28fd4ab39f
Fix a small writeback bug when missing in the L2 in atomic mode
src/mem/bus.cc:
Fix a comment to make sense
src/mem/cache/cache_impl.hh:
Do a functional access to levels above on a read as a temporary solution for L2's in FS
Also fix a small writeback miss in L2 issue
src/mem/cache/coherence/simple_coherence.hh:
src/mem/cache/coherence/uni_coherence.cc:
src/mem/cache/coherence/uni_coherence.hh:
Do a functional access to levels above on a read as a temporary solution for L2's in FS
tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt:
tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt:
Update ref's for writeback changes
--HG--
extra : convert_revision : 937febd577b16b7fd97a5a68acaf53541828a251
410 lines
44 KiB
Text
410 lines
44 KiB
Text
|
|
---------- Begin Simulation Statistics ----------
|
|
global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly.
|
|
global.BPredUnit.BTBHits 675 # Number of BTB hits
|
|
global.BPredUnit.BTBLookups 2343 # Number of BTB lookups
|
|
global.BPredUnit.RASInCorrect 76 # Number of incorrect RAS predictions.
|
|
global.BPredUnit.condIncorrect 437 # Number of conditional branches incorrect
|
|
global.BPredUnit.condPredicted 1563 # Number of conditional branches predicted
|
|
global.BPredUnit.lookups 5229 # Number of BP lookups
|
|
global.BPredUnit.usedRAS 2821 # Number of times the RAS was used to get a target.
|
|
host_inst_rate 15743 # Simulator instruction rate (inst/s)
|
|
host_mem_usage 180184 # Number of bytes of host memory used
|
|
host_seconds 0.36 # Real time elapsed on the host
|
|
host_tick_rate 3916768 # Simulator tick rate (ticks/s)
|
|
memdepunit.memDep.conflictingLoads 23 # Number of conflicting loads.
|
|
memdepunit.memDep.conflictingStores 117 # Number of conflicting stores.
|
|
memdepunit.memDep.insertedLoads 3775 # Number of loads inserted to the mem dependence unit.
|
|
memdepunit.memDep.insertedStores 3734 # Number of stores inserted to the mem dependence unit.
|
|
sim_freq 1000000000000 # Frequency of simulated ticks
|
|
sim_insts 5623 # Number of instructions simulated
|
|
sim_seconds 0.000001 # Number of seconds simulated
|
|
sim_ticks 1400135 # Number of ticks simulated
|
|
system.cpu.commit.COM:branches 862 # Number of branches committed
|
|
system.cpu.commit.COM:bw_lim_events 97 # 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 51243
|
|
system.cpu.commit.COM:committed_per_cycle.min_value 0
|
|
0 48519 9468.42%
|
|
1 1590 310.29%
|
|
2 483 94.26%
|
|
3 227 44.30%
|
|
4 131 25.56%
|
|
5 104 20.30%
|
|
6 61 11.90%
|
|
7 31 6.05%
|
|
8 97 18.93%
|
|
system.cpu.commit.COM:committed_per_cycle.max_value 8
|
|
system.cpu.commit.COM:committed_per_cycle.end_dist
|
|
|
|
system.cpu.commit.COM:count 5640 # Number of instructions committed
|
|
system.cpu.commit.COM:loads 979 # Number of loads committed
|
|
system.cpu.commit.COM:membars 0 # Number of memory barriers committed
|
|
system.cpu.commit.COM:refs 1791 # Number of memory references committed
|
|
system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed
|
|
system.cpu.commit.branchMispredicts 368 # The number of times a branch was mispredicted
|
|
system.cpu.commit.commitCommittedInsts 5640 # 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 13830 # The number of squashed insts skipped by commit
|
|
system.cpu.committedInsts 5623 # Number of Instructions Simulated
|
|
system.cpu.committedInsts_total 5623 # Number of Instructions Simulated
|
|
system.cpu.cpi 249.001423 # CPI: Cycles Per Instruction
|
|
system.cpu.cpi_total 249.001423 # CPI: Total CPI of All Threads
|
|
system.cpu.dcache.ReadReq_accesses 1600 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.dcache.ReadReq_avg_miss_latency 6986.684848 # average ReadReq miss latency
|
|
system.cpu.dcache.ReadReq_avg_mshr_miss_latency 6882.626263 # average ReadReq mshr miss latency
|
|
system.cpu.dcache.ReadReq_hits 1435 # number of ReadReq hits
|
|
system.cpu.dcache.ReadReq_miss_latency 1152803 # number of ReadReq miss cycles
|
|
system.cpu.dcache.ReadReq_miss_rate 0.103125 # miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_misses 165 # number of ReadReq misses
