cpu.rename.RENAME:UnblockCycles 122 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 3979 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:UndoneMaps 4154 # Number of HB maps that are undone due to squashing system.cpu.rename.RENAME:serializeStallCycles 276 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed system.cpu.rename.RENAME:skidInsts 532 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 20 # count of temporary serializing insts renamed -system.cpu.timesIdled 54 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 57 # 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 fe297b10e..2c1517e04 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 Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:40 2007 -M5 executing on zeep +M5 compiled Aug 13 2007 17:39:24 +M5 started Mon Aug 13 17:39:25 2007 +M5 executing on nacho 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 4515000 because target called exit() +Exiting @ tick 4806000 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 d025afdec..264bd19de 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=tracer workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -31,6 +33,14 @@ workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.tracer] type=ExeTracer @@ -41,7 +51,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/linux/hello gid=100 input=cin output=cout 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 f87ad2cd6..c89057e77 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 @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -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) +host_inst_rate 274181 # Simulator instruction rate (inst/s) +host_mem_usage 172576 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 135418658 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 5642 # Number of instructions simulated +sim_insts 5641 # Number of instructions simulated sim_seconds 0.000003 # Number of seconds simulated -sim_ticks 2820500 # Number of ticks simulated +sim_ticks 2833500 # Number of ticks simulated +system.cpu.dtb.accesses 1801 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 1791 # DTB hits +system.cpu.dtb.misses 10 # DTB misses +system.cpu.dtb.read_accesses 986 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 979 # DTB read hits +system.cpu.dtb.read_misses 7 # DTB read misses +system.cpu.dtb.write_accesses 815 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 812 # DTB write hits +system.cpu.dtb.write_misses 3 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 5668 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 5651 # ITB hits +system.cpu.itb.misses 17 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 5642 # 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.numCycles 5668 # number of cpu cycles simulated +system.cpu.num_insts 5641 # Number of instructions executed +system.cpu.num_refs 1801 # Number of memory references system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- 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 0bec3d18f..9af7c0a45 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 Aug 3 2007 03:56:47 -M5 started Fri Aug 3 04:17:12 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 17:36:58 +M5 started Tue Aug 14 17:40:03 2007 +M5 executing on nacho 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() +Exiting @ tick 2833500 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 c95e2e383..78fe6c01f 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 @@ -156,7 +166,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/linux/hello gid=100 input=cin output=cout 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 3c7a26090..0908a82c9 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 @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 334797 # Simulator instruction rate (inst/s) -host_mem_usage 196348 # Number of bytes of host memory used +host_inst_rate 243703 # Simulator instruction rate (inst/s) +host_mem_usage 179944 # Number of bytes of host memory used host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 1064082508 # Simulator tick rate (ticks/s) +host_tick_rate 781539770 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 5642 # Number of instructions simulated +sim_insts 5641 # Number of instructions simulated sim_seconds 0.000018 # Number of seconds simulated -sim_ticks 18365000 # Number of ticks simulated +sim_ticks 18374000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 979 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -76,53 +76,65 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 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 102.396682 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 102.386256 # 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.dtb.accesses 1801 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 1791 # DTB hits +system.cpu.dtb.misses 10 # DTB misses +system.cpu.dtb.read_accesses 986 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 979 # DTB read hits +system.cpu.dtb.read_misses 7 # DTB read misses +system.cpu.dtb.write_accesses 815 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 812 # DTB write hits +system.cpu.dtb.write_misses 3 # DTB write misses +system.cpu.icache.ReadReq_accesses 5652 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 24956.678700 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 22956.678700 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 5366 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 5375 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 6913000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.049087 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.049009 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 277 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 6359000 # 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_miss_rate 0.049009 # 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 system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 19.371841 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 19.404332 # 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 5643 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 5652 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 24956.678700 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 22956.678700 # average overall mshr miss latency -system.cpu.icache.demand_hits 5366 # number of demand (read+write) hits +system.cpu.icache.demand_hits 5375 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 6913000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.049087 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.049009 # 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 6359000 # 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_miss_rate 0.049009 # 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_accesses 5652 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 24956.678700 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 22956.678700 # 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_hits 5375 # number of overall hits system.cpu.icache.overall_miss_latency 6913000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.049087 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.049009 # 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 6359000 # 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_miss_rate 0.049009 # 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 system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 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 128.096333 # Cycle average of tags in use -system.cpu.icache.total_refs 5366 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 128.084203 # Cycle average of tags in use +system.cpu.icache.total_refs 5375 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 5669 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 5652 # ITB hits +system.cpu.itb.misses 17 # ITB misses system.cpu.l2cache.ReadExReq_accesses 73 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -219,14 +235,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements 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 177.517189 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 177.499846 # 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 18365000 # 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.numCycles 18374000 # number of cpu cycles simulated +system.cpu.num_insts 5641 # Number of instructions executed +system.cpu.num_refs 1801 # Number of memory references system.cpu.workload.PROG:num_syscalls 17 # Number of system calls ---------- End Simulation Statistics ---------- 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 940c4ad1c..67d82b1c5 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 Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:41 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 17:58:14 +M5 started Tue Aug 14 17:59:07 2007 +M5 executing on nacho 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 18365000 because target called exit() +Exiting @ tick 18374000 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 f5eb9b8b9..d3406f49b 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt index 536bed0d1..ffd2f7ab7 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/m5stats.txt @@ -1,40 +1,40 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 143 # Number of BTB hits -global.BPredUnit.BTBLookups 610 # Number of BTB lookups -global.BPredUnit.RASInCorrect 32 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 212 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 394 # Number of conditional branches predicted -global.BPredUnit.lookups 779 # Number of BP lookups -global.BPredUnit.usedRAS 155 # Number of times the RAS was used to get a target. -host_inst_rate 72558 # Simulator instruction rate (inst/s) -host_mem_usage 196048 # Number of bytes of host memory used -host_seconds 0.03 # Real time elapsed on the host -host_tick_rate 63572637 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 8 # Number of conflicting loads. +global.BPredUnit.BTBHits 156 # Number of BTB hits +global.BPredUnit.BTBLookups 642 # Number of BTB lookups +global.BPredUnit.RASInCorrect 35 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 213 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 401 # Number of conditional branches predicted +global.BPredUnit.lookups 824 # Number of BP lookups +global.BPredUnit.usedRAS 163 # Number of times the RAS was used to get a target. +host_inst_rate 31893 # Simulator instruction rate (inst/s) +host_mem_usage 179460 # Number of bytes of host memory used +host_seconds 0.08 # Real time elapsed on the host +host_tick_rate 32096529 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 7 # Number of conflicting loads. memdepunit.memDep.conflictingStores 7 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 636 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 369 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 698 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 412 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 2387 # Number of instructions simulated sim_seconds 0.000002 # Number of seconds simulated -sim_ticks 2104000 # Number of ticks simulated +sim_ticks 2410000 # Number of ticks simulated system.cpu.commit.COM:branches 396 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 35 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 32 # number cycles where commit BW limit reached system.cpu.commit.COM:bw_limited 0 # number of insts not committed due to BW limits system.cpu.commit.COM:committed_per_cycle.start_dist # Number of insts commited each cycle -system.cpu.commit.COM:committed_per_cycle.samples 3945 +system.cpu.commit.COM:committed_per_cycle.samples 4452 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 2992 7584.28% - 1 255 646.39% - 2 335 849.18% - 3 139 352.34% - 4 66 167.30% - 5 69 174.90% - 6 33 83.65% - 7 21 53.23% - 8 35 88.72% + 0 3490 7839.17% + 1 258 579.51% + 2 340 763.70% + 3 140 314.47% + 4 70 157.23% + 5 70 157.23% + 6 32 71.88% + 7 20 44.92% + 8 32 71.88% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,69 +43,69 @@ system.cpu.commit.COM:loads 415 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 709 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 131 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 132 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 2576 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 4 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 1134 # The number of squashed insts skipped by commit +system.cpu.commit.commitSquashedInsts 1380 # The number of squashed insts skipped by commit system.cpu.committedInsts 2387 # Number of Instructions Simulated system.cpu.committedInsts_total 2387 # Number of Instructions Simulated -system.cpu.cpi 1.747382 # CPI: Cycles Per Instruction -system.cpu.cpi_total 1.747382 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 519 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 8729.508197 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5745.901639 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 458 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 532500 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.117534 # miss rate for ReadReq accesses +system.cpu.cpi 1.984080 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.984080 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 528 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 8639.344262 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5655.737705 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 467 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 527000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.115530 # miss rate for ReadReq accesses system.cpu.dcache.ReadReq_misses 61 # number of ReadReq misses system.cpu.dcache.ReadReq_mshr_hits 10 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 350500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.117534 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_miss_latency 345000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.115530 # mshr miss rate for ReadReq accesses system.cpu.dcache.ReadReq_mshr_misses 61 # number of ReadReq MSHR misses system.cpu.dcache.WriteReq_accesses 240 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 18810.810811 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 6202.702703 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 18297.297297 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5986.486486 # average WriteReq mshr miss latency system.cpu.dcache.WriteReq_hits 203 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 696000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 677000 # number of WriteReq miss cycles system.cpu.dcache.WriteReq_miss_rate 0.154167 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 37 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_hits 54 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 229500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 221500 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.154167 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 37 # number of WriteReq MSHR misses system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.dcache.avg_refs 7.929412 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 8.035294 # Average number of references to valid blocks. system.cpu.dcache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.dcache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.dcache.cache_copies 0 # number of cache copies performed -system.cpu.dcache.demand_accesses 759 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 12535.714286 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5918.367347 # average overall mshr miss latency -system.cpu.dcache.demand_hits 661 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 1228500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.129117 # miss rate for demand accesses +system.cpu.dcache.demand_accesses 768 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 12285.714286 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5780.612245 # average overall mshr miss latency +system.cpu.dcache.demand_hits 670 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 1204000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.127604 # miss rate for demand accesses system.cpu.dcache.demand_misses 98 # number of demand (read+write) misses system.cpu.dcache.demand_mshr_hits 64 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 580000 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.129117 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_latency 566500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.127604 # mshr miss rate for demand accesses system.cpu.dcache.demand_mshr_misses 98 # number of demand (read+write) MSHR misses system.cpu.dcache.fast_writes 0 # number of fast writes performed system.cpu.dcache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.dcache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.dcache.overall_accesses 759 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 12535.714286 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5918.367347 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 768 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 12285.714286 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5780.612245 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 661 # number of overall hits -system.cpu.dcache.overall_miss_latency 1228500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.129117 # miss rate for overall accesses +system.cpu.dcache.overall_hits 670 # number of overall hits +system.cpu.dcache.overall_miss_latency 1204000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.127604 # miss rate for overall accesses system.cpu.dcache.overall_misses 98 # number of overall misses system.cpu.dcache.overall_mshr_hits 64 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 580000 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.129117 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_latency 566500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.127604 # mshr miss rate for overall accesses system.cpu.dcache.overall_mshr_misses 98 # number of overall MSHR misses system.cpu.dcache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.dcache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -121,89 +121,101 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 85 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 50.690606 # Cycle average of tags in use -system.cpu.dcache.total_refs 674 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 47.072215 # Cycle average of tags in use +system.cpu.dcache.total_refs 683 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 91 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BlockedCycles 93 # Number of cycles decode is blocked system.cpu.decode.DECODE:BranchMispred 83 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 126 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 4236 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 3045 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 809 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 225 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 304 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:BranchResolved 135 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 4564 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 3475 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 884 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 283 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 303 # Number of squashed instructions handled by decode system.cpu.decode.DECODE:UnblockCycles 1 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 779 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 691 # Number of cache lines fetched -system.cpu.fetch.Cycles 1534 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 112 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 4961 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 223 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.186766 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 691 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 298 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.189403 # Number of inst fetches per cycle +system.cpu.dtb.accesses 931 # DTB accesses +system.cpu.dtb.acv 1 # DTB access violations +system.cpu.dtb.hits 904 # DTB hits +system.cpu.dtb.misses 27 # DTB misses +system.cpu.dtb.read_accesses 575 # DTB read accesses +system.cpu.dtb.read_acv 1 # DTB read access violations +system.cpu.dtb.read_hits 563 # DTB read hits +system.cpu.dtb.read_misses 12 # DTB read misses +system.cpu.dtb.write_accesses 356 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 341 # DTB write hits +system.cpu.dtb.write_misses 15 # DTB write misses +system.cpu.fetch.Branches 824 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 707 # Number of cache lines fetched +system.cpu.fetch.Cycles 1626 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 101 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 5268 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 242 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.173986 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 707 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 319 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.112331 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 4171 +system.cpu.fetch.rateDist.samples 4736 system.cpu.fetch.rateDist.min_value 0 - 0 3330 7983.70% - 1 36 86.31% - 2 85 203.79% - 3 57 136.66% - 4 109 261.33% - 5 54 129.47% - 6 40 95.90% - 7 42 100.70% - 8 418 1002.16% + 0 3845 8118.67% + 1 38 80.24% + 2 85 179.48% + 3 63 133.02% + 4 118 249.16% + 5 55 116.13% + 6 42 88.68% + 7 48 101.35% + 8 442 933.28% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 674 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7774.193548 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5451.612903 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 488 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 1446000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.275964 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 186 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 17 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 1014000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.275964 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 186 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 692 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7648.351648 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5370.879121 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 510 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 1392000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.263006 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 182 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 15 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 977500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.263006 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 182 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 2.623656 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 2.802198 # Average number of references to valid blocks. system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 674 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7774.193548 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5451.612903 # average overall mshr miss latency -system.cpu.icache.demand_hits 488 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 1446000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.275964 # miss rate for demand accesses -system.cpu.icache.demand_misses 186 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 17 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 1014000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.275964 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 186 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 692 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7648.351648 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5370.879121 # average overall mshr miss latency +system.cpu.icache.demand_hits 510 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 1392000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.263006 # miss rate for demand accesses +system.cpu.icache.demand_misses 182 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 15 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 977500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.263006 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 182 # number of demand (read+write) MSHR misses system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.icache.overall_accesses 674 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7774.193548 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5451.612903 # average overall mshr miss latency +system.cpu.icache.overall_accesses 692 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7648.351648 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5370.879121 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 488 # number of overall hits -system.cpu.icache.overall_miss_latency 1446000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.275964 # miss rate for overall accesses -system.cpu.icache.overall_misses 186 # number of overall misses -system.cpu.icache.overall_mshr_hits 17 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 1014000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.275964 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 186 # number of overall MSHR misses +system.cpu.icache.overall_hits 510 # number of overall hits +system.cpu.icache.overall_miss_latency 1392000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.263006 # miss rate for overall accesses +system.cpu.icache.overall_misses 182 # number of overall misses +system.cpu.icache.overall_mshr_hits 15 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 977500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.263006 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 182 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -216,61 +228,61 @@ system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.icache.replacements 0 # number of replacements -system.cpu.icache.sampled_refs 186 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 182 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 