From 55df9e348c98f25006ac8a95d11bb2cc6b0fdde7 Mon Sep 17 00:00:00 2001 From: Gabe Black Date: Sat, 5 Feb 2011 00:16:09 -0800 Subject: X86: Add o3 regressions in SE mode. Exclude bzip2 for now. It works, it just takes too long to run. --- .../70.twolf/ref/x86/linux/o3-timing/config.ini | 519 +++++++++++++++++++++ tests/long/70.twolf/ref/x86/linux/o3-timing/simerr | 7 + tests/long/70.twolf/ref/x86/linux/o3-timing/simout | 32 ++ .../70.twolf/ref/x86/linux/o3-timing/smred.out | 276 +++++++++++ .../70.twolf/ref/x86/linux/o3-timing/smred.pin | 17 + .../70.twolf/ref/x86/linux/o3-timing/smred.pl1 | 11 + .../70.twolf/ref/x86/linux/o3-timing/smred.pl2 | 2 + .../70.twolf/ref/x86/linux/o3-timing/smred.sav | 18 + .../70.twolf/ref/x86/linux/o3-timing/smred.sv2 | 19 + .../70.twolf/ref/x86/linux/o3-timing/smred.twf | 29 ++ .../70.twolf/ref/x86/linux/o3-timing/stats.txt | 443 ++++++++++++++++++ 11 files changed, 1373 insertions(+) create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini create mode 100755 tests/long/70.twolf/ref/x86/linux/o3-timing/simerr create mode 100755 tests/long/70.twolf/ref/x86/linux/o3-timing/simout create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.out create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pin create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl1 create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl2 create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sav create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sv2 create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/smred.twf create mode 100644 tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt (limited to 'tests/long/70.twolf') diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini b/tests/long/70.twolf/ref/x86/linux/o3-timing/config.ini new file mode 100644 index 000000000..64a0645d8 --- /dev/null +++ b/tests/long/70.twolf/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=twolf smred +cwd=build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing +egid=100 +env= +errout=cerr +euid=100 +executable=/dist/m5/cpu2000/binaries/x86/linux/twolf +gid=100 +input=cin +max_stack_size=67108864 +output=cout +pid=100 +ppid=99 +simpoint=0 +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/70.twolf/ref/x86/linux/o3-timing/simerr b/tests/long/70.twolf/ref/x86/linux/o3-timing/simerr new file mode 100755 index 000000000..94d399eab --- /dev/null +++ b/tests/long/70.twolf/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/70.twolf/ref/x86/linux/o3-timing/simout b/tests/long/70.twolf/ref/x86/linux/o3-timing/simout new file mode 100755 index 000000000..4773ac641 --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/simout @@ -0,0 +1,32 @@ +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/70.twolf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing +Couldn't unlink build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sav +Couldn't unlink build/X86_SE/tests/opt/long/70.twolf/x86/linux/o3-timing/smred.sv2 +Global frequency set at 1000000000000 ticks per second +info: Entering event queue @ 0. Starting simulation... + +TimberWolfSC version:v4.3a date:Mon Jan 25 18:50:36 EST 1988 +Standard Cell Placement and Global Routing Program +Authors: Carl Sechen, Bill Swartz + Yale University +info: Increasing stack size by one page. +info: Increasing stack size by one page. + 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 + 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 + 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 + 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 + 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 + 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 +106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 +122 123 124 Exiting @ tick 127560542500 because target called exit() diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.out b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.out new file mode 100644 index 000000000..00387ae5c --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.out @@ -0,0 +1,276 @@ + +TimberWolfSC version:v4.3a date:Mon Jan 25 18:50:36 EST 1988 +Standard Cell Placement and Global Routing Program +Authors: Carl Sechen, Bill Swartz + Yale University + + +NOTE: Restart file .rs2 not used + +TimberWolf will perform a global route step +rowSep: 1.000000 +feedThruWidth: 4 + +****************** +BLOCK DATA +block:1 desire:85 +block:2 desire:85 +Total Desired Length: 170 +total cell length: 168 +total block length: 168 +block x-span:84 block y-span:78 +implicit feed thru range: -84 +Using default value of bin.penalty.control:1.000000 +numBins automatically set to:5 +binWidth = average_cell_width + 0 sigma= 17 +average_cell_width is:16 +standard deviation of cell length is:23.6305 +TimberWolfSC starting from the beginning + + + +THIS IS THE ROUTE COST OF THE ORIGINAL PLACEMENT: 645 +The number of nets with 1 pin is 4 +The number of nets with 2 pin is 9 +The number of nets with 3 pin is 0 +The number of nets with 4 pin is 2 +The number of nets with 5 pin is 0 +The number of nets with 6 pin is 0 +The number of nets with 7 pin is 0 +The number