From 752033140228c790e51954bd8ccd3728f4dd7e08 Mon Sep 17 00:00:00 2001 From: Jason Lowe-Power Date: Wed, 30 Nov 2016 17:12:59 -0500 Subject: tests: Regression stats updated for recent patches --- .../00.hello/ref/power/linux/o3-timing/config.ini | 84 +++++++++++++++++----- .../se/00.hello/ref/power/linux/o3-timing/simout | 8 +-- .../00.hello/ref/power/linux/o3-timing/stats.txt | 64 ++++++++--------- 3 files changed, 102 insertions(+), 54 deletions(-) (limited to 'tests/quick/se/00.hello/ref/power/linux') diff --git a/tests/quick/se/00.hello/ref/power/linux/o3-timing/config.ini b/tests/quick/se/00.hello/ref/power/linux/o3-timing/config.ini index 08a1c6669..70198a6d7 100644 --- a/tests/quick/se/00.hello/ref/power/linux/o3-timing/config.ini +++ b/tests/quick/se/00.hello/ref/power/linux/o3-timing/config.ini @@ -178,10 +178,10 @@ addr_ranges=0:18446744073709551615:0:0:0:0 assoc=2 clk_domain=system.cpu_clk_domain clusivity=mostly_incl +data_latency=2 default_p_state=UNDEFINED demand_mshr_reserve=1 eventq_index=0 -hit_latency=2 is_read_only=false max_miss_count=0 mshrs=4 @@ -195,6 +195,7 @@ response_latency=2 sequential_access=false size=262144 system=system +tag_latency=2 tags=system.cpu.dcache.tags tgts_per_mshr=20 write_buffers=8 @@ -207,15 +208,16 @@ type=LRU assoc=2 block_size=64 clk_domain=system.cpu_clk_domain +data_latency=2 default_p_state=UNDEFINED eventq_index=0 -hit_latency=2 p_state_clk_gate_bins=20 p_state_clk_gate_max=1000000000000 p_state_clk_gate_min=1000 power_model=Null sequential_access=false size=262144 +tag_latency=2 [system.cpu.dtb] type=PowerTLB @@ -293,10 +295,10 @@ pipelined=true [system.cpu.fuPool.FUList3] type=FUDesc -children=opList0 opList1 opList2 +children=opList0 opList1 opList2 opList3 opList4 count=2 eventq_index=0 -opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 +opList=system.cpu.fuPool.FUList3.opList0 system.cpu.fuPool.FUList3.opList1 system.cpu.fuPool.FUList3.opList2 system.cpu.fuPool.FUList3.opList3 system.cpu.fuPool.FUList3.opList4 [system.cpu.fuPool.FUList3.opList0] type=OpDesc @@ -308,11 +310,25 @@ pipelined=true [system.cpu.fuPool.FUList3.opList1] type=OpDesc eventq_index=0 +opClass=FloatMultAcc +opLat=5 +pipelined=true + +[system.cpu.fuPool.FUList3.opList2] +type=OpDesc +eventq_index=0 +opClass=FloatMisc +opLat=3 +pipelined=true + +[system.cpu.fuPool.FUList3.opList3] +type=OpDesc +eventq_index=0 opClass=FloatDiv opLat=12 pipelined=false -[system.cpu.fuPool.FUList3.opList2] +[system.cpu.fuPool.FUList3.opList4] type=OpDesc eventq_index=0 opClass=FloatSqrt @@ -321,18 +337,25 @@ pipelined=false [system.cpu.fuPool.FUList4] type=FUDesc -children=opList +children=opList0 opList1 count=0 eventq_index=0 -opList=system.cpu.fuPool.FUList4.opList +opList=system.cpu.fuPool.FUList4.opList0 system.cpu.fuPool.FUList4.opList1 -[system.cpu.fuPool.FUList4.opList] +[system.cpu.fuPool.FUList4.opList0] type=OpDesc eventq_index=0 opClass=MemRead opLat=1 pipelined=true +[system.cpu.fuPool.FUList4.opList1] +type=OpDesc +eventq_index=0 +opClass=FloatMemRead +opLat=1 +pipelined=true + [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 @@ -482,24 +505,31 @@ pipelined=true [system.cpu.fuPool.FUList6] type=FUDesc -children=opList +children=opList0 opList1 count=0 eventq_index=0 -opList=system.cpu.fuPool.FUList6.opList +opList=system.cpu.fuPool.FUList6.opList0 system.cpu.fuPool.FUList6.opList1 -[system.cpu.fuPool.FUList6.opList] +[system.cpu.fuPool.FUList6.opList0] type=OpDesc eventq_index=0 opClass=MemWrite opLat=1 pipelined=true +[system.cpu.fuPool.FUList6.opList1] +type=OpDesc +eventq_index=0 +opClass=FloatMemWrite +opLat=1 +pipelined=true + [system.cpu.fuPool.FUList7] type=FUDesc -children=opList0 opList1 +children=opList0 opList1 opList2 