48d4ca522a
Somehow ending threads with halt() instead of deallocate() reduces the squash count on o3 by 1 (and a few other similarly trivial changes).
439 lines
48 KiB
Text
439 lines
48 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
host_inst_rate 100618 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 204352 # Number of bytes of host memory used
|
|
host_seconds 0.06 # Real time elapsed on the host
|
|
host_tick_rate 195881226 # Simulator tick rate (ticks/s)
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 6386 # Number of instructions simulated
|
|
sim_seconds 0.000012 # Number of seconds simulated
|
|
sim_ticks 12474500 # Number of ticks simulated
|
|
system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
system.cpu.BPredUnit.BTBHits 806 # Number of BTB hits
|
|
system.cpu.BPredUnit.BTBLookups 1937 # Number of BTB lookups
|
|
system.cpu.BPredUnit.RASInCorrect 67 # Number of incorrect RAS predictions.
|
|
system.cpu.BPredUnit.condIncorrect 440 # Number of conditional branches incorrect
|
|
system.cpu.BPredUnit.condPredicted 1370 # Number of conditional branches predicted
|
|
system.cpu.BPredUnit.lookups 2263 # Number of BP lookups
|
|
system.cpu.BPredUnit.usedRAS 304 # Number of times the RAS was used to get a target.
|
|
system.cpu.commit.COM:branches 1051 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 115 # 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 12417 # 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 9514 76.62% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::1-2 1627 13.10% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::2-3 488 3.93% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::3-4 267 2.15% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::4-5 153 1.23% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::5-6 104 0.84% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::6-7 96 0.77% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::7-8 53 0.43% # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::8 115 0.93% # 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 12417 # 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 0.515664 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:committed_per_cycle::stdev 1.304890 # Number of insts commited each cycle
|
|
system.cpu.commit.COM:count 6403 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 1185 # Number of loads committed
|
|
system.cpu.commit.COM:membars 0 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 2050 # Number of memory references committed
|
|
system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed
|
|
system.cpu.commit.branchMispredicts 367 # The number of times a branch was mispredicted
|
|
system.cpu.commit.commitCommittedInsts 6403 # The number of committed instructions
|
|
system.cpu.commit.commitNonSpecStalls 17 # The number of times commit has been forced to stall to communicate backwards
|
|
system.cpu.commit.commitSquashedInsts 4640 # The number of squashed insts skipped by commit
|
|
system.cpu.committedInsts 6386 # Number of Instructions Simulated
|
|
system.cpu.committedInsts_total 6386 # Number of Instructions Simulated
|
|
system.cpu.cpi 3.906984 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 3.906984 # CPI: Total CPI of All Threads
|
|
system.cpu.dcache.ReadReq_accesses 1793 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 34316.091954 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 36237.623762 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 1619 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 5971000 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.097044 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 174 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 73 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 3660000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.056330 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 101 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 865 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 35168.421053 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35747.126437 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 485 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 13364000 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.439306 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 380 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 293 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 3110000 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.100578 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 87 # 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 12.281609 # 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 2658 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 34900.722022 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 36010.638298 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 2104 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 19335000 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.208427 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 554 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 366 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 6770000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.070730 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 188 # 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 2658 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 34900.722022 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 36010.638298 # 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 2104 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 19335000 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.208427 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 554 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 366 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 6770000 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.070730 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 188 # 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 174 # 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 110.270477 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 2137 # 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 1058 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:BranchMispred 74 # Number of times decode detected a branch misprediction
|
|
system.cpu.decode.DECODE:BranchResolved 192 # Number of times decode resolved a branch
|
|
system.cpu.decode.DECODE:DecodedInsts 12405 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 8939 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 2366 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 897 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:SquashedInsts 209 # Number of squashed instructions handled by decode
|
|
system.cpu.decode.DECODE:UnblockCycles 54 # Number of cycles decode is unblocking
|
|
system.cpu.dtb.data_accesses 2951 # DTB accesses
|
|
system.cpu.dtb.data_acv 0 # DTB access violations
|
|
system.cpu.dtb.data_hits 2890 # DTB hits
|
|
system.cpu.dtb.data_misses 61 # 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 1876 # DTB read accesses
|
|