|
|
system.cpu.dcache.ReadReq_mshr_hits 66 # number of ReadReq MSHR hits
|
|
system.cpu.dcache.ReadReq_mshr_miss_latency 681380 # number of ReadReq MSHR miss cycles
|
|
system.cpu.dcache.ReadReq_mshr_miss_rate 0.061875 # mshr miss rate for ReadReq accesses
|
|
system.cpu.dcache.ReadReq_mshr_misses 99 # number of ReadReq MSHR misses
|
|
system.cpu.dcache.WriteReq_accesses 812 # number of WriteReq accesses(hits+misses)
|
|
system.cpu.dcache.WriteReq_avg_miss_latency 5293.047244 # average WriteReq miss latency
|
|
system.cpu.dcache.WriteReq_avg_mshr_miss_latency 5141.082192 # average WriteReq mshr miss latency
|
|
system.cpu.dcache.WriteReq_hits 558 # number of WriteReq hits
|
|
system.cpu.dcache.WriteReq_miss_latency 1344434 # number of WriteReq miss cycles
|
|
system.cpu.dcache.WriteReq_miss_rate 0.312808 # miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_misses 254 # number of WriteReq misses
|
|
system.cpu.dcache.WriteReq_mshr_hits 181 # number of WriteReq MSHR hits
|
|
system.cpu.dcache.WriteReq_mshr_miss_latency 375299 # number of WriteReq MSHR miss cycles
|
|
system.cpu.dcache.WriteReq_mshr_miss_rate 0.089901 # mshr miss rate for WriteReq accesses
|
|
system.cpu.dcache.WriteReq_mshr_misses 73 # number of WriteReq MSHR misses
|
|
system.cpu.dcache.avg_blocked_cycles_no_mshrs no value # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_blocked_cycles_no_targets 3366.651163 # average number of cycles each access was blocked
|
|
system.cpu.dcache.avg_refs 11.587209 # 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 43 # 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 144766 # number of cycles access was blocked
|
|
system.cpu.dcache.cache_copies 0 # number of cache copies performed
|
|
system.cpu.dcache.demand_accesses 2412 # number of demand (read+write) accesses
|
|
system.cpu.dcache.demand_avg_miss_latency 5959.992840 # average overall miss latency
|
|
system.cpu.dcache.demand_avg_mshr_miss_latency 6143.482558 # average overall mshr miss latency
|
|
system.cpu.dcache.demand_hits 1993 # number of demand (read+write) hits
|
|
system.cpu.dcache.demand_miss_latency 2497237 # number of demand (read+write) miss cycles
|
|
system.cpu.dcache.demand_miss_rate 0.173715 # miss rate for demand accesses
|
|
system.cpu.dcache.demand_misses 419 # number of demand (read+write) misses
|
|
system.cpu.dcache.demand_mshr_hits 247 # number of demand (read+write) MSHR hits
|
|
system.cpu.dcache.demand_mshr_miss_latency 1056679 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.dcache.demand_mshr_miss_rate 0.071310 # mshr miss rate for demand accesses
|
|
system.cpu.dcache.demand_mshr_misses 172 # 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 2412 # number of overall (read+write) accesses
|
|
system.cpu.dcache.overall_avg_miss_latency 5959.992840 # average overall miss latency
|
|
system.cpu.dcache.overall_avg_mshr_miss_latency 6143.482558 # 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 1993 # number of overall hits
|
|
system.cpu.dcache.overall_miss_latency 2497237 # number of overall miss cycles
|
|
system.cpu.dcache.overall_miss_rate 0.173715 # miss rate for overall accesses
|
|
system.cpu.dcache.overall_misses 419 # number of overall misses
|
|
system.cpu.dcache.overall_mshr_hits 247 # number of overall MSHR hits
|
|
system.cpu.dcache.overall_mshr_miss_latency 1056679 # number of overall MSHR miss cycles
|
|
system.cpu.dcache.overall_mshr_miss_rate 0.071310 # mshr miss rate for overall accesses
|
|
system.cpu.dcache.overall_mshr_misses 172 # 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.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache
|
|
system.cpu.dcache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.dcache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.dcache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.dcache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.dcache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
system.cpu.dcache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated
|
|
system.cpu.dcache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page
