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/10.mcf | |
| 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/10.mcf')
| -rw-r--r-- | tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini | 519 | ||||
| -rw-r--r-- | tests/long/10.mcf/ref/x86/linux/o3-timing/mcf.out | 999 | ||||
| -rwxr-xr-x | tests/long/10.mcf/ref/x86/linux/o3-timing/simerr | 7 | ||||
| -rwxr-xr-x | tests/long/10.mcf/ref/x86/linux/o3-timing/simout | 31 | ||||
| -rw-r--r-- | tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt | 442 |
5 files changed, 1998 insertions, 0 deletions
diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini b/tests/long/10.mcf/ref/x86/linux/o3-timing/config.ini new file mode 100644 index 000000000..60f53a64a --- /dev/null +++ b/tests/long/10.mcf/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=mcf mcf.in +cwd=build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing +egid=100 +env= +errout=cerr +euid=100 +executable=/dist/m5/cpu2000/binaries/x86/linux/mcf +gid=100 +input=/dist/m5/cpu2000/data/mcf/smred/input/mcf.in +max_stack_size=67108864 +output=cout +pid=100 +ppid=99 +simpoint=55300000000 +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=0:268435455 +zero=false +port=system.membus.port[0] + diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/mcf.out b/tests/long/10.mcf/ref/x86/linux/o3-timing/mcf.out new file mode 100644 index 000000000..095132477 --- /dev/null +++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/mcf.out @@ -0,0 +1,999 @@ +() +500 +() +499 +() +498 +() +496 +() +495 +() +494 +() +493 +() +492 +() +491 +() +490 +() +489 +() +488 +() +487 +() +486 +() +484 +() +482 +() +481 +() +480 +() +479 +() +478 +() +477 +() +476 +() +475 +() +474 +() +473 +() +472 +() +471 +() +469 +() +468 +() +467 +() +466 +() +465 +() +464 +() +463 +() +462 +() +461 +() +460 +() +459 +() +458 +() +457 +() +455 +() +454 +() +452 +() +451 +() +450 +() +449 +() +448 +() +446 +() +445 +() +444 +() +443 +() +442 +() +440 +() +439 +() +438 +() +436 +() +435 +() +433 +() +432 +() +431 +() +428 +() +427 +() +425 +() +424 +() +423 +() +420 +() +419 +() +416 +() +414 +() +413 +() +412 +() +407 +() +406 +() +405 +() +404 +() +403 +() +402 +() +401 +() +400 +() +399 +() +398 +() +396 +() +395 +() +393 +() +392 +() +390 +() +389 +() +388 +() +387 +() +386 +() +385 +() +384 +() +383 +() +382 +() +381 +() +380 +() +379 +() +377 +() +375 +() +374 +() +373 +() +372 +() +371 +() +370 +() +369 +() +368 +() +366 +() +365 +() +364 +() +362 +() +361 +() +360 +() +359 +() +358 +() +357 +() +356 +() +355 +() +354 +() +352 +() +350 +() +347 +() +344 +() +342 +() +341 +() +340 +() +339 +() +338 +() +332 +() +325 +() +320 +*** +345 +() +319 +*** +497 +() +318 +*** +349 +() +317 +*** +408 +() +316 +*** +324 +() +315 +*** +328 +() +314 +*** +335 +() +313 +*** +378 +() +312 +*** +426 +() +311 +*** +411 +() +304 +*** +343 +() +303 +*** +417 +() +302 +*** +485 +() +301 +*** +363 +() +300 +*** +376 +() +299 +*** +333 +() +292 +*** +337 +() +291 +*** +409 +() +290 +*** +421 +() +289 +*** +437 +() +288 +*** +430 +() +287 +*** +348 +() +286 +*** +326 +() +284 +() +282 +*** +308 +() +279 +*** +297 +*** +305 +() +278 +() +277 +*** +307 +() +276 +*** +296 +() +273 +() +271 +() +265 +() +246 +*** +267 +() +245 +*** +280 +() +244 +*** +391 +() +243 +*** +330 +() +242 +*** +456 +() +241 +*** +346 +() +240 +*** +483 +() +239 +*** +260 +() +238 +*** +261 +() +237 +*** +262 +*** +294 +() +236 +*** +253 +() +229 +*** +397 +() +228 +*** +298 +() +227 +*** +415 +() +226 +*** +264 +() +224 +*** +232 +() +222 +*** +233 +() +217 +*** +250 +() +211 +*** +331 +() +210 +*** +394 +() +209 +*** +410 +() +208 +*** +321 +() +207 +*** +327 +() +206 +*** +309 +() +199 +*** +259 +() +198 +*** +219 +() +197 +*** +220 +() +195 +*** +429 +() +194 +*** +470 +() +193 +*** +274 +() +191 +*** +203 +() +190 +*** +263 +() +189 +215 +*** +230 +() +188 +*** +266 +*** +295 +() +182 +*** +329 +() +181 +*** +351 +() +180 +*** +441 +() +179 +*** +453 +() +178 +*** +418 +() +177 +*** +353 +() +176 +*** +422 +() +175 +*** +225 +*** +255 +() +174 +*** +269 +() +173 +*** +214 +() +172 +*** +186 +() +171 +*** +447 +() +170 +*** +270 +*** +306 +() +169 +*** +336 +() +168 +*** +285 +() +165 +*** +249 +() +146 +*** +154 +() +143 +*** +334 +() +142 +*** +216 +*** +257 +() +141 +*** +167 +*** +251 +() +140 +*** +162 +*** +293 +() +139 +*** +158 +() +137 +*** +166 +*** +201 +() +136 +*** +160 +() +134 +*** +221 +() +132 +*** +213 +() +131 +*** +187 +() +129 +*** +235 +() +128 +*** +153 +() +127 +*** +156 +() +126 +*** +159 +*** +218 +() +125 +*** +155 +() +124 +*** +157 +() +123 +*** +152 +() +116 +*** +135 +*** +163 +() +115 +*** +133 +*** +204 +*** +248 +() +114 +*** +192 +*** +212 +() +113 +*** +268 +() +112 +*** +367 +() +111 +*** +272 +() +110 +*** +434 +() +109 +*** +323 +() +108 +*** +281 +() +107 +*** +144 +*** +148 +() +106 +*** +275 +() +105 +*** +196 +*** +254 +() +104 +*** +138 +*** +161 +() +103 +*** +310 +() +102 +*** +223 +*** +252 +() +80 +() +70 +() +69 +() +68 +() +66 +() +64 +() +62 +*** +256 +() +61 +*** +93 +() +59 +*** +120 +() +58 +() +57 +*** +183 +() +55 +() +54 +() +52 +*** +147 +() +51 +*** +118 +() +50 +*** +83 +() +49 +*** +98 +() +48 +*** +99 +() +47 +() +46 +*** +184 +() +45 +*** +121 +() +44 +() +43 +*** +88 +() +42 +*** +122 +() +41 +*** +91 +() +40 +*** +96 +() +38 +*** +100 +() +37 +*** +149 +() +36 +*** +74 +() +35 +*** +258 +() +34 +*** +151 +() +33 +*** +85 +() +32 +() +31 +*** +94 +() +30 +*** +97 +() +29 +*** +90 +() +28 +*** +89 +() +27 +*** +92 +() +26 +*** +72 +*** +247 +() +25 +*** +86 +() +24 +*** +82 +() +23 +*** +87 +*** +117 +() +22 +*** +76 +*** +119 +() +21 +*** +84 +() +20 +*** +78 +() +19 +*** +73 +() +18 +*** +81 +() +17 +*** +65 +() +16 +*** +63 +*** +101 +() +15 +*** +71 +() +14 +*** +75 +() +13 +*** +322 +() +12 +*** +77 +() +11 +*** +283 +() +10 +*** +79 +() +9 +*** +145 +*** +150 +() +8 +*** +67 +() +7 +*** +60 +*** +231 +() +6 +*** +56 +*** +234 +() +5 +*** +164 +*** +202 +() +4 +*** +53 +() +3 +*** +130 +*** +185 +*** +200 +() +2 +*** +205 +() +1 +*** +39 +*** +95 diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/simerr b/tests/long/10.mcf/ref/x86/linux/o3-timing/simerr new file mode 100755 index 000000000..94d399eab --- /dev/null +++ b/tests/long/10.mcf/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/10.mcf/ref/x86/linux/o3-timing/simout b/tests/long/10.mcf/ref/x86/linux/o3-timing/simout new file mode 100755 index 000000000..fde487a8e --- /dev/null +++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/simout @@ -0,0 +1,31 @@ +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/10.mcf/x86/linux/o3-timing -re tests/run.py build/X86_SE/tests/opt/long/10.mcf/x86/linux/o3-timing +Global frequency set at 1000000000000 ticks per second +info: Entering event queue @ 0. Starting simulation... + +MCF SPEC version 1.6.I +by Andreas Loebel +Copyright (c) 1998,1999 ZIB Berlin +All Rights Reserved. + +nodes : 500 +active arcs : 1905 +simplex iterations : 1502 +flow value : 4990014995 +new implicit arcs : 23867 +active arcs : 25772 +simplex iterations : 2663 +flow value : 3080014995 +checksum : 68389 +optimal +Exiting @ tick 170680631000 because target called exit() diff --git a/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt b/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt new file mode 100644 index 000000000..8ba88fe5a --- /dev/null +++ b/tests/long/10.mcf/ref/x86/linux/o3-timing/stats.txt @@ -0,0 +1,442 @@ + +---------- Begin Simulation Statistics ---------- +host_inst_rate 76828 # Simulator instruction rate (inst/s) +host_mem_usage 366252 # Number of bytes of host memory used +host_seconds 3621.00 # Real time elapsed on the host +host_tick_rate 47136339 # Simulator tick rate (ticks/s) +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 278192519 # Number of instructions simulated +sim_seconds 0.170681 # Number of seconds simulated +sim_ticks 170680631000 # Number of ticks simulated +system.cpu.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +system.cpu.BPredUnit.BTBHits 50810617 # Number of BTB hits +system.cpu.BPredUnit.BTBLookups 51416767 # Number of BTB lookups +system.cpu.BPredUnit.RASInCorrect 0 # Number of incorrect RAS predictions. +system.cpu.BPredUnit.condIncorrect 4328981 # Number of conditional branches incorrect +system.cpu.BPredUnit.condPredicted 51416803 # Number of conditional branches predicted +system.cpu.BPredUnit.lookups 51416803 # 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 29309710 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 2488105 # 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 321793097 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::mean 0.864507 # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::stdev 1.425920 # 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 183622049 57.06% 57.06% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::1 75902754 23.59% 80.65% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::2 27223254 8.46% 89.11% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::3 17908154 5.57% 94.67% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::4 5463718 1.70% 96.37% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::5 3630830 1.13% 97.50% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::6 