From 807e2705b4abeefaabdc1cb3e0dfdc1acdccdc30 Mon Sep 17 00:00:00 2001 From: Steve Reinhardt Date: Thu, 18 Feb 2016 10:42:03 -0500 Subject: [PATCH] stats: update gpu-ruby-GPU_RfO stats Output changed way back in this cset: changeset: 11345:b6a66a90e0a1 user: John Kalamatianos summary: gpu: fix bugs with MemFence, Flat Instrs and Resource utilization --- .../ref/x86/linux/gpu-ruby-GPU_RfO/config.ini | 4 +- .../ref/x86/linux/gpu-ruby-GPU_RfO/simout | 10 +- .../ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt | 458 +++++++++--------- 3 files changed, 235 insertions(+), 237 deletions(-) diff --git a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/config.ini b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/config.ini index 5486af826..19a9a115f 100644 --- a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/config.ini +++ b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/config.ini @@ -378,7 +378,7 @@ env= errout=cerr euid=100 eventq_index=0 -executable=/dist/m5/regression/test-progs/gpu-hello/bin/x86/linux/gpu-hello +executable=/home/stever/hg/m5sim.org/gem5/tests/test-progs/gpu-hello/bin/x86/linux/gpu-hello gid=100 input=cin kvmInSE=false @@ -998,7 +998,7 @@ translation_port=system.dispatcher_coalescer.slave[0] [system.cpu2.cl_driver] type=ClDriver -codefile=/dist/m5/regression/test-progs/gpu-hello/bin/x86/linux/gpu-hello-kernel.asm +codefile=/home/stever/hg/m5sim.org/gem5/tests/test-progs/gpu-hello/bin/x86/linux/gpu-hello-kernel.asm eventq_index=0 filename=hsa diff --git a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simout b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simout index 25f60d14c..62281f3ae 100755 --- a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simout +++ b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/simout @@ -1,12 +1,12 @@ gem5 Simulator System. http://gem5.org gem5 is copyrighted software; use the --copyright option for details. -gem5 compiled Jan 21 2016 14:58:44 -gem5 started Jan 21 2016 14:59:07 -gem5 executing on zizzer, pid 26194 -command line: build/HSAIL_X86/gem5.opt -d build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO -re /z/atgutier/gem5/gem5-commit/tests/run.py build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO +gem5 compiled Mar 10 2016 12:22:56 +gem5 started Mar 10 2016 12:23:20 +gem5 executing on phenom, pid 9635 +command line: build/HSAIL_X86/gem5.opt -d build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO -re /home/stever/hg/m5sim.org/gem5/tests/run.py build/HSAIL_X86/tests/opt/quick/se/04.gpu/x86/linux/gpu-ruby-GPU_RfO -Using GPU kernel code file(s) /dist/m5/regression/test-progs/gpu-hello/bin/x86/linux/gpu-hello-kernel.asm +Using GPU kernel code file(s) /home/stever/hg/m5sim.org/gem5/tests/test-progs/gpu-hello/bin/x86/linux/gpu-hello-kernel.asm Global frequency set at 1000000000000 ticks per second Forcing maxCoalescedReqs to 32 (TLB assoc.) Forcing maxCoalescedReqs to 32 (TLB assoc.) diff --git a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt index 9d77c7b26..092f1ac37 100644 --- a/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt +++ b/tests/quick/se/04.gpu/ref/x86/linux/gpu-ruby-GPU_RfO/stats.txt @@ -4,11 +4,11 @@ sim_seconds 0.000663 # Nu sim_ticks 663454500 # Number of ticks simulated final_tick 663454500 # Number of ticks from beginning of simulation (restored from checkpoints and never reset) sim_freq 1000000000000 # Frequency of simulated ticks -host_inst_rate 74039 # Simulator instruction rate (inst/s) -host_op_rate 152254 # Simulator op (including micro ops) rate (op/s) -host_tick_rate 733530611 # Simulator tick rate (ticks/s) -host_mem_usage 1301780 # Number of bytes of host memory used -host_seconds 0.90 # Real time elapsed on the host +host_inst_rate 97803 # Simulator instruction rate (inst/s) +host_op_rate 201121 # Simulator op (including micro ops) rate (op/s) +host_tick_rate 968968514 # Simulator tick rate (ticks/s) +host_mem_usage 1290208 # Number of bytes of host memory used +host_seconds 0.68 # Real time elapsed on the host sim_insts 66963 # Number of instructions simulated sim_ops 137705 # Number of ops (including micro ops) simulated system.voltage_domain.voltage 1 # Voltage in Volts @@ -87,8 +87,8 @@ system.mem_ctrls.rdQLenPdf::1 2 # Wh system.mem_ctrls.rdQLenPdf::2 1 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::3 1 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::4 2 # What read queue length does an incoming req see -system.mem_ctrls.rdQLenPdf::5 3 # What read queue length does an incoming req see -system.mem_ctrls.rdQLenPdf::6 0 # What read queue length does