Mostly just config.ini updates, though the different response latency for bad addresses caused very minor timing changes in the O3 Linux boot tests.
422 lines
46 KiB
Text
422 lines
46 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
host_inst_rate 62820 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 202152 # Number of bytes of host memory used
|
|
host_seconds 0.08 # Real time elapsed on the host
|
|
host_tick_rate 173066613 # Simulator tick rate (ticks/s)
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 5024 # Number of instructions simulated
|
|
sim_seconds 0.000014 # Number of seconds simulated
|
|
sim_ticks 13881500 # Number of ticks simulated
|
|
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
system.cpu.BPredUnit.BTBHits 549 # Number of BTB hits
|
|
system.cpu.BPredUnit.BTBLookups 1924 # Number of BTB lookups
|
|
system.cpu.BPredUnit.RASInCorrect 53 # Number of incorrect RAS predictions.
|
|
system.cpu.BPredUnit.condIncorrect 721 # Number of conditional branches incorrect
|
|
system.cpu.BPredUnit.condPredicted 1540 # Number of conditional branches predicted
|
|
system.cpu.BPredUnit.lookups 2339 # Number of BP lookups
|
|
system.cpu.BPredUnit.usedRAS 384 # Number of times the RAS was used to get a target.
|
|
system.cpu.commit.COM:branches 879 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 63 # 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::samples 14165 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::min_value 0 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::underflows 0 0.00% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::0-1 11701 82.61% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::1-2 1166 8.23% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::2-3 493 3.48% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::3-4 279 1.97% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::4-5 290 2.05% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::5-6 74 0.52% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::6-7 61 0.43% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::7-8 38 0.27% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::8 63 0.44% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::overflows 0 0.00% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::total 14165 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::max_value 8 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::mean 0.399223 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::stdev 1.126414 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:count 5655 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 1130 # Number of loads committed
|
|
system.cpu.commit.COM:membars 0 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 2054 # Number of memory references committed
|
|
system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed
|
|
system.cpu.commit.branchMispredicts 604 # The number of times a branch was mispredicted
|
|
system.cpu.commit.commitCommittedInsts 5655 # The number of committed instructions
|
|
system.cpu.commit.commitNonSpecStalls 15 # The number of times commit has been forced to stall to communicate backwards
|
|
system.cpu.commit.commitSquashedInsts 5936 # The number of squashed insts skipped by commit
|
|
system.cpu.committedInsts 5024 # Number of Instructions Simulated
|
|
system.cpu.committedInsts_total 5024 # Number of Instructions Simulated
|
|
system.cpu.cpi 5.526274 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 5.526274 # CPI: Total CPI of All Threads
|
|
system.cpu.dcache.ReadReq_accesses 2286 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 33976.377953 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 36034.883721 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 2159 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 4315000 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.055556 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 127 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 41 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 3099000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.037620 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 86 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 924 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 27701.724138 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 36093.750000 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 634 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 8033500 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.313853 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 290 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 226 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 2310000 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.069264 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 64 # number of WriteReq MSHR misses
|
|
system.cpu.dcache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_refs 20.970370 # 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 3210 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 29612.709832 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 36060 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 2793 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 12348500 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.129907 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 417 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 267 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 5409000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.046729 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 150 # 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 3210 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 29612.709832 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 36060 # 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 2793 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 12348500 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.129907 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 417 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 267 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 5409000 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.046729 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 150 # 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 0 # number of replacements
|
|
system.cpu.dcache.sampled_refs 135 # 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 87.531358 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 2831 # Total number of references to valid blocks.
