diff options
| author | Gabe Black <gblack@eecs.umich.edu> | 2011-02-05 00:16:09 -0800 |
|---|---|---|
| committer | Gabe Black <gblack@eecs.umich.edu> | 2011-02-05 00:16:09 -0800 |
| commit | 55df9e348c98f25006ac8a95d11bb2cc6b0fdde7 (patch) | |
| tree | c0315fadc19ae7200085f5a0fd7a8dd2ce6d1076 /tests/long/20.parser/ref/x86 | |
| parent | 0aafbe4098dbf41b24b8279bb5e691b702b4383a (diff) | |
| download | gem5-55df9e348c98f25006ac8a95d11bb2cc6b0fdde7.tar.xz | |
X86: Add o3 regressions in SE mode.
Exclude bzip2 for now. It works, it just takes too long to run.
Diffstat (limited to 'tests/long/20.parser/ref/x86')
4 files changed, 1057 insertions, 0 deletions
diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini b/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini new file mode 100644 index 000000000..aa5254a3b --- /dev/null +++ b/tests/long/20.parser/ref/x86/linux/o3-timing/config.ini @@ -0,0 +1,519 @@ +[root] +type=Root +children=system +time_sync_enable=false +time_sync_period=100000000000 +time_sync_spin_threshold=100000000 + +[system] +type=System +children=cpu membus physmem +mem_mode=atomic +physmem=system.physmem + +[system.cpu] +type=DerivO3CPU +children=dcache dtb fuPool icache itb l2cache toL2Bus tracer workload +BTBEntries=4096 +BTBTagSize=16 +LFSTSize=1024 +LQEntries=32 +RASSize=16 +SQEntries=32 +SSITSize=1024 +activity=0 +backComSize=5 +cachePorts=200 +checker=Null +choiceCtrBits=2 +choicePredictorSize=8192 +clock=500 +commitToDecodeDelay=1 +commitToFetchDelay=1 +commitToIEWDelay=1 +commitToRenameDelay=1 +commitWidth=8 +cpu_id=0 +decodeToFetchDelay=1 +decodeToRenameDelay=1 +decodeWidth=8 +defer_registration=false +dispatchWidth=8 +do_checkpoint_insts=true +do_statistics_insts=true +dtb=system.cpu.dtb +fetchToDecodeDelay=1 +fetchTrapLatency=1 +fetchWidth=8 +forwardComSize=5 +fuPool=system.cpu.fuPool +function_trace=false +function_trace_start=0 +globalCtrBits=2 +globalHistoryBits=13 +globalPredictorSize=8192 +iewToCommitDelay=1 +iewToDecodeDelay=1 +iewToFetchDelay=1 +iewToRenameDelay=1 +instShiftAmt=2 +issueToExecuteDelay=1 +issueWidth=8 +itb=system.cpu.itb +localCtrBits=2 +localHistoryBits=11 +localHistoryTableSize=2048 +localPredictorSize=2048 +max_insts_all_threads=0 +max_insts_any_thread=0 +max_loads_all_threads=0 +max_loads_any_thread=0 +numIQEntries=64 +numPhysFloatRegs=256 +numPhysIntRegs=256 +numROBEntries=192 +numRobs=1 +numThreads=1 +phase=0 +predType=tournament +progress_interval=0 +renameToDecodeDelay=1 +renameToFetchDelay=1 +renameToIEWDelay=2 +renameToROBDelay=1 +renameWidth=8 +smtCommitPolicy=RoundRobin +smtFetchPolicy=SingleThread +smtIQPolicy=Partitioned +smtIQThreshold=100 +smtLSQPolicy=Partitioned +smtLSQThreshold=100 +smtNumFetchingThreads=1 +smtROBPolicy=Partitioned +smtROBThreshold=100 +squashWidth=8 +system=system +tracer=system.cpu.tracer +trapLatency=13 +wbDepth=1 +wbWidth=8 +workload=system.cpu.workload +dcache_port=system.cpu.dcache.cpu_side +icache_port=system.cpu.icache.cpu_side + +[system.cpu.dcache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=262144 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.dcache_port +mem_side=system.cpu.toL2Bus.port[1] + +[system.cpu.dtb] +type=X86TLB +size=64 + +[system.cpu.fuPool] +type=FUPool +children=FUList0 FUList1 FUList2 FUList3 FUList4 FUList5 FUList6 FUList7 FUList8 +FUList=system.cpu.fuPool.FUList0 system.cpu.fuPool.FUList1 system.cpu.fuPool.FUList2 system.cpu.fuPool.FUList3 system.cpu.fuPool.FUList4 system.cpu.fuPool.FUList5 system.cpu.fuPool.FUList6 system.cpu.fuPool.FUList7 system.cpu.fuPool.FUList8 + +[system.cpu.fuPool.FUList0] +type=FUDesc +children=opList +count=6 +opList=system.cpu.fuPool.FUList0.opList + +[system.cpu.fuPool.FUList0.opList] +type=OpDesc +issueLat=1 +opClass=IntAlu +opLat=1 + +[system.cpu.fuPool.FUList1] +type=FUDesc +children=opList0 opList1 +count=2 +opList=system.cpu.fuPool.FUList1.opList0 system.cpu.fuPool.FUList1.opList1 + +[system.cpu.fuPool.FUList1.opList0] +type=OpDesc +issueLat=1 +opClass=IntMult +opLat=3 + +[system.cpu.fuPool.FUList1.opList1] +type=OpDesc +issueLat=19 +opClass=IntDiv +opLat=20 + +[system.cpu.fuPool.FUList2] +type=FUDesc +children=opList0 opList1 opList2 +count=4 +opList=system.cpu.fuPool.FUList2.opList0 system.cpu.fuPool.FUList2.opList1 system.cpu.fuPool.FUList2.opList2 + +[system.cpu.fuPool.FUList2.opList0] +type=OpDesc +issueLat=1 +opClass=FloatAdd +opLat=2 + +[system.cpu.fuPool.FUList2.opList1] +type=OpDesc +issueLat=1 +opClass=FloatCmp +opLat=2 + +[system.cpu.fuPool.FUList2.opList2] +type=OpDesc +issueLat=1 +opClass=FloatCvt +opLat=2 + +[system.cpu.fuPool.FUList3] +type=FUDesc +children=opList0 opList1 opList2 +count=2 +opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 + +[system.cpu.fuPool.FUList3.opList0] +type=OpDesc +issueLat=1 +opClass=FloatMult +opLat=4 + +[system.cpu.fuPool.FUList3.opList1] +type=OpDesc +issueLat=12 +opClass=FloatDiv +opLat=12 + +[system.cpu.fuPool.FUList3.opList2] +type=OpDesc +issueLat=24 +opClass=FloatSqrt +opLat=24 + +[system.cpu.fuPool.FUList4] +type=FUDesc +children=opList +count=0 +opList=system.cpu.fuPool.FUList4.opList + +[system.cpu.fuPool.FUList4.opList] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu.fuPool.FUList5] +type=FUDesc +children=opList00 opList01 opList02 opList03 opList04 opList05 opList06 opList07 opList08 opList09 opList10 opList11 opList12 opList13 opList14 opList15 opList16 opList17 opList18 opList19 +count=4 +opList=system.cpu.fuPool.FUList5.opList00 system.cpu.fuPool.FUList5.opList01 system.cpu.fuPool.FUList5.opList02 system.cpu.fuPool.FUList5.opList03 system.cpu.fuPool.FUList5.opList04 system.cpu.fuPool.FUList5.opList05 system.cpu.fuPool.FUList5.opList06 system.cpu.fuPool.FUList5.opList07 system.cpu.fuPool.FUList5.opList08 system.cpu.fuPool.FUList5.opList09 system.cpu.fuPool.FUList5.opList10 system.cpu.fuPool.FUList5.opList11 system.cpu.fuPool.FUList5.opList12 system.cpu.fuPool.FUList5.opList13 system.cpu.fuPool.FUList5.opList14 system.cpu.fuPool.FUList5.opList15 system.cpu.fuPool.FUList5.opList16 system.cpu.fuPool.FUList5.opList17 system.cpu.fuPool.FUList5.opList18 system.cpu.fuPool.FUList5.opList19 + +[system.cpu.fuPool.FUList5.opList00] +type=OpDesc +issueLat=1 +opClass=SimdAdd +opLat=1 + +[system.cpu.fuPool.FUList5.opList01] +type=OpDesc +issueLat=1 +opClass=SimdAddAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList02] +type=OpDesc +issueLat=1 +opClass=SimdAlu +opLat=1 + +[system.cpu.fuPool.FUList5.opList03] +type=OpDesc +issueLat=1 +opClass=SimdCmp +opLat=1 + +[system.cpu.fuPool.FUList5.opList04] +type=OpDesc +issueLat=1 +opClass=SimdCvt +opLat=1 + +[system.cpu.fuPool.FUList5.opList05] +type=OpDesc +issueLat=1 +opClass=SimdMisc +opLat=1 + +[system.cpu.fuPool.FUList5.opList06] +type=OpDesc +issueLat=1 +opClass=SimdMult +opLat=1 + +[system.cpu.fuPool.FUList5.opList07] +type=OpDesc +issueLat=1 +opClass=SimdMultAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList08] +type=OpDesc +issueLat=1 +opClass=SimdShift +opLat=1 + +[system.cpu.fuPool.FUList5.opList09] +type=OpDesc +issueLat=1 +opClass=SimdShiftAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList10] +type=OpDesc +issueLat=1 +opClass=SimdSqrt +opLat=1 + +[system.cpu.fuPool.FUList5.opList11] +type=OpDesc +issueLat=1 +opClass=SimdFloatAdd +opLat=1 + +[system.cpu.fuPool.FUList5.opList12] +type=OpDesc +issueLat=1 +opClass=SimdFloatAlu +opLat=1 + +[system.cpu.fuPool.FUList5.opList13] +type=OpDesc +issueLat=1 +opClass=SimdFloatCmp +opLat=1 + +[system.cpu.fuPool.FUList5.opList14] +type=OpDesc +issueLat=1 +opClass=SimdFloatCvt +opLat=1 + +[system.cpu.fuPool.FUList5.opList15] +type=OpDesc +issueLat=1 +opClass=SimdFloatDiv +opLat=1 + +[system.cpu.fuPool.FUList5.opList16] +type=OpDesc +issueLat=1 +opClass=SimdFloatMisc +opLat=1 + +[system.cpu.fuPool.FUList5.opList17] +type=OpDesc +issueLat=1 +opClass=SimdFloatMult +opLat=1 + +[system.cpu.fuPool.FUList5.opList18] +type=OpDesc +issueLat=1 +opClass=SimdFloatMultAcc +opLat=1 + +[system.cpu.fuPool.FUList5.opList19] +type=OpDesc +issueLat=1 +opClass=SimdFloatSqrt +opLat=1 + +[system.cpu.fuPool.FUList6] +type=FUDesc +children=opList +count=0 +opList=system.cpu.fuPool.FUList6.opList + +[system.cpu.fuPool.FUList6.opList] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu.fuPool.FUList7] +type=FUDesc +children=opList0 opList1 +count=4 +opList=system.cpu.fuPool.FUList7.opList0 system.cpu.fuPool.FUList7.opList1 + +[system.cpu.fuPool.FUList7.opList0] +type=OpDesc +issueLat=1 +opClass=MemRead +opLat=1 + +[system.cpu.fuPool.FUList7.opList1] +type=OpDesc +issueLat=1 +opClass=MemWrite +opLat=1 + +[system.cpu.fuPool.FUList8] +type=FUDesc +children=opList +count=1 +opList=system.cpu.fuPool.FUList8.opList + +[system.cpu.fuPool.FUList8.opList] +type=OpDesc +issueLat=3 +opClass=IprAccess +opLat=3 + +[system.cpu.icache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=131072 +subblock_size=0 +tgts_per_mshr=20 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.icache_port +mem_side=system.cpu.toL2Bus.port[0] + +[system.cpu.itb] +type=X86TLB +size=64 + +[system.cpu.l2cache] +type=BaseCache +addr_range=0:18446744073709551615 +assoc=2 +block_size=64 +forward_snoops=true +hash_delay=1 +latency=1000 +max_miss_count=0 +mshrs=10 +num_cpus=1 +prefetch_data_accesses_only=false +prefetch_degree=1 +prefetch_latency=10000 +prefetch_on_access=false +prefetch_past_page=false +prefetch_policy=none +prefetch_serial_squash=false +prefetch_use_cpu_id=true +prefetcher_size=100 +prioritizeRequests=false +repl=Null +size=2097152 +subblock_size=0 +tgts_per_mshr=5 +trace_addr=0 +two_queue=false +write_buffers=8 +cpu_side=system.cpu.toL2Bus.port[2] +mem_side=system.membus.port[1] + +[system.cpu.toL2Bus] +type=Bus +block_size=64 +bus_id=0 +clock=1000 +header_cycles=1 +use_default_range=false +width=64 +port=system.cpu.icache.mem_side system.cpu.dcache.mem_side system.cpu.l2cache.cpu_side + +[system.cpu.tracer] +type=ExeTracer + +[system.cpu.workload] +type=LiveProcess +cmd=parser 2.1.dict -batch +cwd=build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing +egid=100 +env= +errout=cerr +euid=100 +executable=/dist/m5/cpu2000/binaries/x86/linux/parser +gid=100 +input=/dist/m5/cpu2000/data/parser/mdred/input/parser.in +max_stack_size=67108864 +output=cout +pid=100 +ppid=99 +simpoint=114600000000 +system=system +uid=100 + +[system.membus] +type=Bus +block_size=64 +bus_id=0 +clock=1000 +header_cycles=1 +use_default_range=false +width=64 +port=system.physmem.port[0] system.cpu.l2cache.mem_side + +[system.physmem] +type=PhysicalMemory +file= +latency=30000 +latency_var=0 +null=false +range=0:134217727 +zero=false +port=system.membus.port[0] + diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/simerr b/tests/long/20.parser/ref/x86/linux/o3-timing/simerr new file mode 100755 index 000000000..94d399eab --- /dev/null +++ b/tests/long/20.parser/ref/x86/linux/o3-timing/simerr @@ -0,0 +1,7 @@ +warn: Sockets disabled, not accepting gdb connections +For more information see: http://www.m5sim.org/warn/d946bea6 +warn: instruction 'fnstcw_Mw' unimplemented +For more information see: http://www.m5sim.org/warn/437d5238 +warn: instruction 'fldcw_Mw' unimplemented +For more information see: http://www.m5sim.org/warn/437d5238 +hack: be nice to actually delete the event here diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/simout b/tests/long/20.parser/ref/x86/linux/o3-timing/simout new file mode 100755 index 000000000..6e2ddc167 --- /dev/null +++ b/tests/long/20.parser/ref/x86/linux/o3-timing/simout @@ -0,0 +1,77 @@ +M5 Simulator System + +Copyright (c) 2001-2008 +The Regents of The University of Michigan +All Rights Reserved + + +M5 compiled Jan 31 2011 16:34:44 +M5 revision 1b98eea40540 7883 default qtip tip x86o3regressions.patch +M5 started Jan 31 2011 16:34:46 +M5 executing on burrito +command line: build/X86_SE/m5.opt -d build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/20.parser/x86/linux/o3-timing +Global frequency set at 1000000000000 ticks per second +info: Entering event queue @ 0. Starting simulation... + + Reading the dictionary files: *****************************info: Increasing stack size by one page. +******************** + 58924 words stored in 3784810 bytes + + +Welcome to the Link Parser -- Version 2.1 + + Copyright (C) 1991-1995 Daniel Sleator and Davy Temperley + +Processing sentences in batch mode + +Echoing of input sentence turned on. +* as had expected the party to be a success , it was a success +* do you know where John 's +* he said that , finding that it was impossible to get work as a waiter , he would work as a janitor +info: Increasing stack size by one page. +info: Increasing stack size by one page. +* how fast the program is it +* I am wondering whether to invite to the party +* I gave him for his birthday it +* I thought terrible after our discussion +* I wonder how much money have you earned +* Janet who is an expert on dogs helped me choose one +* she interviewed more programmers than was hired +* such flowers are found chiefly particularly in Europe +* the dogs some of which were very large ran after the man +* the man whom I play tennis is here +* there is going to be an important meeting January +* to pretend that our program is usable in its current form would be happy +* we're thinking about going to a movie this theater +* which dog you said you chased +- also invited to the meeting were several prominent scientists +- he ran home so quickly that his mother could hardly believe he had called from school +- so many people attended that they spilled over into several neighboring fields +- voting in favor of the bill were 36 Republicans and 4 moderate Democrats +: Grace may not be possible to fix the problem + any program as good as ours should be useful + biochemically , I think the experiment has a lot of problems + Fred has had five years of experience as a programmer + he is looking for another job + how did John do it + how many more people do you think will come + how much more spilled + I have more money than John has time + I made it clear that I was angry + I wonder how John did it + I wonder how much more quickly he ran + invite John and whoever else you want to invite + it is easier to ignore the problem than it is to solve it + many who initially supported Thomas later changed their minds + neither Mary nor Louise are coming to the party + she interviewed more programmers than were hired + telling Joe that Sue was coming to the party would create a real problem + the man with whom I play tennis is here + there is a dog in the park + this is not the man we know and love + we like to eat at restaurants , usually on weekends + what did John say he thought you should do + about 2 million people attended + the five best costumes got prizes +No errors! +Exiting @ tick 817002039000 because target called exit() diff --git a/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt b/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt new file mode 100644 index 000000000..c8db50488 --- /dev/null +++ b/tests/long/20.parser/ref/x86/linux/o3-timing/stats.txt @@ -0,0 +1,454 @@ + +---------- Begin Simulation Statistics ---------- +host_inst_rate 123365 # Simulator instruction rate (inst/s) +host_mem_usage 239740 # Number of bytes of host memory used +host_seconds 12393.99 # Real time elapsed on the host +host_tick_rate 65919204 # Simulator tick rate (ticks/s) +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 