opList3 count=4 eventq_index=0 -opList=system.cpu.fuPool.FUList7.opList0 system.cpu.fuPool.FUList7.opList1 +opList=system.cpu.fuPool.FUList7.opList0 system.cpu.fuPool.FUList7.opList1 system.cpu.fuPool.FUList7.opList2 system.cpu.fuPool.FUList7.opList3 [system.cpu.fuPool.FUList7.opList0] type=OpDesc @@ -515,6 +545,20 @@ opClass=MemWrite opLat=1 pipelined=true +[system.cpu.fuPool.FUList7.opList2] +type=OpDesc +eventq_index=0 +opClass=FloatMemRead +opLat=1 +pipelined=true + +[system.cpu.fuPool.FUList7.opList3] +type=OpDesc +eventq_index=0 +opClass=FloatMemWrite +opLat=1 +pipelined=true + [system.cpu.fuPool.FUList8] type=FUDesc children=opList @@ -536,10 +580,10 @@ addr_ranges=0:18446744073709551615:0:0:0:0 assoc=2 clk_domain=system.cpu_clk_domain clusivity=mostly_incl +data_latency=2 default_p_state=UNDEFINED demand_mshr_reserve=1 eventq_index=0 -hit_latency=2 is_read_only=true max_miss_count=0 mshrs=4 @@ -553,6 +597,7 @@ response_latency=2 sequential_access=false size=131072 system=system +tag_latency=2 tags=system.cpu.icache.tags tgts_per_mshr=20 write_buffers=8 @@ -565,15 +610,16 @@ type=LRU assoc=2 block_size=64 clk_domain=system.cpu_clk_domain +data_latency=2 default_p_state=UNDEFINED eventq_index=0 -hit_latency=2 p_state_clk_gate_bins=20 p_state_clk_gate_max=1000000000000 p_state_clk_gate_min=1000 power_model=Null sequential_access=false size=131072 +tag_latency=2 [system.cpu.interrupts] type=PowerInterrupts @@ -595,10 +641,10 @@ addr_ranges=0:18446744073709551615:0:0:0:0 assoc=8 clk_domain=system.cpu_clk_domain clusivity=mostly_incl +data_latency=20 default_p_state=UNDEFINED demand_mshr_reserve=1 eventq_index=0 -hit_latency=20 is_read_only=false max_miss_count=0 mshrs=20 @@ -612,6 +658,7 @@ response_latency=20 sequential_access=false size=2097152 system=system +tag_latency=20 tags=system.cpu.l2cache.tags tgts_per_mshr=12 write_buffers=8 @@ -624,15 +671,16 @@ type=LRU assoc=8 block_size=64 clk_domain=system.cpu_clk_domain +data_latency=20 default_p_state=UNDEFINED eventq_index=0 -hit_latency=20 p_state_clk_gate_bins=20 p_state_clk_gate_max=1000000000000 p_state_clk_gate_min=1000 power_model=Null sequential_access=false size=2097152 +tag_latency=20 [system.cpu.toL2Bus] type=CoherentXBar @@ -677,7 +725,7 @@ env= errout=cerr euid=100 eventq_index=0 -executable=/arm/projectscratch/randd/systems/dist/test-progs/hello/bin/power/linux/hello +executable=/dist/m5/regression/test-progs/hello/bin/power/linux/hello gid=100 input=cin kvmInSE=false diff --git a/tests/quick/se/00.hello/ref/power/linux/o3-timing/simout b/tests/quick/se/00.hello/ref/power/linux/o3-timing/simout index 7df757697..5b262649f 100755 --- a/tests/quick/se/00.hello/ref/power/linux/o3-timing/simout +++ b/tests/quick/se/00.hello/ref/power/linux/o3-timing/simout @@ -3,10 +3,10 @@ Redirecting stderr to build/POWER/tests/opt/quick/se/00.hello/power/linux/o3-tim gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Oct 13 2016 20:40:28 -gem5 started Oct 13 2016 20:40:51 -gem5 executing on e108600-lin, pid 9917 -command line: /work/curdun01/gem5-external.hg/build/POWER/gem5.opt -d build/POWER/tests/opt/quick/se/00.hello/power/linux/o3-timing -re /work/curdun01/gem5-external.hg/tests/testing/../run.py quick/se/00.hello/power/linux/o3-timing +gem5 compiled Nov 29 2016 18:37:43 +gem5 started Nov 29 2016 18:37:59 +gem5 executing on zizzer, pid 53433 +command line: /z/powerjg/gem5-upstream/build/POWER/gem5.opt -d build/POWER/tests/opt/quick/se/00.hello/power/linux/o3-timing -re /z/powerjg/gem5-upstream/tests/testing/../run.py quick/se/00.hello/power/linux/o3-timing Global frequency set at 1000000000000 ticks per second info: Entering event queue @ 0. Starting simulation... diff --git