an incoming req see +system.mem_ctrls.rdQLenPdf::5 2 # What read queue length does an incoming req see +system.mem_ctrls.rdQLenPdf::6 1 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::7 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::8 0 # What read queue length does an incoming req see system.mem_ctrls.rdQLenPdf::9 0 # What read queue length does an incoming req see @@ -192,8 +192,8 @@ system.mem_ctrls.bytesPerActivate::768-895 9 1.86% 98.56% # system.mem_ctrls.bytesPerActivate::896-1023 2 0.41% 98.97% # Bytes accessed per row activation system.mem_ctrls.bytesPerActivate::1024-1151 5 1.03% 100.00% # Bytes accessed per row activation system.mem_ctrls.bytesPerActivate::total 485 # Bytes accessed per row activation -system.mem_ctrls.totQLat 15500500 # Total ticks spent queuing -system.mem_ctrls.totMemAccLat 44581750 # Total ticks spent from burst creation until serviced by the DRAM +system.mem_ctrls.totQLat 15500495 # Total ticks spent queuing +system.mem_ctrls.totMemAccLat 44581745 # Total ticks spent from burst creation until serviced by the DRAM system.mem_ctrls.totBusLat 7755000 # Total ticks spent in databus transfers system.mem_ctrls.avgQLat 9993.87 # Average queueing delay per DRAM burst system.mem_ctrls.avgBusLat 5000.00 # Average bus latency per DRAM burst @@ -293,34 +293,34 @@ system.ruby.outstanding_req_hist_seqr | 0 0.00% 0.00% | system.ruby.outstanding_req_hist_seqr::total 114203 system.ruby.outstanding_req_hist_coalsr::bucket_size 1 system.ruby.outstanding_req_hist_coalsr::max_bucket 9 -system.ruby.outstanding_req_hist_coalsr::samples 28 -system.ruby.outstanding_req_hist_coalsr::mean 1.642857 -system.ruby.outstanding_req_hist_coalsr::gmean 1.455771 -system.ruby.outstanding_req_hist_coalsr::stdev 0.911421 -system.ruby.outstanding_req_hist_coalsr | 0 0.00% 0.00% | 16 57.14% 57.14% | 8 28.57% 85.71% | 2 7.14% 92.86% | 2 7.14% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.outstanding_req_hist_coalsr::total 28 +system.ruby.outstanding_req_hist_coalsr::samples 27 +system.ruby.outstanding_req_hist_coalsr::mean 1.629630 +system.ruby.outstanding_req_hist_coalsr::gmean 1.438746 +system.ruby.outstanding_req_hist_coalsr::stdev 0.926040 +system.ruby.outstanding_req_hist_coalsr | 0 0.00% 0.00% | 16 59.26% 59.26% | 7 25.93% 85.19% | 2 7.41% 92.59% | 2 7.41% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.outstanding_req_hist_coalsr::total 27 system.ruby.latency_hist_seqr::bucket_size 64 system.ruby.latency_hist_seqr::max_bucket 639 system.ruby.latency_hist_seqr::samples 114203 -system.ruby.latency_hist_seqr::mean 4.784183 +system.ruby.latency_hist_seqr::mean 4.784165 system.ruby.latency_hist_seqr::gmean 2.131364 -system.ruby.latency_hist_seqr::stdev 23.846744 +system.ruby.latency_hist_seqr::stdev 23.846473 system.ruby.latency_hist_seqr | 112668 98.66% 98.66% | 0 0.00% 98.66% | 0 0.00% 98.66% | 1506 1.32% 99.97% | 19 0.02% 99.99% | 10 0.01% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.latency_hist_seqr::total 114203 system.ruby.latency_hist_coalsr::bucket_size 64 system.ruby.latency_hist_coalsr::max_bucket 639 -system.ruby.latency_hist_coalsr::samples 28 -system.ruby.latency_hist_coalsr::mean 136.285714 -system.ruby.latency_hist_coalsr::gmean 19.975449 -system.ruby.latency_hist_coalsr::stdev 139.699905 -system.ruby.latency_hist_coalsr | 14 50.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 10 35.71% 85.71% | 1 3.57% 89.29% | 3 10.71% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.latency_hist_coalsr::total 28 +system.ruby.latency_hist_coalsr::samples 27 +system.ruby.latency_hist_coalsr::mean 141.296296 +system.ruby.latency_hist_coalsr::gmean 21.202698 +system.ruby.latency_hist_coalsr::stdev 140.217089 +system.ruby.latency_hist_coalsr | 13 48.15% 48.15% | 0 0.00% 48.15% | 0 0.00% 48.15% | 10 37.04% 85.19% | 1 3.70% 88.89% | 3 11.11% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.latency_hist_coalsr::total 27 system.ruby.hit_latency_hist_seqr::bucket_size 64 system.ruby.hit_latency_hist_seqr::max_bucket 639 system.ruby.hit_latency_hist_seqr::samples 1535 -system.ruby.hit_latency_hist_seqr::mean 208.449511 -system.ruby.hit_latency_hist_seqr::gmean 208.002927 -system.ruby.hit_latency_hist_seqr::stdev 15.847049 +system.ruby.hit_latency_hist_seqr::mean 208.448208 +system.ruby.hit_latency_hist_seqr::gmean 208.002202 +system.ruby.hit_latency_hist_seqr::stdev 15.833423 system.ruby.hit_latency_hist_seqr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 1506 98.11% 98.11% | 19 1.24% 99.35% | 10 0.65% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.hit_latency_hist_seqr::total 1535 system.ruby.miss_latency_hist_seqr::bucket_size 4 @@ -333,12 +333,12 @@ system.ruby.miss_latency_hist_seqr | 112609 99.95% 99.95% | system.ruby.miss_latency_hist_seqr::total 112668 system.ruby.miss_latency_hist_coalsr::bucket_size 64 system.ruby.miss_latency_hist_coalsr::max_bucket 639 -system.ruby.miss_latency_hist_coalsr::samples 28 -system.ruby.miss_latency_hist_coalsr::mean 136.285714 -system.ruby.miss_latency_hist_coalsr::gmean 19.975449 -system.ruby.miss_latency_hist_coalsr::stdev 139.699905 -system.ruby.miss_latency_hist_coalsr | 14 50.