1528988756 # Number of instructions simulated +sim_seconds 0.817002 # Number of seconds simulated +sim_ticks 817002039000 # Number of ticks simulated +system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu.BPredUnit.BTBHits 197674461 # Number of BTB hits +system.cpu.BPredUnit.BTBLookups 215147546 # Number of BTB lookups +system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu.BPredUnit.condIncorrect 17901021 # Number of conditional branches incorrect +system.cpu.BPredUnit.condPredicted 215739151 # Number of conditional branches predicted +system.cpu.BPredUnit.lookups 215739151 # 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 149758588 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 8186576 # 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 1552269342 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::mean 0.985002 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::stdev 1.301395 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::0 694185983 44.72% 44.72% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::1 509617235 32.83% 77.55% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::2 176087126 11.34% 88.90% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::3 105147186 6.77% 95.67% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::4 31137095 2.01% 97.67% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::5 11224991 0.72% 98.40% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::6 11192282 0.72% 99.12% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::7 5490868 0.35% 99.47% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::8 8186576 0.53% 100.00% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::overflows 0 0.00% 100.00% # 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::max_value 8 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::total 1552269342 # Number of insts commited each cycle +system.cpu.commit.COM:count 1528988756 # Number of instructions committed +system.cpu.commit.COM:loads 384102160 # Number of loads committed +system.cpu.commit.COM:membars 0 # Number of memory barriers committed +system.cpu.commit.COM:refs 533262345 # Number of memory references committed +system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu.commit.branchMispredicts 17902344 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 1528988756 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 553 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 459109010 # The number of squashed insts skipped by commit +system.cpu.committedInsts 1528988756 # Number of Instructions Simulated +system.cpu.committedInsts_total 1528988756 # Number of Instructions Simulated +system.cpu.cpi 1.068683 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.068683 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 352008034 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 14100.976079 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 8499.435037 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 350035037 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 27821183500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.005605 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 1972997 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 237485 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 14750871500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.004930 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 1735512 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 149160201 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 15942.157352 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 12645.445755 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 148213244 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 15096537500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.006349 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 946957 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 159966 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 9951852000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.005276 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 786991 # 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 no_value # average number of cycles each access was blocked +system.cpu.dcache.avg_refs 197.709284 # 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 501168235 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 14698.081203 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 9792.941178 # average overall mshr miss latency +system.cpu.dcache.demand_hits 498248281 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 42917721000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.005826 # miss rate for demand accesses +system.cpu.dcache.demand_misses 2919954 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 397451 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 24702723500 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.005033 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 2522503 # 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.occ_%::0 0.997749 # Average