48d4ca522a
Somehow ending threads with halt() instead of deallocate() reduces the squash count on o3 by 1 (and a few other similarly trivial changes).
440 lines
46 KiB
Text
440 lines
46 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
host_inst_rate 193760 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 215160 # Number of bytes of host memory used
|
|
host_seconds 9408.76 # Real time elapsed on the host
|
|
host_tick_rate 74947150 # Simulator tick rate (ticks/s)
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 1823043370 # Number of instructions simulated
|
|
sim_seconds 0.705159 # Number of seconds simulated
|
|
sim_ticks 705159454500 # Number of ticks simulated
|
|
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
system.cpu.BPredUnit.BTBHits 240462096 # Number of BTB hits
|
|
system.cpu.BPredUnit.BTBLookups 294213603 # Number of BTB lookups
|
|
system.cpu.BPredUnit.RASInCorrect 3593 # Number of incorrect RAS predictions.
|
|
system.cpu.BPredUnit.condIncorrect 29107758 # Number of conditional branches incorrect
|
|
system.cpu.BPredUnit.condPredicted 233918302 # Number of conditional branches predicted
|
|
system.cpu.BPredUnit.lookups 349424731 # Number of BP lookups
|
|
system.cpu.BPredUnit.usedRAS 49888256 # Number of times the RAS was used to get a target.
|
|
system.cpu.commit.COM:branches 266706457 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 68860244 # 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 1310002801
|
|
system.cpu.commit.COM:committed_per_cycle.min_value 0
|
|
0 603585597 4607.51%
|
|
1 273587005 2088.45%
|
|
2 174037133 1328.52%
|
|
3 65399708 499.23%
|
|
4 48333001 368.95%
|
|
5 34003110 259.57%
|
|
6 18481318 141.08%
|
|
7 23715685 181.04%
|
|
8 68860244 525.65%
|
|
system.cpu.commit.COM:committed_per_cycle.max_value 8
|
|
system.cpu.commit.COM:committed_per_cycle.end_dist
|
|
|
|
system.cpu.commit.COM:count 2008987604 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 511595302 # Number of loads committed
|
|
system.cpu.commit.COM:membars 0 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 722390433 # Number of memory references committed
|
|
system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed
|
|
system.cpu.commit.branchMispredicts 29095954 # The number of times a branch was mispredicted
|
|
system.cpu.commit.commitCommittedInsts 2008987604 # The number of committed instructions
|
|
system.cpu.commit.commitNonSpecStalls 39 # The number of times commit has been forced to stall to communicate backwards
|
|
system.cpu.commit.commitSquashedInsts 696013930 # The number of squashed insts skipped by commit
|
|
system.cpu.committedInsts 1823043370 # Number of Instructions Simulated
|
|
system.cpu.committedInsts_total 1823043370 # Number of Instructions Simulated
|
|
system.cpu.cpi 0.773607 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 0.773607 # CPI: Total CPI of All Threads
|
|
system.cpu.dcache.LoadLockedReq_accesses 6 # number of LoadLockedReq accesses(hits+misses)
|
|
system.cpu.dcache.LoadLockedReq_hits 6 # number of LoadLockedReq hits
|
|
system.cpu.dcache.ReadReq_accesses 465737269 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 37550.774879 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34829.991989 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 463802710 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 72644189500 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.004154 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 1934559 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 475266 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 50827163500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.003133 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 1459293 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 210794896 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 38583.618605 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 36524.752250 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 210235541 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 21581939985 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.002654 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 559355 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 484574 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 2731357498 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.000355 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 74781 # number of WriteReq MSHR misses
|
|
system.cpu.dcache.avg_blocked_cycles_no_mshrs 5124.928571 # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_blocked_cycles_no_targets 18000 # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_refs 440.284636 # Average number of references to valid blocks.
|
|
system.cpu.dcache.blocked_no_mshrs 28 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_no_targets 1 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_cycles_no_mshrs 143498 # number of cycles access was blocked
|
|
system.cpu.dcache.blocked_cycles_no_targets 18000 # number of cycles access was blocked
|
|
system.cpu.dcache.cache_copies 0 # number of cache copies performed
|
|
system.cpu.dcache.demand_accesses 676532165 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 37782.429340 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 34912.605909 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 674038251 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 94226129485 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.003686 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 2493914 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 959840 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 53558520998 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.002268 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 1534074 # 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 676532165 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 37782.429340 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 34912.605909 # 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 674038251 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 94226129485 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.003686 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 2493914 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 959840 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 53558520998 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.002268 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 1534074 # 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 1526847 # number of replacements
|
|
system.cpu.dcache.sampled_refs 1530943 # 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 4095.104513 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 674050682 # Total number of references to valid blocks.
|
|
system.cpu.dcache.warmup_cycle 274499000 # Cycle when the warmup percentage was hit.
