48d4ca522a
Somehow ending threads with halt() instead of deallocate() reduces the squash count on o3 by 1 (and a few other similarly trivial changes).
448 lines
47 KiB
Text
448 lines
47 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
host_inst_rate 188573 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 207604 # Number of bytes of host memory used
|
|
host_seconds 9206.20 # Real time elapsed on the host
|
|
host_tick_rate 80631433 # Simulator tick rate (ticks/s)
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 1736043781 # Number of instructions simulated
|
|
sim_seconds 0.742309 # Number of seconds simulated
|
|
sim_ticks 742309425500 # Number of ticks simulated
|
|
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
system.cpu.BPredUnit.BTBHits 312845737 # Number of BTB hits
|
|
system.cpu.BPredUnit.BTBLookups 319575559 # Number of BTB lookups
|
|
system.cpu.BPredUnit.RASInCorrect 136 # Number of incorrect RAS predictions.
|
|
system.cpu.BPredUnit.condIncorrect 19647325 # Number of conditional branches incorrect
|
|
system.cpu.BPredUnit.condPredicted 266741494 # Number of conditional branches predicted
|
|
system.cpu.BPredUnit.lookups 345502589 # Number of BP lookups
|
|
system.cpu.BPredUnit.usedRAS 23750300 # Number of times the RAS was used to get a target.
|
|
system.cpu.commit.COM:branches 214632552 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 62782585 # 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 1379215339
|
|
system.cpu.commit.COM:committed_per_cycle.min_value 0
|
|
0 736540831 5340.29%
|
|
1 260049504 1885.49%
|
|
2 126970462 920.60%
|
|
3 77723426 563.53%
|
|
4 51327439 372.15%
|
|
5 27759546 201.27%
|
|
6 26179568 189.81%
|
|
7 9881978 71.65%
|
|
8 62782585 455.21%
|
|
system.cpu.commit.COM:committed_per_cycle.max_value 8
|
|
system.cpu.commit.COM:committed_per_cycle.end_dist
|
|
|
|
system.cpu.commit.COM:count 1819780126 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 445666361 # Number of loads committed
|
|
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 19646824 # 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 627314235 # 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 0.855174 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 0.855174 # 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 38500 # average LoadLockedReq miss latency
|
|
system.cpu.dcache.LoadLockedReq_avg_mshr_miss_latency 35500 # average LoadLockedReq mshr miss latency
|
|
system.cpu.dcache.LoadLockedReq_hits 2 # number of LoadLockedReq hits
|
|
system.cpu.dcache.LoadLockedReq_miss_latency 38500 # 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 35500 # 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 523259964 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 16887.792500 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 11267.111116 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 512954316 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 174039645000 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.019695 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 10305648 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 3030509 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 81969799500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.013903 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 7275139 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 160728502 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 33917.187245 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 37153.824123 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 155297498 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 184204379594 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.033790 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 5431004 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 3182477 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 83541376693 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.013990 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 2248527 # number of WriteReq MSHR misses
|
|
system.cpu.dcache.avg_blocked_cycles_no_mshrs 6337.465393 # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_blocked_cycles_no_targets 31613.485382 # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_refs 73.053349 # Average number of references to valid blocks.
|
|
system.cpu.dcache.blocked_no_mshrs 156253 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_no_targets 65330 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_cycles_no_mshrs 990247980 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_cycles_no_targets 2065309000 # number of cycles access was blocked
|
|
system.cpu.dcache.cache_copies 0 # number of cache copies performed
|
|
system.cpu.dcache.demand_accesses 683988466 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 22764.945466 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 17378.935401 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 668251814 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 358244024594 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.023007 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 15736652 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 6212986 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 165511176193 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.013924 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 9523666 # 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 683988466 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 22764.945466 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 17378.935401 # 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 668251814 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 358244024594 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.023007 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 15736652 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 6212986 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 165511176193 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.013924 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 9523666 # 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.replacements 9155775 # number of replacements
|
|
system.cpu.dcache.sampled_refs 9159871 # 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 4079.315794 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 669159251 # Total number of references to valid blocks.