percentage of cache occupancy +system.cpu.dcache.occ_blocks::0 4086.780222 # Average occupied blocks per context +system.cpu.dcache.overall_accesses 501168235 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 14698.081203 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 9792.941178 # average overall mshr miss latency +system.cpu.dcache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.dcache.overall_hits 498248281 # number of overall hits +system.cpu.dcache.overall_miss_latency 42917721000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.005826 # miss rate for overall accesses +system.cpu.dcache.overall_misses 2919954 # number of overall misses +system.cpu.dcache.overall_mshr_hits 397451 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 24702723500 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.005033 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 2522503 # 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 2516044 # number of replacements +system.cpu.dcache.sampled_refs 2520140 # 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 4086.780222 # Cycle average of tags in use +system.cpu.dcache.total_refs 498255076 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 3876881000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 2224034 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 25470243 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 2119227193 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 403203369 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 1116867689 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 71636028 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 6728041 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 215739151 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 165973622 # Number of cache lines fetched +system.cpu.fetch.Cycles 1190006834 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 2725815 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 1144873460 # Number of instructions fetch has processed +system.cpu.fetch.MiscStallCycles 1839 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.SquashCycles 29822694 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.132031 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 165973622 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 197674461 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.700655 # Number of inst fetches per cycle +system.cpu.fetch.rateDist::samples 1623905370 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.336094 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 1.273592 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::underflows 0 0.00% 0.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 477535637 29.41% 29.41% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 564706157 34.77% 64.18% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 259330057 15.97% 80.15% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 261180842 16.08% 96.23% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 22809127 1.40% 97.64% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 31399021 1.93% 99.57% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 502829 0.03% 99.60% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 12 0.00% 99.60% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 6441688 0.40% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::overflows 0 0.00% 100.00% # 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::max_value 8 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::total 1623905370 # Number of instructions fetched each cycle (Total) +system.cpu.icache.ReadReq_accesses 165973622 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 22741.617211 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 19372.661290 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 165966882 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 153278500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000041 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 6740 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 540 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 120110500 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000037 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 6200 # number of ReadReq MSHR misses +system.cpu.icache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked +system.cpu.icache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked +system.cpu.icache.avg_refs 49795.025203 # 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 165973622 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 22741.617211 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 19372.661290 # average overall mshr miss latency +system.cpu.icache.demand_hits 165966882 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 153278500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000041 # miss rate for demand accesses +system.cpu.icache.demand_misses 6740 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 540 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 120110500 