a/tests/quick/se/00.hello/ref/power/linux/o3-timing/stats.txt b/tests/quick/se/00.hello/ref/power/linux/o3-timing/stats.txt index fbc31e89b..1c774fd71 100644 --- a/tests/quick/se/00.hello/ref/power/linux/o3-timing/stats.txt +++ b/tests/quick/se/00.hello/ref/power/linux/o3-timing/stats.txt @@ -4,11 +4,11 @@ sim_seconds 0.000021 # Nu sim_ticks 21268000 # Number of ticks simulated final_tick 21268000 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 133148 # Simulator instruction rate (inst/s) -host_op_rate 133114 # Simulator op (including micro ops) rate (op/s) -host_tick_rate 488684971 # Simulator tick rate (ticks/s) -host_mem_usage 249832 # Number of bytes of host memory used -host_seconds 0.04 # Real time elapsed on the host +host_inst_rate 49400 # Simulator instruction rate (inst/s) +host_op_rate 49392 # Simulator op (including micro ops) rate (op/s) +host_tick_rate 181337178 # Simulator tick rate (ticks/s) +host_mem_usage 231948 # Number of bytes of host memory used +host_seconds 0.12 # Real time elapsed on the host sim_insts 5792 # Number of instructions simulated sim_ops 5792 # Number of ops (including micro ops) simulated system.voltage_domain.voltage 1 # Voltage in Volts @@ -299,7 +299,7 @@ system.cpu.pwrStateResidencyTicks::ON 21268000 # Cu system.cpu.numCycles 42537 # number of cpu cycles simulated system.cpu.numWorkItemsStarted 0 # number of work items this cpu started system.cpu.numWorkItemsCompleted 0 # number of work items this cpu completed -system.cpu.fetch.icacheStallCycles 7672 # Number of cycles fetch is stalled on an Icache miss +system.cpu.fetch.icacheStallCycles 7674 # Number of cycles fetch is stalled on an Icache miss system.cpu.fetch.Insts 13369 # Number of instructions fetch has processed system.cpu.fetch.Branches 2411 # Number of branches that fetch encountered system.cpu.fetch.predictedBranches 939 # Number of branches that fetch has predicted taken @@ -310,26 +310,26 @@ system.cpu.fetch.PendingTrapStallCycles 146 # Nu system.cpu.fetch.IcacheWaitRetryStallCycles 22 # Number of stall cycles due to full MSHR system.cpu.fetch.CacheLines 1861 # Number of cache lines fetched system.cpu.fetch.IcacheSquashes 290 # Number of outstanding Icache misses that were squashed -system.cpu.fetch.rateDist::samples 12418 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::mean 1.076582 # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::stdev 2.475981 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::samples 12420 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::mean 1.076409 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::stdev 2.475819 # 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 10084 81.20% 81.20% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::0 10086 81.21% 81.21% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::1 166 1.34% 82.54% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::2 214 1.72% 84.26% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::2 214 1.72% 84.27% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::3 147 1.18% 85.45% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::4 241 1.94% 87.39% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::5 150 1.21% 88.60% # Number of instructions fetched each cycle (Total) system.cpu.fetch.rateDist::6 280 2.25% 90.85% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::7 148 1.19% 92.04% # Number of instructions fetched each cycle (Total) -system.cpu.fetch.rateDist::8 988 7.96% 100.00% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::7 148 1.19% 92.05% # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::8 988 7.95% 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 12418 # Number of instructions fetched each cycle (Total) +system.cpu.fetch.rateDist::total 