4674698 1.45% 98.95% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::7 879535 0.27% 99.23% # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle::8 2488105 0.77% 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 321793097 # Number of insts commited each cycle +system.cpu.commit.COM:count 278192519 # Number of instructions committed +system.cpu.commit.COM:loads 90779388 # Number of loads committed +system.cpu.commit.COM:membars 0 # Number of memory barriers committed +system.cpu.commit.COM:refs 122219139 # Number of memory references committed +system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu.commit.branchMispredicts 4328992 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 278192519 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 446 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 111464423 # The number of squashed insts skipped by commit +system.cpu.committedInsts 278192519 # Number of Instructions Simulated +system.cpu.committedInsts_total 278192519 # Number of Instructions Simulated +system.cpu.cpi 1.227068 # CPI: Cycles Per Instruction +system.cpu.cpi_total 1.227068 # CPI: Total CPI of All Threads +system.cpu.dcache.ReadReq_accesses 82779625 # number of ReadReq accesses(hits+misses) +system.cpu.dcache.ReadReq_avg_miss_latency 5978.815311 # average ReadReq miss latency +system.cpu.dcache.ReadReq_avg_mshr_miss_latency 2941.059048 # average ReadReq mshr miss latency +system.cpu.dcache.ReadReq_hits 80764514 # number of ReadReq hits +system.cpu.dcache.ReadReq_miss_latency 12047976500 # number of ReadReq miss cycles +system.cpu.dcache.ReadReq_miss_rate 0.024343 # miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_misses 2015111 # number of ReadReq misses +system.cpu.dcache.ReadReq_mshr_hits 45360 # number of ReadReq MSHR hits +system.cpu.dcache.ReadReq_mshr_miss_latency 5793154000 # number of ReadReq MSHR miss cycles +system.cpu.dcache.ReadReq_mshr_miss_rate 0.023795 # mshr miss rate for ReadReq accesses +system.cpu.dcache.ReadReq_mshr_misses 1969751 # number of ReadReq MSHR misses +system.cpu.dcache.WriteReq_accesses 31439751 # number of WriteReq accesses(hits+misses) +system.cpu.dcache.WriteReq_avg_miss_latency 20696.077989 # average WriteReq miss latency +system.cpu.dcache.WriteReq_avg_mshr_miss_latency 15440.513442 # average WriteReq mshr miss latency +system.cpu.dcache.WriteReq_hits 31284703 # number of WriteReq hits +system.cpu.dcache.WriteReq_miss_latency 3208885500 # number of WriteReq miss cycles +system.cpu.dcache.WriteReq_miss_rate 0.004932 # miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_misses 155048 # number of WriteReq misses +system.cpu.dcache.WriteReq_mshr_hits 48629 # number of WriteReq MSHR hits +system.cpu.dcache.WriteReq_mshr_miss_latency 1643164000 # number of WriteReq MSHR miss cycles +system.cpu.dcache.WriteReq_mshr_miss_rate 0.003385 # mshr miss rate for WriteReq accesses +system.cpu.dcache.WriteReq_mshr_misses 106419 # 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 53.969218 # 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 114219376 # number of demand (read+write) accesses +system.cpu.dcache.demand_avg_miss_latency 7030.296858 # average overall miss latency +system.cpu.dcache.demand_avg_mshr_miss_latency 3581.748123 # average overall mshr miss latency +system.cpu.dcache.demand_hits 112049217 # number of demand (read+write) hits +system.cpu.dcache.demand_miss_latency 15256862000 # number of demand (read+write) miss cycles +system.cpu.dcache.demand_miss_rate 0.019000 # miss rate for demand accesses +system.cpu.dcache.demand_misses 2170159 # number of demand (read+write) misses +system.cpu.dcache.demand_mshr_hits 93989 # number of demand (read+write) MSHR hits +system.cpu.dcache.demand_mshr_miss_latency 7436318000 # number of demand (read+write) MSHR miss cycles +system.cpu.dcache.demand_mshr_miss_rate 0.018177 # mshr miss rate for demand accesses +system.cpu.dcache.demand_mshr_misses 2076170 # 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 0.995143 # Average percentage of cache occupancy +system.cpu.dcache.occ_blocks::0 4076.104755 # Average occupied blocks per context +system.cpu.dcache.overall_accesses 114219376 # number of overall (read+write) accesses +system.cpu.dcache.overall_avg_miss_latency 7030.296858 # average overall miss latency +system.cpu.dcache.overall_avg_mshr_miss_latency 3581.748123 # 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 112049217 # number of overall hits +system.cpu.dcache.overall_miss_latency 15256862000 # number of overall miss cycles +system.cpu.dcache.overall_miss_rate 0.019000 # miss rate for overall accesses +system.cpu.dcache.overall_misses 2170159 # number of overall misses +system.cpu.dcache.overall_mshr_hits 93989 # number of overall MSHR hits +system.cpu.dcache.overall_mshr_miss_latency 7436318000 # number of overall MSHR miss cycles +system.cpu.dcache.overall_mshr_miss_rate 0.018177 # mshr miss rate for overall accesses +system.cpu.dcache.overall_mshr_misses 2076170 # 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 2072073 # number of replacements +system.cpu.dcache.sampled_refs 2076169 # 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 4076.104755 # Cycle average of tags in use +system.cpu.dcache.total_refs 112049217 # Total number of references to valid blocks. +system.cpu.dcache.warmup_cycle 66009760000 # Cycle when the warmup percentage was hit. +system.cpu.dcache.writebacks 1440063 # number of writebacks +system.cpu.decode.DECODE:BlockedCycles 922031 # Number of cycles decode is blocked +system.cpu.decode.DECODE:DecodedInsts 437195268 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 92021485 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 228705655 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 19453848 # Number of cycles decode is squashing +system.cpu.decode.DECODE:UnblockCycles 143926 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 51416803 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 39245397 # Number of cache lines fetched +system.cpu.fetch.Cycles 242939967 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.IcacheSquashes 793923 # Number of outstanding Icache misses that were squashed +system.cpu.fetch.Insts 249694241 # Number of instructions fetch has processed +system.cpu.fetch.MiscStallCycles 16 # Number of cycles fetch has spent waiting on interrupts, or bad addresses, or out of MSHRs +system.cpu.fetch.SquashCycles 9845420 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.150623 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 39245397 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 50810617 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 0.731466 # Number of inst fetches per cycle +system.cpu.fetch.rateDist::samples 341246945 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.321737 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 1.251135 # 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 105340577 30.87% 30.87% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::1 115413940 33.82% 64.69% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 47580781 13.94% 78.63% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::3 58732555 17.21% 95.84% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::4 7189604 2.11% 97.95% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::5 6451059 1.89% 99.84% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::6 527277 0.15% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 932 0.00% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 10220 0.00% 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 341246945 # Number of instructions fetched each cycle (Total) +system.cpu.icache.ReadReq_accesses 39245397 # number of ReadReq accesses(hits+misses) +system.cpu.icache.ReadReq_avg_miss_latency 37208.490566 # average ReadReq miss latency +system.cpu.icache.ReadReq_avg_mshr_miss_latency 35316.192560 # average ReadReq mshr miss latency +system.cpu.icache.ReadReq_hits 39244337 # number of ReadReq hits +system.cpu.icache.ReadReq_miss_latency 39441000 # number of ReadReq miss cycles +system.cpu.icache.ReadReq_miss_rate 0.000027 # miss rate for ReadReq accesses +system.cpu.icache.ReadReq_misses 1060 # number of ReadReq misses +system.cpu.icache.ReadReq_mshr_hits 146 # number of ReadReq MSHR hits +system.cpu.icache.ReadReq_mshr_miss_latency 32279000 # number of ReadReq MSHR miss cycles +system.cpu.icache.ReadReq_mshr_miss_rate 0.000023 # mshr miss rate for ReadReq accesses +system.cpu.icache.ReadReq_mshr_misses 914 # 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 42936.911379 # 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 39245397 # number of demand (read+write) accesses +system.cpu.icache.demand_avg_miss_latency 37208.490566 # average overall miss latency +system.cpu.icache.demand_avg_mshr_miss_latency 35316.192560 # average overall mshr miss latency +system.cpu.icache.demand_hits 39244337 # number of demand (read+write) hits +system.cpu.icache.demand_miss_latency 39441000 # number of demand (read+write) miss cycles +system.cpu.icache.demand_miss_rate 0.000027 # miss rate for demand accesses +system.cpu.icache.demand_misses 1060 # number of demand (read+write) misses +system.cpu.icache.demand_mshr_hits 146 # number