|
|
system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
|
|
system.cpu.dcache.writebacks 0 # number of writebacks
|
|
system.cpu.decode.DECODE:BlockedCycles 479 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:BranchMispred 128 # Number of times decode detected a branch misprediction
|
|
system.cpu.decode.DECODE:BranchResolved 128 # Number of times decode resolved a branch
|
|
system.cpu.decode.DECODE:DecodedInsts 14141 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 9863 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 3823 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 1052 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:SquashedInsts 251 # Number of squashed instructions handled by decode
|
|
system.cpu.dtb.accesses 0 # DTB accesses
|
|
system.cpu.dtb.hits 0 # DTB hits
|
|
system.cpu.dtb.misses 0 # DTB misses
|
|
system.cpu.dtb.read_accesses 0 # DTB read accesses
|
|
system.cpu.dtb.read_hits 0 # DTB read hits
|
|
system.cpu.dtb.read_misses 0 # DTB read misses
|
|
system.cpu.dtb.write_accesses 0 # DTB write accesses
|
|
system.cpu.dtb.write_hits 0 # DTB write hits
|
|
system.cpu.dtb.write_misses 0 # DTB write misses
|
|
system.cpu.fetch.Branches 2339 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 2162 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 6161 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 360 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 15261 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 737 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.084246 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 2162 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 933 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 0.549669 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist::samples 15217 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::min_value 0 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::underflows 0 0.00% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::0-1 11225 73.77% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::1-2 1766 11.61% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::2-3 196 1.29% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::3-4 137 0.90% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::4-5 314 2.06% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::5-6 113 0.74% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::6-7 304 2.00% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::7-8 249 1.64% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::8 913 6.00% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::overflows 0 0.00% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::total 15217 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::max_value 8 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::mean 1.002892 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::stdev 2.262712 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.icache.ReadReq_accesses 2162 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 35500 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 34915.151515 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 1731 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 15300500 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.199352 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 431 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 101 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 11522000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.icache.ReadReq_mshr_miss_rate 0.152636 # mshr miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_mshr_misses 330 # 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 5.245455 # 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 2162 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 35500 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 34915.151515 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 1731 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 15300500 # number of demand (read+write) miss cycles
|
|
system.cpu.icache.demand_miss_rate 0.199352 # miss rate for demand accesses
|
|
system.cpu.icache.demand_misses 431 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 101 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 11522000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.icache.demand_mshr_miss_rate 0.152636 # mshr miss rate for demand accesses
|
|
system.cpu.icache.demand_mshr_misses 330 # 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 2162 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 35500 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 34915.151515 # 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 1731 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 15300500 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.199352 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 431 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 101 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 11522000 # number of overall MSHR miss cycles
|
|
system.cpu.icache.overall_mshr_miss_rate 0.152636 # mshr miss rate for overall accesses
|
|
system.cpu.icache.overall_mshr_misses 330 # 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 16 # number of replacements
|
|
system.cpu.icache.sampled_refs 330 # 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 158.760808 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 1731 # 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 12547 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 1206 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 1806 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 0.291349 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 3420 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 1048 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 4016 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 7315 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.694970 # 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 2791 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 0.263471 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 7402 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 661 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 8 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 2783 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 15 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 968 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 1158 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 11594 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 2372 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 531 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 8089 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 0 # Number of times the IQ has become full, causing a stall
|
|
system.cpu.iew.iewIdleCycles 0 # Number of cycles IEW is idle
|
|
system.cpu.iew.iewLSQFullEvents 1 # Number of times the LSQ has become full, causing a stall
|
|
system.cpu.iew.iewSquashCycles 1052 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 0 # Number of cycles IEW is unblocking
|
|
system.cpu.iew.lsq.thread.0.blockedLoads 0 # Number of blocked loads due to partial load-store forwarding
|
|
system.cpu.iew.lsq.thread.0.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked
|
|
system.cpu.iew.lsq.thread.0.forwLoads 68 # Number of loads that had data forwarded from stores
|
|
system.cpu.iew.lsq.thread.0.ignoredResponses 3 # Number of memory responses ignored because the instruction is squashed
|
|
system.cpu.iew.lsq.thread.0.invAddrLoads 0 # Number of loads ignored due to an invalid address
|
|
system.cpu.iew.lsq.thread.0.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address
|
|
system.cpu.iew.lsq.thread.0.memOrderViolation 22 # Number of memory ordering violations
|
|
system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled
|
|
system.cpu.iew.lsq.thread.0.squashedLoads 1653 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 234 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 22 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 276 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 385 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 0.180954 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 0.180954 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 8620 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 0 0.00% # Type of FU issued
