From 84dac99e2ef0c0c4fcf54d0ebba647b60448c049 Mon Sep 17 00:00:00 2001 From: Korey Sewell Date: Fri, 6 Oct 2006 04:23:27 -0400 Subject: add SMT hello world test - 2 threads --HG-- extra : convert_revision : 54cb19d1325295895b6f0b992499bbb0216b45df --- .../ref/alpha/linux/o3-timing/m5stats.txt | 305 +++++++++++++++++++++ 1 file changed, 305 insertions(+) create mode 100644 tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt (limited to 'tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt') diff --git a/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt new file mode 100644 index 000000000..4473a39f8 --- /dev/null +++ b/tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt @@ -0,0 +1,305 @@ + +---------- Begin Simulation Statistics ---------- +global.BPredUnit.BTBCorrect 0 # Number of correct BTB predictions (this stat may not work properly. +global.BPredUnit.BTBHits 669 # Number of BTB hits +global.BPredUnit.BTBLookups 3666 # Number of BTB lookups +global.BPredUnit.RASInCorrect 78 # Number of incorrect RAS predictions. +global.BPredUnit.condIncorrect 1050 # Number of conditional branches incorrect +global.BPredUnit.condPredicted 2479 # Number of conditional branches predicted +global.BPredUnit.lookups 4216 # Number of BP lookups +global.BPredUnit.usedRAS 545 # Number of times the RAS was used to get a target. +host_inst_rate 13879 # Simulator instruction rate (inst/s) +host_mem_usage 150244 # Number of bytes of host memory used +host_seconds 0.82 # Real time elapsed on the host +host_tick_rate 9101 # Simulator tick rate (ticks/s) +memdepunit.memDep.conflictingLoads 21 # Number of conflicting loads. +memdepunit.memDep.conflictingLoads 25 # Number of conflicting loads. +memdepunit.memDep.conflictingStores 0 # Number of conflicting stores. +memdepunit.memDep.conflictingStores 214 # Number of conflicting stores. +memdepunit.memDep.insertedLoads 1795 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedLoads 1734 # Number of loads inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1066 # Number of stores inserted to the mem dependence unit. +memdepunit.memDep.insertedStores 1051 # Number of stores inserted to the mem dependence unit. +sim_freq 1000000000000 # Frequency of simulated ticks +sim_insts 11399 # Number of instructions simulated +sim_seconds 0.000000 # Number of seconds simulated +sim_ticks 7478 # Number of ticks simulated +system.cpu.commit.COM:branches 1756 # Number of branches committed +system.cpu.commit.COM:branches_0 878 # Number of branches committed +system.cpu.commit.COM:branches_1 878 # Number of branches committed +system.cpu.commit.COM:bw_lim_events 177 # 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:bw_limited_0 0 # number of insts not committed due to BW limits +system.cpu.commit.COM:bw_limited_1 0 # number of insts not committed due to BW limits +system.cpu.commit.COM:committed_per_cycle.start_dist # Number of insts commited each cycle +system.cpu.commit.COM:committed_per_cycle.samples 7424 +system.cpu.commit.COM:committed_per_cycle.min_value 0 + 0 3237 4360.18% + 1 1635 2202.32% + 2 920 1239.22% + 3 476 641.16% + 4 347 467.40% + 5 246 331.36% + 6 206 277.48% + 7 180 242.46% + 8 177 238.42% +system.cpu.commit.COM:committed_per_cycle.max_value 8 +system.cpu.commit.COM:committed_per_cycle.end_dist + +system.cpu.commit.COM:count 11433 # Number of instructions committed +system.cpu.commit.COM:count_0 5716 # Number of instructions committed +system.cpu.commit.COM:count_1 5717 # Number of instructions committed +system.cpu.commit.COM:loads 1976 # Number of loads committed +system.cpu.commit.COM:loads_0 988 # Number of loads committed +system.cpu.commit.COM:loads_1 988 # Number of loads committed +system.cpu.commit.COM:membars 0 # Number of