of demand (read+write) MSHR hits +system.cpu.icache.demand_mshr_miss_latency 32279000 # number of demand (read+write) MSHR miss cycles +system.cpu.icache.demand_mshr_miss_rate 0.000023 # mshr miss rate for demand accesses +system.cpu.icache.demand_mshr_misses 914 # 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 0.360466 # Average percentage of cache occupancy +system.cpu.icache.occ_blocks::0 738.235227 # Average occupied blocks per context +system.cpu.icache.overall_accesses 39245397 # number of overall (read+write) accesses +system.cpu.icache.overall_avg_miss_latency 37208.490566 # average overall miss latency +system.cpu.icache.overall_avg_mshr_miss_latency 35316.192560 # 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 39244337 # number of overall hits +system.cpu.icache.overall_miss_latency 39441000 # number of overall miss cycles +system.cpu.icache.overall_miss_rate 0.000027 # miss rate for overall accesses +system.cpu.icache.overall_misses 1060 # number of overall misses +system.cpu.icache.overall_mshr_hits 146 # number of overall MSHR hits +system.cpu.icache.overall_mshr_miss_latency 32279000 # number of overall MSHR miss cycles +system.cpu.icache.overall_mshr_miss_rate 0.000023 # mshr miss rate for overall accesses +system.cpu.icache.overall_mshr_misses 914 # 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 37 # number of replacements +system.cpu.icache.sampled_refs 914 # 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 738.235227 # Cycle average of tags in use +system.cpu.icache.total_refs 39244337 # 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 114318 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.iew.EXEC:branches 31118985 # Number of branches executed +system.cpu.iew.EXEC:nop 0 # number of nop insts executed +system.cpu.iew.EXEC:rate 0.940576 # Inst execution rate +system.cpu.iew.EXEC:refs 137464023 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 32172568 # Number of stores executed +system.cpu.iew.EXEC:swp 0 # number of swp insts executed +system.cpu.iew.WB:consumers 361852587 # num instructions consuming a value +system.cpu.iew.WB:count 317781549 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.623035 # 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 225446782 # num instructions producing a value +system.cpu.iew.WB:rate 0.930924 # insts written-back per cycle +system.cpu.iew.WB:sent 318008427 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 5390321 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 197365 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 131280417 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 455 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 3671049 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 41039188 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 389592858 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 105291455 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 12266571 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 321076071 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 2799 # 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 1704 # Number of times the LSQ has become full, causing a stall +system.cpu.iew.iewSquashCycles 19453848 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 10507 # 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 22405068 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 64376 # 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 5520980 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 2668 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 40501029 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 9599437 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 5520980 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 16897 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 5373424 # Number of branches that were predicted taken incorrectly +system.cpu.ipc 0.814950 # IPC: Instructions Per Cycle +system.cpu.ipc_total 0.814950 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0::No_OpClass 16700 0.01% 0.01% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntAlu 193455065 58.03% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntMult 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::IntDiv 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatAdd 15 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCmp 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatCvt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatMult 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatDiv 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::FloatSqrt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAdd 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAddAcc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdAlu 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCmp 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdCvt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMisc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMult 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdMultAcc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShift 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdShiftAcc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdSqrt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAdd 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatAlu 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCmp 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatCvt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatDiv 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMisc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMult 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatMultAcc 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::SimdFloatSqrt 0 0.00% 58.04% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemRead 107162338 32.15% 90.19% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0::MemWrite 32708524 9.81% 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 333342642 # Type of FU issued +system.cpu.iq.ISSUE:fu_busy_cnt 98152 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.000294 # 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 15 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 97651 99.49% 99.50% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full::MemWrite 486 0.50% 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 341246945 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::mean 0.976837 # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::stdev 1.032280 # 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 143332703 42.00% 42.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::1 98734149 28.93% 70.94% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::2 68142120 19.97% 90.90% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::3 26890607 7.88% 98.78% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::4 3089152 0.91% 99.69% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::5 1054470 0.31% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::6 2951 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::7 576 0.00% 100.00% # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle::8 217 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 341246945 # Number of insts issued each cycle +system.cpu.iq.ISSUE:rate 0.976510 # Inst issue rate +system.cpu.iq.iqInstsAdded 389592403 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 333342642 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 455 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 109882124 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedNonSpecRemoved 9 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 237362106 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.l2cache.ReadExReq_accesses 106419 # number of ReadExReq accesses(hits+misses) +system.cpu.l2cache.ReadExReq_avg_miss_latency 34277.831445 # average ReadExReq miss latency +system.cpu.l2cache.ReadExReq_avg_mshr_miss_latency 31049.336758 # average ReadExReq mshr miss latency +system.cpu.l2cache.ReadExReq_hits 63976 # number of ReadExReq hits +system.cpu.l2cache.ReadExReq_miss_latency 1454854000 # number of ReadExReq miss cycles +system.cpu.l2cache.ReadExReq_miss_rate 0.398829 # miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_misses 42443 # number of ReadExReq misses +system.cpu.l2cache.ReadExReq_mshr_miss_latency 1317827000 # number of ReadExReq MSHR miss cycles +system.cpu.l2cache.ReadExReq_mshr_miss_rate 0.398829 # mshr miss rate for ReadExReq accesses +system.cpu.l2cache.ReadExReq_mshr_misses 42443 # number of ReadExReq MSHR misses +system.cpu.l2cache.ReadReq_accesses 1970665 # number of ReadReq accesses(hits+misses) +system.cpu.l2cache.ReadReq_avg_miss_latency 34310.495712 # average ReadReq miss latency +system.cpu.l2cache.ReadReq_avg_mshr_miss_latency 31007.530164 # average ReadReq mshr miss latency +system.cpu.l2cache.ReadReq_hits 1936270 # number of ReadReq hits +system.cpu.l2cache.ReadReq_miss_latency 1180109500 # number of ReadReq miss cycles +system.cpu.l2cache.ReadReq_miss_rate 0.017453 # miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_misses 34395 # number of ReadReq misses +system.cpu.l2cache.ReadReq_mshr_miss_latency 