|
|
system.cpu.dcache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time
|
|
system.cpu.dcache.replacements 0 # number of replacements
|
|
system.cpu.dcache.sampled_refs 172 # 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 101.349720 # Cycle average of tags in use
|
|
system.cpu.dcache.total_refs 1993 # 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 17501 # Number of cycles decode is blocked
|
|
system.cpu.decode.DECODE:BranchMispred 70 # Number of times decode detected a branch misprediction
|
|
system.cpu.decode.DECODE:BranchResolved 168 # Number of times decode resolved a branch
|
|
system.cpu.decode.DECODE:DecodedInsts 29666 # Number of instructions handled by decode
|
|
system.cpu.decode.DECODE:IdleCycles 28130 # Number of cycles decode is idle
|
|
system.cpu.decode.DECODE:RunCycles 5553 # Number of cycles decode is running
|
|
system.cpu.decode.DECODE:SquashCycles 2529 # Number of cycles decode is squashing
|
|
system.cpu.decode.DECODE:SquashedInsts 200 # Number of squashed instructions handled by decode
|
|
system.cpu.decode.DECODE:UnblockCycles 60 # Number of cycles decode is unblocking
|
|
system.cpu.fetch.Branches 5229 # Number of branches that fetch encountered
|
|
system.cpu.fetch.CacheLines 6371 # Number of cache lines fetched
|
|
system.cpu.fetch.Cycles 13322 # Number of cycles fetch has run and was not squashing or blocked
|
|
system.cpu.fetch.IcacheSquashes 296 # Number of outstanding Icache misses that were squashed
|
|
system.cpu.fetch.Insts 35572 # Number of instructions fetch has processed
|
|
system.cpu.fetch.SquashCycles 2057 # Number of cycles fetch has spent squashing
|
|
system.cpu.fetch.branchRate 0.097242 # Number of branch fetches per cycle
|
|
system.cpu.fetch.icacheStallCycles 6371 # Number of cycles fetch is stalled on an Icache miss
|
|
system.cpu.fetch.predictedBranches 3496 # Number of branches that fetch has predicted taken
|
|
system.cpu.fetch.rate 0.661522 # Number of inst fetches per cycle
|
|
system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total)
|
|
system.cpu.fetch.rateDist.samples 53773
|
|
system.cpu.fetch.rateDist.min_value 0
|
|
0 46825 8707.90%
|
|
1 199 37.01%
|
|
2 504 93.73%
|
|
3 1429 265.75%
|
|
4 1462 271.88%
|
|
5 245 45.56%
|
|
6 322 59.88%
|
|
7 1223 227.44%
|
|
8 1564 290.85%
|
|
system.cpu.fetch.rateDist.max_value 8
|
|
system.cpu.fetch.rateDist.end_dist
|
|
|
|
system.cpu.icache.ReadReq_accesses 6370 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.icache.ReadReq_avg_miss_latency 5088.614350 # average ReadReq miss latency
|
|
system.cpu.icache.ReadReq_avg_mshr_miss_latency 4278.032258 # average ReadReq mshr miss latency
|
|
system.cpu.icache.ReadReq_hits 5924 # number of ReadReq hits
|
|
system.cpu.icache.ReadReq_miss_latency 2269522 # number of ReadReq miss cycles
|
|
system.cpu.icache.ReadReq_miss_rate 0.070016 # miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_misses 446 # number of ReadReq misses
|
|
system.cpu.icache.ReadReq_mshr_hits 136 # number of ReadReq MSHR hits
|
|
system.cpu.icache.ReadReq_mshr_miss_latency 1326190 # number of ReadReq MSHR miss cycles
|
|
system.cpu.icache.ReadReq_mshr_miss_rate 0.048666 # mshr miss rate for ReadReq accesses
|
|
system.cpu.icache.ReadReq_mshr_misses 310 # 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 3444.375000 # average number of cycles each access was blocked
|
|
system.cpu.icache.avg_refs 19.109677 # 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 8 # 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 27555 # number of cycles access was blocked
|
|
system.cpu.icache.cache_copies 0 # number of cache copies performed
|
|
system.cpu.icache.demand_accesses 6370 # number of demand (read+write) accesses
|
|
system.cpu.icache.demand_avg_miss_latency 5088.614350 # average overall miss latency
|
|
system.cpu.icache.demand_avg_mshr_miss_latency 4278.032258 # average overall mshr miss latency
|
|
system.cpu.icache.demand_hits 5924 # number of demand (read+write) hits
|
|
system.cpu.icache.demand_miss_latency 2269522 # number of demand (read+write) miss cycles
|
|