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000037 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 6200 # 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.occ_%::0 0.436573 # Average percentage of cache occupancy +system.cpu.icache.occ_blocks::0 894.100654 # Average occupied blocks per context +system.cpu.icache.overall_accesses 165973622 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 22741.617211 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 19372.661290 # average overall mshr miss latency +system.cpu.icache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.icache.overall_hits 165966882 # number of overall hits +system.cpu.icache.overall_miss_latency 153278500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000041 # miss rate for overall accesses +system.cpu.icache.overall_misses 6740 # number of overall misses +system.cpu.icache.overall_mshr_hits 540 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 120110500 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000037 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 6200 # 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 1750 # number of replacements +system.cpu.icache.sampled_refs 3333 # 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 894.100654 # Cycle average of tags in use +system.cpu.icache.total_refs 165966819 # 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 10098709 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 158001976 # Number of branches executed +system.cpu.iew.EXEC:nop 0 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.044762 # Inst execution rate +system.cpu.iew.EXEC:refs 586795750 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 160862585 # Number of stores executed +system.cpu.iew.EXEC:swp 0 # number of swp insts executed +system.cpu.iew.WB:consumers 2114014731 # num instructions consuming a value +system.cpu.iew.WB:count 1694146367 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.583880 # 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 1234331323 # num instructions producing a value +system.cpu.iew.WB:rate 1.036807 # insts written-back per cycle +system.cpu.iew.WB:sent 1697627373 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 18573506 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 6103126 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 508224738 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 579 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 12080656 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 194089353 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 1988097398 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 425933165 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 26013466 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 1707144682 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 381189 # 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 10588 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 71636028 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 847228 # 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 72909425 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 277837 # 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 11954619 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 832 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 124122578 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 44929168 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 11954619 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 280770 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 18292736 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.935731 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.935731 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0::No_OpClass 1927969 0.11% 0.11% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntAlu 1131725915 65.30% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntMult 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntDiv 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatAdd 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCmp 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCvt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatMult 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatDiv 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatSqrt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAdd 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAlu 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCmp 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCvt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMisc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMult 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShift 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdSqrt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt 0 0.00% 65.41% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemRead 435582288 25.13% 90.54% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemWrite 163921976 9.46% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IprAccess 0 0.00% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::InstPrefetch 0 0.00% 100.