memory barriers committed +system.cpu.commit.COM:membars_0 0 # Number of memory barriers committed +system.cpu.commit.COM:membars_1 0 # Number of memory barriers committed +system.cpu.commit.COM:refs 3600 # Number of memory references committed +system.cpu.commit.COM:refs_0 1800 # Number of memory references committed +system.cpu.commit.COM:refs_1 1800 # Number of memory references committed +system.cpu.commit.COM:swp_count 0 # Number of s/w prefetches committed +system.cpu.commit.COM:swp_count_0 0 # Number of s/w prefetches committed +system.cpu.commit.COM:swp_count_1 0 # Number of s/w prefetches committed +system.cpu.commit.branchMispredicts 789 # The number of times a branch was mispredicted +system.cpu.commit.commitCommittedInsts 11433 # The number of committed instructions +system.cpu.commit.commitNonSpecStalls 34 # The number of times commit has been forced to stall to communicate backwards +system.cpu.commit.commitSquashedInsts 6802 # The number of squashed insts skipped by commit +system.cpu.committedInsts_0 5699 # Number of Instructions Simulated +system.cpu.committedInsts_1 5700 # Number of Instructions Simulated +system.cpu.committedInsts_total 11399 # Number of Instructions Simulated +system.cpu.cpi_0 1.312160 # CPI: Cycles Per Instruction +system.cpu.cpi_1 1.311930 # CPI: Cycles Per Instruction +system.cpu.cpi_total 0.656022 # CPI: Total CPI of All Threads +system.cpu.decode.DECODE:BlockedCycles 1617 # Number of cycles decode is blocked +system.cpu.decode.DECODE:BranchMispred 282 # Number of times decode detected a branch misprediction +system.cpu.decode.DECODE:BranchResolved 364 # Number of times decode resolved a branch +system.cpu.decode.DECODE:DecodedInsts 22220 # Number of instructions handled by decode +system.cpu.decode.DECODE:IdleCycles 8058 # Number of cycles decode is idle +system.cpu.decode.DECODE:RunCycles 3571 # Number of cycles decode is running +system.cpu.decode.DECODE:SquashCycles 1260 # Number of cycles decode is squashing +system.cpu.decode.DECODE:SquashedInsts 200 # Number of squashed instructions handled by decode +system.cpu.decode.DECODE:UnblockCycles 277 # Number of cycles decode is unblocking +system.cpu.fetch.Branches 4216 # Number of branches that fetch encountered +system.cpu.fetch.CacheLines 2762 # Number of cache lines fetched +system.cpu.fetch.Cycles 6837 # Number of cycles fetch has run and was not squashing or blocked +system.cpu.fetch.Insts 25142 # Number of instructions fetch has processed +system.cpu.fetch.SquashCycles 1098 # Number of cycles fetch has spent squashing +system.cpu.fetch.branchRate 0.563712 # Number of branch fetches per cycle +system.cpu.fetch.icacheStallCycles 2762 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.predictedBranches 1214 # Number of branches that fetch has predicted taken +system.cpu.fetch.rate 3.361679 # Number of inst fetches per cycle +system.cpu.fetch.rateDist.start_dist # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist.samples 7479 +system.cpu.fetch.rateDist.min_value 0 + 0 3407 4555.42% + 1 266 355.66% + 2 222 296.83% + 3 265 354.33% + 4 317 423.85% + 5 275 367.70% + 6 279 373.04% + 7 264 352.99% + 8 2184 2920.18% +system.cpu.fetch.rateDist.max_value 8 +system.cpu.fetch.rateDist.end_dist + +system.cpu.iew.EXEC:branches 2294 # Number of branches executed +system.cpu.iew.EXEC:branches_0 1156 # Number of branches executed +system.cpu.iew.EXEC:branches_1 1138 # Number of branches executed +system.cpu.iew.EXEC:nop 59 # number of nop insts executed +system.cpu.iew.EXEC:nop_0 31 # number of nop insts executed +system.cpu.iew.EXEC:nop_1 28 # number of nop insts executed +system.cpu.iew.EXEC:rate 1.993582 # Inst execution rate +system.cpu.iew.EXEC:refs 4718 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_0 