102.643576 # Cycle average of tags in use -system.cpu.icache.total_refs 488 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 92.900452 # Cycle average of tags in use +system.cpu.icache.total_refs 510 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks -system.cpu.idleCycles 26984 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 522 # Number of branches executed -system.cpu.iew.EXEC:nop 242 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.736514 # Inst execution rate -system.cpu.iew.EXEC:refs 896 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 333 # Number of stores executed +system.cpu.idleCycles 56472 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 538 # Number of branches executed +system.cpu.iew.EXEC:nop 274 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.670608 # Inst execution rate +system.cpu.iew.EXEC:refs 934 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 356 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 1736 # num instructions consuming a value -system.cpu.iew.WB:count 3002 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.793779 # average fanout of values written-back +system.cpu.iew.WB:consumers 1781 # num instructions consuming a value +system.cpu.iew.WB:count 3084 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.794497 # average fanout of values written-back system.cpu.iew.WB:penalized 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_rate 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.iew.WB:producers 1378 # num instructions producing a value -system.cpu.iew.WB:rate 0.719731 # insts written-back per cycle -system.cpu.iew.WB:sent 3020 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 147 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 1415 # num instructions producing a value +system.cpu.iew.WB:rate 0.651182 # insts written-back per cycle +system.cpu.iew.WB:sent 3123 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 149 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 0 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 636 # Number of dispatched load instructions +system.cpu.iew.iewDispLoadInsts 698 # Number of dispatched load instructions system.cpu.iew.iewDispNonSpecInsts 6 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 85 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 369 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 3727 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 563 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 108 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 3072 # Number of executed instructions +system.cpu.iew.iewDispSquashedInsts 83 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 412 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 4056 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 578 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 105 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 3176 # Number of executed instructions system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle system.cpu.iew.iewLSQFullEvents 0 # Number of times the LSQ has become full, causing a stall -system.cpu.iew.iewSquashCycles 225 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 283 # Number of cycles IEW is squashing system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked system.cpu.iew.lsq.thread.0.forwLoads 25 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 1 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.ignoredResponses 2 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address -system.cpu.iew.lsq.thread.0.memOrderViolation 13 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 11 # Number of memory ordering violations system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.0.squashedLoads 221 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 75 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 13 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 99 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 48 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.572285 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.572285 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 3180 # Type of FU issued +system.cpu.iew.lsq.thread.0.squashedLoads 283 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 118 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 11 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 97 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 52 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.504012 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.504012 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 3281 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 0 0.00% # Type of FU issued - IntAlu 2258 71.01% # Type of FU issued + IntAlu 2319 70.68% # Type of FU issued IntMult 1 0.03% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 0 0.00% # Type of FU issued @@ -279,16 +291,16 @@ system.cpu.iq.ISSUE:FU_type_0.start_dist FloatMult 0 0.00% # Type of FU issued FloatDiv 0 0.00% # Type of FU issued FloatSqrt 0 0.00% # Type of FU issued - MemRead 581 18.27% # Type of FU issued - MemWrite 340 10.69% # Type of FU issued + MemRead 597 18.20% # Type of FU issued + MemWrite 364 11.09% # Type of FU issued IprAccess 0 0.00% # Type of FU issued InstPrefetch 0 0.00% # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.end_dist -system.cpu.iq.ISSUE:fu_busy_cnt 36 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.011321 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 35 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.010667 # FU busy rate (busy events/executed inst) system.cpu.iq.ISSUE:fu_full.start_dist No_OpClass 0 0.00% # attempts to use FU when none available - IntAlu 2 5.56% # attempts to use FU when none available + IntAlu 1 2.86% # attempts to use FU when none available IntMult 0 0.00% # attempts to use FU when none available IntDiv 0 0.00% # attempts to use FU when none available FloatAdd 0 0.00% # attempts to use FU when none available @@ -297,59 +309,63 @@ system.cpu.iq.ISSUE:fu_full.start_dist FloatMult 0 0.00% # attempts to use FU when none available FloatDiv 0 0.00% # attempts to use FU when none available FloatSqrt 0 0.00% # attempts to use FU when none available - MemRead 12 33.33% # attempts to use FU when none available - MemWrite 22 61.11% # attempts to use FU when none available + MemRead 12 34.29% # attempts to use FU when none available + MemWrite 22 62.86% # attempts to use FU when none available IprAccess 0 0.00% # attempts to use FU when none available InstPrefetch 0 0.00% # attempts to use FU when none available system.cpu.iq.ISSUE:fu_full.end_dist system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle -system.cpu.iq.ISSUE:issued_per_cycle.samples 4171 +system.cpu.iq.ISSUE:issued_per_cycle.samples 4736 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 2877 6897.63% - 1 465 1114.84% - 2 300 719.25% - 3 228 546.63% - 4 154 369.22% - 5 89 213.38% - 6 40 95.90% - 7 14 33.57% - 8 4 9.59% + 0 3384 7145.27% + 1 494 1043.07% + 2 314 663.01% + 3 237 500.42% + 4 163 344.17% + 5 88 185.81% + 6 40 84.46% + 7 12 25.34% + 8 4 8.45% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.762407 # Inst issue rate -system.cpu.iq.iqInstsAdded 3479 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 3180 # Number of instructions issued +system.cpu.iq.ISSUE:rate 0.692779 # Inst issue rate +system.cpu.iq.iqInstsAdded 3776 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 3281 # Number of instructions issued system.cpu.iq.iqNonSpecInstsAdded 6 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 944 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsExamined 1238 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedInstsIssued 1 # Number of squashed instructions issued system.cpu.iq.iqSquashedNonSpecRemoved 2 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 473 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.iqSquashedOperandsExamined 742 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 735 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 707 # ITB hits +system.cpu.itb.misses 28 # ITB misses system.cpu.l2cache.ReadExReq_accesses 24 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4750 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2750 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 114000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_avg_miss_latency 4604.166667 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2604.166667 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 110500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses system.cpu.l2cache.ReadExReq_misses 24 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 66000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 62500 # number of ReadExReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_rate 1 # mshr miss rate for ReadExReq accesses system.cpu.l2cache.ReadExReq_mshr_misses 24 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 247 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4354.251012 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2354.251012 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_miss_latency 1075500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_accesses 243 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4304.526749 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2304.526749 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_miss_latency 1046000 # number of ReadReq miss cycles system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 247 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 581500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_misses 243 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 560000 # number of ReadReq MSHR miss cycles system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 247 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses 243 # number of ReadReq MSHR misses system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency 4250 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2250 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 59500 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_avg_miss_latency 4178.571429 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2178.571429 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 58500 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 31500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 30500 # number of UpgradeReq MSHR miss cycles system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses system.cpu.l2cache.UpgradeReq_mshr_misses 14 # number of UpgradeReq MSHR misses system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked @@ -360,32 +376,32 @@ system.cpu.l2cache.blocked_no_targets 0 # nu system.cpu.l2cache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.l2cache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.l2cache.cache_copies 0 # number of cache copies performed -system.cpu.l2cache.demand_accesses 271 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4389.298893 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2389.298893 # average overall mshr miss latency +system.cpu.l2cache.demand_accesses 267 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4331.460674 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2331.460674 # average overall mshr miss latency system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 1189500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 1156500 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate 1 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 271 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses 267 # number of demand (read+write) misses system.cpu.l2cache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 647500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 622500 # number of demand (read+write) MSHR miss cycles system.cpu.l2cache.demand_mshr_miss_rate 1 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 271 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses 267 # number of demand (read+write) MSHR misses system.cpu.l2cache.fast_writes 0 # number of fast writes performed system.cpu.l2cache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.l2cache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.l2cache.overall_accesses 271 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4389.298893 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2389.298893 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 267 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4331.460674 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2331.460674 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency system.cpu.l2cache.overall_hits 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 1189500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 1156500 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate 1 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 271 # number of overall misses +system.cpu.l2cache.overall_misses 267 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 647500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 622500 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_miss_rate 1 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 271 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses 267 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -398,28 +414,28 @@ system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.l2cache.replacements 0 # number of replacements -system.cpu.l2cache.sampled_refs 233 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 229 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 127.304233 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 115.687599 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks -system.cpu.numCycles 4171 # number of cpu cycles simulated +system.cpu.numCycles 4736 # number of cpu cycles simulated system.cpu.rename.RENAME:CommittedMaps 1768 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 3117 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 1 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 4657 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 4106 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 2936 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 738 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 225 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 7 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 1168 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:IdleCycles 3552 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 2 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 4989 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 4410 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 3154 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 808 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 283 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 9 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 1386 # Number of HB maps that are undone due to squashing system.cpu.rename.RENAME:serializeStallCycles 84 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 8 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 50 # count of insts added to the skid buffer +system.cpu.rename.RENAME:skidInsts 60 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 6 # count of temporary serializing insts renamed -system.cpu.timesIdled 16 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 28 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout index 57159efac..895bd710c 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:41 2007 -M5 executing on zeep +M5 compiled Aug 13 2007 17:39:24 +M5 started Mon Aug 13 17:39:27 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/o3-timing tests/run.py quick/00.hello/alpha/tru64/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 2104000 because target called exit() +Exiting @ tick 2410000 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini index 16ea738bc..ac0ec32b8 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=tracer workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -31,6 +33,14 @@ workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.tracer] type=ExeTracer @@ -41,7 +51,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/tru64/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/tru64/hello gid=100 input=cin output=cout diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt index dfc8b7f6b..28ff448c6 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/m5stats.txt @@ -1,18 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 34280 # Simulator instruction rate (inst/s) -host_mem_usage 147884 # Number of bytes of host memory used -host_seconds 0.08 # Real time elapsed on the host -host_tick_rate 17043200 # Simulator tick rate (ticks/s) +host_inst_rate 124133 # Simulator instruction rate (inst/s) +host_mem_usage 171628 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 61574601 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2578 # Number of instructions simulated +sim_insts 2577 # Number of instructions simulated sim_seconds 0.000001 # Number of seconds simulated -sim_ticks 1288500 # Number of ticks simulated +sim_ticks 1297500 # Number of ticks simulated +system.cpu.dtb.accesses 717 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 709 # DTB hits +system.cpu.dtb.misses 8 # DTB misses +system.cpu.dtb.read_accesses 419 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 415 # DTB read hits +system.cpu.dtb.read_misses 4 # DTB read misses +system.cpu.dtb.write_accesses 298 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 294 # DTB write hits +system.cpu.dtb.write_misses 4 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2596 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2585 # ITB hits +system.cpu.itb.misses 11 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 2578 # number of cpu cycles simulated -system.cpu.num_insts 2578 # Number of instructions executed -system.cpu.num_refs 710 # Number of memory references +system.cpu.numCycles 2596 # number of cpu cycles simulated +system.cpu.num_insts 2577 # Number of instructions executed +system.cpu.num_refs 717 # Number of memory references system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout index 6e78c47eb..89de75b41 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-atomic/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 3 2007 03:56:47 -M5 started Fri Aug 3 04:17:14 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 17:36:58 +M5 started Tue Aug 14 17:40:04 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-atomic tests/run.py quick/00.hello/alpha/tru64/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 1288500 because target called exit() +Exiting @ tick 1297500 because target called exit() diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini index f8e125ea1..48fcc2b94 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 @@ -156,7 +166,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/alpha/tru64/hello +executable=/dist/m5/regression/test-progs/hello/bin/alpha/tru64/hello gid=100 input=cin output=cout diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt index 23e886f55..942cc1b79 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 196854 # Simulator instruction rate (inst/s) -host_mem_usage 195480 # Number of bytes of host memory used -host_seconds 0.01 # Real time elapsed on the host -host_tick_rate 706389035 # Simulator tick rate (ticks/s) +host_inst_rate 123219 # Simulator instruction rate (inst/s) +host_mem_usage 178996 # Number of bytes of host memory used +host_seconds 0.02 # Real time elapsed on the host +host_tick_rate 443932267 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 2578 # Number of instructions simulated +sim_insts 2577 # Number of instructions simulated sim_seconds 0.000009 # Number of seconds simulated -sim_ticks 9431000 # Number of ticks simulated +sim_ticks 9438000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 415 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -76,53 +76,65 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 82 # Sample count of references to valid blocks. system.cpu.dcache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 48.863963 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 48.838317 # Cycle average of tags in use system.cpu.dcache.total_refs 627 # Total number of references to valid blocks. system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.dcache.writebacks 0 # number of writebacks -system.cpu.icache.ReadReq_accesses 2579 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 717 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 709 # DTB hits +system.cpu.dtb.misses 8 # DTB misses +system.cpu.dtb.read_accesses 419 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 415 # DTB read hits +system.cpu.dtb.read_misses 4 # DTB read misses +system.cpu.dtb.write_accesses 298 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 294 # DTB write hits +system.cpu.dtb.write_misses 4 # DTB write misses +system.cpu.icache.ReadReq_accesses 2586 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 2416 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 2423 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 4075000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.063203 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.063032 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 163 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 3749000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.063203 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate 0.063032 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 163 # number of ReadReq MSHR misses system.cpu.icache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 14.822086 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 14.865031 # Average number of references to valid blocks. system.cpu.icache.blocked_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_no_targets 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_mshrs 0 # number of cycles access was blocked system.cpu.icache.blocked_cycles_no_targets 0 # number of cycles access was blocked system.cpu.icache.cache_copies 0 # number of cache copies performed -system.cpu.icache.demand_accesses 2579 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 2586 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 23000 # average overall mshr miss latency -system.cpu.icache.demand_hits 2416 # number of demand (read+write) hits +system.cpu.icache.demand_hits 2423 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 4075000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.063203 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.063032 # miss rate for demand accesses system.cpu.icache.demand_misses 163 # number of demand (read+write) misses system.cpu.icache.demand_mshr_hits 0 # number of demand (read+write) MSHR hits system.cpu.icache.demand_mshr_miss_latency 3749000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.063203 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate 0.063032 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 163 # number of demand (read+write) MSHR misses system.cpu.icache.fast_writes 0 # number of fast writes performed system.cpu.icache.mshr_cap_events 0 # number of times MSHR cap was activated system.cpu.icache.no_allocate_misses 0 # Number of misses that were no-allocate -system.cpu.icache.overall_accesses 2579 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 2586 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 23000 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 2416 # number of overall hits +system.cpu.icache.overall_hits 2423 # number of overall hits system.cpu.icache.overall_miss_latency 4075000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.063203 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.063032 # miss rate for overall accesses system.cpu.icache.overall_misses 163 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.icache.overall_mshr_miss_latency 3749000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.063203 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate 0.063032 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 163 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 163 # Sample count of references to valid blocks. system.cpu.icache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 83.443652 # Cycle average of tags in use -system.cpu.icache.total_refs 2416 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 83.395749 # Cycle average of tags in use +system.cpu.icache.total_refs 2423 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 2597 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 2586 # ITB hits +system.cpu.itb.misses 11 # ITB misses system.cpu.l2cache.ReadExReq_accesses 27 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -218,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 207 # Sample count of references to valid blocks. system.cpu.l2cache.soft_prefetch_mshr_full 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 106.620093 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 106.559981 # Cycle average of tags in use system.cpu.l2cache.total_refs 0 # Total number of references to valid blocks. system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 9431000 # number of cpu cycles simulated -system.cpu.num_insts 2578 # Number of instructions executed -system.cpu.num_refs 710 # Number of memory references +system.cpu.numCycles 9438000 # number of cpu cycles simulated +system.cpu.num_insts 2577 # Number of instructions executed +system.cpu.num_refs 717 # Number of memory references system.cpu.workload.PROG:num_syscalls 4 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout index eb8910969..8d08b94be 100644 --- a/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout +++ b/tests/quick/00.hello/ref/alpha/tru64/simple-timing/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:42 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 17:58:14 +M5 started Tue Aug 14 17:59:08 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/00.hello/alpha/tru64/simple-timing tests/run.py quick/00.hello/alpha/tru64/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 9431000 because target called exit() +Exiting @ tick 9438000 because target called exit() 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 c6807e6a7..653ab3552 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=tracer workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -31,6 +33,12 @@ workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.dtb] +type=MipsDTB + +[system.cpu.itb] +type=MipsITB + [system.cpu.tracer] type=ExeTracer @@ -41,7 +49,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/mips/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/mips/linux/hello gid=100 input=cin output=cout 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 98d540d90..23e6b5f2c 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 @@ -1,17 +1,17 @@ ---------- Begin Simulation Statistics ---------- -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) +host_inst_rate 9753 # Simulator instruction rate (inst/s) +host_mem_usage 173424 # Number of bytes of host memory used +host_seconds 0.58 # Real time elapsed on the host +host_tick_rate 4872477 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 5657 # Number of instructions simulated +sim_insts 5656 # Number of instructions simulated sim_seconds 0.000003 # Number of seconds simulated sim_ticks 2828000 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles system.cpu.numCycles 5657 # number of cpu cycles simulated -system.cpu.num_insts 5657 # Number of instructions executed +system.cpu.num_insts 5656 # 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-atomic/stdout b/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout index 3919c7c81..1cc3f6662 100644 --- a/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/mips/linux/simple-atomic/stdout @@ -6,9 +6,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 3 2007 04:06:41 -M5 started Fri Aug 3 04:31:09 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:02:23 +M5 started Tue Aug 14 22:02:24 2007 +M5 executing on nacho 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 Exiting @ tick 2828000 because target called exit() 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 f2dee3856..7da6cb048 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,9 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=MipsDTB + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +106,9 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=MipsITB + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 @@ -156,7 +164,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/mips/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/mips/linux/hello gid=100 input=cin output=cout 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 a9c46636a..cb408c2ca 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 @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 269189 # Simulator instruction rate (inst/s) -host_mem_usage 197500 # Number of bytes of host memory used -host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 866482072 # Simulator tick rate (ticks/s) +host_inst_rate 186969 # Simulator instruction rate (inst/s) +host_mem_usage 180780 # Number of bytes of host memory used +host_seconds 0.03 # Real time elapsed on the host +host_tick_rate 602814418 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 5657 # Number of instructions simulated +sim_insts 5656 # Number of instructions simulated sim_seconds 0.000018 # Number of seconds simulated sim_ticks 18463000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 1130 # number of ReadReq accesses(hits+misses) @@ -225,7 +225,7 @@ system.cpu.l2cache.warmup_cycle 0 # Cy system.cpu.l2cache.writebacks 0 # number of writebacks system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles system.cpu.numCycles 18463000 # number of cpu cycles simulated -system.cpu.num_insts 5657 # Number of instructions executed +system.cpu.num_insts 5656 # 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 ad6e002b5..08628c4d1 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 Aug 12 2007 17:11:48 -M5 started Sun Aug 12 17:11:50 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:02:23 +M5 started Tue Aug 14 22:02:25 2007 +M5 executing on nacho 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 18463000 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 d7237a4af..c019a4e06 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=tracer workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -31,6 +33,14 @@ workload=system.cpu.workload dcache_port=system.membus.port[2] icache_port=system.membus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.tracer] type=ExeTracer @@ -41,7 +51,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/sparc/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/sparc/linux/hello gid=100 input=cin output=cout 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 ab2e76d2a..5a17e8489 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 @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -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) +host_inst_rate 5187 # Simulator instruction rate (inst/s) +host_mem_usage 173740 # Number of bytes of host memory used +host_seconds 0.93 # Real time elapsed on the host +host_tick_rate 2625893 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 4863 # Number of instructions simulated +sim_insts 4833 # Number of instructions simulated sim_seconds 0.000002 # Number of seconds simulated -sim_ticks 2431000 # Number of ticks simulated +sim_ticks 2447500 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 4863 # 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.numCycles 4896 # number of cpu cycles simulated +system.cpu.num_insts 4833 # Number of instructions executed +system.cpu.num_refs 1282 # Number of memory references system.cpu.workload.PROG:num_syscalls 11 # Number of system calls ---------- End Simulation Statistics ---------- 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 40d1acccc..5bc4aa638 100644 --- a/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout +++ b/tests/quick/00.hello/ref/sparc/linux/simple-atomic/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 3 2007 04:11:25 -M5 started Fri Aug 3 04:31:18 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:08:21 +M5 started Tue Aug 14 22:08:22 2007 +M5 executing on nacho 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 -Exiting @ tick 2431000 because target called exit() +Exiting @ tick 2447500 because target called exit() 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 719701ccd..4674f8812 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 @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 @@ -156,7 +166,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/hello/bin/sparc/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/sparc/linux/hello gid=100 input=cin output=cout 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 8907d716d..ff4bd3dbe 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 @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 277220 # Simulator instruction rate (inst/s) -host_mem_usage 197684 # Number of bytes of host memory used +host_inst_rate 198489 # Simulator instruction rate (inst/s) +host_mem_usage 181156 # Number of bytes of host memory used host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 892278360 # Simulator tick rate (ticks/s) +host_tick_rate 645076356 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 4863 # Number of instructions simulated +sim_insts 4833 # Number of instructions simulated sim_seconds 0.000016 # Number of seconds simulated -sim_ticks 15912000 # Number of ticks simulated +sim_ticks 15925000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 608 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 24777.777778 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 22777.777778 # average ReadReq mshr miss latency @@ -76,53 +76,53 @@ 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 83.464621 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 83.440192 # 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_accesses 4877 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 24906.250000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 22906.250000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 4608 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 4621 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 6376000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.052632 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.052491 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 256 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 5864000 # 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_miss_rate 0.052491 # 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 system.cpu.icache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked -system.cpu.icache.avg_refs 18 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 18.050781 # 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 4864 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 4877 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 24906.250000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 22906.250000 # average overall mshr miss latency -system.cpu.icache.demand_hits 4608 # number of demand (read+write) hits +system.cpu.icache.demand_hits 4621 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 6376000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.052632 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.052491 # 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 5864000 # 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_miss_rate 0.052491 # 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_accesses 4877 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 24906.250000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 22906.250000 # 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_hits 4621 # number of overall hits system.cpu.icache.overall_miss_latency 6376000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.052632 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.052491 # 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 5864000 # 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_miss_rate 0.052491 # 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 system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses @@ -138,8 +138,8 @@ 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 114.953503 # Cycle average of tags in use -system.cpu.icache.total_refs 4608 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 114.921642 # Cycle average of tags in use +system.cpu.icache.total_refs 4621 # 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 @@ -219,14 +219,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements 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 133.743977 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 133.706132 # 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 15912000 # 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.numCycles 15925000 # number of cpu cycles simulated +system.cpu.num_insts 4833 # Number of instructions executed +system.cpu.num_refs 1282 # Number of memory references system.cpu.workload.PROG:num_syscalls 11 # Number of system calls ---------- End Simulation Statistics ---------- 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 85df476d4..d947b5fb6 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 Aug 12 2007 12:23:15 -M5 started Sun Aug 12 16:58:40 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:08:21 +M5 started Tue Aug 14 22:08:24 2007 +M5 executing on nacho 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 15912000 because target called exit() +Exiting @ tick 15925000 because target called exit() diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini index 5a35877e6..71b1480ab 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload0 workload1 +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload0 workload1 BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt index 5a48eb9ba..e76204a83 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt @@ -1,54 +1,54 @@ ---------- Begin Simulation Statistics ---------- global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. -global.BPredUnit.BTBHits 691 # Number of BTB hits -global.BPredUnit.BTBLookups 3468 # Number of BTB lookups -global.BPredUnit.RASInCorrect 112 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 1111 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 2334 # Number of conditional branches predicted -global.BPredUnit.lookups 4040 # Number of BP lookups -global.BPredUnit.usedRAS 559 # Number of times the RAS was used to get a target. -host_inst_rate 99825 # Simulator instruction rate (inst/s) -host_mem_usage 197616 # Number of bytes of host memory used -host_seconds 0.11 # Real time elapsed on the host -host_tick_rate 48783081 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 19 # Number of conflicting loads. -memdepunit.memDep.conflictingLoads 10 # Number of conflicting loads. -memdepunit.memDep.conflictingStores 44 # Number of conflicting stores. +global.BPredUnit.BTBHits 706 # Number of BTB hits +global.BPredUnit.BTBLookups 3499 # Number of BTB lookups +global.BPredUnit.RASInCorrect 117 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1092 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 2350 # Number of conditional branches predicted +global.BPredUnit.lookups 4075 # Number of BP lookups +global.BPredUnit.usedRAS 561 # Number of times the RAS was used to get a target. +host_inst_rate 76336 # Simulator instruction rate (inst/s) +host_mem_usage 181020 # Number of bytes of host memory used +host_seconds 0.15 # Real time elapsed on the host +host_tick_rate 38800813 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 14 # Number of conflicting loads. +memdepunit.memDep.conflictingLoads 12 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 35 # Number of conflicting stores. memdepunit.memDep.conflictingStores 38 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 1952 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedLoads 1960 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1112 # Number of stores inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 1121 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 1959 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 1940 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1118 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1140 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks sim_insts 11247 # Number of instructions simulated sim_seconds 0.000006 # Number of seconds simulated -sim_ticks 5506000 # Number of ticks simulated +sim_ticks 5727000 # Number of ticks simulated system.cpu.commit.COM:branches 1724 # Number of branches committed system.cpu.commit.COM:branches_0 862 # Number of branches committed system.cpu.commit.COM:branches_1 862 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 153 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 161 # 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:bw_limited_0 0 # number of insts not committed due to BW limits system.cpu.commit.COM:bw_limited_1 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 10938 +system.cpu.commit.COM:committed_per_cycle.samples 11403 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 6318 5776.19% - 1 2129 1946.43% - 2 954 872.19% - 3 501 458.04% - 4 328 299.87% - 5 233 213.02% - 6 214 195.65% - 7 108 98.74% - 8 153 139.88% + 0 6781 5946.68% + 1 2144 1880.21% + 2 950 833.11% + 3 495 434.10% + 4 331 290.27% + 5 216 189.42% + 6 215 188.55% + 7 110 96.47% + 8 161 141.19% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist system.cpu.commit.COM:count 11281 # Number of instructions committed -system.cpu.commit.COM:count_0 5641 # Number of instructions committed -system.cpu.commit.COM:count_1 5640 # Number of instructions committed +system.cpu.commit.COM:count_0 5640 # Number of instructions committed +system.cpu.commit.COM:count_1 5641 # Number of instructions committed system.cpu.commit.COM:loads 1958 # Number of loads committed system.cpu.commit.COM:loads_0 979 # Number of loads committed system.cpu.commit.COM:loads_1 979 # Number of loads committed @@ -61,133 +61,133 @@ system.cpu.commit.COM:refs_1 1791 # Nu system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed system.cpu.commit.COM:swp_count_0 0 # Number of s/w prefetches committed system.cpu.commit.COM:swp_count_1 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 859 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 854 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 11281 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 34 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 8029 # The number of squashed insts skipped by commit -system.cpu.committedInsts_0 5624 # Number of Instructions Simulated -system.cpu.committedInsts_1 5623 # Number of Instructions Simulated +system.cpu.commit.commitSquashedInsts 8053 # The number of squashed insts skipped by commit +system.cpu.committedInsts_0 5623 # Number of Instructions Simulated +system.cpu.committedInsts_1 5624 # Number of Instructions Simulated system.cpu.committedInsts_total 11247 # Number of Instructions Simulated -system.cpu.cpi_0 1.952703 # CPI: Cycles Per Instruction -system.cpu.cpi_1 1.953050 # CPI: Cycles Per Instruction -system.cpu.cpi_total 0.976438 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 2963 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_accesses_0 2963 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency_0 12228.855721 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency_0 7833.333333 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 2762 # number of ReadReq hits -system.cpu.dcache.ReadReq_hits_0 2762 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 2458000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_latency_0 2458000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate_0 0.067837 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 201 # number of ReadReq misses -system.cpu.dcache.ReadReq_misses_0 201 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 75 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_hits_0 75 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 1574500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_latency_0 1574500 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate_0 0.067837 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 201 # number of ReadReq MSHR misses -system.cpu.dcache.ReadReq_mshr_misses_0 201 # number of ReadReq MSHR misses -system.cpu.dcache.WriteReq_accesses 1252 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_accesses_0 1252 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency_0 21841.954023 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency_0 6695.402299 # average WriteReq mshr miss latency -system.cpu.dcache.WriteReq_hits 1078 # number of WriteReq hits -system.cpu.dcache.WriteReq_hits_0 1078 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 3800500 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_latency_0 3800500 # number of WriteReq miss cycles -system.cpu.dcache.WriteReq_miss_rate_0 0.138978 # miss rate for WriteReq accesses +system.cpu.cpi_0 2.035568 # CPI: Cycles Per Instruction +system.cpu.cpi_1 2.035206 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.017694 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 2934 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_accesses_0 2934 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency_0 12119.897959 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency_0 7403.061224 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 2738 # number of ReadReq hits +system.cpu.dcache.ReadReq_hits_0 2738 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 2375500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_latency_0 2375500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate_0 0.066803 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 196 # number of ReadReq misses +system.cpu.dcache.ReadReq_misses_0 196 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 81 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_hits_0 81 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 1451000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_latency_0 1451000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate_0 0.066803 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 196 # number of ReadReq MSHR misses +system.cpu.dcache.ReadReq_mshr_misses_0 196 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 1240 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_accesses_0 1240 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency_0 21692.528736 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency_0 6310.344828 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 1066 # number of WriteReq hits +system.cpu.dcache.WriteReq_hits_0 1066 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 3774500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_latency_0 3774500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate_0 0.140323 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 174 # number of WriteReq misses system.cpu.dcache.WriteReq_misses_0 174 # number of WriteReq misses -system.cpu.dcache.WriteReq_mshr_hits 372 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_hits_0 372 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 1165000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_latency_0 1165000 # number of WriteReq MSHR miss cycles -system.cpu.dcache.WriteReq_mshr_miss_rate_0 0.138978 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_hits 384 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_hits_0 384 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 1098000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency_0 1098000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate_0 0.140323 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 174 # number of WriteReq MSHR misses system.cpu.dcache.WriteReq_mshr_misses_0 174 # 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 11.146974 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 11.276471 # 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 4215 # number of demand (read+write) accesses -system.cpu.dcache.demand_accesses_0 4215 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses 4174 # number of demand (read+write) accesses +system.cpu.dcache.demand_accesses_0 4174 # number of demand (read+write) accesses system.cpu.dcache.demand_accesses_1 0 # number of demand (read+write) accesses system.cpu.dcache.demand_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.dcache.demand_avg_miss_latency_0 16689.333333 # average overall miss latency +system.cpu.dcache.demand_avg_miss_latency_0 16621.621622 # average overall miss latency system.cpu.dcache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.dcache.demand_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency_0 7305.333333 # average overall mshr miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency_0 6889.189189 # average overall mshr miss latency system.cpu.dcache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency -system.cpu.dcache.demand_hits 3840 # number of demand (read+write) hits -system.cpu.dcache.demand_hits_0 3840 # number of demand (read+write) hits +system.cpu.dcache.demand_hits 3804 # number of demand (read+write) hits +system.cpu.dcache.demand_hits_0 3804 # number of demand (read+write) hits system.cpu.dcache.demand_hits_1 0 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 6258500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_latency_0 6258500 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_latency 6150000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_latency_0 6150000 # number of demand (read+write) miss cycles system.cpu.dcache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles system.cpu.dcache.demand_miss_rate <err: div-0> # miss rate for demand accesses -system.cpu.dcache.demand_miss_rate_0 0.088968 # miss rate for demand accesses +system.cpu.dcache.demand_miss_rate_0 0.088644 # miss rate for demand accesses system.cpu.dcache.demand_miss_rate_1 <err: div-0> # miss rate for demand accesses -system.cpu.dcache.demand_misses 375 # number of demand (read+write) misses -system.cpu.dcache.demand_misses_0 375 # number of demand (read+write) misses +system.cpu.dcache.demand_misses 370 # number of demand (read+write) misses +system.cpu.dcache.demand_misses_0 370 # number of demand (read+write) misses system.cpu.dcache.demand_misses_1 0 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 447 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_hits_0 447 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_hits 465 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_hits_0 465 # number of demand (read+write) MSHR hits system.cpu.dcache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 2739500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_latency_0 2739500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency 2549000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_latency_0 2549000 # number of demand (read+write) MSHR miss cycles system.cpu.dcache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles system.cpu.dcache.demand_mshr_miss_rate <err: div-0> # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_miss_rate_0 0.088968 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_miss_rate_0 0.088644 # mshr miss rate for demand accesses system.cpu.dcache.demand_mshr_miss_rate_1 <err: div-0> # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 375 # number of demand (read+write) MSHR misses -system.cpu.dcache.demand_mshr_misses_0 375 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses 370 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_mshr_misses_0 370 # number of demand (read+write) MSHR misses system.cpu.dcache.demand_mshr_misses_1 0 # 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.mshr_cap_events_0 0 # number of times MSHR cap was activated system.cpu.dcache.mshr_cap_events_1 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 4215 # number of overall (read+write) accesses -system.cpu.dcache.overall_accesses_0 4215 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses 4174 # number of overall (read+write) accesses +system.cpu.dcache.overall_accesses_0 4174 # number of overall (read+write) accesses system.cpu.dcache.overall_accesses_1 0 # number of overall (read+write) accesses system.cpu.dcache.overall_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.dcache.overall_avg_miss_latency_0 16689.333333 # average overall miss latency +system.cpu.dcache.overall_avg_miss_latency_0 16621.621622 # average overall miss latency system.cpu.dcache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.dcache.overall_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency_0 7305.333333 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency_0 6889.189189 # average overall mshr miss latency system.cpu.dcache.overall_avg_mshr_miss_latency_1 <err: div-0> # 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_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency system.cpu.dcache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency -system.cpu.dcache.overall_hits 3840 # number of overall hits -system.cpu.dcache.overall_hits_0 3840 # number of overall hits +system.cpu.dcache.overall_hits 3804 # number of overall hits +system.cpu.dcache.overall_hits_0 3804 # number of overall hits system.cpu.dcache.overall_hits_1 0 # number of overall hits -system.cpu.dcache.overall_miss_latency 6258500 # number of overall miss cycles -system.cpu.dcache.overall_miss_latency_0 6258500 # number of overall miss cycles +system.cpu.dcache.overall_miss_latency 6150000 # number of overall miss cycles +system.cpu.dcache.overall_miss_latency_0 6150000 # number of overall miss cycles system.cpu.dcache.overall_miss_latency_1 0 # number of overall miss cycles system.cpu.dcache.overall_miss_rate <err: div-0> # miss rate for overall accesses -system.cpu.dcache.overall_miss_rate_0 0.088968 # miss rate for overall accesses +system.cpu.dcache.overall_miss_rate_0 0.088644 # miss rate for overall accesses system.cpu.dcache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses -system.cpu.dcache.overall_misses 375 # number of overall misses -system.cpu.dcache.overall_misses_0 375 # number of overall misses +system.cpu.dcache.overall_misses 370 # number of overall misses +system.cpu.dcache.overall_misses_0 370 # number of overall misses system.cpu.dcache.overall_misses_1 0 # number of overall misses -system.cpu.dcache.overall_mshr_hits 447 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_hits_0 447 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_hits 465 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_hits_0 465 # number of overall MSHR hits system.cpu.dcache.overall_mshr_hits_1 0 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 2739500 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_latency_0 2739500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency 2549000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_latency_0 2549000 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles system.cpu.dcache.overall_mshr_miss_rate <err: div-0> # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_miss_rate_0 0.088968 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_miss_rate_0 0.088644 # mshr miss rate for overall accesses system.cpu.dcache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 375 # number of overall MSHR misses -system.cpu.dcache.overall_mshr_misses_0 375 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses 370 # number of overall MSHR misses +system.cpu.dcache.overall_mshr_misses_0 370 # number of overall MSHR misses system.cpu.dcache.overall_mshr_misses_1 0 # 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_latency_0 0 # number of overall MSHR uncacheable cycles @@ -207,149 +207,161 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.replacements_0 0 # number of replacements system.cpu.dcache.replacements_1 0 # number of replacements -system.cpu.dcache.sampled_refs 347 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 340 # 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.