of nets with 8 pin is 0 +The number of nets with 9 pin is 0 +The number of nets with 10 pin or more is 0 + +New Cost Function: Initial Horizontal Cost:242 +New Cost Function: FEEDS:0 MISSING_ROWS:-46 + +bdxlen:86 bdylen:78 +l:0 t:78 r:86 b:0 + + + +THIS IS THE ROUTE COST OF THE CURRENT PLACEMENT: 645 + + + +THIS IS THE PENALTY OF THE CURRENT PLACEMENT: 44 + +The rand generator seed was at utemp() : 1 + + + tempfile[0][0] = 0.982500 tempfile[0][1] = 90.000000 + tempfile[1][0] = 0.915000 tempfile[1][1] = 20.000000 + tempfile[2][0] = 0.700000 tempfile[2][1] = 10.000000 + tempfile[3][0] = 0.100000 tempfile[3][1] = 0.000000 + + I T fds Wire Penalty P_lim Epct binC rowC acc s/p early FDs MRs + 1 500 0 929 592 160 30.0 1.0 3.0 84.2 34.7 0.0 0 40 + 2 491 0 876 106 726 0.0 0.8 2.5 80.0 18.5 0.0 0 46 + 3 482 0 822 273 372 0.0 0.5 1.5 80.8 21.2 0.0 0 46 + 4 474 0 826 53 247 0.0 0.5 0.9 65.0 21.9 0.0 0 48 + 5 465 8 987 73 190 0.0 0.5 0.5 50.0 38.3 0.0 0 46 + 6 457 8 851 67 226 0.0 0.5 0.5 53.8 42.9 0.0 0 52 + 7 449 8 1067 108 190 0.0 0.5 0.5 46.2 53.8 0.0 0 50 + 8 441 8 918 106 171 0.0 0.5 0.5 47.1 40.4 0.0 0 48 + 9 434 8 812 101 197 0.0 0.5 0.5 53.6 21.0 0.0 0 48 + 10 426 8 1038 121 181 0.0 0.5 0.5 43.6 27.1 0.0 0 48 + 11 419 8 898 93 187 0.0 0.5 0.5 45.3 47.8 0.0 0 50 + 12 411 4 857 94 240 0.0 0.5 0.5 62.7 51.6 0.0 0 44 + 13 404 8 1043 88 185 0.0 0.5 0.5 54.0 52.8 0.0 0 50 + 14 397 8 767 94 154 0.0 0.5 0.5 33.8 35.0 0.0 0 50 + 15 390 8 862 89 183 0.0 0.5 0.5 55.6 29.0 0.0 0 46 + 16 383 4 798 79 173 0.0 0.5 0.5 57.5 35.3 0.0 0 52 + 17 376 8 827 100 152 0.0 0.5 0.5 35.3 81.8 0.0 0 50 + 18 370 8 878 101 208 0.0 0.5 0.5 44.7 46.2 0.0 0 48 + 19 363 4 921 67 167 0.0 0.5 0.5 57.1 34.7 0.0 0 48 + 20 357 8 933 93 154 0.0 0.5 0.5 46.5 43.6 0.0 0 52 + 21 351 8 930 89 147 0.0 0.5 0.5 39.4 36.5 0.0 0 52 + 22 345 8 951 79 142 0.0 0.5 0.5 32.8 51.3 0.0 0 50 + 23 339 8 1046 87 207 0.0 0.5 0.5 52.8 61.0 0.0 0 48 + 24 333 4 989 96 185 0.0 0.5 0.5 45.3 43.3 0.0 0 42 + 25 327 4 577 86 157 0.0 0.5 0.5 31.1 55.3 0.0 0 52 + 26 321 8 776 97 174 0.0 0.5 0.5 47.9 62.5 0.0 0 52 + 27 315 8 850 81 188 0.0 0.5 0.5 45.0 55.2 0.0 0 50 + 28 310 8 898 97 148 0.0 0.5 0.5 43.0 45.8 0.0 0 48 + 29 304 8 889 65 173 0.0 0.5 0.5 32.5 41.3 0.0 0 50 + 30 299 8 858 81 153 0.0 0.5 0.5 44.3 29.2 0.0 0 46 + 31 294 8 871 82 187 0.0 0.5 0.5 45.7 47.7 0.0 0 48 + 32 289 8 782 109 173 0.0 0.5 0.5 35.2 57.4 0.0 0 48 + 33 284 8 743 98 189 0.0 0.6 0.5 41.8 64.3 0.0 0 52 + 34 279 8 943 90 147 0.0 0.5 0.5 38.6 32.8 0.0 0 48 + 35 274 8 907 57 166 0.0 0.5 0.5 33.6 51.0 0.0 0 48 + 36 269 8 900 70 148 0.0 0.5 0.5 45.0 41.4 0.0 0 50 + 37 264 4 875 106 133 0.0 0.5 0.5 31.7 55.3 0.0 0 52 + 38 260 8 1023 145 149 0.0 0.6 0.5 28.7 65.0 0.0 0 52 + 39 255 8 801 151 173 0.0 0.9 0.5 41.7 41.2 0.0 0 48 + 40 251 8 741 104 159 0.0 0.8 0.5 36.2 47.5 0.0 0 48 + 41 246 8 828 108 149 0.0 0.5 0.5 34.6 50.9 0.0 0 50 + 42 242 8 947 128 132 0.0 0.7 0.5 34.2 39.0 0.0 0 50 + 43 238 8 917 101 142 0.0 0.8 0.5 34.4 50.9 0.0 0 48 + 44 234 8 761 86 129 0.0 0.5 0.5 42.0 36.4 0.0 0 52 + 45 229 8 979 106 137 0.0 0.5 0.5 29.2 55.3 0.0 0 50 + 46 225 8 806 74 130 0.0 0.7 0.5 33.1 65.4 0.0 0 52 + 47 221 8 971 125 114 0.0 0.5 0.5 31.9 45.6 0.0 0 52 + 48 218 8 869 125 104 0.0 0.9 0.5 30.0 56.0 0.0 0 48 + 49 214 8 999 153 140 0.0 0.8 0.5 30.4 46.4 0.0 0 52 + 50 210 8 798 192 139 0.0 1.0 0.5 28.9 50.0 0.0 0 52 + 51 206 8 860 125 157 0.0 1.2 0.5 31.5 26.9 0.0 0 52 + 52 203 8 893 186 127 5.9 0.9 0.5 26.4 42.3 0.0 0 46 + 53 199 8 863 126 141 0.0 1.2 0.5 32.5 44.4 0.0 0 44 + 54 196 8 788 97 133 0.0 0.9 0.5 37.5 40.0 0.0 0 50 + 55 192 8 926 119 116 0.0 0.6 0.5 26.1 55.3 0.0 0 52 + 56 189 8 789 162 107 0.0 0.8 0.5 25.2 40.4 0.0 0 48 + 57 186 8 878 107 128 0.0 1.1 0.5 23.1 34.0 0.0 0 52 + 58 182 8 775 105 122 0.0 0.8 0.5 25.5 57.4 0.0 0 50 + 59 179 8 747 94 129 0.0 0.7 0.5 34.3 37.3 0.0 0 50 + 60 176 8 845 96 138 0.0 0.6 0.5 28.3 41.7 0.0 0 52 + 61 173 8 961 121 110 0.0 0.6 0.5 29.0 52.6 0.0 0 48 + 62 170 4 911 110 109 0.0 0.9 0.5 33.5 33.3 0.0 0 48 + 63 167 8 656 109 109 0.0 0.8 0.5 21.9 44.7 0.0 0 52 + 64 164 8 934 117 105 0.0 0.8 0.5 15.5 50.0 0.0 0 52 + 65 161 8 972 125 95 0.0 0.8 0.5 24.4 50.0 0.0 0 50 + 66 158 8 894 125 101 0.0 0.9 0.5 27.2 35.9 0.0 0 52 + 67 155 8 798 146 129 0.0 1.0 0.5 22.8 58.7 0.0 0 52 + 68 153 8 901 183 92 0.0 1.1 0.5 23.6 34.5 0.0 0 52 + 69 150 8 977 197 103 0.0 1.4 0.5 23.6 36.8 0.0 0 52 + 70 147 8 905 262 93 0.0 1.5 0.5 20.3 63.4 0.0 0 52 + 71 145 8 995 148 122 0.0 1.9 0.5 20.9 35.3 0.0 0 52 + 72 142 8 934 230 99 0.0 1.6 0.5 20.0 65.9 0.0 0 52 + 73 140 8 862 173 100 0.0 1.8 0.5 26.8 46.8 0.0 0 52 + 74 137 8 924 139 90 0.0 1.7 0.5 16.8 42.5 0.0 0 52 + 75 135 8 888 168 113 0.0 1.6 0.5 22.9 40.4 0.0 0 52 + 76 133 8 712 212 84 0.0 1.6 0.5 13.4 46.9 0.0 0 52 + 77 130 8 868 210 91 0.0 1.7 0.5 17.7 51.2 0.0 0 52 + 78 128 8 952 307 92 0.0 1.9 0.5 19.7 44.9 0.0 0 50 + 79 126 8 801 157 107 0.0 2.2 0.5 15.8 39.0 0.0 0 52 + 80 123 8 849 147 93 0.0 2.1 0.5 15.6 51.4 0.0 0 52 + 81 121 8 799 154 86 0.0 1.9 0.5 12.2 50.0 0.0 0 52 + 82 119 8 941 213 82 0.0 1.8 0.5 19.5 41.2 0.0 0 50 + 83 117 8 751 268 94 0.0 2.0 0.5 20.8 42.6 0.0 0 50 + 84 115 8 828 