|
|
system.cpu.dcache.warmup_cycle 7089291000 # Cycle when the warmup percentage was hit.
|
|
system.cpu.dcache.writebacks 2245449 # number of writebacks
|
|
system.cpu.decode.DECODE:BlockedCycles 98604488 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:BranchMispred 553 # Number of times decode detected a branch misprediction
|
|
system.cpu.decode.DECODE:BranchResolved 54363606 # Number of times decode resolved a branch
|
|
system.cpu.decode.DECODE:DecodedInsts 2810650778 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 726334611 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 549143104 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 93084202 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:SquashedInsts 1641 # Number of squashed instructions handled by decode
|
|
system.cpu.decode.DECODE:UnblockCycles 5133136 # Number of cycles decode is unblocking
|
|
system.cpu.dtb.data_accesses 768331639 # DTB accesses
|
|
system.cpu.dtb.data_acv 0 # DTB access violations
|
|
system.cpu.dtb.data_hits 752318838 # DTB hits
|
|
system.cpu.dtb.data_misses 16012801 # DTB misses
|
|
system.cpu.dtb.fetch_accesses 0 # ITB accesses
|
|
system.cpu.dtb.fetch_acv 0 # ITB acv
|
|
system.cpu.dtb.fetch_hits 0 # ITB hits
|
|
system.cpu.dtb.fetch_misses 0 # ITB misses
|
|
system.cpu.dtb.read_accesses 566617551 # DTB read accesses
|
|
system.cpu.dtb.read_acv 0 # DTB read access violations
|
|
system.cpu.dtb.read_hits 557381525 # DTB read hits
|
|
system.cpu.dtb.read_misses 9236026 # DTB read misses
|
|
system.cpu.dtb.write_accesses 201714088 # DTB write accesses
|
|
system.cpu.dtb.write_acv 0 # DTB write access violations
|
|
system.cpu.dtb.write_hits 194937313 # DTB write hits
|
|
system.cpu.dtb.write_misses 6776775 # DTB write misses
|
|
system.cpu.fetch.Branches 345502589 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 355180518 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 920206770 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 7941781 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 2863046502 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 28103165 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.232721 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 355180518 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 336596037 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 1.928472 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist.samples 1472299541
|
|
system.cpu.fetch.rateDist.min_value 0
|
|
0 907273323 6162.29%
|
|
1 47886355 325.25%
|
|
2 34613456 235.10%
|
|
3 52095475 353.84%
|
|
4 125971058 855.61%
|
|
5 69335096 470.93%
|
|
6 50458684 342.72%
|
|
7 40993758 278.43%
|
|
8 143672336 975.84%
|
|
system.cpu.fetch.rateDist.max_value 8
|
|
system.cpu.fetch.rateDist.end_dist
|
|
|
|
system.cpu.icache.ReadReq_accesses 355180518 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 35446.920583 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 35464.523282 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 355179284 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 43741500 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.000003 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 1234 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 332 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 31989000 # 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 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 393768.607539 # 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 355180518 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 35446.920583 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 35464.523282 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 355179284 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 43741500 # 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 1234 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 332 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 31989000 # 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 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 355180518 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 35446.920583 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 35464.523282 # 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 355179284 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 43741500 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.000003 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 1234 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 332 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 31989000 # 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 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.replacements 1 # 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 711.425375 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 355179284 # 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 12319311 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 282186314 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 128796557 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 1.535065 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 769619324 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 201925301 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 1531990762 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 2240290242 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.811831 # 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 1243717865 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 1.509000 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 2261678939 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 21342134 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 17373691 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 621608435 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 43 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 22154841 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 234046222 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 2621719109 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 567694023 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 36858073 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 2278986827 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 339653 # 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 40208 # Number of times the LSQ has become full, causing a stall