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions system.cpu.dcache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions -system.cpu.dcache.tagsinuse 219.667658 # Cycle average of tags in use -system.cpu.dcache.total_refs 3868 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 215.589336 # Cycle average of tags in use +system.cpu.dcache.total_refs 3834 # 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.dcache.writebacks_0 0 # number of writebacks system.cpu.dcache.writebacks_1 0 # number of writebacks -system.cpu.decode.DECODE:BlockedCycles 1907 # Number of cycles decode is blocked -system.cpu.decode.DECODE:BranchMispred 262 # Number of times decode detected a branch misprediction -system.cpu.decode.DECODE:BranchResolved 358 # Number of times decode resolved a branch -system.cpu.decode.DECODE:DecodedInsts 22173 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 14421 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 3707 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 1515 # Number of cycles decode is squashing -system.cpu.decode.DECODE:SquashedInsts 340 # Number of squashed instructions handled by decode -system.cpu.decode.DECODE:UnblockCycles 183 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 4040 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 2997 # Number of cache lines fetched -system.cpu.fetch.Cycles 7042 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 442 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 24368 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 1175 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.367875 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 2997 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 1250 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 2.218904 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BlockedCycles 1981 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 247 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 354 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 22591 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 15034 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 3799 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 1569 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 329 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 215 # Number of cycles decode is unblocking +system.cpu.dtb.accesses 5095 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 4970 # DTB hits +system.cpu.dtb.misses 125 # DTB misses +system.cpu.dtb.read_accesses 3183 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 3106 # DTB read hits +system.cpu.dtb.read_misses 77 # DTB read misses +system.cpu.dtb.write_accesses 1912 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 1864 # DTB write hits +system.cpu.dtb.write_misses 48 # DTB write misses +system.cpu.fetch.Branches 4075 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 3019 # Number of cache lines fetched +system.cpu.fetch.Cycles 7174 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 439 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 24770 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 1207 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.356020 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 3019 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 1267 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 2.164075 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 10982 +system.cpu.fetch.rateDist.samples 11446 system.cpu.fetch.rateDist.min_value 0 - 0 6938 6317.61% - 1 305 277.73% - 2 235 213.99% - 3 261 237.66% - 4 343 312.33% - 5 297 270.44% - 6 304 276.82% - 7 263 239.48% - 8 2036 1853.94% + 0 7343 6415.34% + 1 306 267.34% + 2 243 212.30% + 3 264 230.65% + 4 343 299.67% + 5 290 253.36% + 6 316 276.08% + 7 260 227.15% + 8 2081 1818.10% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 2933 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_accesses_0 2933 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency_0 8509.630819 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency_0 6073.033708 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 2310 # number of ReadReq hits -system.cpu.icache.ReadReq_hits_0 2310 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 5301500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_latency_0 5301500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate_0 0.212411 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 623 # number of ReadReq misses -system.cpu.icache.ReadReq_misses_0 623 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 64 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_hits_0 64 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 3783500 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_latency_0 3783500 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate_0 0.212411 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 623 # number of ReadReq MSHR misses -system.cpu.icache.ReadReq_mshr_misses_0 623 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 2953 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses_0 2953 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency_0 8345.528455 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency_0 5903.252033 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 2338 # number of ReadReq hits +system.cpu.icache.ReadReq_hits_0 2338 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 5132500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_latency_0 5132500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate_0 0.208263 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 615 # number of ReadReq misses +system.cpu.icache.ReadReq_misses_0 615 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 66 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_hits_0 66 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 3630500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_latency_0 3630500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate_0 0.208263 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 615 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_mshr_misses_0 615 # 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 3.707865 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 3.801626 # 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 2933 # number of demand (read+write) accesses -system.cpu.icache.demand_accesses_0 2933 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 2953 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses_0 2953 # number of demand (read+write) accesses system.cpu.icache.demand_accesses_1 0 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.icache.demand_avg_miss_latency_0 8509.630819 # average overall miss latency +system.cpu.icache.demand_avg_miss_latency_0 8345.528455 # average overall miss latency system.cpu.icache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.icache.demand_avg_mshr_miss_latency_0 6073.033708 # average overall mshr miss latency +system.cpu.icache.demand_avg_mshr_miss_latency_0 5903.252033 # average overall mshr miss latency system.cpu.icache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency -system.cpu.icache.demand_hits 2310 # number of demand (read+write) hits -system.cpu.icache.demand_hits_0 2310 # number of demand (read+write) hits +system.cpu.icache.demand_hits 2338 # number of demand (read+write) hits +system.cpu.icache.demand_hits_0 2338 # number of demand (read+write) hits system.cpu.icache.demand_hits_1 0 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 5301500 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_latency_0 5301500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency 5132500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_latency_0 5132500 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate <err: div-0> # miss rate for demand accesses -system.cpu.icache.demand_miss_rate_0 0.212411 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate_0 0.208263 # miss rate for demand accesses system.cpu.icache.demand_miss_rate_1 <err: div-0> # miss rate for demand accesses -system.cpu.icache.demand_misses 623 # number of demand (read+write) misses -system.cpu.icache.demand_misses_0 623 # number of demand (read+write) misses +system.cpu.icache.demand_misses 615 # number of demand (read+write) misses +system.cpu.icache.demand_misses_0 615 # number of demand (read+write) misses system.cpu.icache.demand_misses_1 0 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 64 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_hits_0 64 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_hits 66 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_hits_0 66 # number of demand (read+write) MSHR hits system.cpu.icache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 3783500 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_latency_0 3783500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency 3630500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_latency_0 3630500 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles system.cpu.icache.demand_mshr_miss_rate <err: div-0> # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_miss_rate_0 0.212411 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate_0 0.208263 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_miss_rate_1 <err: div-0> # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 623 # number of demand (read+write) MSHR misses -system.cpu.icache.demand_mshr_misses_0 623 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses 615 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_mshr_misses_0 615 # number of demand (read+write) MSHR misses system.cpu.icache.demand_mshr_misses_1 0 # 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.mshr_cap_events_0 0 # number of times MSHR cap was activated system.cpu.icache.mshr_cap_events_1 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 2933 # number of overall (read+write) accesses -system.cpu.icache.overall_accesses_0 2933 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 2953 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses_0 2953 # number of overall (read+write) accesses system.cpu.icache.overall_accesses_1 0 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.icache.overall_avg_miss_latency_0 8509.630819 # average overall miss latency +system.cpu.icache.overall_avg_miss_latency_0 8345.528455 # average overall miss latency system.cpu.icache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.icache.overall_avg_mshr_miss_latency_0 6073.033708 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_miss_latency_0 5903.252033 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_miss_latency_1 <err: div-0> # 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_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency system.cpu.icache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 2310 # number of overall hits -system.cpu.icache.overall_hits_0 2310 # number of overall hits +system.cpu.icache.overall_hits 2338 # number of overall hits +system.cpu.icache.overall_hits_0 2338 # number of overall hits system.cpu.icache.overall_hits_1 0 # number of overall hits -system.cpu.icache.overall_miss_latency 5301500 # number of overall miss cycles -system.cpu.icache.overall_miss_latency_0 5301500 # number of overall miss cycles +system.cpu.icache.overall_miss_latency 5132500 # number of overall miss cycles +system.cpu.icache.overall_miss_latency_0 5132500 # number of overall miss cycles system.cpu.icache.overall_miss_latency_1 0 # number of overall miss cycles system.cpu.icache.overall_miss_rate <err: div-0> # miss rate for overall accesses -system.cpu.icache.overall_miss_rate_0 0.212411 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate_0 0.208263 # miss rate for overall accesses system.cpu.icache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses -system.cpu.icache.overall_misses 623 # number of overall misses -system.cpu.icache.overall_misses_0 623 # number of overall misses +system.cpu.icache.overall_misses 615 # number of overall misses +system.cpu.icache.overall_misses_0 615 # number of overall misses system.cpu.icache.overall_misses_1 0 # number of overall misses -system.cpu.icache.overall_mshr_hits 64 # number of overall MSHR hits -system.cpu.icache.overall_mshr_hits_0 64 # number of overall MSHR hits +system.cpu.icache.overall_mshr_hits 66 # number of overall MSHR hits +system.cpu.icache.overall_mshr_hits_0 66 # number of overall MSHR hits system.cpu.icache.overall_mshr_hits_1 0 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 3783500 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_latency_0 3783500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency 3630500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_latency_0 3630500 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles system.cpu.icache.overall_mshr_miss_rate <err: div-0> # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_miss_rate_0 0.212411 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate_0 0.208263 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 623 # number of overall MSHR misses -system.cpu.icache.overall_mshr_misses_0 623 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses 615 # number of overall MSHR misses +system.cpu.icache.overall_mshr_misses_0 615 # number of overall MSHR misses system.cpu.icache.overall_mshr_misses_1 0 # 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_latency_0 0 # number of overall MSHR uncacheable cycles @@ -366,107 +378,107 @@ system.cpu.icache.prefetcher.num_hwpf_issued 0 system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time -system.cpu.icache.replacements 9 # number of replacements -system.cpu.icache.replacements_0 9 # number of replacements +system.cpu.icache.replacements 7 # number of replacements +system.cpu.icache.replacements_0 7 # number of replacements system.cpu.icache.replacements_1 0 # number of replacements -system.cpu.icache.sampled_refs 623 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 615 # 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.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions system.cpu.icache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions -system.cpu.icache.tagsinuse 319.917416 # Cycle average of tags in use -system.cpu.icache.total_refs 2310 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 319.122278 # Cycle average of tags in use +system.cpu.icache.total_refs 2338 # 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.icache.writebacks_0 0 # number of writebacks system.cpu.icache.writebacks_1 0 # number of writebacks -system.cpu.idleCycles 18494 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 2371 # Number of branches executed -system.cpu.iew.EXEC:branches_0 1190 # Number of branches executed -system.cpu.iew.EXEC:branches_1 1181 # Number of branches executed -system.cpu.iew.EXEC:nop 73 # number of nop insts executed -system.cpu.iew.EXEC:nop_0 36 # number of nop insts executed -system.cpu.iew.EXEC:nop_1 37 # number of nop insts executed -system.cpu.iew.EXEC:rate 1.425514 # Inst execution rate -system.cpu.iew.EXEC:refs 5064 # number of memory reference insts executed -system.cpu.iew.EXEC:refs_0 2541 # number of memory reference insts executed -system.cpu.iew.EXEC:refs_1 2523 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 1883 # Number of stores executed -system.cpu.iew.EXEC:stores_0 944 # Number of stores executed -system.cpu.iew.EXEC:stores_1 939 # Number of stores executed +system.cpu.idleCycles 6496 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 2386 # Number of branches executed +system.cpu.iew.EXEC:branches_0 1188 # Number of branches executed +system.cpu.iew.EXEC:branches_1 1198 # Number of branches executed +system.cpu.iew.EXEC:nop 127 # number of nop insts executed +system.cpu.iew.EXEC:nop_0 66 # number of nop insts executed +system.cpu.iew.EXEC:nop_1 61 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.378123 # Inst execution rate +system.cpu.iew.EXEC:refs 5110 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_0 2531 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_1 2579 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 1925 # Number of stores executed +system.cpu.iew.EXEC:stores_0 958 # Number of stores executed +system.cpu.iew.EXEC:stores_1 967 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed system.cpu.iew.EXEC:swp_0 0 # number of swp insts executed system.cpu.iew.EXEC:swp_1 0 # number of swp insts executed -system.cpu.iew.WB:consumers 10238 # num instructions consuming a value -system.cpu.iew.WB:consumers_0 5115 # num instructions consuming a value -system.cpu.iew.WB:consumers_1 5123 # num instructions consuming a value -system.cpu.iew.WB:count 15036 # cumulative count of insts written-back -system.cpu.iew.WB:count_0 7510 # cumulative count of insts written-back -system.cpu.iew.WB:count_1 7526 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 1.535845 # average fanout of values written-back -system.cpu.iew.WB:fanout_0 0.766960 # average fanout of values written-back -system.cpu.iew.WB:fanout_1 0.768885 # average fanout of values written-back +system.cpu.iew.WB:consumers 10281 # num instructions consuming a value +system.cpu.iew.WB:consumers_0 5147 # num instructions consuming a value +system.cpu.iew.WB:consumers_1 5134 # num instructions consuming a value +system.cpu.iew.WB:count 15145 # cumulative count of insts written-back +system.cpu.iew.WB:count_0 7584 # cumulative count of insts written-back +system.cpu.iew.WB:count_1 7561 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 1.539346 # average fanout of values written-back +system.cpu.iew.WB:fanout_0 0.768992 # average fanout of values written-back +system.cpu.iew.WB:fanout_1 0.770354 # 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_0 0 # number of instrctions required to write to 'other' IQ system.cpu.iew.WB:penalized_1 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:penalized_rate_0 0 # fraction of instructions written-back that wrote to 'other' IQ system.cpu.iew.WB:penalized_rate_1 0 # fraction of instructions written-back that wrote to 'other' IQ -system.cpu.iew.WB:producers 7862 # num instructions producing a value -system.cpu.iew.WB:producers_0 3923 # num instructions producing a value -system.cpu.iew.WB:producers_1 3939 # num instructions producing a value -system.cpu.iew.WB:rate 1.369150 # insts written-back per cycle -system.cpu.iew.WB:rate_0 0.683846 # insts written-back per cycle -system.cpu.iew.WB:rate_1 0.685303 # insts written-back per cycle -system.cpu.iew.WB:sent 15186 # cumulative count of insts sent to commit -system.cpu.iew.WB:sent_0 7583 # cumulative count of insts sent to commit -system.cpu.iew.WB:sent_1 7603 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 992 # Number of branch mispredicts detected at execute -system.cpu.iew.iewBlockCycles 8 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 3912 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 42 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 367 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 2233 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 19338 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 3181 # Number of load instructions executed -system.cpu.iew.iewExecLoadInsts_0 1597 # Number of load instructions executed -system.cpu.iew.iewExecLoadInsts_1 1584 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 917 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 15655 # Number of executed instructions -system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall +system.cpu.iew.WB:producers 7913 # num instructions producing a value +system.cpu.iew.WB:producers_0 3958 # num instructions producing a value +system.cpu.iew.WB:producers_1 3955 # num instructions producing a value +system.cpu.iew.WB:rate 1.323170 # insts written-back per cycle +system.cpu.iew.WB:rate_0 0.662590 # insts written-back per cycle +system.cpu.iew.WB:rate_1 0.660580 # insts written-back per cycle +system.cpu.iew.WB:sent 15343 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_0 7675 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_1 7668 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 991 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 60 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 3899 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 46 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 435 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 2258 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 19501 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 3185 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_0 1573 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_1 1612 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 923 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 15774 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 16 # 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 1515 # Number of cycles IEW is squashing -system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking +system.cpu.iew.iewSquashCycles 1569 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 15 # 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 44 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 2 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 39 # 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 70 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 62 # 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 973 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 300 # Number of stores squashed +system.cpu.iew.lsq.thread.0.squashedLoads 980 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 306 # Number of stores squashed system.cpu.iew.lsq.thread.1.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding system.cpu.iew.lsq.thread.1.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked -system.cpu.iew.lsq.thread.1.forwLoads 45 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.1.ignoredResponses 4 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.1.forwLoads 50 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.1.ignoredResponses 7 # Number of memory responses ignored because the instruction is squashed system.cpu.iew.lsq.thread.1.invAddrLoads 0 # Number of loads ignored due to an invalid address system.cpu.iew.lsq.thread.1.