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 10 35.71% 85.71% | 1 3.57% 89.29% | 3 10.71% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.miss_latency_hist_coalsr::total 28 +system.ruby.miss_latency_hist_coalsr::samples 27 +system.ruby.miss_latency_hist_coalsr::mean 141.296296 +system.ruby.miss_latency_hist_coalsr::gmean 21.202698 +system.ruby.miss_latency_hist_coalsr::stdev 140.217089 +system.ruby.miss_latency_hist_coalsr | 13 48.15% 48.15% | 0 0.00% 48.15% | 0 0.00% 48.15% | 10 37.04% 85.19% | 1 3.70% 88.89% | 3 11.11% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.miss_latency_hist_coalsr::total 27 system.ruby.L1Cache.incomplete_times_seqr 112609 system.ruby.L2Cache.incomplete_times_seqr 59 system.cp_cntrl0.L1D0cache.demand_hits 0 # Number of cache demand hits @@ -388,10 +388,10 @@ system.cpu0.num_cc_register_writes 42183 # nu system.cpu0.num_mem_refs 27198 # number of memory refs system.cpu0.num_load_insts 16684 # Number of load instructions system.cpu0.num_store_insts 10514 # Number of store instructions -system.cpu0.num_idle_cycles 5227.003992 # Number of idle cycles -system.cpu0.num_busy_cycles 1321681.996008 # Number of busy cycles -system.cpu0.not_idle_fraction 0.996061 # Percentage of non-idle cycles -system.cpu0.idle_fraction 0.003939 # Percentage of idle cycles +system.cpu0.num_idle_cycles 5231.003992 # Number of idle cycles +system.cpu0.num_busy_cycles 1321677.996008 # Number of busy cycles +system.cpu0.not_idle_fraction 0.996058 # Percentage of non-idle cycles +system.cpu0.idle_fraction 0.003942 # Percentage of idle cycles system.cpu0.Branches 16199 # Number of branches fetched system.cpu0.op_class::No_OpClass 615 0.45% 0.45% # Class of executed instruction system.cpu0.op_class::IntAlu 108791 79.00% 79.45% # Class of executed instruction @@ -432,7 +432,7 @@ system.cpu1.clk_domain.voltage_domain.voltage 1 system.cpu1.clk_domain.clock 1000 # Clock period in ticks system.cpu1.CUs0.wavefronts00.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs0.wavefronts00.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs0.wavefronts00.timesBlockedDueRAWDependencies 297 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs0.wavefronts00.timesBlockedDueRAWDependencies 307 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::samples 39 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::mean 0.794872 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts00.src_reg_operand_dist::stdev 0.863880 # number of executed instructions with N source register operands @@ -624,7 +624,7 @@ system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::max_value 0 system.cpu1.CUs0.wavefronts07.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs0.wavefronts08.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs0.wavefronts08.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs0.wavefronts08.timesBlockedDueRAWDependencies 273 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs0.wavefronts08.timesBlockedDueRAWDependencies 279 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts08.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -816,7 +816,7 @@ system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::max_value 0 system.cpu1.CUs0.wavefronts15.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs0.wavefronts16.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs0.wavefronts16.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs0.wavefronts16.timesBlockedDueRAWDependencies 272 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs0.wavefronts16.timesBlockedDueRAWDependencies 282 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts16.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -1008,7 +1008,7 @@ system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::max_value 0 system.cpu1.CUs0.wavefronts23.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs0.wavefronts24.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs0.wavefronts24.