1066504000 # number of ReadReq MSHR miss cycles +system.cpu.l2cache.ReadReq_mshr_miss_rate 0.017453 # mshr miss rate for ReadReq accesses +system.cpu.l2cache.ReadReq_mshr_misses 34395 # number of ReadReq MSHR misses +system.cpu.l2cache.Writeback_accesses 1440063 # number of Writeback accesses(hits+misses) +system.cpu.l2cache.Writeback_hits 1440063 # 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 42.751383 # 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 2077084 # number of demand (read+write) accesses +system.cpu.l2cache.demand_avg_miss_latency 34292.452953 # average overall miss latency +system.cpu.l2cache.demand_avg_mshr_miss_latency 31030.622869 # average overall mshr miss latency +system.cpu.l2cache.demand_hits 2000246 # number of demand (read+write) hits +system.cpu.l2cache.demand_miss_latency 2634963500 # number of demand (read+write) miss cycles +system.cpu.l2cache.demand_miss_rate 0.036993 # miss rate for demand accesses +system.cpu.l2cache.demand_misses 76838 # 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 2384331000 # number of demand (read+write) MSHR miss cycles +system.cpu.l2cache.demand_mshr_miss_rate 0.036993 # mshr miss rate for demand accesses +system.cpu.l2cache.demand_mshr_misses 76838 # 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 0.192442 # Average percentage of cache occupancy +system.cpu.l2cache.occ_%::1 0.349126 # Average percentage of cache occupancy +system.cpu.l2cache.occ_blocks::0 6305.950681 # Average occupied blocks per context +system.cpu.l2cache.occ_blocks::1 11440.167306 # Average occupied blocks per context +system.cpu.l2cache.overall_accesses 2077084 # number of overall (read+write) accesses +system.cpu.l2cache.overall_avg_miss_latency 34292.452953 # average overall miss latency +system.cpu.l2cache.overall_avg_mshr_miss_latency 31030.622869 # 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 2000246 # number of overall hits +system.cpu.l2cache.overall_miss_latency 2634963500 # number of overall miss cycles +system.cpu.l2cache.overall_miss_rate 0.036993 # miss rate for overall accesses +system.cpu.l2cache.overall_misses 76838 # number of overall misses +system.cpu.l2cache.overall_mshr_hits 0 # number of overall MSHR hits +system.cpu.l2cache.overall_mshr_miss_latency 2384331000 # number of overall MSHR miss cycles +system.cpu.l2cache.overall_mshr_miss_rate 0.036993 # mshr miss rate for overall accesses +system.cpu.l2cache.overall_mshr_misses 76838 # 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 49392 # number of replacements +system.cpu.l2cache.sampled_refs 77392 # 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 17746.117987 # Cycle average of tags in use +system.cpu.l2cache.total_refs 3308615 # Total number of references to valid blocks. +system.cpu.l2cache.warmup_cycle 0 # Cycle when the warmup percentage was hit. +system.cpu.l2cache.writebacks 29474 # number of writebacks +system.cpu.memDep0.conflictingLoads 22358679 # Number of conflicting loads. +system.cpu.memDep0.conflictingStores 3757180 # Number of conflicting stores. +system.cpu.memDep0.insertedLoads 131280417 # Number of loads inserted to the mem dependence unit. +system.cpu.memDep0.insertedStores 41039188 # Number of stores inserted to the mem dependence unit. +system.cpu.numCycles 341361263 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 486743 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 248344192 # Number of HB maps that are committed +system.cpu.rename.RENAME:IQFullEvents 12249 # Number of times rename has blocked due to IQ full +system.cpu.rename.RENAME:IdleCycles 98511117 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 368076 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 1292599643 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 423407319 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 377348250 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 222275258 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 19453848 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 514692 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 129004058 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 5287 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 454 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 779091 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 452 # count of temporary serializing insts renamed +system.cpu.timesIdled 5627 # Number of times that the entire CPU went into an idle state and unscheduled itself +system.cpu.workload.PROG:num_syscalls 444 # Number of system calls + +---------- End Simulation Statistics ---------- |