198 102 0.0 2.2 0.5 15.5 59.5 0.0 0 52 + 85 113 8 898 266 123 0.0 2.2 0.5 13.2 85.2 0.0 0 52 + 86 111 8 943 190 93 0.0 2.4 0.5 19.5 45.1 0.0 0 52 + 87 109 8 864 183 65 0.0 2.4 0.5 14.9 31.8 0.0 0 52 + 88 107 8 793 203 93 0.0 2.4 0.5 11.8 35.3 0.0 0 52 + 89 105 8 752 162 74 1.2 2.4 0.5 13.1 21.4 0.0 0 52 + 90 103 8 801 149 77 0.0 2.3 0.5 9.7 58.3 0.0 0 52 + 91 102 8 901 230 99 0.0 2.2 0.5 16.0 25.5 0.0 0 52 + 92 100 8 826 201 87 0.0 2.4 0.5 12.8 45.7 0.0 0 52 + 93 98 8 810 196 83 0.0 2.5 0.5 14.0 24.4 0.0 0 52 + 94 96 8 857 209 68 1.0 2.5 0.5 11.5 27.0 5.1 0 52 + 95 95 8 771 174 91 0.0 2.6 0.5 10.5 26.5 0.0 0 52 + 96 93 8 955 210 59 0.0 2.6 0.5 10.0 36.7 0.7 0 52 + 97 91 8 833 206 53 0.0 2.7 0.5 10.2 19.4 1.4 0 52 + 98 90 8 888 229 86 0.0 2.8 0.5 8.1 36.0 0.0 0 52 + 99 88 8 794 186 91 1.0 2.9 0.5 8.3 25.0 0.5 0 52 +100 81 8 756 170 72 1.0 2.9 0.5 6.0 23.8 7.0 0 52 +101 74 8 791 176 67 0.0 2.9 0.5 4.4 58.3 4.0 0 52 +102 67 8 813 213 43 0.0 3.0 0.5 7.0 150.0 4.2 0 52 +103 62 8 779 245 39 0.0 3.1 0.5 3.2 16.7 13.0 0 52 +104 56 8 767 303 63 0.0 3.2 0.5 4.1 20.0 0.7 0 52 +105 52 8 757 270 57 0.0 3.5 0.5 6.4 3.7 0.5 0 52 +106 47 8 763 283 41 0.0 3.7 0.5 4.5 0.0 0.0 0 52 +107 43 8 768 283 36 0.0 3.7 0.5 2.9 18.2 3.6 0 52 +108 39 8 804 283 25 0.0 3.7 0.5 3.1 0.0 6.2 0 52 +109 36 8 781 283 24 0.0 3.7 0.5 3.6 6.7 6.7 0 52 +110 33 8 738 298 42 0.0 3.7 0.5 3.3 15.4 3.5 0 52 +111 30 8 761 298 36 0.0 3.7 0.5 2.2 0.0 4.3 0 52 +112 27 8 769 298 37 0.0 3.7 0.5 0.9 0.0 2.2 0 52 +113 25 8 745 298 31 0.0 3.7 0.5 1.5 0.0 6.6 0 52 +114 23 8 753 298 16 0.0 3.7 0.5 1.3 0.0 2.8 0 52 +115 21 8 745 298 11 0.0 3.7 0.5 1.5 0.0 14.0 0 52 +116 19 8 747 298 21 0.0 3.7 0.5 2.1 0.0 5.8 0 52 +117 13 8 737 298 12 0.0 3.7 0.5 1.0 0.0 10.0 0 52 +118 9 8 736 298 4 0.0 3.7 0.5 1.5 0.0 18.5 0 52 +119 0 8 739 298 0 0.0 3.7 0.5 1.8 0.0 18.0 0 52 +120 0 8 732 298 0 0.0 3.7 0.5 1.2 0.0 21.8 0 52 +121 0 8 732 19 -1 0.0 0.0 0.5 0.0 100.0 54.8 + +Initial Wiring Cost: 645 Final Wiring Cost: 732 +############## Percent Wire Cost Reduction: -13 + + +Initial Wire Length: 645 Final Wire Length: 732 +************** Percent Wire Length Reduction: -13 + + +Initial Horiz. Wire: 216 Final Horiz. Wire: 147 +$$$$$$$$$$$ Percent H-Wire Length Reduction: 32 + + +Initial Vert. Wire: 429 Final Vert. Wire: 585 +@@@@@@@@@@@ Percent V-Wire Length Reduction: -36 + +Before Feeds are Added: +BLOCK TOTAL CELL LENGTHS OVER/UNDER TARGET + 1 82 -20 + 2 86 -16 + +LONGEST Block is:2 Its length is:86 +BLOCK TOTAL CELL LENGTHS OVER/UNDER TARGET + 1 86 -16 + 2 86 -16 + +LONGEST Block is:1 Its length is:86 +Added: 1 feed-through cells + +Removed the cell overlaps --- Will do neighbor interchanges only now + +TOTAL INTERCONNECT LENGTH: 994 +OVERLAP PENALTY: 0 + +initialRowControl: 1.650 +finalRowControl: 0.300 +iter T Wire accept + 122 0.001 976 16% + 123 0.001 971 0% + 124 0.001 971 0% +Total Feed-Alignment Movement (Pass 1): 0 +Total Feed-Alignment Movement (Pass 2): 0 +Total Feed-Alignment Movement (Pass 3): 0 +Total Feed-Alignment Movement (Pass 4): 0 +Total Feed-Alignment Movement (Pass 5): 0 +Total Feed-Alignment Movement (Pass 6): 0 +Total Feed-Alignment Movement (Pass 7): 0 +Total Feed-Alignment Movement (Pass 8): 0 + +The rand generator seed was at globroute() : 987654321 + + +Total Number of Net Segments: 9 +Number of Switchable Net Segments: 0 + +Number of channels: 3 + + + +THIS IS THE ORIGINAL NUMBER OF TRACKS: 5 + + +no. of accepted flips: 0 +no. of attempted flips: 0 +THIS IS THE NUMBER OF TRACKS: 5 + + + +FINAL NUMBER OF ROUTING TRACKS: 5 + +MAX OF CHANNEL: 1 is: 0 +MAX OF CHANNEL: 2 is: 4 +MAX OF CHANNEL: 3 is: 1 +FINAL TOTAL INTERCONNECT LENGTH: 978 +FINAL OVERLAP PENALTY: 0 FINAL VALUE OF TOTAL COST IS: 978 +MAX NUMBER OF ATTEMPTED FLIPS PER T: 55 + + +cost_scale_factor:3.90616 + +Number of Feed Thrus: 0 +Number of Implicit Feed Thrus: 0 + +Statistics: +Number of Standard Cells: 10 +Number of Pads: 0 +Number of Nets: 15 +Number of Pins: 46 +Usage statistics not available diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pin b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pin new file mode 100644 index 000000000..62b922e4e --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pin @@ -0,0 +1,17 @@ +$COUNT_1/$AND2_1/$ND2_1$Z 1 $COUNT_1/$AND2_1/$ND2_1 00#Z 17 52 2 1 0 +$COUNT_1/$AND2_1/$ND2_1$Z 1 ACOUNT_1 00#A 15 26 2 -1 0 +B7 2 $COUNT_1/$FJK3_2 00#K 25 78 3 -1 0 +B7 2 $COUNT_1/$FJK3_2 00#J 23 78 3 -1 0 +B7 3 $COUNT_1/$AND2_2/$ND2_1 00#A 9 26 2 -1 0 +B7 3 ACOUNT_1 01#Z 17 26 2 -1 0 +B6 5 $COUNT_1/$FJK3_1 00#K 25 26 2 -1 0 +B6 5 $COUNT_1/$FJK3_1 00#J 23 26 2 -1 0 +B6 5 $COUNT_1/$AND2_3/$IV_1 01#Z 7 26 2 -1 0 +$COUNT_1/$FJK3_1$Q 6 $COUNT_1/$FJK3_1 01#Q 81 26 2 -1 0 +$COUNT_1/$FJK3_1$Q 6 $COUNT_1/$AND2_1/$ND2_1 00#B 19 52 2 1 0 +$COUNT_1/$FJK3_2$Q 7 $COUNT_1/$FJK3_2 00#Q 81 52 2 1 0 +$COUNT_1/$FJK3_2$Q 7 $COUNT_1/$AND2_2/$ND2_1 01#B 11 26 2 -1 0 +$COUNT_1/$AND2_3/$ND2_1$Z 8 $COUNT_1/$AND2_3/$ND2_1 00#Z 5 52 2 1 0 +$COUNT_1/$AND2_3/$ND2_1$Z 8 $COUNT_1/$AND2_3/$IV_1 00#A 5 26 2 -1 0 +$COUNT_1/$AND2_4/$ND2_1$Z 9 $COUNT_1/$AND2_4/$ND2_1 00#Z 7 52 2 1 0 +$COUNT_1/$AND2_4/$ND2_1$Z 9 $COUNT_1/$AND2_4/$IV_1 00#A 3 