2364 # number of memory reference insts executed +system.cpu.iew.EXEC:refs_1 2354 # number of memory reference insts executed +system.cpu.iew.EXEC:stores 1857 # Number of stores executed +system.cpu.iew.EXEC:stores_0 924 # Number of stores executed +system.cpu.iew.EXEC:stores_1 933 # Number of stores executed +system.cpu.iew.EXEC:swp 0 # number of swp insts executed +system.cpu.iew.EXEC:swp_0 0 # number of swp insts executed +system.cpu.iew.EXEC:swp_1 0 # number of swp insts executed +system.cpu.iew.WB:consumers 9920 # num instructions consuming a value +system.cpu.iew.WB:consumers_0 4998 # num instructions consuming a value +system.cpu.iew.WB:consumers_1 4922 # num instructions consuming a value +system.cpu.iew.WB:count 14666 # cumulative count of insts written-back +system.cpu.iew.WB:count_0 7373 # cumulative count of insts written-back +system.cpu.iew.WB:count_1 7293 # cumulative count of insts written-back +system.cpu.iew.WB:fanout 0.776915 # average fanout of values written-back +system.cpu.iew.WB:fanout_0 0.775710 # average fanout of values written-back +system.cpu.iew.WB:fanout_1 0.778139 # 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_0 0 # number of instrctions required to write to 'other' IQ +system.cpu.iew.WB:penalized_1 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:penalized_rate_0 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu.iew.WB:penalized_rate_1 0 # fraction of instructions written-back that wrote to 'other' IQ +system.cpu.iew.WB:producers 7707 # num instructions producing a value +system.cpu.iew.WB:producers_0 3877 # num instructions producing a value +system.cpu.iew.WB:producers_1 3830 # num instructions producing a value +system.cpu.iew.WB:rate 1.960957 # insts written-back per cycle +system.cpu.iew.WB:rate_0 0.985827 # insts written-back per cycle +system.cpu.iew.WB:rate_1 0.975130 # insts written-back per cycle +system.cpu.iew.WB:sent 14753 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_0 7419 # cumulative count of insts sent to commit +system.cpu.iew.WB:sent_1 7334 # cumulative count of insts sent to commit +system.cpu.iew.branchMispredicts 869 # Number of branch mispredicts detected at execute +system.cpu.iew.iewBlockCycles 3 # Number of cycles IEW is blocking +system.cpu.iew.iewDispLoadInsts 3529 # Number of dispatched load instructions +system.cpu.iew.iewDispNonSpecInsts 39 # Number of dispatched non-speculative instructions +system.cpu.iew.iewDispSquashedInsts 789 # Number of squashed instructions skipped by dispatch +system.cpu.iew.iewDispStoreInsts 2117 # Number of dispatched store instructions +system.cpu.iew.iewDispatchedInsts 18235 # Number of instructions dispatched to IQ +system.cpu.iew.iewExecLoadInsts 2861 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_0 1440 # Number of load instructions executed +system.cpu.iew.iewExecLoadInsts_1 1421 # Number of load instructions executed +system.cpu.iew.iewExecSquashedInsts 1188 # Number of squashed instructions skipped in execute +system.cpu.iew.iewExecutedInsts 14910 # Number of executed instructions +system.cpu.iew.iewIQFullEvents 0 # 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 1260 # Number of cycles IEW is squashing +system.cpu.iew.iewUnblockCycles 0 # 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 45 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.0.ignoredResponses 4 # 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 27 # Number of memory ordering violations +system.cpu.iew.lsq.thread.0.rescheduledLoads 0 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.0.squashedLoads 807 # Number of loads squashed +system.cpu.iew.lsq.thread.0.squashedStores 254 # Number of stores squashed +system.cpu.iew.lsq.thread.1.blockedLoads 