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs0.wavefronts24.timesBlockedDueRAWDependencies 256 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs0.wavefronts24.timesBlockedDueRAWDependencies 276 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs0.wavefronts24.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -1238,65 +1238,65 @@ system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::overflows 0 system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::min_value 2 # For each instruction fetch request recieved record how many instructions you got from it system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::max_value 8 # For each instruction fetch request recieved record how many instructions you got from it system.cpu1.CUs0.FetchStage.inst_fetch_instr_returned::total 43 # For each instruction fetch request recieved record how many instructions you got from it -system.cpu1.CUs0.ExecStage.num_cycles_with_no_issue 3230 # number of cycles the CU issues nothing -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_issued 128 # number of cycles the CU issued at least one instruction +system.cpu1.CUs0.ExecStage.num_cycles_with_no_issue 3261 # number of cycles the CU issues nothing +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_issued 99 # number of cycles the CU issued at least one instruction system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU0 30 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU1 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU2 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::ALU3 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::GM 18 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs0.ExecStage.num_cycles_with_instrtype_issue::LM 6 # Number of cycles at least one instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU0 780 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU1 367 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU2 384 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU3 327 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::GM 414 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::LM 30 # Number of cycles no instruction of specific type issued -system.cpu1.CUs0.ExecStage.spc::samples 3358 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::mean 0.041989 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::stdev 0.220406 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU0 769 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU1 357 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU2 375 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::ALU3 332 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::GM 398 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.num_cycles_with_instr_type_no_issue::LM 22 # Number of cycles no instruction of specific type issued +system.cpu1.CUs0.ExecStage.spc::samples 3360 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::mean 0.041964 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::stdev 0.257708 # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::underflows 0 0.00% 0.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::0 3230 96.19% 96.19% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::1 116 3.45% 99.64% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::2 11 0.33% 99.97% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::3 1 0.03% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::0 3261 97.05% 97.05% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::1 59 1.76% 98.81% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::2 38 1.13% 99.94% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.spc::3 2 0.06% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::4 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::5 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::6 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::overflows 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::min_value 0 # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs0.ExecStage.spc::max_value 3 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.spc::total 3358 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs0.ExecStage.num_transitions_active_to_idle 82 # number of CU transitions from active to idle -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::samples 82 # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::mean 39.280488 # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::stdev 158.161058 # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.spc::total 3360 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs0.ExecStage.num_transitions_active_to_idle 93 # number of CU transitions from