26 2 -1 0 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl1 b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl1 new file mode 100644 index 000000000..bdc569e39 --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl1 @@ -0,0 +1,11 @@ +$COUNT_1/$AND2_4/$IV_1 0 0 4 26 0 1 +$COUNT_1/$AND2_3/$IV_1 4 0 8 26 2 1 +$COUNT_1/$AND2_2/$ND2_1 8 0 14 26 0 1 +ACOUNT_1 14 0 18 26 2 1 +twfeed1 18 0 22 26 0 1 +$COUNT_1/$FJK3_1 22 0 86 26 0 1 +$COUNT_1/$AND2_3/$ND2_1 0 52 6 78 0 2 +$COUNT_1/$AND2_4/$ND2_1 6 52 12 78 2 2 +$COUNT_1/$AND2_2/$IV_1 12 52 16 78 2 2 +$COUNT_1/$AND2_1/$ND2_1 16 52 22 78 2 2 +$COUNT_1/$FJK3_2 22 52 86 78 0 2 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl2 b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl2 new file mode 100644 index 000000000..6e2601e82 --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.pl2 @@ -0,0 +1,2 @@ +1 0 0 86 26 0 0 +2 0 52 86 78 0 0 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sav b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sav new file mode 100644 index 000000000..04c8e9935 --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sav @@ -0,0 +1,18 @@ +0.009592 +121 +0 +1 +0.000000 +0.500000 +3.906156 +1 +1 1 2 37 13 +2 2 0 34 65 +3 2 2 63 65 +4 1 0 59 13 +5 1 2 32 13 +6 2 0 23 65 +7 1 2 12 13 +8 2 0 6 65 +9 1 0 70 13 +10 2 0 70 65 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sv2 b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sv2 new file mode 100644 index 000000000..9dd68ecdb --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.sv2 @@ -0,0 +1,19 @@ +0.001000 +123 +0 +2 +0.000000 +0.500000 +3.906156 +1 +1 1 2 16 13 +2 2 2 19 65 +3 2 2 14 65 +4 1 0 11 13 +5 1 2 6 13 +6 2 0 3 65 +7 1 0 2 13 +8 2 2 9 65 +9 1 0 50 13 +10 2 0 54 65 +11 1 0 84 13 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.twf b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.twf new file mode 100644 index 000000000..a4c2eac35 --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/smred.twf @@ -0,0 +1,29 @@ +net 1 +segment channel 2 + pin1 1 pin2 7 0 0 +net 2 +segment channel 3 +pin1 41 pin2 42 0 0 +segment channel 2 +pin1 12 pin2 3 0 0 +net 3 +segment channel 2 +pin1 35 pin2 36 0 0 +segment channel 2 +pin1 19 pin2 35 0 0 +net 4 +segment channel 2 + pin1 5 pin2 38 0 0 +net 5 +net 7 +segment channel 2 + pin1 14 pin2 43 0 0 +net 8 +segment channel 2 + pin1 23 pin2 17 0 0 +net 9 +net 11 +segment channel 2 + pin1 25 pin2 31 0 0 +net 14 +net 15 diff --git a/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt b/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt new file mode 100644 index 000000000..daddf87eb --- /dev/null +++ b/tests/long/70.twolf/ref/x86/linux/o3-timing/stats.txt @@ -0,0 +1,443 @@ + +---------- Begin Simulation Statistics ---------- +host_inst_rate 118559 # Simulator instruction rate (inst/s) +host_mem_usage 239716 # Number of bytes of host memory used +host_seconds 1867.12 # Real time elapsed on the host +host_tick_rate 68319429 # Simulator tick rate (ticks/s) +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 221363017 # Number of instructions simulated +sim_seconds 0.127561 # Number of seconds simulated +sim_ticks 127560542500 # Number of ticks simulated +system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu.BPredUnit.BTBHits 16939138 # Number of BTB hits +system.cpu.BPredUnit.BTBLookups 19067543 # Number of BTB lookups +system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu.BPredUnit.condIncorrect 3582609 # Number of conditional branches incorrect +system.cpu.BPredUnit.condPredicted 19223942 # Number of conditional branches predicted +system.cpu.BPredUnit.lookups 19223942 # 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 12326943 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 324452 # 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 243992167 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::mean 0.907255 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::stdev 1.057266 # 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 97637775 40.02% 40.02% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::1 102801930 42.13% 82.15% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::2 24473335 10.03% 92.18% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::3 10688182 4.38% 96.56% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::4 6438517 2.64% 99.20% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::5 836047 0.34% 99.54% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::6 523551 0.21% 99.76% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::7 268378 0.11% 99.87% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::8 324452 0.13% 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 243992167 # Number of insts commited each cycle +system.cpu.commit.COM:count 221363017 # Number of instructions committed +system.cpu.commit.COM:loads 56649590 # Number of loads committed +system.cpu.commit.COM:membars 0 # Number of memory barriers committed +system.cpu.commit.COM:refs 77165306 # Number of memory references committed +system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu.commit.branchMispredicts 