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::total 1733158148 # Type of FU issued +system.cpu.iq.ISSUE:fu_busy_cnt 1029171 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.000594 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntAlu 182 0.02% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntMult 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntDiv 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatAdd 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCmp 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCvt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatMult 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatDiv 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatSqrt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAdd 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAddAcc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAlu 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCmp 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCvt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMisc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMult 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMultAcc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShift 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShiftAcc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdSqrt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAdd 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAlu 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCmp 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCvt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatDiv 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMisc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMult 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt 0 0.00% 0.02% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemRead 466697 45.35% 45.36% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemWrite 562292 54.64% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IprAccess 0 0.00% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::InstPrefetch 0 0.00% 100.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:issued_per_cycle::samples 1623905370 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::mean 1.067278 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.066518 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::0 608633589 37.48% 37.48% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::1 503635145 31.01% 68.49% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::2 353739534 21.78% 90.28% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::3 117719188 7.25% 97.53% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::4 32883027 2.02% 99.55% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::5 6737765 0.41% 99.97% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::6 234496 0.01% 99.98% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::7 322546 0.02% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::8 80 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::min_value 0 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::max_value 8 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::total 1623905370 # Number of insts issued each cycle +system.cpu.iq.ISSUE:rate 1.060682 # Inst issue rate +system.cpu.iq.iqInstsAdded 1988096819 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 1733158148 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 579 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 452995728 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 112 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 26 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 1010995901 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 789062 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 34275.179377 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31001.682665 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_hits 541538 # number of ReadExReq hits +system.cpu.l2cache.ReadExReq_miss_latency 8483929500 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 0.313694 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 247524 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 7673660500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.313694 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 247524 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 1734408 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 34153.383782 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31001.108327 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 1401925 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 11355419500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.191698 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 332483 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 10307341500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.191698 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 332483 # number of ReadReq MSHR misses +system.cpu.l2cache.UpgradeReq_accesses 