48d4ca522a
Somehow ending threads with halt() instead of deallocate() reduces the squash count on o3 by 1 (and a few other similarly trivial changes).
414 lines
44 KiB
Text
414 lines
44 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
host_inst_rate 120324 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 213384 # Number of bytes of host memory used
|
|
host_seconds 11681.98 # Real time elapsed on the host
|
|
host_tick_rate 94389741 # Simulator tick rate (ticks/s)
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 1405618365 # Number of instructions simulated
|
|
sim_seconds 1.102659 # Number of seconds simulated
|
|
sim_ticks 1102659088000 # Number of ticks simulated
|
|
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
system.cpu.BPredUnit.BTBHits 182414509 # Number of BTB hits
|
|
system.cpu.BPredUnit.BTBLookups 203429498 # Number of BTB lookups
|
|
system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions.
|
|
system.cpu.BPredUnit.condIncorrect 83681535 # Number of conditional branches incorrect
|
|
system.cpu.BPredUnit.condPredicted 254458061 # Number of conditional branches predicted
|
|
system.cpu.BPredUnit.lookups 254458061 # Number of BP lookups
|
|
system.cpu.BPredUnit.usedRAS 0 # Number of times the RAS was used to get a target.
|
|
system.cpu.commit.COM:branches 86248929 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 8096109 # 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 1964055004
|
|
system.cpu.commit.COM:committed_per_cycle.min_value 0
|
|
0 1088074201 5539.94%
|
|
1 575643784 2930.89%
|
|
2 120435541 613.20%
|
|
3 120975798 615.95%
|
|
4 27955067 142.33%
|
|
5 8084166 41.16%
|
|
6 10447088 53.19%
|
|
7 4343250 22.11%
|
|
8 8096109 41.22%
|
|
system.cpu.commit.COM:committed_per_cycle.max_value 8
|
|
system.cpu.commit.COM:committed_per_cycle.end_dist
|
|
|
|
system.cpu.commit.COM:count 1489537508 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 402517243 # Number of loads committed
|
|
system.cpu.commit.COM:membars 51356 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 569375199 # Number of memory references committed
|
|
system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed
|
|
system.cpu.commit.branchMispredicts 83681535 # The number of times a branch was mispredicted
|
|
system.cpu.commit.commitCommittedInsts 1489537508 # The number of committed instructions
|
|
system.cpu.commit.commitNonSpecStalls 2243671 # The number of times commit has been forced to stall to communicate backwards
|
|
system.cpu.commit.commitSquashedInsts 1390237652 # The number of squashed insts skipped by commit
|
|
system.cpu.committedInsts 1405618365 # Number of Instructions Simulated
|
|
system.cpu.committedInsts_total 1405618365 # Number of Instructions Simulated
|
|
system.cpu.cpi 1.568931 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 1.568931 # CPI: Total CPI of All Threads
|
|
system.cpu.dcache.ReadReq_accesses 426261934 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 14297.662769 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 6789.135084 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 425346235 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 13092355500 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.002148 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 915699 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 667386 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 1685830500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.000583 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 248313 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.SwapReq_accesses 1326 # number of SwapReq accesses(hits+misses)
|
|
system.cpu.dcache.SwapReq_avg_miss_latency 38037.500000 # average SwapReq miss latency
|
|
system.cpu.dcache.SwapReq_avg_mshr_miss_latency 35037.500000 # average SwapReq mshr miss latency
|
|
system.cpu.dcache.SwapReq_hits 1286 # number of SwapReq hits
|
|
system.cpu.dcache.SwapReq_miss_latency 1521500 # number of SwapReq miss cycles
|
|
system.cpu.dcache.SwapReq_miss_rate 0.030166 # miss rate for SwapReq accesses
|
|
system.cpu.dcache.SwapReq_misses 40 # number of SwapReq misses
|
|
system.cpu.dcache.SwapReq_mshr_miss_latency 1401500 # number of SwapReq MSHR miss cycles
|
|
system.cpu.dcache.SwapReq_mshr_miss_rate 0.030166 # mshr miss rate for SwapReq accesses
|
|
system.cpu.dcache.SwapReq_mshr_misses 40 # number of SwapReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 166856630 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 37763.269313 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 36078.327068 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 164634096 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 83930150000 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.013320 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 2222534 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 1870625 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 12696288000 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.002109 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 351909 # 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 1119.158447 # 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 593118564 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 30916.284897 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 23961.331807 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 589980331 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 97022505500 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.005291 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 3138233 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 2538011 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 14382118500 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.001012 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 600222 # 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 593118564 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 30916.284897 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 23961.331807 # 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 589980331 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 97022505500 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.005291 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 3138233 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 2538011 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 14382118500 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.001012 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 600222 # 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 523278 # number of replacements
|
|
system.cpu.dcache.sampled_refs 527374 # 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 4095.579742 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 590215067 # Total number of references to valid blocks.