system.cpu.icache.demand_miss_rate 0.070016 # miss rate for demand accesses
|
|
system.cpu.icache.demand_misses 446 # number of demand (read+write) misses
|
|
system.cpu.icache.demand_mshr_hits 136 # number of demand (read+write) MSHR hits
|
|
system.cpu.icache.demand_mshr_miss_latency 1326190 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.icache.demand_mshr_miss_rate 0.048666 # mshr miss rate for demand accesses
|
|
system.cpu.icache.demand_mshr_misses 310 # 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 6370 # number of overall (read+write) accesses
|
|
system.cpu.icache.overall_avg_miss_latency 5088.614350 # average overall miss latency
|
|
system.cpu.icache.overall_avg_mshr_miss_latency 4278.032258 # 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 5924 # number of overall hits
|
|
system.cpu.icache.overall_miss_latency 2269522 # number of overall miss cycles
|
|
system.cpu.icache.overall_miss_rate 0.070016 # miss rate for overall accesses
|
|
system.cpu.icache.overall_misses 446 # number of overall misses
|
|
system.cpu.icache.overall_mshr_hits 136 # number of overall MSHR hits
|
|
system.cpu.icache.overall_mshr_miss_latency 1326190 # number of overall MSHR miss cycles
|
|
system.cpu.icache.overall_mshr_miss_rate 0.048666 # mshr miss rate for overall accesses
|
|
system.cpu.icache.overall_mshr_misses 310 # 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.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache
|
|
system.cpu.icache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.icache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.icache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.icache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.icache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
system.cpu.icache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated
|
|
system.cpu.icache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page
|
|
system.cpu.icache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time
|
|
system.cpu.icache.replacements 0 # number of replacements
|
|
system.cpu.icache.sampled_refs 310 # 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 147.070827 # Cycle average of tags in use
|
|
system.cpu.icache.total_refs 5924 # 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 1346363 # Total number of cycles that the CPU has spent unscheduled due to idling
|
|
system.cpu.iew.EXEC:branches 2364 # Number of branches executed
|
|
system.cpu.iew.EXEC:nop 48 # number of nop insts executed
|
|
system.cpu.iew.EXEC:rate 0.251650 # Inst execution rate
|
|
system.cpu.iew.EXEC:refs 5460 # number of memory reference insts executed
|
|
system.cpu.iew.EXEC:stores 2123 # Number of stores executed
|
|
system.cpu.iew.EXEC:swp 0 # number of swp insts executed
|
|
system.cpu.iew.WB:consumers 6466 # num instructions consuming a value
|
|
system.cpu.iew.WB:count 11620 # cumulative count of insts written-back
|
|
system.cpu.iew.WB:fanout 0.798639 # 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 5164 # num instructions producing a value
|
|
system.cpu.iew.WB:rate 0.216094 # insts written-back per cycle
|
|
system.cpu.iew.WB:sent 11692 # cumulative count of insts sent to commit
|
|
system.cpu.iew.branchMispredicts 401 # Number of branch mispredicts detected at execute
|
|
system.cpu.iew.iewBlockCycles 7230 # Number of cycles IEW is blocking
|
|
system.cpu.iew.iewDispLoadInsts 3775 # Number of dispatched load instructions
|
|
system.cpu.iew.iewDispNonSpecInsts 24 # Number of dispatched non-speculative instructions
|
|
system.cpu.iew.iewDispSquashedInsts 2557 # Number of squashed instructions skipped by dispatch
|
|
system.cpu.iew.iewDispStoreInsts 3734 # Number of dispatched store instructions
|
|
system.cpu.iew.iewDispatchedInsts 19465 # Number of instructions dispatched to IQ
|
|
system.cpu.iew.iewExecLoadInsts 3337 # Number of load instructions executed
|
|
system.cpu.iew.iewExecSquashedInsts 308 # Number of squashed instructions skipped in execute
|
|
system.cpu.iew.iewExecutedInsts 13532 # Number of executed instructions
|
|