3582617 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 221363017 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 1246 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 70151117 # The number of squashed insts skipped by commit +system.cpu.committedInsts 221363017 # Number of Instructions Simulated +system.cpu.committedInsts_total 221363017 # Number of Instructions Simulated +system.cpu.cpi 1.152501 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.152501 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 51727133 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 34247.563353 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 34193.055556 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 51726620 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 17569000 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.000010 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 513 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 153 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 12309500 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.000007 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 360 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 20515730 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 26394.870828 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 35294.285714 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 20510427 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 139972000 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.000258 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 5303 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 3728 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 55588500 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.000077 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 1575 # 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 37331.807235 # 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 72242863 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 27087.517194 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 35089.405685 # average overall mshr miss latency +system.cpu.dcache.demand_hits 72237047 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 157541000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.000081 # miss rate for demand accesses +system.cpu.dcache.demand_misses 5816 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 3881 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 67898000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.000027 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 1935 # 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 0.336997 # Average percentage of cache occupancy +system.cpu.dcache.occ_blocks::0 1380.340507 # Average occupied blocks per context +system.cpu.dcache.overall_accesses 72242863 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 27087.517194 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 35089.405685 # 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 72237047 # number of overall hits +system.cpu.dcache.overall_miss_latency 157541000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.000081 # miss rate for overall accesses +system.cpu.dcache.overall_misses 5816 # number of overall misses +system.cpu.dcache.overall_mshr_hits 3881 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 67898000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.000027 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 1935 # 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 46 # number of replacements +system.cpu.dcache.sampled_refs 1935 # 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 1380.340507 # Cycle average of tags in use +system.cpu.dcache.total_refs 72237047 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 9 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 5656231 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 309852988 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 53029625 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 184220573 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 11003980 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 1085738 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 19223942 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 20440935 # Number of cache lines fetched +system.cpu.fetch.Cycles 196264127 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 182297 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 184675827 # Number of instructions fetch has processed +system.cpu.fetch.MiscStallCycles 11 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.SquashCycles 4455378 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.075352 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 20440935 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 16939138 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.723875 # Number of inst fetches per cycle +system.cpu.fetch.rateDist::samples 254996147 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.239017 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 1.348981 # 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 66307953 26.00% 26.