|
|
system.cpu.dcache.warmup_cycle 166150000 # Cycle when the warmup percentage was hit.
|
|
system.cpu.dcache.writebacks 348749 # number of writebacks
|
|
system.cpu.decode.DECODE:BlockedCycles 416443317 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:DecodedInsts 3435538799 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 762668513 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 782001789 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 239759977 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:UnblockCycles 2941385 # Number of cycles decode is unblocking
|
|
system.cpu.fetch.Branches 254458061 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 354588619 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 1199300749 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 10659931 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 3732201000 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 88873599 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.115384 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 354588619 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 182414509 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 1.692364 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist.samples 2203814981
|
|
system.cpu.fetch.rateDist.min_value 0
|
|
0 1359102894 6167.05%
|
|
1 256500547 1163.89%
|
|
2 81150170 368.23%
|
|
3 38425919 174.36%
|
|
4 85384463 387.44%
|
|
5 41200023 186.95%
|
|
6 32567288 147.78%
|
|
7 20688755 93.88%
|
|
8 288794922 1310.43%
|
|
system.cpu.fetch.rateDist.max_value 8
|
|
system.cpu.fetch.rateDist.end_dist
|
|
|
|
system.cpu.icache.ReadReq_accesses 354588619 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 33291.255289 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 34798.042059 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 354586492 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 70810500 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.000006 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 2127 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 748 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 47986500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.icache.ReadReq_mshr_miss_rate 0.000004 # mshr miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_mshr_misses 1379 # 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 257319.660377 # 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 354588619 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 33291.255289 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 34798.042059 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 354586492 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 70810500 # number of demand (read+write) miss cycles
|
|
system.cpu.icache.demand_miss_rate 0.000006 # miss rate for demand accesses
|
|
system.cpu.icache.demand_misses 2127 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 748 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 47986500 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.icache.demand_mshr_miss_rate 0.000004 # mshr miss rate for demand accesses
|
|
system.cpu.icache.demand_mshr_misses 1379 # 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 354588619 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 33291.255289 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 34798.042059 # 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 354586492 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 70810500 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.000006 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 2127 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 748 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 47986500 # number of overall MSHR miss cycles
|
|
system.cpu.icache.overall_mshr_miss_rate 0.000004 # mshr miss rate for overall accesses
|
|
system.cpu.icache.overall_mshr_misses 1379 # 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 222 # number of replacements
|
|
system.cpu.icache.sampled_refs 1378 # 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 1057.993144 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 354586492 # 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 1503196 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 128154505 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 351416641 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 0.859194 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 749485536 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 207432555 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 1490113215 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 1862924801 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.963395 # 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 1435567297 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 0.844742 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 1872447487 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 91815044 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 3100855 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 743909112 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 21390967 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 17059392 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 301399339 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 2879831174 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 542052981 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 94512444 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 1894795217 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 42359 # 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 9892 # Number of times the LSQ has become full, causing a stall
|
|
system.cpu.iew.iewSquashCycles 239759977 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 75722 # 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 115767211 # Number of loads that had data forwarded from stores
|
|
system.cpu.iew.lsq.thread.0.ignoredResponses 47414 # 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 5474059 # 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 341391869 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 134541383 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 5474059 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 1481544 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 90333500 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 0.637377 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 0.637377 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 1989307661 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 0 0.00% # Type of FU issued
|
|
IntAlu 1186637129 59.65% # Type of FU issued
|
|
IntMult 0 0.00% # Type of FU issued
|
|
IntDiv 0 0.00% # Type of FU issued
|
|
FloatAdd 2990803 0.15% # Type of FU issued
|
|
FloatCmp 0 0.00% # Type of FU issued
|
|
FloatCvt 0 0.00% # Type of FU issued
|
|
FloatMult 0 0.00% # Type of FU issued
|
|
FloatDiv 0 0.00% # Type of FU issued
|
|
FloatSqrt 0 0.00% # Type of FU issued
|
|
MemRead 571681967 28.74% # Type of FU issued
|
|
MemWrite 227997762 11.46% # 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 4014627 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.002018 # 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 142220 3.54% # attempts to use FU when none available
|
|
IntMult 0 0.00% # attempts to use FU when none available
|
|
IntDiv 0 0.00% # attempts to use FU when none available
|
|
FloatAdd 232755 5.80% # 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 3328922 82.92% # attempts to use FU when none available
|
|
MemWrite 310730 7.74% # 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 2203814981
|
|