system.cpu.iew.iewIQFullEvents 10 # 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 2529 # Number of cycles IEW is squashing
|
|
system.cpu.iew.iewUnblockCycles 39 # Number of cycles IEW is unblocking
|
|
system.cpu.iew.lsq.thread.0.blockedLoads 1 # Number of blocked loads due to partial load-store forwarding
|
|
system.cpu.iew.lsq.thread.0.cacheBlocked 1656 # Number of times an access to memory failed due to the cache being blocked
|
|
system.cpu.iew.lsq.thread.0.forwLoads 81 # 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 40 # 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 2796 # Number of loads squashed
|
|
system.cpu.iew.lsq.thread.0.squashedStores 2922 # Number of stores squashed
|
|
system.cpu.iew.memOrderViolationEvents 40 # Number of memory order violations
|
|
system.cpu.iew.predictedNotTakenIncorrect 281 # Number of branches that were predicted not taken incorrectly
|
|
system.cpu.iew.predictedTakenIncorrect 120 # Number of branches that were predicted taken incorrectly
|
|
system.cpu.ipc 0.004016 # IPC: Instructions Per Cycle
|
|
system.cpu.ipc_total 0.004016 # IPC: Total IPC of All Threads
|
|
system.cpu.iq.ISSUE:FU_type_0 13840 # Type of FU issued
|
|
system.cpu.iq.ISSUE:FU_type_0.start_dist
|
|
(null) 2 0.01% # Type of FU issued
|
|
IntAlu 8249 59.60% # Type of FU issued
|
|
IntMult 1 0.01% # Type of FU issued
|
|
IntDiv 0 0.00% # Type of FU issued
|
|
FloatAdd 2 0.01% # 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 3432 24.80% # Type of FU issued
|
|
MemWrite 2154 15.56% # 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 86 # FU busy when requested
|
|
system.cpu.iq.ISSUE:fu_busy_rate 0.006214 # FU busy rate (busy events/executed inst)
|
|
system.cpu.iq.ISSUE:fu_full.start_dist
|
|
(null) 0 0.00% # attempts to use FU when none available
|
|
IntAlu 1 1.16% # 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 53 61.63% # attempts to use FU when none available
|
|
MemWrite 32 37.21% # 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.start_dist # Number of insts issued each cycle
|
|
system.cpu.iq.ISSUE:issued_per_cycle.samples 53773
|
|
system.cpu.iq.ISSUE:issued_per_cycle.min_value 0
|
|
0 46903 8722.41%
|
|
1 3262 606.62%
|
|
2 1316 244.73%
|
|
3 1665 309.63%
|
|
4 333 61.93%
|
|
5 188 34.96%
|
|
6 73 13.58%
|
|
7 23 4.28%
|
|
8 10 1.86%
|
|
system.cpu.iq.ISSUE:issued_per_cycle.max_value 8
|
|
system.cpu.iq.ISSUE:issued_per_cycle.end_dist
|
|
|
|
system.cpu.iq.ISSUE:rate 0.257378 # Inst issue rate
|
|
system.cpu.iq.iqInstsAdded 19393 # Number of instructions added to the IQ (excludes non-spec)
|
|
system.cpu.iq.iqInstsIssued 13840 # Number of instructions issued
|
|
system.cpu.iq.iqNonSpecInstsAdded 24 # Number of non-speculative instructions added to the IQ
|
|
system.cpu.iq.iqSquashedInstsExamined 13381 # Number of squashed instructions iterated over during squash; mainly for profiling
|
|
system.cpu.iq.iqSquashedInstsIssued 72 # Number of squashed instructions issued
|
|
system.cpu.iq.iqSquashedNonSpecRemoved 7 # Number of squashed non-spec instructions that were removed
|
|
system.cpu.iq.iqSquashedOperandsExamined 9575 # Number of squashed operands that are examined and possibly removed from graph
|
|
system.cpu.l2cache.ReadReq_accesses 480 # number of ReadReq accesses(hits+misses)
|
|
system.cpu.l2cache.ReadReq_avg_miss_latency 4520.691667 # average ReadReq miss latency
|
|
system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 2303.372917 # average ReadReq mshr miss latency
|
|
system.cpu.l2cache.ReadReq_miss_latency 2169932 # number of ReadReq miss cycles
|
|
system.cpu.l2cache.ReadReq_miss_rate 1 # miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_misses 480 # number of ReadReq misses
|
|
system.cpu.l2cache.ReadReq_mshr_miss_latency 1105619 # number of ReadReq MSHR miss cycles
|
|
system.cpu.l2cache.ReadReq_mshr_miss_rate 1 # mshr miss rate for ReadReq accesses
|
|
system.cpu.l2cache.ReadReq_mshr_misses 480 # number of ReadReq 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 # 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 480 # number of demand (read+write) accesses
|
|
system.cpu.l2cache.demand_avg_miss_latency 4520.691667 # average overall miss latency