system.cpu.dtb.read_acv 0 # DTB read access violations
|
|
system.cpu.dtb.read_hits 1840 # DTB read hits
|
|
system.cpu.dtb.read_misses 36 # DTB read misses
|
|
system.cpu.dtb.write_accesses 1075 # DTB write accesses
|
|
system.cpu.dtb.write_acv 0 # DTB write access violations
|
|
system.cpu.dtb.write_hits 1050 # DTB write hits
|
|
system.cpu.dtb.write_misses 25 # DTB write misses
|
|
system.cpu.fetch.Branches 2263 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 1802 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 4308 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 270 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 13251 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 501 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.090701 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 1802 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 1110 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 0.531102 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist::samples 13314 # 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 10844 81.45% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::1-2 252 1.89% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::2-3 238 1.79% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::3-4 230 1.73% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::4-5 272 2.04% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::5-6 162 1.22% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::6-7 232 1.74% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::7-8 129 0.97% # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::8 955 7.17% # 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 13314 # 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 0.995268 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist::stdev 2.362110 # Number of instructions fetched each cycle (Total)
|
|
system.cpu.icache.ReadReq_accesses 1802 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 35400.943396 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 35286.644951 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 1378 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 15010000 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.235294 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 424 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 117 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 10833000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.icache.ReadReq_mshr_miss_rate 0.170366 # mshr miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_mshr_misses 307 # 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 4.488599 # 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 1802 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 35400.943396 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 35286.644951 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 1378 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 15010000 # number of demand (read+write) miss cycles
|
|
system.cpu.icache.demand_miss_rate 0.235294 # miss rate for demand accesses
|
|
system.cpu.icache.demand_misses 424 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 117 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 10833000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.icache.demand_mshr_miss_rate 0.170366 # mshr miss rate for demand accesses
|
|
system.cpu.icache.demand_mshr_misses 307 # 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 1802 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 35400.943396 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 35286.644951 # 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 1378 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 15010000 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.235294 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 424 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 117 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 10833000 # number of overall MSHR miss cycles
|
|
system.cpu.icache.overall_mshr_miss_rate 0.170366 # mshr miss rate for overall accesses
|
|
system.cpu.icache.overall_mshr_misses 307 # 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 0 # number of replacements
|
|
system.cpu.icache.sampled_refs 307 # 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 158.550695 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 1378 # 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 11636 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 1450 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 82 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 0.362325 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 2959 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 1077 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 6020 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 8734 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.746013 # 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 4491 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 0.350060 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 8835 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 428 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 102 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 2287 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 24 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 201 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 1266 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 11078 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 1882 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 305 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 9040 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 8 # 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 0 # Number of times the LSQ has become full, causing a stall
|
|
system.cpu.iew.iewSquashCycles 897 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 15 # 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 46 # Number of loads that had data forwarded from stores
|
|
system.cpu.iew.lsq.thread.0.ignoredResponses 6 # 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 64 # Number of memory ordering violations
|
|
system.cpu.iew.lsq.thread.0.rescheduledLoads 1 # Number of loads that were rescheduled
|
|
system.cpu.iew.lsq.thread.0.squashedLoads 1102 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 401 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 64 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 290 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 138 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 0.255952 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 0.255952 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 9345 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
No_OpClass 2 0.02% # Type of FU issued
|
|
IntAlu 6254 66.92% # Type of FU issued
|
|
IntMult 1 0.01% # Type of FU issued
|
|
IntDiv 0 0.00% # 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 1986 21.25% # Type of FU issued
|
|
