441 lines
47 KiB
Text
441 lines
47 KiB
Text
|
|
---------- 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.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.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.
|
|
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
|
|
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_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.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%
|
|
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:membars 51356 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 569359656 # 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.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_hits 1286 # number of SwapReq hits
|
|
system.cpu.dcache.SwapReq_miss_latency 280500 # 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_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.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.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.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_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_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
|
|
system.cpu.dcache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.dcache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.dcache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.dcache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.dcache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
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.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.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist.samples 2199803710
|
|
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%
|
|
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_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_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.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.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_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_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.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_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_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_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_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
|
|
system.cpu.icache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.icache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.icache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.icache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.icache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
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.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.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.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: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.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.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.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.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 351441317 14.97% # Type of FU issued
|
|
IntAlu 1181231771 50.32% # 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
|
|
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
|
|
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_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
|
|
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
|
|
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
|
|
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.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%
|
|
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.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_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.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_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.Writeback_miss_rate 1 # miss rate for Writeback accesses
|
|
system.cpu.l2cache.Writeback_misses 346070 # 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.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.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_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.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_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_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_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
|
|
system.cpu.l2cache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.l2cache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.l2cache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.l2cache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.l2cache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
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 19390 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 20790 # 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.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.workload.PROG:num_syscalls 19 # Number of system calls
|
|
|
|
---------- End Simulation Statistics ----------
|