|
|
system.cpu.iew.iewSquashCycles 93084202 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 758573 # 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 361643 # Number of times an access to memory failed due to the cache being blocked
|
|
system.cpu.iew.lsq.thread.0.forwLoads 33889596 # Number of loads that had data forwarded from stores
|
|
system.cpu.iew.lsq.thread.0.ignoredResponses 220185 # 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 3031505 # 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 175942074 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 73141240 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 3031505 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 703796 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 20638338 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 1.169353 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 1.169353 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 2315844900 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 0 0.00% # Type of FU issued
|
|
IntAlu 1532920254 66.19% # Type of FU issued
|
|
IntMult 99 0.00% # Type of FU issued
|
|
IntDiv 0 0.00% # Type of FU issued
|
|
FloatAdd 234 0.00% # Type of FU issued
|
|
FloatCmp 20 0.00% # Type of FU issued
|
|
FloatCvt 143 0.00% # Type of FU issued
|
|
FloatMult 16 0.00% # Type of FU issued
|
|
FloatDiv 24 0.00% # Type of FU issued
|
|
FloatSqrt 0 0.00% # Type of FU issued
|
|
MemRead 577889733 24.95% # Type of FU issued
|
|
MemWrite 205034377 8.85% # 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 14393569 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.006215 # 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 2738956 19.03% # 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
|
|
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 9224843 64.09% # attempts to use FU when none available
|
|
MemWrite 2429770 16.88% # attempts to use FU when none available
|
|
IprAccess 0 0.00% # attempts to use FU when none available
|
|
InstPrefetch 0 0.00% # attempts to use FU when none available
|
|
system.cpu.iq.ISSUE:fu_full.end_dist
|
|
system.cpu.iq.ISSUE:issued_per_cycle::samples 1472299541
|
|
system.cpu.iq.ISSUE:issued_per_cycle::min_value 0
|
|
system.cpu.iq.ISSUE:issued_per_cycle::underflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::0-1 577695763 39.24%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::1-2 271543756 18.44%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::2-3 242868170 16.50%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::3-4 139713874 9.49%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::4-5 122021082 8.29%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::5-6 69652698 4.73%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::6-7 39670196 2.69%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::7-8 8017828 0.54%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::8 1116174 0.08%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::total 1472299541
|
|
system.cpu.iq.ISSUE:issued_per_cycle::max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle::mean 1.572944
|
|
system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.737325
|
|
system.cpu.iq.ISSUE:rate 1.559892 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 2492922509 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 2315844900 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 43 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 739697610 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 1501741 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedNonSpecRemoved 14 # Number of squashed non-spec instructions that were removed
|
|
system.cpu.iq.iqSquashedOperandsExamined 329349456 # Number of squashed operands that are examined and possibly removed from graph
|
|
system.cpu.itb.data_accesses 0 # DTB accesses
|
|
system.cpu.itb.data_acv 0 # DTB access violations
|
|
system.cpu.itb.data_hits 0 # DTB hits
|
|
system.cpu.itb.data_misses 0 # DTB misses
|
|
system.cpu.itb.fetch_accesses 355180552 # ITB accesses
|
|
system.cpu.itb.fetch_acv 0 # ITB acv
|
|
system.cpu.itb.fetch_hits 355180518 # ITB hits
|
|
system.cpu.itb.fetch_misses 34 # ITB misses
|
|
system.cpu.itb.read_accesses 0 # DTB read accesses
|
|
system.cpu.itb.read_acv 0 # DTB read access violations
|
|
system.cpu.itb.read_hits 0 # DTB read hits
|
|
system.cpu.itb.read_misses 0 # DTB read misses
|
|
system.cpu.itb.write_accesses 0 # DTB write accesses
|
|
system.cpu.itb.write_acv 0 # DTB write access violations
|
|
system.cpu.itb.write_hits 0 # DTB write hits
|
|
system.cpu.itb.write_misses 0 # DTB write misses
|
|
system.cpu.l2cache.ReadExReq_accesses 1884731 # number of ReadExReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadExReq_avg_miss_latency 34610.251241 # average ReadExReq miss latency
|
|
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31460.593787 # average ReadExReq mshr miss latency
|
|
system.cpu.l2cache.ReadExReq_miss_latency 65231013432 # number of ReadExReq miss cycles
|
|