12420 # Number of instructions fetched each cycle (Total) system.cpu.fetch.branchRate 0.056680 # Number of branch fetches per cycle system.cpu.fetch.rate 0.314291 # Number of inst fetches per cycle -system.cpu.decode.IdleCycles 7245 # Number of cycles decode is idle +system.cpu.decode.IdleCycles 7247 # Number of cycles decode is idle system.cpu.decode.BlockedCycles 2821 # Number of cycles decode is blocked system.cpu.decode.RunCycles 1946 # Number of cycles decode is running system.cpu.decode.UnblockCycles 130 # Number of cycles decode is unblocking @@ -339,7 +339,7 @@ system.cpu.decode.BranchMispred 149 # Nu system.cpu.decode.DecodedInsts 11479 # Number of instructions handled by decode system.cpu.decode.SquashedInsts 451 # Number of squashed instructions handled by decode system.cpu.rename.SquashCycles 276 # Number of cycles rename is squashing -system.cpu.rename.IdleCycles 7413 # Number of cycles rename is idle +system.cpu.rename.IdleCycles 7415 # Number of cycles rename is idle system.cpu.rename.BlockCycles 800 # Number of cycles rename is blocking system.cpu.rename.serializeStallCycles 463 # count of cycles rename stalled for serializing inst system.cpu.rename.RunCycles 1897 # Number of cycles rename is running @@ -368,11 +368,11 @@ system.cpu.iq.iqSquashedInstsIssued 53 # Nu system.cpu.iq.iqSquashedInstsExamined 4442 # Number of squashed instructions iterated over during squash; mainly for profiling system.cpu.iq.iqSquashedOperandsExamined 3474 # Number of squashed operands that are examined and possibly removed from graph system.cpu.iq.iqSquashedNonSpecRemoved 47 # Number of squashed non-spec instructions that were removed -system.cpu.iq.issued_per_cycle::samples 12418 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::mean 0.709293 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::stdev 1.511827 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::samples 12420 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::mean 0.709179 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::stdev 1.511732 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::underflows 0 0.00% 0.00% # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::0 9303 74.92% 74.92% # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::0 9305 74.92% 74.92% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::1 969 7.80% 82.72% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::2 656 5.28% 88.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::3 462 3.72% 91.72% # Number of insts issued each cycle @@ -384,7 +384,7 @@ system.cpu.iq.issued_per_cycle::8 30 0.24% 100.00% # Nu system.cpu.iq.issued_per_cycle::overflows 0 0.00% 100.00% # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::min_value 0 # Number of insts issued each cycle system.cpu.iq.issued_per_cycle::max_value 8 # Number of insts issued each cycle -system.cpu.iq.issued_per_cycle::total 12418 # Number of insts issued each cycle +system.cpu.iq.issued_per_cycle::total 12420 # Number of insts issued each cycle system.cpu.iq.fu_full::No_OpClass 0 0.00% 0.00% # attempts to use FU when none available system.cpu.iq.fu_full::IntAlu 12 6.06% 6.06% # attempts to use FU when none available system.cpu.iq.fu_full::IntMult 0 0.00% 6.06% # attempts to use FU when none available @@ -465,7 +465,7 @@ system.cpu.iq.FU_type_0::total 8808 # Ty system.cpu.iq.rate 0.207067 # Inst issue rate system.cpu.iq.fu_busy_cnt 198 # FU busy when requested system.cpu.iq.fu_busy_rate 0.022480 # FU busy rate (busy events/executed inst) -system.cpu.iq.int_inst_queue_reads 30218 # Number of integer instruction queue reads +system.cpu.iq.int_inst_queue_reads 30220 # Number of integer instruction queue reads system.cpu.iq.int_inst_queue_writes 