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 121646972 47.71% 73.71% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 37731127 14.80% 88.51% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 20479784 8.03% 96.54% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 1948325 0.76% 97.30% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 1108960 0.43% 97.74% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 1062530 0.42% 98.15% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 1340 0.00% 98.15% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 4709156 1.85% 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 254996147 # Number of instructions fetched each cycle (Total) +system.cpu.icache.ReadReq_accesses 20440935 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 25661.556820 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 22374.875175 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 20435488 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 139778500 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000266 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 5447 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 440 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 112031000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000245 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 5007 # 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 4082.198961 # 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 20440935 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 25661.556820 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 22374.875175 # average overall mshr miss latency +system.cpu.icache.demand_hits 20435488 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 139778500 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000266 # miss rate for demand accesses +system.cpu.icache.demand_misses 5447 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 440 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 112031000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000245 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 5007 # 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 0.746987 # Average percentage of cache occupancy +system.cpu.icache.occ_blocks::0 1529.828433 # Average occupied blocks per context +system.cpu.icache.overall_accesses 20440935 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 25661.556820 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 22374.875175 # 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 20435488 # number of overall hits +system.cpu.icache.overall_miss_latency 139778500 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000266 # miss rate for overall accesses +system.cpu.icache.overall_misses 5447 # number of overall misses +system.cpu.icache.overall_mshr_hits 440 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 112031000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000245 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 5007 # 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 3101 # number of replacements +system.cpu.icache.sampled_refs 5006 # 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 1529.828433 # Cycle average of tags in use +system.cpu.icache.total_refs 20435488 # 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 124939 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 13366188 # Number of branches executed +system.cpu.iew.EXEC:nop 0 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.954963 # Inst execution rate +system.cpu.iew.EXEC:refs 84717237 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 21535662 # Number of stores executed +system.cpu.iew.EXEC:swp 0 # number of swp insts executed +system.cpu.iew.WB:consumers 389337537 # num instructions consuming a value +system.cpu.iew.WB:count 241459353 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.499412 # 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 194439848 # num instructions producing a value +system.cpu.iew.WB:rate 0.946450 # insts written-back per cycle +system.cpu.iew.WB:sent 242120517 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 3656523 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 214895 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 75869162 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 1275 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 2489008 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 25600521 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 291514094 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 63181575 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 4005104 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 243631219 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 25200 # 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 11003980 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 40028 # 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 11103688 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 71380 # 