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address -system.cpu.iew.lsq.thread.1.memOrderViolation 61 # Number of memory ordering violations +system.cpu.iew.lsq.thread.1.memOrderViolation 63 # Number of memory ordering violations system.cpu.iew.lsq.thread.1.rescheduledLoads 1 # Number of loads that were rescheduled -system.cpu.iew.lsq.thread.1.squashedLoads 981 # Number of loads squashed -system.cpu.iew.lsq.thread.1.squashedStores 309 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 131 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 807 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 185 # Number of branches that were predicted taken incorrectly -system.cpu.ipc_0 0.512111 # IPC: Instructions Per Cycle -system.cpu.ipc_1 0.512020 # IPC: Instructions Per Cycle -system.cpu.ipc_total 1.024130 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 8256 # Type of FU issued +system.cpu.iew.lsq.thread.1.squashedLoads 961 # Number of loads squashed +system.cpu.iew.lsq.thread.1.squashedStores 328 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 125 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 788 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 203 # Number of branches that were predicted taken incorrectly +system.cpu.ipc_0 0.491263 # IPC: Instructions Per Cycle +system.cpu.ipc_1 0.491351 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.982614 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8365 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist No_OpClass 2 0.02% # Type of FU issued - IntAlu 5550 67.22% # Type of FU issued + IntAlu 5650 67.54% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 2 0.02% # Type of FU issued @@ -475,15 +487,15 @@ 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 1728 20.93% # Type of FU issued - MemWrite 973 11.79% # Type of FU issued + MemRead 1721 20.57% # Type of FU issued + MemWrite 989 11.82% # 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_type_1 8316 # Type of FU issued +system.cpu.iq.ISSUE:FU_type_1 8332 # Type of FU issued system.cpu.iq.ISSUE:FU_type_1.start_dist No_OpClass 2 0.02% # Type of FU issued - IntAlu 5613 67.50% # Type of FU issued + IntAlu 5594 67.14% # Type of FU issued IntMult 1 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 2 0.02% # Type of FU issued @@ -492,15 +504,15 @@ system.cpu.iq.ISSUE:FU_type_1.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 1726 20.76% # Type of FU issued - MemWrite 972 11.69% # Type of FU issued + MemRead 1734 20.81% # Type of FU issued + MemWrite 999 11.99% # 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_1.end_dist -system.cpu.iq.ISSUE:FU_type 16572 # Type of FU issued +system.cpu.iq.ISSUE:FU_type 16697 # Type of FU issued system.cpu.iq.ISSUE:FU_type.start_dist No_OpClass 4 0.02% # Type of FU issued - IntAlu 11163 67.36% # Type of FU issued + IntAlu 11244 67.34% # Type of FU issued IntMult 2 0.01% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 4 0.02% # Type of FU issued @@ -509,20 +521,20 @@ system.cpu.iq.ISSUE:FU_type.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 3454 20.84% # Type of FU issued - MemWrite 1945 11.74% # Type of FU issued + MemRead 3455 20.69% # Type of FU issued + MemWrite 1988 11.91% # 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.end_dist -system.cpu.iq.ISSUE:fu_busy_cnt 198 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_cnt_0 95 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_cnt_1 103 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.011948 # FU busy rate (busy events/executed inst) -system.cpu.iq.ISSUE:fu_busy_rate_0 0.005733 # FU busy rate (busy events/executed inst) -system.cpu.iq.ISSUE:fu_busy_rate_1 0.006215 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 193 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_0 88 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_1 105 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.011559 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_0 0.005270 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_1 0.006289 # 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 14 7.07% # attempts to use FU when none available + IntAlu 13 6.74% # 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 @@ -531,159 +543,163 @@ 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 119 60.10% # attempts to use FU when none available - MemWrite 65 32.83% # attempts to use FU when none available + MemRead 111 57.51% # attempts to use FU when none available + MemWrite 69 35.75% # 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 10982 +system.cpu.iq.ISSUE:issued_per_cycle.samples 11446 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 4716 4294.30% - 1 1863 1696.41% - 2 1568 1427.79% - 3 1132 1030.78% - 4 836 761.25% - 5 492 448.01% - 6 274 249.50% - 7 79 71.94% - 8 22 20.03% + 0 5082 4439.98% + 1 1881 1643.37% + 2 1650 1441.55% + 3 1151 1005.59% + 4 829 724.27% + 5 503 439.45% + 6 239 208.81% + 7 90 78.63% + 8 21 18.35% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 1.509015 # Inst issue rate -system.cpu.iq.iqInstsAdded 19223 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 16572 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 42 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 7181 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 51 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 8 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 4476 # Number of squashed operands that are examined and possibly removed from graph -system.cpu.l2cache.ReadExReq_accesses 146 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_accesses_0 146 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency_0 4770.547945 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency_0 2770.547945 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 696500 # number of ReadExReq miss cycles -system.cpu.l2cache.ReadExReq_miss_latency_0 696500 # number of ReadExReq miss cycles +system.cpu.iq.ISSUE:rate 1.458763 # Inst issue rate +system.cpu.iq.iqInstsAdded 19328 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 16697 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 46 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 7298 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 56 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 12 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 4495 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.itb.accesses 3071 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 3019 # ITB hits +system.cpu.itb.misses 52 # ITB misses +system.cpu.l2cache.ReadExReq_accesses 144 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_accesses_0 144 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency_0 4743.055556 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency_0 2743.055556 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 683000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_latency_0 683000 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate_0 1 # miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_misses 146 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_misses_0 146 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 404500 # number of ReadExReq MSHR miss cycles -system.cpu.l2cache.ReadExReq_mshr_miss_latency_0 404500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_misses 144 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_misses_0 144 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 395000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency_0 395000 # number of ReadExReq MSHR miss cycles system.cpu.l2cache.ReadExReq_mshr_miss_rate_0 1 # mshr miss rate for ReadExReq accesses -system.cpu.l2cache.ReadExReq_mshr_misses 146 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadExReq_mshr_misses_0 146 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 824 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_accesses_0 824 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency_0 4751.219512 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency_0 2751.219512 # average ReadReq mshr miss latency -system.cpu.l2cache.ReadReq_hits 4 # number of ReadReq hits -system.cpu.l2cache.ReadReq_hits_0 4 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 3896000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_latency_0 3896000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate_0 0.995146 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 820 # number of ReadReq misses -system.cpu.l2cache.ReadReq_misses_0 820 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 2256000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_latency_0 2256000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate_0 0.995146 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 820 # number of ReadReq MSHR misses -system.cpu.l2cache.ReadReq_mshr_misses_0 820 # number of ReadReq MSHR misses -system.cpu.l2cache.UpgradeReq_accesses 28 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_accesses_0 28 # number of UpgradeReq accesses(hits+misses) -system.cpu.l2cache.UpgradeReq_avg_miss_latency_0 4482.142857 # average UpgradeReq miss latency -system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency_0 2482.142857 # average UpgradeReq mshr miss latency -system.cpu.l2cache.UpgradeReq_miss_latency 125500 # number of UpgradeReq miss cycles -system.cpu.l2cache.UpgradeReq_miss_latency_0 125500 # number of UpgradeReq miss cycles +system.cpu.l2cache.ReadExReq_mshr_misses 144 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadExReq_mshr_misses_0 144 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 811 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_accesses_0 811 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency_0 4691.831683 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency_0 2691.831683 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 3 # number of ReadReq hits +system.cpu.l2cache.ReadReq_hits_0 3 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 3791000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_latency_0 3791000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate_0 0.996301 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 808 # number of ReadReq misses +system.cpu.l2cache.ReadReq_misses_0 808 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 2175000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_latency_0 2175000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate_0 0.996301 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 808 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_mshr_misses_0 808 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 30 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_accesses_0 30 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency_0 4500 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency_0 2500 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_miss_latency 135000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_latency_0 135000 # number of UpgradeReq miss cycles system.cpu.l2cache.UpgradeReq_miss_rate_0 1 # miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_misses 28 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_misses_0 28 # number of UpgradeReq misses -system.cpu.l2cache.UpgradeReq_mshr_miss_latency 69500 # number of UpgradeReq MSHR miss cycles -system.cpu.l2cache.UpgradeReq_mshr_miss_latency_0 69500 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_misses 30 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_misses_0 30 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 75000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_latency_0 75000 # number of UpgradeReq MSHR miss cycles system.cpu.l2cache.UpgradeReq_mshr_miss_rate_0 1 # mshr miss rate for UpgradeReq accesses -system.cpu.l2cache.UpgradeReq_mshr_misses 28 # number of UpgradeReq MSHR misses -system.cpu.l2cache.UpgradeReq_mshr_misses_0 28 # number of UpgradeReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses 30 # number of UpgradeReq MSHR misses +system.cpu.l2cache.UpgradeReq_mshr_misses_0 30 # 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 0.005051 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.003856 # 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 970 # number of demand (read+write) accesses -system.cpu.l2cache.demand_accesses_0 970 # number of demand (read+write) accesses +system.cpu.l2cache.demand_accesses 955 # number of demand (read+write) accesses +system.cpu.l2cache.demand_accesses_0 955 # number of demand (read+write) accesses system.cpu.l2cache.demand_accesses_1 0 # number of demand (read+write) accesses system.cpu.l2cache.demand_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.l2cache.demand_avg_miss_latency_0 4754.140787 # average overall miss latency +system.cpu.l2cache.demand_avg_miss_latency_0 4699.579832 # average overall miss latency system.cpu.l2cache.demand_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency_0 2754.140787 # average overall mshr miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency_0 2699.579832 # average overall mshr miss latency system.cpu.l2cache.demand_avg_mshr_miss_latency_1 <err: div-0> # average overall mshr miss latency -system.cpu.l2cache.demand_hits 4 # number of demand (read+write) hits -system.cpu.l2cache.demand_hits_0 4 # number of demand (read+write) hits +system.cpu.l2cache.demand_hits 3 # number of demand (read+write) hits +system.cpu.l2cache.demand_hits_0 3 # number of demand (read+write) hits system.cpu.l2cache.demand_hits_1 0 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 4592500 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_latency_0 4592500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency 4474000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_latency_0 4474000 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_latency_1 0 # number of demand (read+write) miss cycles system.cpu.l2cache.demand_miss_rate <err: div-0> # miss rate for demand accesses -system.cpu.l2cache.demand_miss_rate_0 0.995876 # miss rate for demand accesses +system.cpu.l2cache.demand_miss_rate_0 0.996859 # miss rate for demand accesses system.cpu.l2cache.demand_miss_rate_1 <err: div-0> # miss rate for demand accesses -system.cpu.l2cache.demand_misses 966 # number of demand (read+write) misses -system.cpu.l2cache.demand_misses_0 966 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses 952 # number of demand (read+write) misses +system.cpu.l2cache.demand_misses_0 952 # number of demand (read+write) misses system.cpu.l2cache.demand_misses_1 0 # 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_hits_0 0 # number of demand (read+write) MSHR hits system.cpu.l2cache.demand_mshr_hits_1 0 # number of demand (read+write) MSHR hits -system.cpu.l2cache.demand_mshr_miss_latency 2660500 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_latency_0 2660500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency 2570000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_latency_0 2570000 # number of demand (read+write) MSHR miss cycles system.cpu.l2cache.demand_mshr_miss_latency_1 0 # number of demand (read+write) MSHR miss cycles system.cpu.l2cache.demand_mshr_miss_rate <err: div-0> # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_miss_rate_0 0.995876 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_miss_rate_0 0.996859 # mshr miss rate for demand accesses system.cpu.l2cache.demand_mshr_miss_rate_1 <err: div-0> # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 966 # number of demand (read+write) MSHR misses -system.cpu.l2cache.demand_mshr_misses_0 966 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses 952 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_misses_0 952 # number of demand (read+write) MSHR misses system.cpu.l2cache.demand_mshr_misses_1 0 # 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.mshr_cap_events_0 0 # number of times MSHR cap was activated system.cpu.l2cache.mshr_cap_events_1 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 970 # number of overall (read+write) accesses -system.cpu.l2cache.overall_accesses_0 970 # number of overall (read+write) accesses +system.cpu.l2cache.overall_accesses 955 # number of overall (read+write) accesses +system.cpu.l2cache.overall_accesses_0 955 # number of overall (read+write) accesses system.cpu.l2cache.overall_accesses_1 0 # number of overall (read+write) accesses system.cpu.l2cache.overall_avg_miss_latency <err: div-0> # average overall miss latency -system.cpu.l2cache.overall_avg_miss_latency_0 4754.140787 # average overall miss latency +system.cpu.l2cache.overall_avg_miss_latency_0 4699.579832 # average overall miss latency system.cpu.l2cache.overall_avg_miss_latency_1 <err: div-0> # average overall miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency <err: div-0> # average overall mshr miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency_0 2754.140787 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency_0 2699.579832 # average overall mshr miss latency system.cpu.l2cache.overall_avg_mshr_miss_latency_1 <err: div-0> # 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_avg_mshr_uncacheable_latency_0 <err: div-0> # average overall mshr uncacheable latency system.cpu.l2cache.overall_avg_mshr_uncacheable_latency_1 <err: div-0> # average overall mshr uncacheable latency -system.cpu.l2cache.overall_hits 4 # number of overall hits -system.cpu.l2cache.overall_hits_0 4 # number of overall hits +system.cpu.l2cache.overall_hits 3 # number of overall hits +system.cpu.l2cache.overall_hits_0 3 # number of overall hits system.cpu.l2cache.overall_hits_1 0 # number of overall hits -system.cpu.l2cache.overall_miss_latency 4592500 # number of overall miss cycles -system.cpu.l2cache.overall_miss_latency_0 4592500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency 4474000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_latency_0 4474000 # number of overall miss cycles system.cpu.l2cache.overall_miss_latency_1 0 # number of overall miss cycles system.cpu.l2cache.overall_miss_rate <err: div-0> # miss rate for overall accesses -system.cpu.l2cache.overall_miss_rate_0 0.995876 # miss rate for overall accesses +system.cpu.l2cache.overall_miss_rate_0 0.996859 # miss rate for overall accesses system.cpu.l2cache.overall_miss_rate_1 <err: div-0> # miss rate for overall accesses -system.cpu.l2cache.overall_misses 966 # number of overall misses -system.cpu.l2cache.overall_misses_0 966 # number of overall misses +system.cpu.l2cache.overall_misses 952 # number of overall misses +system.cpu.l2cache.overall_misses_0 952 # number of overall misses system.cpu.l2cache.overall_misses_1 0 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.l2cache.overall_mshr_hits_0 0 # number of overall MSHR hits system.cpu.l2cache.overall_mshr_hits_1 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 2660500 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_latency_0 2660500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency 2570000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_latency_0 2570000 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_miss_latency_1 0 # number of overall MSHR miss cycles system.cpu.l2cache.overall_mshr_miss_rate <err: div-0> # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_miss_rate_0 0.995876 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_miss_rate_0 0.996859 # mshr miss rate for overall accesses system.cpu.l2cache.overall_mshr_miss_rate_1 <err: div-0> # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 966 # number of overall MSHR misses -system.cpu.l2cache.overall_mshr_misses_0 966 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses 952 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_misses_0 952 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_misses_1 0 # 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_latency_0 0 # number of overall MSHR uncacheable cycles @@ -703,33 +719,33 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.replacements_0 0 # number of replacements system.cpu.l2cache.replacements_1 0 # number of replacements -system.cpu.l2cache.sampled_refs 792 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 778 # 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.soft_prefetch_mshr_full_0 0 # number of mshr full events for SW prefetching instrutions system.cpu.l2cache.soft_prefetch_mshr_full_1 0 # number of mshr full events for SW prefetching instrutions -system.cpu.l2cache.tagsinuse 429.647178 # Cycle average of tags in use -system.cpu.l2cache.total_refs 4 # Total number of references to valid blocks. +system.cpu.l2cache.tagsinuse 424.676856 # 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.l2cache.writebacks_0 0 # number of writebacks system.cpu.l2cache.writebacks_1 0 # number of writebacks -system.cpu.numCycles 10982 # number of cpu cycles simulated -system.cpu.rename.RENAME:BlockCycles 592 # Number of cycles rename is blocking +system.cpu.numCycles 11446 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 641 # Number of cycles rename is blocking system.cpu.rename.RENAME:CommittedMaps 8102 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 14764 # Number of cycles rename is idle -system.cpu.rename.RENAME:LSQFullEvents 762 # Number of times rename has blocked due to LSQ full -system.cpu.rename.RENAME:RenameLookups 26692 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 21016 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 15806 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 3542 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 1515 # Number of cycles rename is squashing -system.cpu.rename.RENAME:UnblockCycles 817 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 7704 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 503 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:IdleCycles 15417 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 776 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 27043 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 21312 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 15958 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 3623 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 1569 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 844 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 7856 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 504 # count of cycles rename stalled for serializing inst system.cpu.rename.RENAME:serializingInsts 48 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 2234 # count of insts added to the skid buffer +system.cpu.rename.RENAME:skidInsts 2318 # count of insts added to the skid buffer system.cpu.rename.RENAME:tempSerializingInsts 36 # count of temporary serializing insts renamed -system.cpu.timesIdled 7 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.timesIdled 4 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload0.PROG:num_syscalls 17 # Number of system calls system.cpu.workload1.PROG:num_syscalls 17 # Number of system calls diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout index 5b0ff582b..c45cb0224 100644 --- a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout @@ -7,9 +7,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:26:55 -M5 started Sun Aug 12 00:29:42 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 15:45:23 +M5 started Tue Aug 14 15:45:27 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/01.hello-2T-smt/alpha/linux/o3-timing tests/run.py quick/01.hello-2T-smt/alpha/linux/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 5506000 because target called exit() +Exiting @ tick 5727000 because target called exit() diff --git a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/config.ini b/tests/quick/02.insttest/ref/sparc/linux/o3-timing/config.ini index bfef15018..8c35e4da1 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/config.ini +++ b/tests/quick/02.insttest/ref/sparc/linux/o3-timing/config.ini @@ -11,7 +11,7 @@ physmem=system.physmem [system.cpu] type=DerivO3CPU -children=dcache fuPool icache l2cache toL2Bus tracer workload +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload BTBEntries=4096 BTBTagSize=16 LFSTSize=1024 @@ -36,6 +36,7 @@ decodeToRenameDelay=1 decodeWidth=8 defer_registration=false dispatchWidth=8 +dtb=system.cpu.dtb fetchToDecodeDelay=1 fetchTrapLatency=1 fetchWidth=8 @@ -53,6 +54,7 @@ iewToRenameDelay=1 instShiftAmt=2 issueToExecuteDelay=1 issueWidth=8 +itb=system.cpu.itb localCtrBits=2 localHistoryBits=11 localHistoryTableSize=2048 @@ -130,6 +132,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.fuPool] type=FUPool children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 @@ -303,6 +309,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/m5stats.txt b/tests/quick/02.insttest/ref/sparc/linux/o3-timing/m5stats.txt index 0f88834b5..eae7625e9 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/m5stats.txt +++ b/tests/quick/02.insttest/ref/sparc/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 2657 # Number of BTB hits -global.BPredUnit.BTBLookups 6786 # Number of BTB lookups +global.BPredUnit.BTBHits 2711 # Number of BTB hits +global.BPredUnit.BTBLookups 6964 # Number of BTB lookups global.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. -global.BPredUnit.condIncorrect 1999 # Number of conditional branches incorrect -global.BPredUnit.condPredicted 7531 # Number of conditional branches predicted -global.BPredUnit.lookups 7531 # Number of BP lookups +global.BPredUnit.condIncorrect 2012 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 7659 # Number of conditional branches predicted +global.BPredUnit.lookups 7659 # Number of BP lookups global.