14647 # Number of integer instruction queue writes system.cpu.iq.int_inst_queue_wakeup_accesses 8115 # Number of integer instruction queue wakeup accesses system.cpu.iq.fp_inst_queue_reads 67 # Number of floating instruction queue reads @@ -516,14 +516,14 @@ system.cpu.iew.wb_fanout 0.621403 # av system.cpu.commit.commitSquashedInsts 4444 # The number of squashed insts skipped by commit system.cpu.commit.commitNonSpecStalls 16 # The number of times commit has been forced to stall to communicate backwards system.cpu.commit.branchMispredicts 270 # The number of times a branch was mispredicted -system.cpu.commit.committed_per_cycle::samples 11716 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::mean 0.494367 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::stdev 1.358573 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::samples 11718 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::mean 0.494282 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::stdev 1.358473 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::underflows 0 0.00% 0.00% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::0 9551 81.52% 81.52% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::1 850 7.26% 88.78% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::2 527 4.50% 93.27% # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::3 215 1.84% 95.11% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::0 9553 81.52% 81.52% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::1 850 7.25% 88.78% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::2 527 4.50% 93.28% # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::3 215 1.83% 95.11% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::4 176 1.50% 96.61% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::5 112 0.96% 97.57% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::6 126 1.08% 98.64% # Number of insts commited each cycle @@ -532,7 +532,7 @@ system.cpu.commit.committed_per_cycle::8 110 0.94% 100.00% # Nu system.cpu.commit.committed_per_cycle::overflows 0 0.00% 100.00% # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::min_value 0 # Number of insts commited each cycle system.cpu.commit.committed_per_cycle::max_value 8 # Number of insts commited each cycle -system.cpu.commit.committed_per_cycle::total 11716 # Number of insts commited each cycle +system.cpu.commit.committed_per_cycle::total 11718 # Number of insts commited each cycle system.cpu.commit.committedInsts 5792 # Number of instructions committed system.cpu.commit.committedOps 5792 # Number of ops (including micro ops) committed system.cpu.commit.swp_count 0 # Number of s/w prefetches committed @@ -583,10 +583,10 @@ system.cpu.commit.op_class_0::IprAccess 0 0.00% 100.00% # Cl system.cpu.commit.op_class_0::InstPrefetch 0 0.00% 100.00% # Class of committed instruction system.cpu.commit.op_class_0::total 5792 # Class of committed instruction system.cpu.commit.bw_lim_events 110 # number cycles where commit BW limit reached -system.cpu.rob.rob_reads 21842 # The number of ROB reads +system.cpu.rob.rob_reads 21844 # The number of ROB reads system.cpu.rob.rob_writes 21175 # The number of ROB writes system.cpu.timesIdled 228 # Number of times that the entire CPU went into an idle state and unscheduled itself -system.cpu.idleCycles 30119 # Total number of cycles that the CPU has spent unscheduled due to idling +system.cpu.idleCycles 30117 # Total number of cycles that the CPU has spent unscheduled due to idling system.cpu.committedInsts 5792 # Number of Instructions Simulated system.cpu.committedOps 5792 # Number of Ops (including micro ops) Simulated system.cpu.cpi 7.344095 # CPI: Cycles Per Instruction -- cgit v1.2.3