MemWrite 1100 11.77% # 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 105 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.011236 # 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 14 13.33% # 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 56 53.33% # attempts to use FU when none available
|
|
MemWrite 35 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 13314
|
|
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 9113 68.45%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::1-2 1716 12.89%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::2-3 1071 8.04%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::3-4 725 5.45%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::4-5 355 2.67%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::5-6 172 1.29%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::6-7 115 0.86%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::7-8 34 0.26%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::8 13 0.10%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00%
|
|
system.cpu.iq.ISSUE:issued_per_cycle::total 13314
|
|
system.cpu.iq.ISSUE:issued_per_cycle::max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle::mean 0.701893
|
|
system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.302449
|
|
system.cpu.iq.ISSUE:rate 0.374549 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 10972 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 9345 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 24 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 4189 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 53 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedNonSpecRemoved 7 # Number of squashed non-spec instructions that were removed
|
|
system.cpu.iq.iqSquashedOperandsExamined 2547 # 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 1838 # ITB accesses
|
|
system.cpu.itb.fetch_acv 0 # ITB acv
|
|
system.cpu.itb.fetch_hits 1802 # ITB hits
|
|
system.cpu.itb.fetch_misses 36 # 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 73 # number of ReadExReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadExReq_avg_miss_latency 34547.945205 # average ReadExReq miss latency
|
|
system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31465.753425 # average ReadExReq mshr miss latency
|
|
system.cpu.l2cache.ReadExReq_miss_latency 2522000 # number of ReadExReq miss cycles
|
|
system.cpu.l2cache.ReadExReq_miss_rate 1 # miss rate for ReadExReq accesses
|
|
system.cpu.l2cache.ReadExReq_misses 73 # number of ReadExReq misses
|
|
system.cpu.l2cache.ReadExReq_mshr_miss_latency 2297000 # 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 73 # number of ReadExReq MSHR misses
|
|
system.cpu.l2cache.ReadReq_accesses 408 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 34421.375921 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31240.786241 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_hits 1 # number of ReadReq hits
|
|
system.cpu.l2cache.ReadReq_miss_latency 14009500 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 0.997549 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 407 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 12715000 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 0.997549 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 407 # number of ReadReq MSHR misses
|
|
system.cpu.l2cache.UpgradeReq_accesses 14 # number of UpgradeReq accesses(hits+misses)
|
|
system.cpu.l2cache.UpgradeReq_avg_miss_latency 34357.142857 # average UpgradeReq miss latency
|
|
system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31142.857143 # average UpgradeReq mshr miss latency
|
|
system.cpu.l2cache.UpgradeReq_miss_latency 481000 # number of UpgradeReq miss cycles
|
|
system.cpu.l2cache.UpgradeReq_miss_rate 1 # miss rate for UpgradeReq accesses
|
|
system.cpu.l2cache.UpgradeReq_misses 14 # number of UpgradeReq misses
|
|
system.cpu.l2cache.UpgradeReq_mshr_miss_latency 436000 # 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 14 # 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 0.002545 # 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 481 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 34440.625000 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 31275 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 1 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 16531500 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 0.997921 # miss rate for demand accesses
|
|
system.cpu.l2cache.demand_misses 480 # 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 15012000 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 0.997921 # mshr miss rate for demand accesses
|
|
system.cpu.l2cache.demand_mshr_misses 480 # 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 481 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 34440.625000 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 31275 # 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 1 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 16531500 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 0.997921 # miss rate for overall accesses
|
|
system.cpu.l2cache.overall_misses 480 # number of overall misses
|
|
system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits
|
|
system.cpu.l2cache.overall_mshr_miss_latency 15012000 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 0.997921 # mshr miss rate for overall accesses
|
|
system.cpu.l2cache.overall_mshr_misses 480 # 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 393 # 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 214.901533 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 1 # 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 36 # Number of conflicting loads.
|
|
system.cpu.memDep0.conflictingStores 29 # Number of conflicting stores.
|
|
system.cpu.memDep0.insertedLoads 2287 # Number of loads inserted to the mem dependence unit.
|
|
system.cpu.memDep0.insertedStores 1266 # Number of stores inserted to the mem dependence unit.
|
|
system.cpu.numCycles 24950 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 371 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 4583 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:IQFullEvents 6 # Number of times rename has blocked due to IQ full
|
|
system.cpu.rename.RENAME:IdleCycles 9094 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 226 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:RenameLookups 15058 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 11988 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 8902 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 2263 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 897 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 258 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 4319 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 431 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 26 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 663 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 20 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 237 # Number of times that the entire CPU went into an idle state and unscheduled itself
|
|
system.cpu.workload.PROG:num_syscalls 17 # Number of system calls
|
|
|
|
---------- End Simulation Statistics ----------
|