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 879354 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 44904 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 19219572 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 5084805 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 879354 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 151398 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 3505125 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.867678 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.867678 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0::No_OpClass 1180294 0.48% 0.48% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntAlu 158353329 63.95% 64.42% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntMult 0 0.00% 64.42% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntDiv 0 0.00% 64.42% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatAdd 1520272 0.61% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCmp 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCvt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatMult 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatDiv 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatSqrt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAdd 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAlu 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCmp 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCvt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMisc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMult 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShift 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdSqrt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt 0 0.00% 65.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemRead 64587764 26.08% 91.12% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemWrite 21994664 8.88% 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 247636323 # Type of FU issued +system.cpu.iq.ISSUE:fu_busy_cnt 40899 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.000165 # 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 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntMult 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::IntDiv 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatAdd 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCmp 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatCvt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatMult 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatDiv 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::FloatSqrt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAdd 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAddAcc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdAlu 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCmp 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdCvt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMisc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMult 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdMultAcc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShift 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdShiftAcc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdSqrt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAdd 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatAlu 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCmp 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatCvt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatDiv 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMisc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMult 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatMultAcc 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::SimdFloatSqrt 0 0.00% 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemRead 37912 92.70% 92.70% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemWrite 2987 7.30% 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 254996147 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::mean 0.971138 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::stdev 0.960460 # 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 97493255 38.23% 38.23% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::1 86911390 34.08% 72.32% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::2 54912481 21.53% 93.85% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::3 12234045 4.80% 98.65% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::4 3109625 1.22% 99.87% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::5 255105 0.10% 99.97% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::6 77911 0.03% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::7 2335 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::8 0 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 7 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::total 254996147 # Number of insts issued each cycle +system.cpu.iq.ISSUE:rate 0.970662 # Inst issue rate +system.cpu.iq.iqInstsAdded 291512819 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 247636323 