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 1083881876 49.18%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::1-2 586425801 26.61%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::2-3 298714420 13.55%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::3-4 164995038 7.49%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::4-5 47215803 2.14%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::5-6 14943143 0.68%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::6-7 6716019 0.30%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::7-8 790183 0.04%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::8 132698 0.01%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::total 2203814981
|
|
system.cpu.iq.ISSUE:issued_per_cycle::max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle::mean 0.902665
|
|
system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.144866
|
|
system.cpu.iq.ISSUE:rate 0.902050 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 2506731488 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 1989307661 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 21683045 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 1079315429 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 646014 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedNonSpecRemoved 19439374 # Number of squashed non-spec instructions that were removed
|
|
system.cpu.iq.iqSquashedOperandsExamined 1293054156 # Number of squashed operands that are examined and possibly removed from graph
|
|
system.cpu.l2cache.ReadExReq_accesses 279061 # number of ReadExReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadExReq_avg_miss_latency 34294.562838 # average ReadExReq miss latency
|
|
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31161.514866 # average ReadExReq mshr miss latency
|
|
system.cpu.l2cache.ReadExReq_miss_latency 9570275000 # number of ReadExReq miss cycles
|
|
system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses
|
|
system.cpu.l2cache.ReadExReq_misses 279061 # number of ReadExReq misses
|
|
system.cpu.l2cache.ReadExReq_mshr_miss_latency 8695963500 # 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 279061 # number of ReadExReq MSHR misses
|
|
system.cpu.l2cache.ReadReq_accesses 249692 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 34106.857257 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31002.384760 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_hits 214678 # number of ReadReq hits
|
|
system.cpu.l2cache.ReadReq_miss_latency 1194217500 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 0.140229 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 35014 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 1085517500 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.140229 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 35014 # number of ReadReq MSHR misses
|
|
system.cpu.l2cache.UpgradeReq_accesses 72896 # number of UpgradeReq accesses(hits+misses)
|
|
system.cpu.l2cache.UpgradeReq_avg_miss_latency 34203.262182 # average UpgradeReq miss latency
|
|
system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31019.788466 # average UpgradeReq mshr miss latency
|
|
system.cpu.l2cache.UpgradeReq_miss_latency 2493281000 # number of UpgradeReq miss cycles
|
|
system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_misses 72896 # number of UpgradeReq misses
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_latency 2261218500 # 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 72896 # number of UpgradeReq MSHR misses
|
|
system.cpu.l2cache.Writeback_accesses 348749 # number of Writeback accesses(hits+misses)
|
|
system.cpu.l2cache.Writeback_hits 348749 # number of Writeback hits
|
|
system.cpu.l2cache.avg_blocked_cycles_no_mshrs <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.l2cache.avg_blocked_cycles_no_targets <err: div-0> # average number of cycles each access was blocked
|
|
system.cpu.l2cache.avg_refs 4.234507 # 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 528753 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 34273.636870 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 31143.774576 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 214678 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 10764492500 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 0.593992 # miss rate for demand accesses
|
|
system.cpu.l2cache.demand_misses 314075 # 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 9781481000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 0.593992 # mshr miss rate for demand accesses
|
|
system.cpu.l2cache.demand_mshr_misses 314075 # 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 528753 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 34273.636870 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 31143.774576 # 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 214678 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 10764492500 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 0.593992 # miss rate for overall accesses
|
|
system.cpu.l2cache.overall_misses 314075 # number of overall misses
|
|
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
|
|
system.cpu.l2cache.overall_mshr_miss_latency 9781481000 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 0.593992 # mshr miss rate for overall accesses
|
|
system.cpu.l2cache.overall_mshr_misses 314075 # 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 84499 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 99950 # 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 16402.920353 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 423239 # Total number of references to valid blocks.
|
|
system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit.
|
|
system.cpu.l2cache.writebacks 61948 # number of writebacks
|
|
system.cpu.memDep0.conflictingLoads 460341314 # Number of conflicting loads.
|
|
system.cpu.memDep0.conflictingStores 141106002 # Number of conflicting stores.
|
|
system.cpu.memDep0.insertedLoads 743909112 # Number of loads inserted to the mem dependence unit.
|
|
system.cpu.memDep0.insertedStores 301399339 # Number of stores inserted to the mem dependence unit.
|
|
system.cpu.numCycles 2205318177 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 17694861 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 1244779250 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:FullRegisterEvents 863 # Number of times there has been no free registers
|
|
system.cpu.rename.RENAME:IQFullEvents 27117 # Number of times rename has blocked due to IQ full
|
|
system.cpu.rename.RENAME:IdleCycles 826425901 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 23298995 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:ROBFullEvents 7 # Number of times rename has blocked due to ROB full
|
|
system.cpu.rename.RENAME:RenameLookups 4917191691 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 3093611594 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 2420068259 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 717791884 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 239759977 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 32521130 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 1175289009 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 369621228 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 21984761 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 170791702 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 21775082 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 43184 # Number of times that the entire CPU went into an idle state and unscheduled itself
|
|
system.cpu.workload.PROG:num_syscalls 49 # Number of system calls
|
|
|
|
---------- End Simulation Statistics ----------
|