system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses
|
|
system.cpu.l2cache.ReadExReq_misses 1884731 # number of ReadExReq misses
|
|
system.cpu.l2cache.ReadExReq_mshr_miss_latency 59294756388 # 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 1884731 # number of ReadExReq MSHR misses
|
|
system.cpu.l2cache.ReadReq_accesses 7276042 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 34304.499446 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31138.330859 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_hits 5387454 # number of ReadReq hits
|
|
system.cpu.l2cache.ReadReq_miss_latency 64787066000 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 0.259563 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 1888588 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 58807478000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.259563 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 1888588 # number of ReadReq MSHR misses
|
|
system.cpu.l2cache.UpgradeReq_accesses 363811 # number of UpgradeReq accesses(hits+misses)
|
|
system.cpu.l2cache.UpgradeReq_avg_miss_latency 34327.098007 # average UpgradeReq miss latency
|
|
system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31261.459167 # average UpgradeReq mshr miss latency
|
|
system.cpu.l2cache.UpgradeReq_miss_latency 12488575853 # number of UpgradeReq miss cycles
|
|
system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_misses 363811 # number of UpgradeReq misses
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_latency 11373262721 # 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 363811 # number of UpgradeReq MSHR misses
|
|
system.cpu.l2cache.Writeback_accesses 2245449 # number of Writeback accesses(hits+misses)
|
|
system.cpu.l2cache.Writeback_hits 2245449 # number of Writeback hits
|
|
system.cpu.l2cache.avg_blocked_cycles_no_mshrs 11899.405570 # 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 2.417950 # Average number of references to valid blocks.
|
|
system.cpu.l2cache.blocked_no_mshrs 39818 # 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 473810531 # 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 9160773 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 34457.219077 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 31299.297618 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 5387454 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 130018079432 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 0.411900 # miss rate for demand accesses
|
|
system.cpu.l2cache.demand_misses 3773319 # 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 118102234388 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 0.411900 # mshr miss rate for demand accesses
|
|
system.cpu.l2cache.demand_mshr_misses 3773319 # 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 9160773 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 34457.219077 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 31299.297618 # 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 5387454 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 130018079432 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 0.411900 # miss rate for overall accesses
|
|
system.cpu.l2cache.overall_misses 3773319 # number of overall misses
|
|
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
|
|
system.cpu.l2cache.overall_mshr_miss_latency 118102234388 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 0.411900 # mshr miss rate for overall accesses
|
|
system.cpu.l2cache.overall_mshr_misses 3773319 # 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.replacements 2759426 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 2784020 # 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 25902.034914 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 6731622 # Total number of references to valid blocks.
|
|
system.cpu.l2cache.warmup_cycle 154290039500 # Cycle when the warmup percentage was hit.
|
|
system.cpu.l2cache.writebacks 1195718 # number of writebacks
|
|
system.cpu.memDep0.conflictingLoads 127392983 # Number of conflicting loads.
|
|
system.cpu.memDep0.conflictingStores 67515291 # Number of conflicting stores.
|
|
system.cpu.memDep0.insertedLoads 621608435 # Number of loads inserted to the mem dependence unit.
|
|
system.cpu.memDep0.insertedStores 234046222 # Number of stores inserted to the mem dependence unit.
|
|
system.cpu.numCycles 1484618852 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 68342801 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 1376202963 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:IQFullEvents 5307310 # Number of times rename has blocked due to IQ full
|
|
system.cpu.rename.RENAME:IdleCycles 744648238 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 20682075 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:ROBFullEvents 1073015 # Number of times rename has blocked due to ROB full
|
|
system.cpu.rename.RENAME:RenameLookups 3556218340 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 2749142928 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 2059304862 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 535957522 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 93084202 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 30265720 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 683101899 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 1058 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 46 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 60936722 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 44 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 457423 # 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 ----------
|