|
|
system.cpu.dcache.writebacks 74589 # number of writebacks
|
|
system.cpu.decode.DECODE:BlockedCycles 32190527 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:BranchMispred 12129 # Number of times decode detected a branch misprediction
|
|
system.cpu.decode.DECODE:BranchResolved 30585324 # Number of times decode resolved a branch
|
|
system.cpu.decode.DECODE:DecodedInsts 2936172402 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 716337474 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 561391036 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 100159084 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:SquashedInsts 45706 # Number of squashed instructions handled by decode
|
|
system.cpu.decode.DECODE:UnblockCycles 83764 # Number of cycles decode is unblocking
|
|
system.cpu.dtb.data_accesses 775959987 # DTB accesses
|
|
system.cpu.dtb.data_acv 0 # DTB access violations
|
|
system.cpu.dtb.data_hits 775335043 # DTB hits
|
|
system.cpu.dtb.data_misses 624944 # 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 516992085 # DTB read accesses
|
|
system.cpu.dtb.read_acv 0 # DTB read access violations
|
|
system.cpu.dtb.read_hits 516404963 # DTB read hits
|
|
system.cpu.dtb.read_misses 587122 # DTB read misses
|
|
system.cpu.dtb.write_accesses 258967902 # DTB write accesses
|
|
system.cpu.dtb.write_acv 0 # DTB write access violations
|
|
system.cpu.dtb.write_hits 258930080 # DTB write hits
|
|
system.cpu.dtb.write_misses 37822 # DTB write misses
|
|
system.cpu.fetch.Branches 349424731 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 348447899 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 928021937 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 4387629 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 3030218619 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 29544621 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.247763 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 348447899 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 290350352 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 2.148605 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist.samples 1410161885
|
|
system.cpu.fetch.rateDist.min_value 0
|
|
0 830588040 5890.02%
|
|
1 53463106 379.13%
|
|
2 39766072 282.00%
|
|
3 63538024 450.57%
|
|
4 121390719 860.83%
|
|
5 35256321 250.02%
|
|
6 38761682 274.87%
|
|
7 6988644 49.56%
|
|
8 220409277 1563.01%
|
|
system.cpu.fetch.rateDist.max_value 8
|
|
system.cpu.fetch.rateDist.end_dist
|
|
|
|
system.cpu.icache.ReadReq_accesses 348447899 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 15851.065828 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 11638.513514 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 348437250 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 168798000 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.000031 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 10649 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 881 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 113685000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.icache.ReadReq_mshr_miss_rate 0.000028 # mshr miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_mshr_misses 9768 # 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 35671.299140 # 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 348447899 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 15851.065828 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 11638.513514 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 348437250 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 168798000 # number of demand (read+write) miss cycles
|
|
system.cpu.icache.demand_miss_rate 0.000031 # miss rate for demand accesses
|
|
system.cpu.icache.demand_misses 10649 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 881 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 113685000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.icache.demand_mshr_miss_rate 0.000028 # mshr miss rate for demand accesses
|
|
system.cpu.icache.demand_mshr_misses 9768 # 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 348447899 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 15851.065828 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 11638.513514 # 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 348437250 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 168798000 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.000031 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 10649 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 881 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 113685000 # number of overall MSHR miss cycles
|
|
system.cpu.icache.overall_mshr_miss_rate 0.000028 # mshr miss rate for overall accesses
|
|
system.cpu.icache.overall_mshr_misses 9768 # 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 8097 # number of replacements
|
|
system.cpu.icache.sampled_refs 9768 # 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 1614.102824 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 348437250 # 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 157025 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 274534145 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 329178061 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 1.421117 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 776495503 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 258968900 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 1631503179 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 2002130585 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.696431 # 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 1136229268 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 1.419630 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 2003425032 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 31680133 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 3459468 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 655954745 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 57 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 62130 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 303651290 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 2715209778 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 517526603 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 85279852 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 2004227953 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 131519 # 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 3361 # Number of times the LSQ has become full, causing a stall
|
|
system.cpu.iew.iewSquashCycles 100159084 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 141229 # 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 64 # Number of times an access to memory failed due to the cache being blocked
|
|
system.cpu.iew.lsq.thread.0.forwLoads 50663539 # Number of loads that had data forwarded from stores
|
|
system.cpu.iew.lsq.thread.0.ignoredResponses 152 # 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 3589 # Number of memory ordering violations
|
|
system.cpu.iew.lsq.thread.0.rescheduledLoads 4102 # Number of loads that were rescheduled
|
|
system.cpu.iew.lsq.thread.0.squashedLoads 144359443 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 92856159 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 3589 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 816990 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 30863143 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 1.292646 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 1.292646 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 2089507805 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 2752 0.00% # Type of FU issued
|
|
IntAlu 1204412678 57.64% # Type of FU issued
|
|
IntMult 17591 0.00% # Type of FU issued
|
|
IntDiv 0 0.00% # Type of FU issued
|
|
FloatAdd 27851349 1.33% # Type of FU issued
|
|
FloatCmp 8254694 0.40% # Type of FU issued
|
|
FloatCvt 7204646 0.34% # 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 557993260 26.70% # Type of FU issued
|
|