active to idle +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::samples 93 # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::mean 34.967742 # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::stdev 149.478110 # duration of idle periods in cycles system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::underflows 0 0.00% 0.00% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::0-4 62 75.61% 75.61% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::5-9 9 10.98% 86.59% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::10-14 1 1.22% 87.80% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::15-19 0 0.00% 87.80% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::20-24 2 2.44% 90.24% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::25-29 1 1.22% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::30-34 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::35-39 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::40-44 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::45-49 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::50-54 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::55-59 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::60-64 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::65-69 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::70-74 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::75 0 0.00% 91.46% # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::overflows 7 8.54% 100.00% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::0-4 74 79.57% 79.57% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::5-9 7 7.53% 87.10% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::10-14 1 1.08% 88.17% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::15-19 1 1.08% 89.25% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::20-24 2 2.15% 91.40% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::25-29 1 1.08% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::30-34 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::35-39 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::40-44 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::45-49 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::50-54 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::55-59 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::60-64 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::65-69 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::70-74 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::75 0 0.00% 92.47% # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::overflows 7 7.53% 100.00% # duration of idle periods in cycles system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::min_value 1 # duration of idle periods in cycles system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::max_value 1285 # duration of idle periods in cycles -system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::total 82 # duration of idle periods in cycles +system.cpu1.CUs0.ExecStage.idle_duration_in_cycles::total 93 # duration of idle periods in cycles system.cpu1.CUs0.GlobalMemPipeline.load_vrf_bank_conflict_cycles 0 # total number of cycles GM data are delayed before updating the VRF system.cpu1.CUs0.LocalMemPipeline.load_vrf_bank_conflict_cycles 0 # total number of cycles LDS data are delayed before updating the VRF system.cpu1.CUs0.tlb_requests 769 # number of uncoalesced requests -system.cpu1.CUs0.tlb_cycles -452460956000 # total number of cycles for all uncoalesced requests -system.cpu1.CUs0.avg_translation_latency -588375755.526658 # Avg. translation latency for data translations +system.cpu1.CUs0.tlb_cycles -452453001000 # total number of cycles for all uncoalesced requests +system.cpu1.CUs0.avg_translation_latency -588365410.923277 # Avg. translation latency for data translations system.cpu1.CUs0.TLB_hits_distribution::page_table 769 # TLB hits distribution (0 for page table, x for Lx-TLB system.cpu1.CUs0.TLB_hits_distribution::L1_TLB 0 # TLB hits distribution (0 for page table, x for Lx-TLB system.cpu1.CUs0.TLB_hits_distribution::L2_TLB 0 # TLB hits distribution (0 for page table, x for Lx-TLB @@ -1373,22 +1373,22 @@ system.cpu1.CUs0.wg_blocked_due_lds_alloc 0 # W system.cpu1.CUs0.num_instr_executed 141 # number of instructions executed system.cpu1.CUs0.inst_exec_rate::samples 141 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs0.inst_exec_rate::mean 86.382979 # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::stdev 229.391669 # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::stdev 229.706697 