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target. -host_inst_rate 57578 # Simulator instruction rate (inst/s) -host_mem_usage 198128 # Number of bytes of host memory used -host_seconds 0.19 # Real time elapsed on the host -host_tick_rate 76965798 # Simulator tick rate (ticks/s) -memdepunit.memDep.conflictingLoads 14 # Number of conflicting loads. +host_inst_rate 7502 # Simulator instruction rate (inst/s) +host_mem_usage 186228 # Number of bytes of host memory used +host_seconds 1.39 # Real time elapsed on the host +host_tick_rate 10800438 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 15 # Number of conflicting loads. memdepunit.memDep.conflictingStores 0 # Number of conflicting stores. -memdepunit.memDep.insertedLoads 3022 # Number of loads inserted to the mem dependence unit. -memdepunit.memDep.insertedStores 2929 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 3077 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 2956 # Number of stores inserted to the mem dependence unit. sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 10976 # Number of instructions simulated +sim_insts 10411 # Number of instructions simulated sim_seconds 0.000015 # Number of seconds simulated -sim_ticks 14690000 # Number of ticks simulated +sim_ticks 14990500 # Number of ticks simulated system.cpu.commit.COM:branches 2152 # Number of branches committed -system.cpu.commit.COM:bw_lim_events 93 # number cycles where commit BW limit reached +system.cpu.commit.COM:bw_lim_events 87 # 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 26502 +system.cpu.commit.COM:committed_per_cycle.samples 26989 system.cpu.commit.COM:committed_per_cycle.min_value 0 - 0 20989 7919.78% - 1 3011 1136.14% - 2 1202 453.55% - 3 588 221.87% - 4 307 115.84% - 5 82 30.94% - 6 195 73.58% - 7 35 13.21% - 8 93 35.09% + 0 21416 7935.08% + 1 3114 1153.80% + 2 1160 429.80% + 3 589 218.24% + 4 306 113.38% + 5 84 31.12% + 6 196 72.62% + 7 37 13.71% + 8 87 32.24% system.cpu.commit.COM:committed_per_cycle.max_value 8 system.cpu.commit.COM:committed_per_cycle.end_dist @@ -43,72 +43,72 @@ system.cpu.commit.COM:loads 1462 # Nu system.cpu.commit.COM:membars 0 # Number of memory barriers committed system.cpu.commit.COM:refs 2760 # Number of memory references committed system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed -system.cpu.commit.branchMispredicts 1999 # The number of times a branch was mispredicted +system.cpu.commit.branchMispredicts 2012 # The number of times a branch was mispredicted system.cpu.commit.commitCommittedInsts 10976 # The number of committed instructions system.cpu.commit.commitNonSpecStalls 329 # The number of times commit has been forced to stall to communicate backwards -system.cpu.commit.commitSquashedInsts 13065 # The number of squashed insts skipped by commit -system.cpu.committedInsts 10976 # Number of Instructions Simulated -system.cpu.committedInsts_total 10976 # Number of Instructions Simulated -system.cpu.cpi 2.675656 # CPI: Cycles Per Instruction -system.cpu.cpi_total 2.675656 # CPI: Total CPI of All Threads -system.cpu.dcache.ReadReq_accesses 2253 # number of ReadReq accesses(hits+misses) -system.cpu.dcache.ReadReq_avg_miss_latency 9417.910448 # average ReadReq miss latency -system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5611.940299 # average ReadReq mshr miss latency -system.cpu.dcache.ReadReq_hits 2186 # number of ReadReq hits -system.cpu.dcache.ReadReq_miss_latency 631000 # number of ReadReq miss cycles -system.cpu.dcache.ReadReq_miss_rate 0.029738 # miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_misses 67 # number of ReadReq misses -system.cpu.dcache.ReadReq_mshr_hits 20 # number of ReadReq MSHR hits -system.cpu.dcache.ReadReq_mshr_miss_latency 376000 # number of ReadReq MSHR miss cycles -system.cpu.dcache.ReadReq_mshr_miss_rate 0.029738 # mshr miss rate for ReadReq accesses -system.cpu.dcache.ReadReq_mshr_misses 67 # number of ReadReq MSHR misses +system.cpu.commit.commitSquashedInsts 13198 # The number of squashed insts skipped by commit +system.cpu.committedInsts 10411 # Number of Instructions Simulated +system.cpu.committedInsts_total 10411 # Number of Instructions Simulated +system.cpu.cpi 2.871770 # CPI: Cycles Per Instruction +system.cpu.cpi_total 2.871770 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 2274 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 9734.848485 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 5560.606061 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 2208 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 642500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.029024 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 66 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 25 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 367000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.029024 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 66 # number of ReadReq MSHR misses system.cpu.dcache.SwapReq_accesses 6 # number of SwapReq accesses(hits+misses) system.cpu.dcache.SwapReq_hits 6 # number of SwapReq hits system.cpu.dcache.WriteReq_accesses 1171 # number of WriteReq accesses(hits+misses) -system.cpu.dcache.WriteReq_avg_miss_latency 16509.523810 # average WriteReq miss latency -system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5709.523810 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_avg_miss_latency 16414.285714 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5623.809524 # average WriteReq mshr miss latency system.cpu.dcache.WriteReq_hits 1066 # number of WriteReq hits -system.cpu.dcache.WriteReq_miss_latency 1733500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_latency 1723500 # number of WriteReq miss cycles system.cpu.dcache.WriteReq_miss_rate 0.089667 # miss rate for WriteReq accesses system.cpu.dcache.WriteReq_misses 105 # number of WriteReq misses system.cpu.dcache.WriteReq_mshr_hits 121 # number of WriteReq MSHR hits -system.cpu.dcache.WriteReq_mshr_miss_latency 599500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_latency 590500 # number of WriteReq MSHR miss cycles system.cpu.dcache.WriteReq_mshr_miss_rate 0.089667 # mshr miss rate for WriteReq accesses system.cpu.dcache.WriteReq_mshr_misses 105 # 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 21.418301 # Average number of references to valid blocks. +system.cpu.dcache.avg_refs 21.703947 # 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 3424 # number of demand (read+write) accesses -system.cpu.dcache.demand_avg_miss_latency 13747.093023 # average overall miss latency -system.cpu.dcache.demand_avg_mshr_miss_latency 5671.511628 # average overall mshr miss latency -system.cpu.dcache.demand_hits 3252 # number of demand (read+write) hits -system.cpu.dcache.demand_miss_latency 2364500 # number of demand (read+write) miss cycles -system.cpu.dcache.demand_miss_rate 0.050234 # miss rate for demand accesses -system.cpu.dcache.demand_misses 172 # number of demand (read+write) misses -system.cpu.dcache.demand_mshr_hits 141 # number of demand (read+write) MSHR hits -system.cpu.dcache.demand_mshr_miss_latency 975500 # number of demand (read+write) MSHR miss cycles -system.cpu.dcache.demand_mshr_miss_rate 0.050234 # mshr miss rate for demand accesses -system.cpu.dcache.demand_mshr_misses 172 # number of demand (read+write) MSHR misses +system.cpu.dcache.demand_accesses 3445 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 13836.257310 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 5599.415205 # average overall mshr miss latency +system.cpu.dcache.demand_hits 3274 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 2366000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.049637 # miss rate for demand accesses +system.cpu.dcache.demand_misses 171 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 146 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 957500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.049637 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 171 # 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 3424 # number of overall (read+write) accesses -system.cpu.dcache.overall_avg_miss_latency 13747.093023 # average overall miss latency -system.cpu.dcache.overall_avg_mshr_miss_latency 5671.511628 # average overall mshr miss latency +system.cpu.dcache.overall_accesses 3445 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 13836.257310 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 5599.415205 # 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 3252 # number of overall hits -system.cpu.dcache.overall_miss_latency 2364500 # number of overall miss cycles -system.cpu.dcache.overall_miss_rate 0.050234 # miss rate for overall accesses -system.cpu.dcache.overall_misses 172 # number of overall misses -system.cpu.dcache.overall_mshr_hits 141 # number of overall MSHR hits -system.cpu.dcache.overall_mshr_miss_latency 975500 # number of overall MSHR miss cycles -system.cpu.dcache.overall_mshr_miss_rate 0.050234 # mshr miss rate for overall accesses -system.cpu.dcache.overall_mshr_misses 172 # number of overall MSHR misses +system.cpu.dcache.overall_hits 3274 # number of overall hits +system.cpu.dcache.overall_miss_latency 2366000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.049637 # miss rate for overall accesses +system.cpu.dcache.overall_misses 171 # number of overall misses +system.cpu.dcache.overall_mshr_hits 146 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 957500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.049637 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 171 # 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 @@ -121,88 +121,88 @@ 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 153 # Sample count of references to valid blocks. +system.cpu.dcache.sampled_refs 152 # 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 112.521037 # Cycle average of tags in use -system.cpu.dcache.total_refs 3277 # Total number of references to valid blocks. +system.cpu.dcache.tagsinuse 111.288485 # Cycle average of tags in use +system.cpu.dcache.total_refs 3299 # 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 4038 # Number of cycles decode is blocked -system.cpu.decode.DECODE:DecodedInsts 37564 # Number of instructions handled by decode -system.cpu.decode.DECODE:IdleCycles 12395 # Number of cycles decode is idle -system.cpu.decode.DECODE:RunCycles 10006 # Number of cycles decode is running -system.cpu.decode.DECODE:SquashCycles 2866 # Number of cycles decode is squashing -system.cpu.decode.DECODE:UnblockCycles 63 # Number of cycles decode is unblocking -system.cpu.fetch.Branches 7531 # Number of branches that fetch encountered -system.cpu.fetch.CacheLines 4872 # Number of cache lines fetched -system.cpu.fetch.Cycles 15997 # Number of cycles fetch has run and was not squashing or blocked -system.cpu.fetch.IcacheSquashes 576 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.Insts 41653 # Number of instructions fetch has processed -system.cpu.fetch.SquashCycles 2060 # Number of cycles fetch has spent squashing -system.cpu.fetch.branchRate 0.256436 # Number of branch fetches per cycle -system.cpu.fetch.icacheStallCycles 4872 # Number of cycles fetch is stalled on an Icache miss -system.cpu.fetch.predictedBranches 2657 # Number of branches that fetch has predicted taken -system.cpu.fetch.rate 1.418312 # Number of inst fetches per cycle +system.cpu.decode.DECODE:BlockedCycles 3945 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 38084 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 12820 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 10159 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 2909 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 65 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 7659 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 4927 # Number of cache lines fetched +system.cpu.fetch.Cycles 16219 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 589 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 42202 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 2099 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.256171 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 4927 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 2711 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 1.411533 # Number of inst fetches per cycle system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist.samples 29368 +system.cpu.fetch.rateDist.samples 29898 system.cpu.fetch.rateDist.min_value 0 - 0 18244 6212.20% - 1 4822 1641.92% - 2 611 208.05% - 3 702 239.04% - 4 788 268.32% - 5 623 212.14% - 6 599 203.96% - 7 190 64.70% - 8 2789 949.67% + 0 18628 6230.52% + 1 4885 1633.89% + 2 619 207.04% + 3 712 238.14% + 4 788 263.56% + 5 640 214.06% + 6 611 204.36% + 7 195 65.22% + 8 2820 943.21% system.cpu.fetch.rateDist.max_value 8 system.cpu.fetch.rateDist.end_dist -system.cpu.icache.ReadReq_accesses 4851 # number of ReadReq accesses(hits+misses) -system.cpu.icache.ReadReq_avg_miss_latency 7514.784946 # average ReadReq miss latency -system.cpu.icache.ReadReq_avg_mshr_miss_latency 5338.709677 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 4479 # number of ReadReq hits -system.cpu.icache.ReadReq_miss_latency 2795500 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.076685 # miss rate for ReadReq accesses -system.cpu.icache.ReadReq_misses 372 # number of ReadReq misses -system.cpu.icache.ReadReq_mshr_hits 21 # number of ReadReq MSHR hits -system.cpu.icache.ReadReq_mshr_miss_latency 1986000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.076685 # mshr miss rate for ReadReq accesses -system.cpu.icache.ReadReq_mshr_misses 372 # number of ReadReq MSHR misses +system.cpu.icache.ReadReq_accesses 4907 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 7495.945946 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 5325.675676 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 4537 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 2773500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.075402 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 370 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 20 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 1970500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.075402 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 370 # 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 12.040323 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 12.262162 # 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 4851 # number of demand (read+write) accesses -system.cpu.icache.demand_avg_miss_latency 7514.784946 # average overall miss latency -system.cpu.icache.demand_avg_mshr_miss_latency 5338.709677 # average overall mshr miss latency -system.cpu.icache.demand_hits 4479 # number of demand (read+write) hits -system.cpu.icache.demand_miss_latency 2795500 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.076685 # miss rate for demand accesses -system.cpu.icache.demand_misses 372 # number of demand (read+write) misses -system.cpu.icache.demand_mshr_hits 21 # number of demand (read+write) MSHR hits -system.cpu.icache.demand_mshr_miss_latency 1986000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.076685 # mshr miss rate for demand accesses -system.cpu.icache.demand_mshr_misses 372 # number of demand (read+write) MSHR misses +system.cpu.icache.demand_accesses 4907 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 7495.945946 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 5325.675676 # average overall mshr miss latency +system.cpu.icache.demand_hits 4537 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 2773500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.075402 # miss rate for demand accesses +system.cpu.icache.demand_misses 370 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 20 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 1970500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.075402 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 370 # 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 4851 # number of overall (read+write) accesses -system.cpu.icache.overall_avg_miss_latency 7514.784946 # average overall miss latency -system.cpu.icache.overall_avg_mshr_miss_latency 5338.709677 # average overall mshr miss latency +system.cpu.icache.overall_accesses 4907 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 7495.945946 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 5325.675676 # 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 4479 # number of overall hits -system.cpu.icache.overall_miss_latency 2795500 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.076685 # miss rate for overall accesses -system.cpu.icache.overall_misses 372 # number of overall misses -system.cpu.icache.overall_mshr_hits 21 # number of overall MSHR hits -system.cpu.icache.overall_mshr_miss_latency 1986000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.076685 # mshr miss rate for overall accesses -system.cpu.icache.overall_mshr_misses 372 # number of overall MSHR misses +system.cpu.icache.overall_hits 4537 # number of overall hits +system.cpu.icache.overall_miss_latency 2773500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.075402 # miss rate for overall accesses +system.cpu.icache.overall_misses 370 # number of overall misses +system.cpu.icache.overall_mshr_hits 20 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 1970500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.075402 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 370 # number of overall MSHR misses system.cpu.icache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.icache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.icache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -215,61 +215,61 @@ system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time system.cpu.icache.replacements 1 # number of replacements -system.cpu.icache.sampled_refs 372 # Sample count of references to valid blocks. +system.cpu.icache.sampled_refs 370 # 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 236.918934 # Cycle average of tags in use -system.cpu.icache.total_refs 4479 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 233.477311 # Cycle average of tags in use +system.cpu.icache.total_refs 4537 # 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 8496 # Total number of cycles that the CPU has spent unscheduled due to idling -system.cpu.iew.EXEC:branches 3046 # Number of branches executed -system.cpu.iew.EXEC:nop 0 # number of nop insts executed -system.cpu.iew.EXEC:rate 0.623842 # Inst execution rate -system.cpu.iew.EXEC:refs 4481 # number of memory reference insts executed -system.cpu.iew.EXEC:stores 2103 # Number of stores executed +system.cpu.idleCycles 51980 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 3086 # Number of branches executed +system.cpu.iew.EXEC:nop 1794 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.576995 # Inst execution rate +system.cpu.iew.EXEC:refs 4543 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 2116 # Number of stores executed system.cpu.iew.EXEC:swp 0 # number of swp insts executed -system.cpu.iew.WB:consumers 9128 # num instructions consuming a value -system.cpu.iew.WB:count 17742 # cumulative count of insts written-back -system.cpu.iew.WB:fanout 0.828330 # average fanout of values written-back +system.cpu.iew.WB:consumers 9189 # num instructions consuming a value +system.cpu.iew.WB:count 16618 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.827620 # 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 7561 # num instructions producing a value -system.cpu.iew.WB:rate 0.604127 # insts written-back per cycle -system.cpu.iew.WB:sent 17903 # cumulative count of insts sent to commit -system.cpu.iew.branchMispredicts 2179 # Number of branch mispredicts detected at execute +system.cpu.iew.WB:producers 7605 # num instructions producing a value +system.cpu.iew.WB:rate 0.555823 # insts written-back per cycle +system.cpu.iew.WB:sent 16830 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 2216 # Number of branch mispredicts detected at execute system.cpu.iew.iewBlockCycles 0 # Number of cycles IEW is blocking -system.cpu.iew.iewDispLoadInsts 3022 # Number of dispatched load instructions -system.cpu.iew.iewDispNonSpecInsts 611 # Number of dispatched non-speculative instructions -system.cpu.iew.iewDispSquashedInsts 2901 # Number of squashed instructions skipped by dispatch -system.cpu.iew.iewDispStoreInsts 2929 # Number of dispatched store instructions -system.cpu.iew.iewDispatchedInsts 24042 # Number of instructions dispatched to IQ -system.cpu.iew.iewExecLoadInsts 2378 # Number of load instructions executed -system.cpu.iew.iewExecSquashedInsts 3319 # Number of squashed instructions skipped in execute -system.cpu.iew.iewExecutedInsts 18321 # Number of executed instructions +system.cpu.iew.iewDispLoadInsts 3077 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 612 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 2973 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 2956 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 24330 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 2427 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 2838 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 17251 # 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 2866 # Number of cycles IEW is squashing +system.cpu.iew.iewSquashCycles 2909 # 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 45 # Number of loads that had data forwarded from stores -system.cpu.iew.lsq.thread.0.ignoredResponses 6 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.0.forwLoads 46 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 7 # 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 60 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.memOrderViolation 57 # 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 1560 # Number of loads squashed -system.cpu.iew.lsq.thread.0.squashedStores 1631 # Number of stores squashed -system.cpu.iew.memOrderViolationEvents 60 # Number of memory order violations -system.cpu.iew.predictedNotTakenIncorrect 684 # Number of branches that were predicted not taken incorrectly -system.cpu.iew.predictedTakenIncorrect 1495 # Number of branches that were predicted taken incorrectly -system.cpu.ipc 0.373740 # IPC: Instructions Per Cycle -system.cpu.ipc_total 0.373740 # IPC: Total IPC of All Threads -system.cpu.iq.ISSUE:FU_type_0 21640 # Type of FU issued +system.cpu.iew.lsq.thread.0.squashedLoads 1615 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 1658 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 57 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 695 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 1521 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.348217 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.348217 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 20089 # Type of FU issued system.cpu.iq.ISSUE:FU_type_0.start_dist - No_OpClass 1766 8.16% # Type of FU issued - IntAlu 14389 66.49% # Type of FU issued + No_OpClass 0 0.00% # Type of FU issued + IntAlu 14535 72.35% # Type of FU issued IntMult 0 0.00% # Type of FU issued IntDiv 0 0.00% # Type of FU issued FloatAdd 0 0.00% # Type of FU issued @@ -278,16 +278,16 @@ 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 2855 13.19% # Type of FU issued - MemWrite 2630 12.15% # Type of FU issued + MemRead 2907 14.47% # Type of FU issued + MemWrite 2647 13.18% # 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 181 # FU busy when requested -system.cpu.iq.ISSUE:fu_busy_rate 0.008364 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_cnt 188 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.009358 # 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 43 23.76% # attempts to use FU when none available + IntAlu 50 26.60% # 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 @@ -296,53 +296,53 @@ 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 23 12.71% # attempts to use FU when none available - MemWrite 115 63.54% # attempts to use FU when none available + MemRead 23 12.23% # attempts to use FU when none available + MemWrite 115 61.17% # 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 29368 +system.cpu.iq.ISSUE:issued_per_cycle.samples 29898 system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 - 0 20067 6832.95% - 1 3826 1302.78% - 2 2129 724.94% - 3 1515 515.87% - 4 870 296.24% - 5 480 163.44% - 6 307 104.54% - 7 103 35.07% - 8 71 24.18% + 0 21040 7037.26% + 1 3621 1211.12% + 2 2127 711.42% + 3 1561 522.11% + 4 748 250.18% + 5 407 136.13% + 6 293 98.00% + 7 62 20.74% + 8 39 13.04% system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 system.cpu.iq.ISSUE:issued_per_cycle.end_dist -system.cpu.iq.ISSUE:rate 0.736856 # Inst issue rate -system.cpu.iq.iqInstsAdded 23431 # Number of instructions added to the IQ (excludes non-spec) -system.cpu.iq.iqInstsIssued 21640 # Number of instructions issued -system.cpu.iq.iqNonSpecInstsAdded 611 # Number of non-speculative instructions added to the IQ -system.cpu.iq.iqSquashedInstsExamined 11038 # Number of squashed instructions iterated over during squash; mainly for profiling -system.cpu.iq.iqSquashedInstsIssued 111 # Number of squashed instructions issued -system.cpu.iq.iqSquashedNonSpecRemoved 282 # Number of squashed non-spec instructions that were removed -system.cpu.iq.iqSquashedOperandsExamined 7964 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.iq.ISSUE:rate 0.671918 # Inst issue rate +system.cpu.iq.iqInstsAdded 21924 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 20089 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 612 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 10307 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 110 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 283 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 8241 # Number of squashed operands that are examined and possibly removed from graph system.cpu.l2cache.ReadExReq_accesses 86 # number of ReadExReq accesses(hits+misses) -system.cpu.l2cache.ReadExReq_avg_miss_latency 4430.232558 # average ReadExReq miss latency -system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2430.232558 # average ReadExReq mshr miss latency -system.cpu.l2cache.ReadExReq_miss_latency 381000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_avg_miss_latency 4424.418605 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 2424.418605 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_miss_latency 380500 # number of ReadExReq miss cycles system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses system.cpu.l2cache.ReadExReq_misses 86 # number of ReadExReq misses -system.cpu.l2cache.ReadExReq_mshr_miss_latency 209000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_latency 208500 # 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 86 # number of ReadExReq MSHR misses -system.cpu.l2cache.ReadReq_accesses 439 # number of ReadReq accesses(hits+misses) -system.cpu.l2cache.ReadReq_avg_miss_latency 4291.954023 # average ReadReq miss latency -system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2291.954023 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_accesses 436 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 4287.037037 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2287.037037 # average ReadReq mshr miss latency system.cpu.l2cache.ReadReq_hits 4 # number of ReadReq hits -system.cpu.l2cache.ReadReq_miss_latency 1867000 # number of ReadReq miss cycles -system.cpu.l2cache.ReadReq_miss_rate 0.990888 # miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_misses 435 # number of ReadReq misses -system.cpu.l2cache.ReadReq_mshr_miss_latency 997000 # number of ReadReq MSHR miss cycles -system.cpu.l2cache.ReadReq_mshr_miss_rate 0.990888 # mshr miss rate for ReadReq accesses -system.cpu.l2cache.ReadReq_mshr_misses 435 # number of ReadReq MSHR misses +system.cpu.l2cache.ReadReq_miss_latency 