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 1275 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 69673728 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 1298 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 29 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 182988092 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 1575 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 34364.012739 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31058.917197 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_hits 5 # number of ReadExReq hits +system.cpu.l2cache.ReadExReq_miss_latency 53951500 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 0.996825 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 1570 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 48762500 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.996825 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 1570 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 5367 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 34265.528407 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31035.178098 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 1970 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 116400000 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.632942 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 3397 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 105426500 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.632942 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 3397 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 9 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 9 # 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 0.579412 # 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 6942 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 34296.657942 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31042.681699 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 1975 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 170351500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.715500 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 4967 # 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 154189000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.715500 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 4967 # 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 0.068086 # Average percentage of cache occupancy +system.cpu.l2cache.occ_%::1 0.000031 # Average percentage of cache occupancy +system.cpu.l2cache.occ_blocks::0 2231.049035 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 1.015700 # Average occupied blocks per context +system.cpu.l2cache.overall_accesses 6942 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 34296.657942 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31042.681699 # 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 1975 # number of overall hits +system.cpu.l2cache.overall_miss_latency 170351500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.715500 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 4967 # number of overall misses +system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_miss_latency 154189000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.715500 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 4967 # 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 3400 # 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 2232.064735 # Cycle average of tags in use +system.cpu.l2cache.total_refs 1970 # 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 21807942 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 4495847 # Number of conflicting stores. +system.cpu.memDep0.insertedLoads 75869162 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 25600521 # Number of stores inserted to the mem dependence unit. +system.cpu.numCycles 255121086 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 1303093 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 234363409 # Number of HB maps that are committed +system.cpu.rename.RENAME:IQFullEvents 2662460 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 57579297 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 975892 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 963293874 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 304077108 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 331962025 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 180705413 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 11003980 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 4387817 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 97598616 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 16547 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 1274 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 8156807 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 1279 # count of temporary serializing insts renamed +system.cpu.timesIdled 2349 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.workload.PROG:num_syscalls 400 # Number of system calls + +---------- End Simulation Statistics ---------- -- cgit v1.2.3