2863 # number of UpgradeReq accesses(hits+misses) +system.cpu.l2cache.UpgradeReq_avg_miss_latency 24.346581 # average UpgradeReq miss latency +system.cpu.l2cache.UpgradeReq_avg_mshr_miss_latency 31002.148228 # average UpgradeReq mshr miss latency +system.cpu.l2cache.UpgradeReq_hits 70 # number of UpgradeReq hits +system.cpu.l2cache.UpgradeReq_miss_latency 68000 # number of UpgradeReq miss cycles +system.cpu.l2cache.UpgradeReq_miss_rate 0.975550 # miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_misses 2793 # number of UpgradeReq misses +system.cpu.l2cache.UpgradeReq_mshr_miss_latency 86589000 # number of UpgradeReq MSHR miss cycles +system.cpu.l2cache.UpgradeReq_mshr_miss_rate 0.975550 # mshr miss rate for UpgradeReq accesses +system.cpu.l2cache.UpgradeReq_mshr_misses 2793 # number of UpgradeReq MSHR misses +system.cpu.l2cache.Writeback_accesses 2224034 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 2224034 # number of Writeback hits +system.cpu.l2cache.avg_blocked_cycles::no_mshrs no_value # average number of cycles each access was blocked +system.cpu.l2cache.avg_blocked_cycles::no_targets no_value # average number of cycles each access was blocked +system.cpu.l2cache.avg_refs 5.356881 # 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 2523470 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 34205.361315 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31001.353432 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 1943463 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 19839349000 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.229845 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 580007 # 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 17981002000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.229845 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 580007 # 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.occ_%::0 0.233067 # Average percentage of cache occupancy +system.cpu.l2cache.occ_%::1 0.421257 # Average percentage of cache occupancy +system.cpu.l2cache.occ_blocks::0 7637.149597 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 13803.753842 # Average occupied blocks per context +system.cpu.l2cache.overall_accesses 2523470 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 34205.361315 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31001.353432 # average overall mshr miss latency +system.cpu.l2cache.overall_avg_mshr_uncacheable_latency no_value # average overall mshr uncacheable latency +system.cpu.l2cache.overall_hits 1943463 # number of overall hits +system.cpu.l2cache.overall_miss_latency 19839349000 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.229845 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 580007 # number of overall misses +system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_miss_latency 17981002000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.229845 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 580007 # 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 569254 # number of replacements +system.cpu.l2cache.sampled_refs 588327 # 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 21440.903439 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3151598 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 469235659000 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 411363 # number of writebacks +system.cpu.memDep0.conflictingLoads 151128770 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 47539398 # Number of conflicting stores. +system.cpu.memDep0.insertedLoads 508224738 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 194089353 # Number of stores inserted to the mem dependence unit. +system.cpu.numCycles 1634004079 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 11181498 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 1427299027 # Number of HB maps that are committed +system.cpu.rename.RENAME:IQFullEvents 8162354 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 430755417 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 1988994 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:ROBFullEvents 37 # Number of times rename has blocked due to ROB full +system.cpu.rename.RENAME:RenameLookups 6064799926 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 2072679155 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 1965930252 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 1095363349 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 71636028 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 14962968 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 538631225 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 6110 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 566 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 21122292 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 563 # count of temporary serializing insts renamed +system.cpu.timesIdled 351337 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.workload.PROG:num_syscalls 551 # Number of system calls + +---------- End Simulation Statistics ---------- |