MemWrite 283770831 13.58% # 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 37093546 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.017752 # 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 8291 0.02% # 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 28032977 75.57% # attempts to use FU when none available
|
|
MemWrite 9052278 24.40% # 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 1410161885
|
|
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 537278436 38.10%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::1-2 285217724 20.23%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::2-3 273546804 19.40%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::3-4 154810620 10.98%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::4-5 63341841 4.49%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::5-6 51438515 3.65%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::6-7 32491109 2.30%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::7-8 9036668 0.64%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::8 3000168 0.21%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::total 1410161885
|
|
system.cpu.iq.ISSUE:issued_per_cycle::max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle::mean 1.481750
|
|
system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.637343
|
|
system.cpu.iq.ISSUE:rate 1.481585 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 2386031660 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 2089507805 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 57 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 562621267 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 12403599 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedNonSpecRemoved 18 # Number of squashed non-spec instructions that were removed
|
|
system.cpu.iq.iqSquashedOperandsExamined 516017454 # 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 348448092 # ITB accesses
|
|
system.cpu.itb.fetch_acv 0 # ITB acv
|
|
system.cpu.itb.fetch_hits 348447899 # ITB hits
|
|
system.cpu.itb.fetch_misses 193 # 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 71650 # number of ReadExReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadExReq_avg_miss_latency 35090.990928 # average ReadExReq miss latency
|
|
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 32065.847872 # average ReadExReq mshr miss latency
|
|
system.cpu.l2cache.ReadExReq_miss_latency 2514269500 # number of ReadExReq miss cycles
|
|
system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses
|
|
system.cpu.l2cache.ReadExReq_misses 71650 # number of ReadExReq misses
|
|
system.cpu.l2cache.ReadExReq_mshr_miss_latency 2297518000 # 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 71650 # number of ReadExReq MSHR misses
|
|
system.cpu.l2cache.ReadReq_accesses 1469061 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 34325.576147 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31000.455515 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_hits 28934 # number of ReadReq hits
|
|
system.cpu.l2cache.ReadReq_miss_latency 49433189000 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 0.980304 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 1440127 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 44644593000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.980304 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 1440127 # number of ReadReq MSHR misses
|
|
system.cpu.l2cache.UpgradeReq_accesses 3137 # number of UpgradeReq accesses(hits+misses)
|
|
system.cpu.l2cache.UpgradeReq_avg_miss_latency 34069.333758 # average UpgradeReq miss latency
|
|
system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31036.659229 # average UpgradeReq mshr miss latency
|
|
system.cpu.l2cache.UpgradeReq_miss_latency 106875500 # number of UpgradeReq miss cycles
|
|
system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_misses 3137 # number of UpgradeReq misses
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_latency 97362000 # 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 3137 # number of UpgradeReq MSHR misses
|
|
system.cpu.l2cache.Writeback_accesses 74589 # number of Writeback accesses(hits+misses)
|
|
system.cpu.l2cache.Writeback_hits 74589 # number of Writeback hits
|
|
system.cpu.l2cache.avg_blocked_cycles_no_mshrs 8187.500000 # 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 0.023462 # Average number of references to valid blocks.
|
|
system.cpu.l2cache.blocked_no_mshrs 8 # 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 65500 # 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 1540711 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 34361.852641 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 31050.949313 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 28934 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 51947458500 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 0.981220 # miss rate for demand accesses
|
|
system.cpu.l2cache.demand_misses 1511777 # 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 46942111000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 0.981220 # mshr miss rate for demand accesses
|
|
system.cpu.l2cache.demand_mshr_misses 1511777 # 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 1540711 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 34361.852641 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 31050.949313 # 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 28934 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 51947458500 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 0.981220 # miss rate for overall accesses
|
|
system.cpu.l2cache.overall_misses 1511777 # number of overall misses
|
|
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
|
|
system.cpu.l2cache.overall_mshr_miss_latency 46942111000 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 0.981220 # mshr miss rate for overall accesses
|
|
system.cpu.l2cache.overall_mshr_misses 1511777 # 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 1474251 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 1506809 # 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 31919.645552 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 35353 # Total number of references to valid blocks.
|
|
system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
|
|
system.cpu.l2cache.writebacks 66899 # number of writebacks
|
|
system.cpu.memDep0.conflictingLoads 118847053 # Number of conflicting loads.
|
|
system.cpu.memDep0.conflictingStores 21034746 # Number of conflicting stores.
|
|
system.cpu.memDep0.insertedLoads 655954745 # Number of loads inserted to the mem dependence unit.
|
|
system.cpu.memDep0.insertedStores 303651290 # Number of stores inserted to the mem dependence unit.
|
|
system.cpu.numCycles 1410318910 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 20063964 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 1384969070 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:IQFullEvents 687776 # Number of times rename has blocked due to IQ full
|
|
system.cpu.rename.RENAME:IdleCycles 730652071 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 11530186 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:ROBFullEvents 16 # Number of times rename has blocked due to ROB full
|
|
system.cpu.rename.RENAME:RenameLookups 3303379014 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 2836019296 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 1886227369 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 545599397 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 100159084 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 13665899 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 501258299 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 21470 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 2842 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 27803045 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 61 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 4055 # Number of times that the entire CPU went into an idle state and unscheduled itself
|
|
system.cpu.workload.PROG:num_syscalls 39 # Number of system calls
|
|
|
|
---------- End Simulation Statistics ----------
|