|
|
system.cpu.l2cache.demand_avg_mshr_miss_latency 2303.372917 # average overall mshr miss latency
|
|
system.cpu.l2cache.demand_hits 0 # number of demand (read+write) hits
|
|
system.cpu.l2cache.demand_miss_latency 2169932 # number of demand (read+write) miss cycles
|
|
system.cpu.l2cache.demand_miss_rate 1 # 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 1105619 # number of demand (read+write) MSHR miss cycles
|
|
system.cpu.l2cache.demand_mshr_miss_rate 1 # 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 480 # number of overall (read+write) accesses
|
|
system.cpu.l2cache.overall_avg_miss_latency 4520.691667 # average overall miss latency
|
|
system.cpu.l2cache.overall_avg_mshr_miss_latency 2303.372917 # 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 0 # number of overall hits
|
|
system.cpu.l2cache.overall_miss_latency 2169932 # number of overall miss cycles
|
|
system.cpu.l2cache.overall_miss_rate 1 # 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 1105619 # number of overall MSHR miss cycles
|
|
system.cpu.l2cache.overall_mshr_miss_rate 1 # 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.prefetcher.num_hwpf_already_in_cache 0 # number of hwpf that were already in the cache
|
|
system.cpu.l2cache.prefetcher.num_hwpf_already_in_mshr 0 # number of hwpf that were already in mshr
|
|
system.cpu.l2cache.prefetcher.num_hwpf_already_in_prefetcher 0 # number of hwpf that were already in the prefetch queue
|
|
system.cpu.l2cache.prefetcher.num_hwpf_evicted 0 # number of hwpf removed due to no buffer left
|
|
system.cpu.l2cache.prefetcher.num_hwpf_identified 0 # number of hwpf identified
|
|
system.cpu.l2cache.prefetcher.num_hwpf_issued 0 # number of hwpf issued
|
|
system.cpu.l2cache.prefetcher.num_hwpf_removed_MSHR_hit 0 # number of hwpf removed because MSHR allocated
|
|
system.cpu.l2cache.prefetcher.num_hwpf_span_page 0 # number of hwpf spanning a virtual page
|
|
system.cpu.l2cache.prefetcher.num_hwpf_squashed_from_miss 0 # number of hwpf that got squashed due to a miss aborting calculation time
|
|
system.cpu.l2cache.replacements 0 # number of replacements
|
|
system.cpu.l2cache.sampled_refs 480 # 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 248.469634 # Cycle average of tags in use
|
|
system.cpu.l2cache.total_refs 0 # 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.numCycles 53773 # number of cpu cycles simulated
|
|
system.cpu.rename.RENAME:BlockCycles 7860 # Number of cycles rename is blocking
|
|
system.cpu.rename.RENAME:CommittedMaps 4051 # Number of HB maps that are committed
|
|
system.cpu.rename.RENAME:IQFullEvents 2 # Number of times rename has blocked due to IQ full
|
|
system.cpu.rename.RENAME:IdleCycles 28280 # Number of cycles rename is idle
|
|
system.cpu.rename.RENAME:LSQFullEvents 453 # Number of times rename has blocked due to LSQ full
|
|
system.cpu.rename.RENAME:ROBFullEvents 8 # Number of times rename has blocked due to ROB full
|
|
system.cpu.rename.RENAME:RenameLookups 36016 # Number of register rename lookups that rename has made
|
|
system.cpu.rename.RENAME:RenamedInsts 29203 # Number of instructions processed by rename
|
|
system.cpu.rename.RENAME:RenamedOperands 20142 # Number of destination operands rename has renamed
|
|
system.cpu.rename.RENAME:RunCycles 5460 # Number of cycles rename is running
|
|
system.cpu.rename.RENAME:SquashCycles 2529 # Number of cycles rename is squashing
|
|
system.cpu.rename.RENAME:UnblockCycles 483 # Number of cycles rename is unblocking
|
|
system.cpu.rename.RENAME:UndoneMaps 16091 # Number of HB maps that are undone due to squashing
|
|
system.cpu.rename.RENAME:serializeStallCycles 9161 # count of cycles rename stalled for serializing inst
|
|
system.cpu.rename.RENAME:serializingInsts 27 # count of serializing insts renamed
|
|
system.cpu.rename.RENAME:skidInsts 828 # count of insts added to the skid buffer
|
|
system.cpu.rename.RENAME:tempSerializingInsts 21 # count of temporary serializing insts renamed
|
|
system.cpu.timesIdled 369 # 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 ----------
|