1 # Number of blocked loads due to partial load-store forwarding +system.cpu.iew.lsq.thread.1.cacheBlocked 0 # Number of times an access to memory failed due to the cache being blocked +system.cpu.iew.lsq.thread.1.forwLoads 43 # Number of loads that had data forwarded from stores +system.cpu.iew.lsq.thread.1.ignoredResponses 2 # Number of memory responses ignored because the instruction is squashed +system.cpu.iew.lsq.thread.1.invAddrLoads 0 # Number of loads ignored due to an invalid address +system.cpu.iew.lsq.thread.1.invAddrSwpfs 0 # Number of software prefetches ignored due to an invalid address +system.cpu.iew.lsq.thread.1.memOrderViolation 29 # Number of memory ordering violations +system.cpu.iew.lsq.thread.1.rescheduledLoads 1 # Number of loads that were rescheduled +system.cpu.iew.lsq.thread.1.squashedLoads 746 # Number of loads squashed +system.cpu.iew.lsq.thread.1.squashedStores 239 # Number of stores squashed +system.cpu.iew.memOrderViolationEvents 56 # Number of memory order violations +system.cpu.iew.predictedNotTakenIncorrect 733 # Number of branches that were predicted not taken incorrectly +system.cpu.iew.predictedTakenIncorrect 136 # Number of branches that were predicted taken incorrectly +system.cpu.ipc_0 0.762102 # IPC: Instructions Per Cycle +system.cpu.ipc_1 0.762236 # IPC: Instructions Per Cycle +system.cpu.ipc_total 1.524338 # IPC: Total IPC of All Threads +system.cpu.iq.ISSUE:FU_type_0 8140 # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0.start_dist +(null) 2 0.02% # Type of FU issued +IntAlu 5556 68.26% # Type of FU issued +IntMult 1 0.01% # Type of FU issued +IntDiv 0 0.00% # Type of FU issued +FloatAdd 2 0.02% # Type of FU issued +FloatCmp 0 0.00% # Type of FU issued +FloatCvt 0 0.00% # Type of FU issued +FloatMult 0 0.00% # Type of FU issued +FloatDiv 0 0.00% # Type of FU issued +FloatSqrt 0 0.00% # Type of FU issued +MemRead 1619 19.89% # Type of FU issued +MemWrite 960 11.79% # Type of FU issued +IprAccess 0 0.00% # Type of FU issued +InstPrefetch 0 0.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_0.end_dist +system.cpu.iq.ISSUE:FU_type_1 7958 # Type of FU issued +system.cpu.iq.ISSUE:FU_type_1.start_dist + (null) 2 0.03% # Type of FU issued + IntAlu 5440 68.36% # Type of FU issued + IntMult 1 0.01% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 2 0.03% # Type of FU issued + FloatCmp 0 0.00% # Type of FU issued + FloatCvt 0 0.00% # Type of FU issued + FloatMult 0 0.00% # Type of FU issued + FloatDiv 0 0.00% # Type of FU issued + FloatSqrt 0 0.00% # Type of FU issued + MemRead 1553 19.51% # Type of FU issued + MemWrite 960 12.06% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type_1.end_dist +system.cpu.iq.ISSUE:FU_type 16098 # Type of FU issued +system.cpu.iq.ISSUE:FU_type.start_dist + (null) 4 0.02% # Type of FU issued + IntAlu 10996 68.31% # Type of FU issued + IntMult 2 0.01% # Type of FU issued + IntDiv 0 0.00% # Type of FU issued + FloatAdd 4 0.02% # Type of FU issued + FloatCmp 0 0.00% # Type of FU issued + FloatCvt 0 0.00% # Type of FU issued + FloatMult 0 0.00% # Type of FU issued + FloatDiv 0 0.00% # Type of FU issued + FloatSqrt 0 0.00% # Type of FU issued + MemRead 3172 19.70% # Type of FU issued + MemWrite 1920 11.93% # Type of FU issued + IprAccess 0 0.00% # Type of FU issued + InstPrefetch 0 0.00% # Type of FU issued +system.cpu.iq.ISSUE:FU_type.end_dist +system.cpu.iq.ISSUE:fu_busy_cnt 198 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_0 101 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_cnt_1 97 # FU busy when requested +system.cpu.iq.ISSUE:fu_busy_rate 0.012300 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_0 0.006274 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_busy_rate_1 0.006026 # FU busy rate (busy events/executed inst) +system.cpu.iq.ISSUE:fu_full.start_dist + (null) 0 0.00% # attempts to use FU when none available + IntAlu 9 4.55% # attempts to use FU when none available + IntMult 0 0.00% # attempts to use FU when none available + IntDiv 0 0.00% # attempts to use FU when none available + FloatAdd 0 0.00% # attempts to use FU when none available + FloatCmp 0 0.00% # attempts to use FU when none available + FloatCvt 0 0.00% # attempts to use FU when none available + FloatMult 0 0.00% # attempts to use FU when none available + FloatDiv 0 0.00% # attempts to use FU when none available + FloatSqrt 0 0.00% # attempts to use FU when none available + MemRead 114 57.58% # attempts to use FU when none available + MemWrite 75 37.88% # attempts to use FU when none available + IprAccess 0 0.00% # attempts to use FU when none available + InstPrefetch 0 0.00% # attempts to use FU when none available +system.cpu.iq.ISSUE:fu_full.end_dist +system.cpu.iq.ISSUE:issued_per_cycle.start_dist # Number of insts issued each cycle +system.cpu.iq.ISSUE:issued_per_cycle.samples 7479 +system.cpu.iq.ISSUE:issued_per_cycle.min_value 0 + 0 2160 2888.09% + 1 1088 1454.74% + 2 1332 1780.99% + 3 1011 1351.78% + 4 818 1093.73% + 5 568 759.46% + 6 358 478.67% + 7 99 132.37% + 8 45 60.17% +system.cpu.iq.ISSUE:issued_per_cycle.max_value 8 +system.cpu.iq.ISSUE:issued_per_cycle.end_dist + +system.cpu.iq.ISSUE:rate 2.152427 # Inst issue rate +system.cpu.iq.iqInstsAdded 18137 # Number of instructions added to the IQ (excludes non-spec) +system.cpu.iq.iqInstsIssued 16098 # Number of instructions issued +system.cpu.iq.iqNonSpecInstsAdded 39 # Number of non-speculative instructions added to the IQ +system.cpu.iq.iqSquashedInstsExamined 5869 # Number of squashed instructions iterated over during squash; mainly for profiling +system.cpu.iq.iqSquashedInstsIssued 22 # Number of squashed instructions issued +system.cpu.iq.iqSquashedNonSpecRemoved 5 # Number of squashed non-spec instructions that were removed +system.cpu.iq.iqSquashedOperandsExamined 3337 # Number of squashed operands that are examined and possibly removed from graph +system.cpu.numCycles 7479 # number of cpu cycles simulated +system.cpu.rename.RENAME:BlockCycles 350 # Number of cycles rename is blocking +system.cpu.rename.RENAME:CommittedMaps 8222 # Number of HB maps that are committed +system.cpu.rename.RENAME:IdleCycles 8416 # Number of cycles rename is idle +system.cpu.rename.RENAME:LSQFullEvents 695 # Number of times rename has blocked due to LSQ full +system.cpu.rename.RENAME:RenameLookups 26609 # Number of register rename lookups that rename has made +system.cpu.rename.RENAME:RenamedInsts 20867 # Number of instructions processed by rename +system.cpu.rename.RENAME:RenamedOperands 15602 # Number of destination operands rename has renamed +system.cpu.rename.RENAME:RunCycles 3486 # Number of cycles rename is running +system.cpu.rename.RENAME:SquashCycles 1260 # Number of cycles rename is squashing +system.cpu.rename.RENAME:UnblockCycles 771 # Number of cycles rename is unblocking +system.cpu.rename.RENAME:UndoneMaps 7380 # Number of HB maps that are undone due to squashing +system.cpu.rename.RENAME:serializeStallCycles 500 # count of cycles rename stalled for serializing inst +system.cpu.rename.RENAME:serializingInsts 49 # count of serializing insts renamed +system.cpu.rename.RENAME:skidInsts 2217 # count of insts added to the skid buffer +system.cpu.rename.RENAME:tempSerializingInsts 38 # count of temporary serializing insts renamed +system.cpu.workload0.PROG:num_syscalls 17 # Number of system calls +system.cpu.workload1.PROG:num_syscalls 17 # Number of system calls + +---------- End Simulation Statistics ---------- -- cgit v1.2.3