1852000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.990826 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 432 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 988000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.990826 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 432 # number of ReadReq MSHR misses system.cpu.l2cache.UpgradeReq_accesses 19 # number of UpgradeReq accesses(hits+misses) system.cpu.l2cache.UpgradeReq_avg_miss_latency 4421.052632 # average UpgradeReq miss latency system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 2421.052632 # average UpgradeReq mshr miss latency @@ -354,38 +354,38 @@ system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 system.cpu.l2cache.UpgradeReq_mshr_misses 19 # 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 0.009615 # Average number of references to valid blocks. +system.cpu.l2cache.avg_refs 0.009685 # 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 525 # number of demand (read+write) accesses -system.cpu.l2cache.demand_avg_miss_latency 4314.779271 # average overall miss latency -system.cpu.l2cache.demand_avg_mshr_miss_latency 2314.779271 # average overall mshr miss latency +system.cpu.l2cache.demand_accesses 522 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 4309.845560 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 2309.845560 # average overall mshr miss latency system.cpu.l2cache.demand_hits 4 # number of demand (read+write) hits -system.cpu.l2cache.demand_miss_latency 2248000 # number of demand (read+write) miss cycles -system.cpu.l2cache.demand_miss_rate 0.992381 # miss rate for demand accesses -system.cpu.l2cache.demand_misses 521 # number of demand (read+write) misses +system.cpu.l2cache.demand_miss_latency 2232500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.992337 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 518 # 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 1206000 # number of demand (read+write) MSHR miss cycles -system.cpu.l2cache.demand_mshr_miss_rate 0.992381 # mshr miss rate for demand accesses -system.cpu.l2cache.demand_mshr_misses 521 # number of demand (read+write) MSHR misses +system.cpu.l2cache.demand_mshr_miss_latency 1196500 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.992337 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 518 # 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 525 # number of overall (read+write) accesses -system.cpu.l2cache.overall_avg_miss_latency 4314.779271 # average overall miss latency -system.cpu.l2cache.overall_avg_mshr_miss_latency 2314.779271 # average overall mshr miss latency +system.cpu.l2cache.overall_accesses 522 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 4309.845560 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 2309.845560 # 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 4 # number of overall hits -system.cpu.l2cache.overall_miss_latency 2248000 # number of overall miss cycles -system.cpu.l2cache.overall_miss_rate 0.992381 # miss rate for overall accesses -system.cpu.l2cache.overall_misses 521 # number of overall misses +system.cpu.l2cache.overall_miss_latency 2232500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.992337 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 518 # number of overall misses system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits -system.cpu.l2cache.overall_mshr_miss_latency 1206000 # number of overall MSHR miss cycles -system.cpu.l2cache.overall_mshr_miss_rate 0.992381 # mshr miss rate for overall accesses -system.cpu.l2cache.overall_mshr_misses 521 # number of overall MSHR misses +system.cpu.l2cache.overall_mshr_miss_latency 1196500 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.992337 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 518 # number of overall MSHR misses system.cpu.l2cache.overall_mshr_uncacheable_latency 0 # number of overall MSHR uncacheable cycles system.cpu.l2cache.overall_mshr_uncacheable_misses 0 # number of overall MSHR uncacheable misses system.cpu.l2cache.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache @@ -398,27 +398,27 @@ 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 416 # Sample count of references to valid blocks. +system.cpu.l2cache.sampled_refs 413 # 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 263.558349 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 259.708792 # Cycle average of tags in use system.cpu.l2cache.total_refs 4 # 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 29368 # number of cpu cycles simulated +system.cpu.numCycles 29898 # number of cpu cycles simulated system.cpu.rename.RENAME:CommittedMaps 9868 # Number of HB maps that are committed -system.cpu.rename.RENAME:IdleCycles 13747 # Number of cycles rename is idle -system.cpu.rename.RENAME:RenameLookups 51214 # Number of register rename lookups that rename has made -system.cpu.rename.RENAME:RenamedInsts 29558 # Number of instructions processed by rename -system.cpu.rename.RENAME:RenamedOperands 24111 # Number of destination operands rename has renamed -system.cpu.rename.RENAME:RunCycles 8739 # Number of cycles rename is running -system.cpu.rename.RENAME:SquashCycles 2866 # Number of cycles rename is squashing +system.cpu.rename.RENAME:IdleCycles 14192 # Number of cycles rename is idle +system.cpu.rename.RENAME:RenameLookups 51924 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 30001 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 24487 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 8874 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 2909 # Number of cycles rename is squashing system.cpu.rename.RENAME:UnblockCycles 230 # Number of cycles rename is unblocking -system.cpu.rename.RENAME:UndoneMaps 14243 # Number of HB maps that are undone due to squashing -system.cpu.rename.RENAME:serializeStallCycles 3786 # count of cycles rename stalled for serializing inst -system.cpu.rename.RENAME:serializingInsts 643 # count of serializing insts renamed -system.cpu.rename.RENAME:skidInsts 4459 # count of insts added to the skid buffer -system.cpu.rename.RENAME:tempSerializingInsts 681 # count of temporary serializing insts renamed -system.cpu.timesIdled 4 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.rename.RENAME:UndoneMaps 14619 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 3693 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 648 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 4472 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 685 # count of temporary serializing insts renamed +system.cpu.timesIdled 20 # Number of times that the entire CPU went into an idle state and unscheduled itself system.cpu.workload.PROG:num_syscalls 8 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/stdout b/tests/quick/02.insttest/ref/sparc/linux/o3-timing/stdout index 9ba201750..82d7a93ac 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/o3-timing/stdout +++ b/tests/quick/02.insttest/ref/sparc/linux/o3-timing/stdout @@ -16,9 +16,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 14 2007 00:08:15 -M5 started Tue Aug 14 00:08:28 2007 -M5 executing on zeep -command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/quick/02.insttest/sparc/linux/o3-timing tests/run.py quick/02.insttest/sparc/linux/o3-timing +M5 compiled Aug 19 2007 19:19:06 +M5 started Sun Aug 19 19:19:36 2007 +M5 executing on nacho +command line: build/SPARC_SE/m5.debug -d build/SPARC_SE/tests/debug/quick/02.insttest/sparc/linux/o3-timing tests/run.py quick/02.insttest/sparc/linux/o3-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 14690000 because target called exit() +Exiting @ tick 14990500 because target called exit() diff --git a/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/config.ini b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/config.ini index 5493b952f..f3afb96c0 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/config.ini +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -25,11 +27,23 @@ 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.dtb] +type=SparcDTB +size=64 + +[system.cpu.itb] +type=SparcITB +size=64 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=LiveProcess cmd=insttest @@ -37,7 +51,7 @@ cwd= egid=100 env= euid=100 -executable=tests/test-progs/insttest/bin/sparc/linux/insttest +executable=/dist/m5/regression/test-progs/insttest/bin/sparc/linux/insttest gid=100 input=cin output=cout @@ -53,7 +67,7 @@ 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/02.insttest/ref/sparc/linux/simple-atomic/m5stats.txt b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/m5stats.txt index 468b3f0a1..9a14dd885 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/m5stats.txt +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/m5stats.txt @@ -1,18 +1,18 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 563720 # Simulator instruction rate (inst/s) -host_mem_usage 149048 # Number of bytes of host memory used +host_inst_rate 464357 # Simulator instruction rate (inst/s) +host_mem_usage 173536 # Number of bytes of host memory used host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 276035132 # Simulator tick rate (ticks/s) +host_tick_rate 229778722 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 11001 # Number of instructions simulated -sim_seconds 0.000005 # Number of seconds simulated -sim_ticks 5500000 # Number of ticks simulated +sim_insts 10976 # Number of instructions simulated +sim_seconds 0.000006 # Number of seconds simulated +sim_ticks 5514000 # Number of ticks simulated system.cpu.idle_fraction 0 # Percentage of idle cycles system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 11001 # number of cpu cycles simulated -system.cpu.num_insts 11001 # Number of instructions executed -system.cpu.num_refs 2760 # Number of memory references +system.cpu.numCycles 11029 # number of cpu cycles simulated +system.cpu.num_insts 10976 # Number of instructions executed +system.cpu.num_refs 2770 # Number of memory references system.cpu.workload.PROG:num_syscalls 8 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/stdout b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/stdout index 01c59e833..1641f2696 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/stdout +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-atomic/stdout @@ -16,9 +16,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled May 15 2007 13:02:31 -M5 started Tue May 15 17:00:07 2007 -M5 executing on zizzer.eecs.umich.edu +M5 compiled Aug 14 2007 22:08:21 +M5 started Tue Aug 14 22:08:25 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/quick/02.insttest/sparc/linux/simple-atomic tests/run.py quick/02.insttest/sparc/linux/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 5500000 because target called exit() +Exiting @ tick 5514000 because target called exit() diff --git a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/config.ini b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/config.ini index b2e950872..85d4c9288 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/config.ini +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=0 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=SparcDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=SparcITB +size=64 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/m5stats.txt b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/m5stats.txt index 351d5ef89..4a899f629 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/m5stats.txt +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 459524 # Simulator instruction rate (inst/s) -host_mem_usage 197560 # Number of bytes of host memory used -host_seconds 0.02 # Real time elapsed on the host -host_tick_rate 1004580342 # Simulator tick rate (ticks/s) +host_inst_rate 343655 # Simulator instruction rate (inst/s) +host_mem_usage 180816 # Number of bytes of host memory used +host_seconds 0.03 # Real time elapsed on the host +host_tick_rate 753768067 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 11001 # Number of instructions simulated +sim_insts 10976 # Number of instructions simulated sim_seconds 0.000024 # Number of seconds simulated -sim_ticks 24345000 # Number of ticks simulated +sim_ticks 24355000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 1462 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -78,53 +78,53 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 142 # 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 100.391376 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 100.373888 # Cycle average of tags in use system.cpu.dcache.total_refs 2618 # 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 11002 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_accesses 11012 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 24915.194346 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 22915.194346 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 10719 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 10729 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 7051000 # number of ReadReq miss cycles -system.cpu.icache.ReadReq_miss_rate 0.025723 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_miss_rate 0.025699 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 283 # number of ReadReq misses system.cpu.icache.ReadReq_mshr_miss_latency 6485000 # number of ReadReq MSHR miss cycles -system.cpu.icache.ReadReq_mshr_miss_rate 0.025723 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_miss_rate 0.025699 # mshr miss rate for ReadReq accesses system.cpu.icache.ReadReq_mshr_misses 283 # 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 37.876325 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 37.911661 # 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 11002 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 11012 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 24915.194346 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 22915.194346 # average overall mshr miss latency -system.cpu.icache.demand_hits 10719 # number of demand (read+write) hits +system.cpu.icache.demand_hits 10729 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 7051000 # number of demand (read+write) miss cycles -system.cpu.icache.demand_miss_rate 0.025723 # miss rate for demand accesses +system.cpu.icache.demand_miss_rate 0.025699 # miss rate for demand accesses system.cpu.icache.demand_misses 283 # 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 6485000 # number of demand (read+write) MSHR miss cycles -system.cpu.icache.demand_mshr_miss_rate 0.025723 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_miss_rate 0.025699 # mshr miss rate for demand accesses system.cpu.icache.demand_mshr_misses 283 # 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 11002 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 11012 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 24915.194346 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 22915.194346 # 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 10719 # number of overall hits +system.cpu.icache.overall_hits 10729 # number of overall hits system.cpu.icache.overall_miss_latency 7051000 # number of overall miss cycles -system.cpu.icache.overall_miss_rate 0.025723 # miss rate for overall accesses +system.cpu.icache.overall_miss_rate 0.025699 # miss rate for overall accesses system.cpu.icache.overall_misses 283 # number of overall misses system.cpu.icache.overall_mshr_hits 0 # number of overall MSHR hits system.cpu.icache.overall_mshr_miss_latency 6485000 # number of overall MSHR miss cycles -system.cpu.icache.overall_mshr_miss_rate 0.025723 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_miss_rate 0.025699 # mshr miss rate for overall accesses system.cpu.icache.overall_mshr_misses 283 # 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 @@ -140,8 +140,8 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 283 # 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 156.007276 # Cycle average of tags in use -system.cpu.icache.total_refs 10719 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 155.977710 # Cycle average of tags in use +system.cpu.icache.total_refs 10729 # 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 @@ -221,14 +221,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 318 # 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 178.142170 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 178.108320 # 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 24345000 # number of cpu cycles simulated -system.cpu.num_insts 11001 # Number of instructions executed -system.cpu.num_refs 2760 # Number of memory references +system.cpu.numCycles 24355000 # number of cpu cycles simulated +system.cpu.num_insts 10976 # Number of instructions executed +system.cpu.num_refs 2770 # Number of memory references system.cpu.workload.PROG:num_syscalls 8 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/stdout b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/stdout index e268ba0c6..838fa7706 100644 --- a/tests/quick/02.insttest/ref/sparc/linux/simple-timing/stdout +++ b/tests/quick/02.insttest/ref/sparc/linux/simple-timing/stdout @@ -16,9 +16,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 14 2007 00:08:15 -M5 started Tue Aug 14 00:08:29 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 22:08:21 +M5 started Tue Aug 14 22:08:25 2007 +M5 executing on nacho command line: build/SPARC_SE/m5.fast -d build/SPARC_SE/tests/fast/quick/02.insttest/sparc/linux/simple-timing tests/run.py quick/02.insttest/sparc/linux/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 24345000 because target called exit() +Exiting @ tick 24355000 because target called exit() diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/m5stats.txt b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/m5stats.txt index d9ba4afe5..eabfb44c3 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/m5stats.txt +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/m5stats.txt @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 2271343 # Simulator instruction rate (inst/s) -host_mem_usage 326380 # Number of bytes of host memory used -host_seconds 27.79 # Real time elapsed on the host -host_tick_rate 67296173797 # Simulator tick rate (ticks/s) +host_inst_rate 2322076 # Simulator instruction rate (inst/s) +host_mem_usage 309268 # Number of bytes of host memory used +host_seconds 27.18 # Real time elapsed on the host +host_tick_rate 68811889767 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 63125943 # Number of instructions simulated +sim_insts 63114079 # Number of instructions simulated sim_seconds 1.870335 # Number of seconds simulated sim_ticks 1870335101500 # Number of ticks simulated system.cpu0.dcache.LoadLockedReq_accesses 188283 # number of LoadLockedReq accesses(hits+misses) @@ -240,7 +240,7 @@ system.cpu0.kern.syscall_144 2 0.88% 99.12% # nu system.cpu0.kern.syscall_147 2 0.88% 100.00% # number of syscalls executed system.cpu0.not_idle_fraction 0.015290 # Percentage of non-idle cycles system.cpu0.numCycles 57193784 # number of cpu cycles simulated -system.cpu0.num_insts 57190172 # Number of instructions executed +system.cpu0.num_insts 57182116 # Number of instructions executed system.cpu0.num_refs 15322419 # Number of memory references system.cpu1.dcache.LoadLockedReq_accesses 16418 # number of LoadLockedReq accesses(hits+misses) system.cpu1.dcache.LoadLockedReq_hits 15129 # number of LoadLockedReq hits @@ -457,7 +457,7 @@ system.cpu1.kern.syscall_90 1 1.00% 98.00% # nu system.cpu1.kern.syscall_132 2 2.00% 100.00% # number of syscalls executed system.cpu1.not_idle_fraction 0.001587 # Percentage of non-idle cycles system.cpu1.numCycles 5937367 # number of cpu cycles simulated -system.cpu1.num_insts 5935771 # Number of instructions executed +system.cpu1.num_insts 5931963 # Number of instructions executed system.cpu1.num_refs 1926645 # Number of memory references system.disk0.dma_read_bytes 1024 # Number of bytes transfered via DMA reads (not PRD). system.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/stdout b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/stdout index b97e23c2a..007c73bfe 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/stdout +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 10 2007 16:03:34 -M5 started Fri Aug 10 16:04:07 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 18:18:39 +M5 started Tue Aug 14 18:19:09 2007 +M5 executing on nacho command line: build/ALPHA_FS/m5.fast -d build/ALPHA_FS/tests/fast/quick/10.linux-boot/alpha/linux/tsunami-simple-atomic-dual tests/run.py quick/10.linux-boot/alpha/linux/tsunami-simple-atomic-dual Global frequency set at 1000000000000 ticks per second Exiting @ tick 1870335101500 because m5_exit instruction encountered diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/m5stats.txt b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/m5stats.txt index a4dd50e83..73b22dfec 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/m5stats.txt +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/m5stats.txt @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 2322212 # Simulator instruction rate (inst/s) -host_mem_usage 325356 # Number of bytes of host memory used -host_seconds 25.84 # Real time elapsed on the host -host_tick_rate 70754225205 # Simulator tick rate (ticks/s) +host_inst_rate 2191272 # Simulator instruction rate (inst/s) +host_mem_usage 308228 # Number of bytes of host memory used +host_seconds 27.38 # Real time elapsed on the host +host_tick_rate 66777888282 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 60007317 # Number of instructions simulated +sim_insts 59995479 # Number of instructions simulated sim_seconds 1.828355 # Number of seconds simulated sim_ticks 1828355476000 # Number of ticks simulated system.cpu.dcache.LoadLockedReq_accesses 200279 # number of LoadLockedReq accesses(hits+misses) @@ -235,7 +235,7 @@ system.cpu.kern.syscall_144 2 0.61% 99.39% # nu system.cpu.kern.syscall_147 2 0.61% 100.00% # number of syscalls executed system.cpu.not_idle_fraction 0.016412 # Percentage of non-idle cycles system.cpu.numCycles 60012507 # number of cpu cycles simulated -system.cpu.num_insts 60007317 # Number of instructions executed +system.cpu.num_insts 59995479 # Number of instructions executed system.cpu.num_refs 16302129 # Number of memory references system.disk0.dma_read_bytes 1024 # Number of bytes transfered via DMA reads (not PRD). system.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/stdout b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/stdout index 00122ad9f..45d7ecef6 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/stdout +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 10 2007 16:03:34 -M5 started Fri Aug 10 16:03:39 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 18:18:39 +M5 started Tue Aug 14 18:18:41 2007 +M5 executing on nacho command line: build/ALPHA_FS/m5.fast -d build/ALPHA_FS/tests/fast/quick/10.linux-boot/alpha/linux/tsunami-simple-atomic tests/run.py quick/10.linux-boot/alpha/linux/tsunami-simple-atomic Global frequency set at 1000000000000 ticks per second Exiting @ tick 1828355476000 because m5_exit instruction encountered diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/m5stats.txt b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/m5stats.txt index 69eddfa1f..8b29b06d6 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/m5stats.txt +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/m5stats.txt @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1168071 # Simulator instruction rate (inst/s) -host_mem_usage 295844 # Number of bytes of host memory used -host_seconds 55.50 # Real time elapsed on the host -host_tick_rate 35475030756 # Simulator tick rate (ticks/s) +host_inst_rate 979093 # Simulator instruction rate (inst/s) +host_mem_usage 278732 # Number of bytes of host memory used +host_seconds 66.19 # Real time elapsed on the host +host_tick_rate 29741162851 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 64822650 # Number of instructions simulated +sim_insts 64810685 # Number of instructions simulated sim_seconds 1.968714 # Number of seconds simulated sim_ticks 1968713509000 # Number of ticks simulated system.cpu0.dcache.LoadLockedReq_accesses 151114 # number of LoadLockedReq accesses(hits+misses) @@ -274,7 +274,7 @@ system.cpu0.kern.syscall_144 1 0.47% 99.06% # nu system.cpu0.kern.syscall_147 2 0.94% 100.00% # number of syscalls executed system.cpu0.not_idle_fraction 0.057929 # Percentage of non-idle cycles system.cpu0.numCycles 1967810461000 # number of cpu cycles simulated -system.cpu0.num_insts 50999228 # Number of instructions executed +system.cpu0.num_insts 50990937 # Number of instructions executed system.cpu0.num_refs 13220047 # Number of memory references system.cpu1.dcache.LoadLockedReq_accesses 60083 # number of LoadLockedReq accesses(hits+misses) system.cpu1.dcache.LoadLockedReq_avg_miss_latency 15361.860059 # average LoadLockedReq miss latency @@ -529,7 +529,7 @@ system.cpu1.kern.syscall_132 2 1.75% 99.12% # nu system.cpu1.kern.syscall_144 1 0.88% 100.00% # number of syscalls executed system.cpu1.not_idle_fraction 0.013720 # Percentage of non-idle cycles system.cpu1.numCycles 1968713509000 # number of cpu cycles simulated -system.cpu1.num_insts 13823422 # Number of instructions executed +system.cpu1.num_insts 13819748 # Number of instructions executed system.cpu1.num_refs 4429865 # Number of memory references system.disk0.dma_read_bytes 1024 # Number of bytes transfered via DMA reads (not PRD). system.