|
|
IntAlu 4988 57.87% # Type of FU issued
|
|
IntMult 5 0.06% # Type of FU issued
|
|
IntDiv 2 0.02% # Type of FU issued
|
|
FloatAdd 2 0.02% # Type of FU issued
|
|
FloatCmp 0 0.00% # Type of FU issued
|
|
FloatCvt 0 0.00% # Type of FU issued
|
|
FloatMult 0 0.00% # Type of FU issued
|
|
FloatDiv 0 0.00% # Type of FU issued
|
|
FloatSqrt 0 0.00% # Type of FU issued
|
|
MemRead 2560 29.70% # Type of FU issued
|
|
MemWrite 1063 12.33% # 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 162 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.018794 # 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 10 6.17% # 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 98 60.49% # attempts to use FU when none available
|
|
MemWrite 54 33.33% # 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 15217
|
|
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 11370 74.72%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::1-2 1673 10.99%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::2-3 787 5.17%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::3-4 717 4.71%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::4-5 332 2.18%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::5-6 198 1.30%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::6-7 91 0.60%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::7-8 34 0.22%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::8 15 0.10%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::total 15217
|
|
system.cpu.iq.ISSUE:issued_per_cycle::max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle::mean 0.566472
|
|
system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.217507
|
|
system.cpu.iq.ISSUE:rate 0.310474 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 9773 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 8620 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 15 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 4182 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 30 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedOperandsExamined 2741 # Number of squashed operands that are examined and possibly removed from graph
|
|
system.cpu.itb.accesses 0 # DTB accesses
|
|
system.cpu.itb.hits 0 # DTB hits
|
|
system.cpu.itb.misses 0 # DTB misses
|
|
system.cpu.itb.read_accesses 0 # DTB read accesses
|
|
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_hits 0 # DTB write hits
|
|
system.cpu.itb.write_misses 0 # DTB write misses
|
|
system.cpu.l2cache.ReadExReq_accesses 49 # number of ReadExReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadExReq_avg_miss_latency 34704.081633 # average ReadExReq miss latency
|
|
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31408.163265 # average ReadExReq mshr miss latency
|
|
system.cpu.l2cache.ReadExReq_miss_latency 1700500 # number of ReadExReq miss cycles
|
|
system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses
|
|
system.cpu.l2cache.ReadExReq_misses 49 # number of ReadExReq misses
|
|
system.cpu.l2cache.ReadExReq_mshr_miss_latency 1539000 # 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 49 # number of ReadExReq MSHR misses
|
|
system.cpu.l2cache.ReadReq_accesses 416 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 34308.252427 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31129.854369 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_hits 4 # number of ReadReq hits
|
|
system.cpu.l2cache.ReadReq_miss_latency 14135000 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 0.990385 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 412 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 12825500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.990385 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 412 # number of ReadReq MSHR misses
|
|
system.cpu.l2cache.UpgradeReq_accesses 15 # number of UpgradeReq accesses(hits+misses)
|
|
system.cpu.l2cache.UpgradeReq_avg_miss_latency 34400 # average UpgradeReq miss latency
|
|
system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31166.666667 # average UpgradeReq mshr miss latency
|
|
system.cpu.l2cache.UpgradeReq_miss_latency 516000 # number of UpgradeReq miss cycles
|
|
system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_misses 15 # number of UpgradeReq misses
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_latency 467500 # number of UpgradeReq MSHR miss cycles
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_rate 1 # mshr miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_mshr_misses 15 # number of UpgradeReq MSHR misses
|
|
system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.l2cache.avg_refs 0.010076 # 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 465 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 34350.325380 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 31159.436009 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 4 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 15835500 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 0.991398 # miss rate for demand accesses
|
|
system.cpu.l2cache.demand_misses 461 # 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 14364500 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 0.991398 # mshr miss rate for demand accesses
|
|
system.cpu.l2cache.demand_mshr_misses 461 # 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 465 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 34350.325380 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 31159.436009 # average overall mshr miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_uncacheable_latency <err: div-0> # average overall mshr uncacheable latency
|
|
system.cpu.l2cache.overall_hits 4 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 15835500 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 0.991398 # miss rate for overall accesses
|
|
system.cpu.l2cache.overall_misses 461 # number of overall misses
|
|
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
|
|
system.cpu.l2cache.overall_mshr_miss_latency 14364500 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 0.991398 # mshr miss rate for overall accesses
|
|
system.cpu.l2cache.overall_mshr_misses 461 # 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 0 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 397 # 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 208.689672 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 4 # Total number of references to valid blocks.
|
|
system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
|
|
system.cpu.l2cache.writebacks 0 # number of writebacks
|
|
system.cpu.memDep0.conflictingLoads 5 # Number of conflicting loads.
|
|
system.cpu.memDep0.conflictingStores 2 # Number of conflicting stores.
|
|
system.cpu.memDep0.insertedLoads 2783 # Number of loads inserted to the mem dependence unit.
|
|
system.cpu.memDep0.insertedStores 1158 # Number of stores inserted to the mem dependence unit.
|
|
system.cpu.numCycles 27764 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 20 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 3304 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:IdleCycles 10242 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 16 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:RenameLookups 15583 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 13384 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 8214 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 3446 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 1052 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 29 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 4910 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 428 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 20 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 125 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 14 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 249 # Number of times that the entire CPU went into an idle state and unscheduled itself
|
|
system.cpu.workload.PROG:num_syscalls 13 # Number of system calls
|
|
|
|
---------- End Simulation Statistics ----------
|