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/stdout b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/stdout index 92c2ca4fd..6f89d18ec 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/stdout +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:31:07 -M5 started Sun Aug 12 00:33:04 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 18:18:39 +M5 started Tue Aug 14 18:20:39 2007 +M5 executing on nacho command line: build/ALPHA_FS/m5.fast -d build/ALPHA_FS/tests/fast/quick/10.linux-boot/alpha/linux/tsunami-simple-timing-dual tests/run.py quick/10.linux-boot/alpha/linux/tsunami-simple-timing-dual Global frequency set at 1000000000000 ticks per second Exiting @ tick 1968713509000 because m5_exit instruction encountered diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/m5stats.txt b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/m5stats.txt index 677926722..8aeb586fd 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/m5stats.txt +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/m5stats.txt @@ -1,11 +1,11 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1148695 # Simulator instruction rate (inst/s) -host_mem_usage 285372 # Number of bytes of host memory used -host_seconds 52.29 # Real time elapsed on the host -host_tick_rate 36880663274 # Simulator tick rate (ticks/s) +host_inst_rate 986602 # Simulator instruction rate (inst/s) +host_mem_usage 268252 # Number of bytes of host memory used +host_seconds 60.87 # Real time elapsed on the host +host_tick_rate 31682591808 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 60069471 # Number of instructions simulated +sim_insts 60057633 # Number of instructions simulated sim_seconds 1.928634 # Number of seconds simulated sim_ticks 1928634086000 # Number of ticks simulated system.cpu.dcache.LoadLockedReq_accesses 200253 # number of LoadLockedReq accesses(hits+misses) @@ -269,7 +269,7 @@ system.cpu.kern.syscall_144 2 0.61% 99.39% # nu system.cpu.kern.syscall_147 2 0.61% 100.00% # number of syscalls executed system.cpu.not_idle_fraction 0.069379 # Percentage of non-idle cycles system.cpu.numCycles 1928634086000 # number of cpu cycles simulated -system.cpu.num_insts 60069471 # Number of instructions executed +system.cpu.num_insts 60057633 # Number of instructions executed system.cpu.num_refs 16313038 # Number of memory references system.disk0.dma_read_bytes 1024 # Number of bytes transfered via DMA reads (not PRD). system.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). diff --git a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/stdout b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/stdout index 2743905fa..73f1f9652 100644 --- a/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/stdout +++ b/tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 12 2007 00:31:07 -M5 started Sun Aug 12 00:32:11 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 18:18:39 +M5 started Tue Aug 14 18:19:37 2007 +M5 executing on nacho command line: build/ALPHA_FS/m5.fast -d build/ALPHA_FS/tests/fast/quick/10.linux-boot/alpha/linux/tsunami-simple-timing tests/run.py quick/10.linux-boot/alpha/linux/tsunami-simple-timing Global frequency set at 1000000000000 ticks per second Exiting @ tick 1928634086000 because m5_exit instruction encountered diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini index a89c6ef26..9db92d8dc 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=AtomicSimpleCPU -children=workload +children=dtb itb tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=500000 max_loads_all_threads=0 @@ -25,15 +27,27 @@ 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.dtb] +type=AlphaDTB +size=64 + +[system.cpu.itb] +type=AlphaITB +size=48 + +[system.cpu.tracer] +type=ExeTracer + [system.cpu.workload] type=EioProcess chkpt= -file=tests/test-progs/anagram/bin/alpha/eio/anagram-vshort.eio.gz +file=/dist/m5/regression/test-progs/anagram/bin/alpha/eio/anagram-vshort.eio.gz output=cout system=system diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt index 5747db5c2..a82f45966 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/m5stats.txt @@ -1,17 +1,34 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 188118 # Simulator instruction rate (inst/s) -host_seconds 2.66 # Real time elapsed on the host -host_tick_rate 94046824 # Simulator tick rate (ticks/s) +host_inst_rate 2121237 # Simulator instruction rate (inst/s) +host_mem_usage 171724 # Number of bytes of host memory used +host_seconds 0.24 # Real time elapsed on the host +host_tick_rate 1058992833 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 500000 # Number of instructions simulated +sim_insts 500001 # Number of instructions simulated sim_seconds 0.000250 # Number of seconds simulated -sim_ticks 249999500 # Number of ticks simulated +sim_ticks 250015500 # Number of ticks simulated +system.cpu.dtb.accesses 180793 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 180775 # DTB hits +system.cpu.dtb.misses 18 # DTB misses +system.cpu.dtb.read_accesses 124443 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 124435 # DTB read hits +system.cpu.dtb.read_misses 8 # DTB read misses +system.cpu.dtb.write_accesses 56350 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 56340 # DTB write hits +system.cpu.dtb.write_misses 10 # DTB write misses system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 500032 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 500019 # ITB hits +system.cpu.itb.misses 13 # ITB misses system.cpu.not_idle_fraction 1 # Percentage of non-idle cycles -system.cpu.numCycles 500000 # number of cpu cycles simulated -system.cpu.num_insts 500000 # Number of instructions executed -system.cpu.num_refs 182204 # Number of memory references +system.cpu.numCycles 500032 # number of cpu cycles simulated +system.cpu.num_insts 500001 # Number of instructions executed +system.cpu.num_refs 182222 # Number of memory references system.cpu.workload.PROG:num_syscalls 18 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout index 01450bbce..fee99ba99 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/stdout @@ -7,9 +7,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Jun 10 2007 14:06:20 -M5 started Sun Jun 10 14:22:41 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/20.eio-short/alpha/eio/simple-atomic tests/run.py quick/20.eio-short/alpha/eio/simple-atomic +M5 compiled Aug 14 2007 17:58:14 +M5 started Tue Aug 14 17:58:32 2007 +M5 executing on nacho +command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/20.eio-short/alpha/eio/simple-atomic tests/run.py quick/20.eio-short/alpha/eio/simple-atomic Global frequency set at 1000000000000 ticks per second -Exiting @ tick 249999500 because a thread reached the max instruction count +Exiting @ tick 250015500 because a thread reached the max instruction count diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini index aa9f81e79..f967fc1b8 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini @@ -11,12 +11,14 @@ physmem=system.physmem [system.cpu] type=TimingSimpleCPU -children=dcache icache l2cache toL2Bus tracer workload +children=dcache dtb icache itb l2cache toL2Bus tracer workload clock=500 cpu_id=0 defer_registration=false +dtb=system.cpu.dtb function_trace=false function_trace_start=0 +itb=system.cpu.itb max_insts_all_threads=0 max_insts_any_thread=500000 max_loads_all_threads=0 @@ -65,6 +67,10 @@ write_buffers=8 cpu_side=system.cpu.dcache_port mem_side=system.cpu.toL2Bus.port[1] +[system.cpu.dtb] +type=AlphaDTB +size=64 + [system.cpu.icache] type=BaseCache addr_range=0:18446744073709551615 @@ -101,6 +107,10 @@ write_buffers=8 cpu_side=system.cpu.icache_port mem_side=system.cpu.toL2Bus.port[0] +[system.cpu.itb] +type=AlphaITB +size=48 + [system.cpu.l2cache] type=BaseCache addr_range=0:18446744073709551615 diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt index d9f2463fd..62a259095 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/m5stats.txt @@ -1,13 +1,13 @@ ---------- Begin Simulation Statistics ---------- -host_inst_rate 1380632 # Simulator instruction rate (inst/s) -host_mem_usage 195668 # Number of bytes of host memory used -host_seconds 0.36 # Real time elapsed on the host -host_tick_rate 1946559093 # Simulator tick rate (ticks/s) +host_inst_rate 1285667 # Simulator instruction rate (inst/s) +host_mem_usage 179016 # Number of bytes of host memory used +host_seconds 0.39 # Real time elapsed on the host +host_tick_rate 1812257249 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 500000 # Number of instructions simulated +sim_insts 500001 # Number of instructions simulated sim_seconds 0.000705 # Number of seconds simulated -sim_ticks 705470000 # Number of ticks simulated +sim_ticks 705490000 # Number of ticks simulated system.cpu.dcache.ReadReq_accesses 124435 # number of ReadReq accesses(hits+misses) system.cpu.dcache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.dcache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency @@ -76,14 +76,26 @@ system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.dcache.replacements 0 # number of replacements system.cpu.dcache.sampled_refs 454 # 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 289.564356 # Cycle average of tags in use +system.cpu.dcache.tagsinuse 289.561085 # Cycle average of tags in use system.cpu.dcache.total_refs 180321 # 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 500000 # number of ReadReq accesses(hits+misses) +system.cpu.dtb.accesses 180793 # DTB accesses +system.cpu.dtb.acv 0 # DTB access violations +system.cpu.dtb.hits 180775 # DTB hits +system.cpu.dtb.misses 18 # DTB misses +system.cpu.dtb.read_accesses 124443 # DTB read accesses +system.cpu.dtb.read_acv 0 # DTB read access violations +system.cpu.dtb.read_hits 124435 # DTB read hits +system.cpu.dtb.read_misses 8 # DTB read misses +system.cpu.dtb.write_accesses 56350 # DTB write accesses +system.cpu.dtb.write_acv 0 # DTB write access violations +system.cpu.dtb.write_hits 56340 # DTB write hits +system.cpu.dtb.write_misses 10 # DTB write misses +system.cpu.icache.ReadReq_accesses 500020 # number of ReadReq accesses(hits+misses) system.cpu.icache.ReadReq_avg_miss_latency 25000 # average ReadReq miss latency system.cpu.icache.ReadReq_avg_mshr_miss_latency 23000 # average ReadReq mshr miss latency -system.cpu.icache.ReadReq_hits 499597 # number of ReadReq hits +system.cpu.icache.ReadReq_hits 499617 # number of ReadReq hits system.cpu.icache.ReadReq_miss_latency 10075000 # number of ReadReq miss cycles system.cpu.icache.ReadReq_miss_rate 0.000806 # miss rate for ReadReq accesses system.cpu.icache.ReadReq_misses 403 # number of ReadReq misses @@ -92,16 +104,16 @@ system.cpu.icache.ReadReq_mshr_miss_rate 0.000806 # ms system.cpu.icache.ReadReq_mshr_misses 403 # 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 1239.694789 # Average number of references to valid blocks. +system.cpu.icache.avg_refs 1239.744417 # 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 500000 # number of demand (read+write) accesses +system.cpu.icache.demand_accesses 500020 # number of demand (read+write) accesses system.cpu.icache.demand_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.demand_avg_mshr_miss_latency 23000 # average overall mshr miss latency -system.cpu.icache.demand_hits 499597 # number of demand (read+write) hits +system.cpu.icache.demand_hits 499617 # number of demand (read+write) hits system.cpu.icache.demand_miss_latency 10075000 # number of demand (read+write) miss cycles system.cpu.icache.demand_miss_rate 0.000806 # miss rate for demand accesses system.cpu.icache.demand_misses 403 # number of demand (read+write) misses @@ -112,11 +124,11 @@ system.cpu.icache.demand_mshr_misses 403 # nu 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 500000 # number of overall (read+write) accesses +system.cpu.icache.overall_accesses 500020 # number of overall (read+write) accesses system.cpu.icache.overall_avg_miss_latency 25000 # average overall miss latency system.cpu.icache.overall_avg_mshr_miss_latency 23000 # average overall mshr miss latency system.cpu.icache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency -system.cpu.icache.overall_hits 499597 # number of overall hits +system.cpu.icache.overall_hits 499617 # number of overall hits system.cpu.icache.overall_miss_latency 10075000 # number of overall miss cycles system.cpu.icache.overall_miss_rate 0.000806 # miss rate for overall accesses system.cpu.icache.overall_misses 403 # number of overall misses @@ -138,11 +150,15 @@ system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.icache.replacements 0 # number of replacements system.cpu.icache.sampled_refs 403 # 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 266.632904 # Cycle average of tags in use -system.cpu.icache.total_refs 499597 # Total number of references to valid blocks. +system.cpu.icache.tagsinuse 266.630553 # Cycle average of tags in use +system.cpu.icache.total_refs 499617 # Total number of references to valid blocks. system.cpu.icache.warmup_cycle 0 # Cycle when the warmup percentage was hit. system.cpu.icache.writebacks 0 # number of writebacks system.cpu.idle_fraction 0 # Percentage of idle cycles +system.cpu.itb.accesses 500033 # ITB accesses +system.cpu.itb.acv 0 # ITB acv +system.cpu.itb.hits 500020 # ITB hits +system.cpu.itb.misses 13 # ITB misses system.cpu.l2cache.ReadExReq_accesses 139 # number of ReadExReq accesses(hits+misses) system.cpu.l2cache.ReadExReq_avg_miss_latency 22000 # average ReadExReq miss latency system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 11000 # average ReadExReq mshr miss latency @@ -218,14 +234,14 @@ system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 system.cpu.l2cache.replacements 0 # number of replacements system.cpu.l2cache.sampled_refs 546 # 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 373.548776 # Cycle average of tags in use +system.cpu.l2cache.tagsinuse 373.545251 # 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 705470000 # number of cpu cycles simulated -system.cpu.num_insts 500000 # Number of instructions executed -system.cpu.num_refs 182203 # Number of memory references +system.cpu.numCycles 705490000 # number of cpu cycles simulated +system.cpu.num_insts 500001 # Number of instructions executed +system.cpu.num_refs 182222 # Number of memory references system.cpu.workload.PROG:num_syscalls 18 # Number of system calls ---------- End Simulation Statistics ---------- diff --git a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout index c055fe4ae..0de340a66 100644 --- a/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout +++ b/tests/quick/20.eio-short/ref/alpha/eio/simple-timing/stdout @@ -7,9 +7,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 14 2007 13:54:58 -M5 started Tue Aug 14 13:57:54 2007 -M5 executing on zeep +M5 compiled Aug 14 2007 17:58:14 +M5 started Tue Aug 14 17:58:16 2007 +M5 executing on nacho command line: build/ALPHA_SE/m5.fast -d build/ALPHA_SE/tests/fast/quick/20.eio-short/alpha/eio/simple-timing tests/run.py quick/20.eio-short/alpha/eio/simple-timing Global frequency set at 1000000000000 ticks per second -Exiting @ tick 705470000 because a thread reached the max instruction count +Exiting @ tick 705490000 because a thread reached the max instruction count diff --git a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini index 3385f4fea..e39fb749f 100644 --- a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini +++ b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini @@ -14,7 +14,7 @@ kernel=/dist/m5/system/binaries/vmlinux mem_mode=atomic pal=/dist/m5/system/binaries/ts_osfpal physmem=drivesys.physmem -readfile=/z/saidi/work/m5.bb/configs/boot/netperf-server.rcS +readfile=/home/blackga/m5/repos/m5/configs/boot/netperf-server.rcS symbolfile= system_rev=1024 system_type=34 @@ -179,7 +179,7 @@ read_only=true [drivesys.tsunami] type=Tsunami -children=cchip console etherint ethernet fake_OROM fake_ata0 fake_ata1 fake_pnp_addr fake_pnp_read0 fake_pnp_read1 fake_pnp_read2 fake_pnp_read3 fake_pnp_read4 fake_pnp_read5 fake_pnp_read6 fake_pnp_read7 fake_pnp_write fake_ppc fake_sm_chip fake_uart1 fake_uart2 fake_uart3 fake_uart4 fb ide io pchip pciconfig uart +children=cchip console ethernet fake_OROM fake_ata0 fake_ata1 fake_pnp_addr fake_pnp_read0 fake_pnp_read1 fake_pnp_read2 fake_pnp_read3 fake_pnp_read4 fake_pnp_read5 fake_pnp_read6 fake_pnp_read7 fake_pnp_write fake_ppc fake_sm_chip fake_uart1 fake_uart2 fake_uart3 fake_uart4 fb ide io pchip pciconfig uart intrctrl=drivesys.intrctrl system=drivesys @@ -203,48 +203,8 @@ sim_console=drivesys.sim_console system=drivesys pio=drivesys.iobus.port[25] -[drivesys.tsunami.etherint] -type=NSGigEInt -device=drivesys.tsunami.ethernet -peer=Null - [drivesys.tsunami.ethernet] type=NSGigE -children=configdata -clock=0 -config_latency=20000 -configdata=drivesys.tsunami.ethernet.configdata -dma_data_free=false -dma_desc_free=false -dma_no_allocate=true -dma_read_delay=0 -dma_read_factor=0 -dma_write_delay=0 -dma_write_factor=0 -hardware_address=00:90:00:00:00:01 -intr_delay=10000000 -max_backoff_delay=10000000 -min_backoff_delay=4000 -pci_bus=0 -pci_dev=1 -pci_func=0 -pio_latency=1000 -platform=drivesys.tsunami -rss=false -rx_delay=1000000 -rx_fifo_size=524288 -rx_filter=true -rx_thread=false -system=drivesys -tx_delay=1000000 -tx_fifo_size=524288 -tx_thread=false -config=drivesys.iobus.port[28] -dma=drivesys.iobus.port[29] -pio=drivesys.iobus.port[27] - -[drivesys.tsunami.ethernet.configdata] -type=PciConfigData BAR0=1 BAR0Size=256 BAR1=0 @@ -277,6 +237,37 @@ SubClassCode=0 SubsystemID=0 SubsystemVendorID=0 VendorID=4107 +clock=0 +config_latency=20000 +dma_data_free=false +dma_desc_free=false +dma_no_allocate=true +dma_read_delay=0 +dma_read_factor=0 +dma_write_delay=0 +dma_write_factor=0 +hardware_address=00:90:00:00:00:01 +intr_delay=10000000 +max_backoff_delay=10000000 +min_backoff_delay=4000 +pci_bus=0 +pci_dev=1 +pci_func=0 +pio_latency=1000 +platform=drivesys.tsunami +rss=false +rx_delay=1000000 +rx_fifo_size=524288 +rx_filter=true +rx_thread=false +system=drivesys +tx_delay=1000000 +tx_fifo_size=524288 +tx_thread=false +config=drivesys.iobus.port[28] +dma=drivesys.iobus.port[29] +interface=etherlink.int1 +pio=drivesys.iobus.port[27] [drivesys.tsunami.fake_OROM] type=IsaFake @@ -593,24 +584,6 @@ pio=drivesys.iobus.port[22] [drivesys.tsunami.ide] type=IdeController -children=configdata -config_latency=20000 -configdata=drivesys.tsunami.ide.configdata -disks=drivesys.disk0 drivesys.disk2 -max_backoff_delay=10000000 -min_backoff_delay=4000 -pci_bus=0 -pci_dev=0 -pci_func=0 -pio_latency=1000 -platform=drivesys.tsunami -system=drivesys -config=drivesys.iobus.port[30] -dma=drivesys.iobus.port[31] -pio=drivesys.iobus.port[26] - -[drivesys.tsunami.ide.configdata] -type=PciConfigData BAR0=1 BAR0Size=8 BAR1=1 @@ -643,6 +616,19 @@ SubClassCode=1 SubsystemID=0 SubsystemVendorID=0 VendorID=32902 +config_latency=20000 +disks=drivesys.disk0 drivesys.disk2 +max_backoff_delay=10000000 +min_backoff_delay=4000 +pci_bus=0 +pci_dev=0 +pci_func=0 +pio_latency=1000 +platform=drivesys.tsunami +system=drivesys +config=drivesys.iobus.port[30] +dma=drivesys.iobus.port[31] +pio=drivesys.iobus.port[26] [drivesys.tsunami.io] type=TsunamiIO @@ -693,9 +679,9 @@ type=EtherLink delay=0 delay_var=0 dump=etherdump -int1=testsys.tsunami.etherint -int2=drivesys.tsunami.etherint speed=8000.000000 +int0=testsys.tsunami.ethernet.interface +int1=drivesys.tsunami.ethernet.interface [testsys] type=LinuxAlphaSystem @@ -708,7 +694,7 @@ kernel=/dist/m5/system/binaries/vmlinux mem_mode=atomic pal=/dist/m5/system/binaries/ts_osfpal physmem=testsys.physmem -readfile=/z/saidi/work/m5.bb/configs/boot/netperf-stream-client.rcS +readfile=/home/blackga/m5/repos/m5/configs/boot/netperf-stream-client.rcS symbolfile= system_rev=1024 system_type=34 @@ -873,7 +859,7 @@ read_only=true [testsys.tsunami] type=Tsunami -children=cchip console etherint ethernet fake_OROM fake_ata0 fake_ata1 fake_pnp_addr fake_pnp_read0 fake_pnp_read1 fake_pnp_read2 fake_pnp_read3 fake_pnp_read4 fake_pnp_read5 fake_pnp_read6 fake_pnp_read7 fake_pnp_write fake_ppc fake_sm_chip fake_uart1 fake_uart2 fake_uart3 fake_uart4 fb ide io pchip pciconfig uart +children=cchip console ethernet fake_OROM fake_ata0 fake_ata1 fake_pnp_addr fake_pnp_read0 fake_pnp_read1 fake_pnp_read2 fake_pnp_read3 fake_pnp_read4 fake_pnp_read5 fake_pnp_read6 fake_pnp_read7 fake_pnp_write fake_ppc fake_sm_chip fake_uart1 fake_uart2 fake_uart3 fake_uart4 fb ide io pchip pciconfig uart intrctrl=testsys.intrctrl system=testsys @@ -897,48 +883,8 @@ sim_console=testsys.sim_console system=testsys pio=testsys.iobus.port[25] -[testsys.tsunami.etherint] -type=NSGigEInt -device=testsys.tsunami.ethernet -peer=Null - [testsys.tsunami.ethernet] type=NSGigE -children=configdata -clock=0 -config_latency=20000 -configdata=testsys.tsunami.ethernet.configdata -dma_data_free=false -dma_desc_free=false -dma_no_allocate=true -dma_read_delay=0 -dma_read_factor=0 -dma_write_delay=0 -dma_write_factor=0 -hardware_address=00:90:00:00:00:02 -intr_delay=10000000 -max_backoff_delay=10000000 -min_backoff_delay=4000 -pci_bus=0 -pci_dev=1 -pci_func=0 -pio_latency=1000 -platform=testsys.tsunami -rss=false -rx_delay=1000000 -rx_fifo_size=524288 -rx_filter=true -rx_thread=false -system=testsys -tx_delay=1000000 -tx_fifo_size=524288 -tx_thread=false -config=testsys.iobus.port[28] -dma=testsys.iobus.port[29] -pio=testsys.iobus.port[27] - -[testsys.tsunami.ethernet.configdata] -type=PciConfigData BAR0=1 BAR0Size=256 BAR1=0 @@ -971,6 +917,37 @@ SubClassCode=0 SubsystemID=0 SubsystemVendorID=0 VendorID=4107 +clock=0 +config_latency=20000 +dma_data_free=false +dma_desc_free=false +dma_no_allocate=true +dma_read_delay=0 +dma_read_factor=0 +dma_write_delay=0 +dma_write_factor=0 +hardware_address=00:90:00:00:00:02 +intr_delay=10000000 +max_backoff_delay=10000000 +min_backoff_delay=4000 +pci_bus=0 +pci_dev=1 +pci_func=0 +pio_latency=1000 +platform=testsys.tsunami +rss=false +rx_delay=1000000 +rx_fifo_size=524288 +rx_filter=true +rx_thread=false +system=testsys +tx_delay=1000000 +tx_fifo_size=524288 +tx_thread=false +config=testsys.iobus.port[28] +dma=testsys.iobus.port[29] +interface=etherlink.int0 +pio=testsys.iobus.port[27] [testsys.tsunami.fake_OROM] type=IsaFake @@ -1287,24 +1264,6 @@ pio=testsys.iobus.port[22] [testsys.tsunami.ide] type=IdeController -children=configdata -config_latency=20000 -configdata=testsys.tsunami.ide.configdata -disks=testsys.disk0 testsys.disk2 -max_backoff_delay=10000000 -min_backoff_delay=4000 -pci_bus=0 -pci_dev=0 -pci_func=0 -pio_latency=1000 -platform=testsys.tsunami -system=testsys -config=testsys.iobus.port[30] -dma=testsys.iobus.port[31] -pio=testsys.iobus.port[26] - -[testsys.tsunami.ide.configdata] -type=PciConfigData BAR0=1 BAR0Size=8 BAR1=1 @@ -1337,6 +1296,19 @@ SubClassCode=1 SubsystemID=0 SubsystemVendorID=0 VendorID=32902 +config_latency=20000 +disks=testsys.disk0 testsys.disk2 +max_backoff_delay=10000000 +min_backoff_delay=4000 +pci_bus=0 +pci_dev=0 +pci_func=0 +pio_latency=1000 +platform=testsys.tsunami +system=testsys +config=testsys.iobus.port[30] +dma=testsys.iobus.port[31] +pio=testsys.iobus.port[26] [testsys.tsunami.io] type=TsunamiIO diff --git a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt index c63520549..e80f9a2ec 100644 --- a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt +++ b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt @@ -77,7 +77,7 @@ drivesys.cpu.kern.syscall_118 2 9.09% 95.45% # nu drivesys.cpu.kern.syscall_150 1 4.55% 100.00% # number of syscalls executed drivesys.cpu.not_idle_fraction 0.000000 # Percentage of non-idle cycles drivesys.cpu.numCycles 1958954 # number of cpu cycles simulated -drivesys.cpu.num_insts 1958738 # Number of instructions executed +drivesys.cpu.num_insts 1958129 # Number of instructions executed drivesys.cpu.num_refs 626223 # Number of memory references drivesys.disk0.dma_read_bytes 0 # Number of bytes transfered via DMA reads (not PRD). drivesys.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). @@ -139,12 +139,12 @@ drivesys.tsunami.ethernet.txPPS 25 # Pa drivesys.tsunami.ethernet.txPackets 5 # Number of Packets Transmitted drivesys.tsunami.ethernet.txTcpChecksums 2 # Number of tx TCP Checksums done by device drivesys.tsunami.ethernet.txUdpChecksums 0 # Number of tx UDP Checksums done by device -host_inst_rate 109126509 # Simulator instruction rate (inst/s) -host_mem_usage 477016 # Number of bytes of host memory used -host_seconds 2.51 # Real time elapsed on the host -host_tick_rate 79838467246 # Simulator tick rate (ticks/s) +host_inst_rate 118863353 # Simulator instruction rate (inst/s) +host_mem_usage 459784 # Number of bytes of host memory used +host_seconds 2.30 # Real time elapsed on the host +host_tick_rate 86976188826 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 273348482 # Number of instructions simulated +sim_insts 273294782 # Number of instructions simulated sim_seconds 0.200001 # Number of seconds simulated sim_ticks 200000789468 # Number of ticks simulated testsys.cpu.dtb.accesses 335402 # DTB accesses @@ -234,7 +234,7 @@ testsys.cpu.kern.syscall_105 3 3.61% 97.59% # nu testsys.cpu.kern.syscall_118 2 2.41% 100.00% # number of syscalls executed testsys.cpu.not_idle_fraction 0.000001 # Percentage of non-idle cycles testsys.cpu.numCycles 3566060 # number of cpu cycles simulated -testsys.cpu.num_insts 3564494 # Number of instructions executed +testsys.cpu.num_insts 3560518 # Number of instructions executed testsys.cpu.num_refs 1173605 # Number of memory references testsys.disk0.dma_read_bytes 0 # Number of bytes transfered via DMA reads (not PRD). testsys.disk0.dma_read_full_pages 0 # Number of full page size DMA reads (not PRD). @@ -381,12 +381,12 @@ drivesys.tsunami.ethernet.totalSwi 0 # to drivesys.tsunami.ethernet.totalTxDesc 0 # total number of TxDesc written to ISR drivesys.tsunami.ethernet.totalTxIdle 0 # total number of TxIdle written to ISR drivesys.tsunami.ethernet.totalTxOk 0 # total number of TxOk written to ISR -host_inst_rate 139108642239 # Simulator instruction rate (inst/s) -host_mem_usage 477016 # Number of bytes of host memory used +host_inst_rate 116742751815 # Simulator instruction rate (inst/s) +host_mem_usage 459784 # Number of bytes of host memory used host_seconds 0.00 # Real time elapsed on the host -host_tick_rate 375168496 # Simulator tick rate (ticks/s) +host_tick_rate 317182405 # Simulator tick rate (ticks/s) sim_freq 1000000000000 # Frequency of simulated ticks -sim_insts 273348482 # Number of instructions simulated +sim_insts 273294782 # Number of instructions simulated sim_seconds 0.000001 # Number of seconds simulated sim_ticks 785978 # Number of ticks simulated testsys.cpu.dtb.accesses 0 # DTB accesses diff --git a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout index 345be7558..324ab7868 100644 --- a/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout +++ b/tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout @@ -5,9 +5,9 @@ The Regents of The University of Michigan All Rights Reserved -M5 compiled Aug 10 2007 16:03:34 -M5 started Fri Aug 10 16:06:35 2007 -M5 executing on zeep +M5 compiled Aug 21 2007 15:42:55 +M5 started Tue Aug 21 15:45:44 2007 +M5 executing on nacho command line: build/ALPHA_FS/m5.fast -d build/ALPHA_FS/tests/fast/quick/80.netperf-stream/alpha/linux/twosys-tsunami-simple-atomic tests/run.py quick/80.netperf-stream/alpha/linux/twosys-tsunami-simple-atomic Global frequency set at 1000000000000 ticks per second Exiting @ tick 4300235844056 because checkpoint |