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs0.inst_exec_rate::underflows 0 0.00% 0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::0-1 1 0.71% 0.71% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::2-3 12 8.51% 9.22% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::4-5 51 36.17% 45.39% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::6-7 32 22.70% 68.09% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::8-9 2 1.42% 69.50% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::10 2 1.42% 70.92% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::overflows 41 29.08% 100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs0.inst_exec_rate::min_value 1 # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::0-1 0 0.00% 0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::2-3 12 8.51% 8.51% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::4-5 52 36.88% 45.39% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::6-7 31 21.99% 67.38% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::8-9 3 2.13% 69.50% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::10 3 2.13% 71.63% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::overflows 40 28.37% 100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs0.inst_exec_rate::min_value 2 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs0.inst_exec_rate::max_value 1291 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs0.inst_exec_rate::total 141 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs0.num_vec_ops_executed 6769 # number of vec ops executed (e.g. VSZ/inst) -system.cpu1.CUs0.num_total_cycles 3358 # number of cycles the CU ran for -system.cpu1.CUs0.vpc 2.015783 # Vector Operations per cycle (this CU only) -system.cpu1.CUs0.ipc 0.041989 # Instructions per cycle (this CU only) +system.cpu1.CUs0.num_total_cycles 3360 # number of cycles the CU ran for +system.cpu1.CUs0.vpc 2.014583 # Vector Operations per cycle (this CU only) +system.cpu1.CUs0.ipc 0.041964 # Instructions per cycle (this CU only) system.cpu1.CUs0.warp_execution_dist::samples 141 # number of lanes active per instruction (oval all instructions) system.cpu1.CUs0.warp_execution_dist::mean 48.007092 # number of lanes active per instruction (oval all instructions) system.cpu1.CUs0.warp_execution_dist::stdev 23.719942 # number of lanes active per instruction (oval all instructions) @@ -1468,7 +1468,7 @@ system.cpu1.CUs0.num_failed_CAS_ops 0 # nu system.cpu1.CUs0.num_completed_wfs 4 # number of completed wavefronts system.cpu1.CUs1.wavefronts00.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs1.wavefronts00.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs1.wavefronts00.timesBlockedDueRAWDependencies 381 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs1.wavefronts00.timesBlockedDueRAWDependencies 401 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::samples 39 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::mean 0.794872 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts00.src_reg_operand_dist::stdev 0.863880 # number of executed instructions with N source register operands @@ -1660,7 +1660,7 @@ system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::max_value 0 system.cpu1.CUs1.wavefronts07.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs1.wavefronts08.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs1.wavefronts08.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs1.wavefronts08.timesBlockedDueRAWDependencies 356 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs1.wavefronts08.timesBlockedDueRAWDependencies 372 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts08.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -1852,7 +1852,7 @@ system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::max_value 0 system.cpu1.CUs1.wavefronts15.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs1.wavefronts16.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs1.wavefronts16.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs1.wavefronts16.timesBlockedDueRAWDependencies 356 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs1.wavefronts16.timesBlockedDueRAWDependencies 371 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts16.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -2044,7 +2044,7 @@ system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::max_value 0 system.cpu1.CUs1.wavefronts23.dst_reg_operand_dist::total 0 # number of executed instructions with N destination register operands system.cpu1.CUs1.wavefronts24.timesBlockedDueVrfPortAvail 0 # number of times instructions are blocked due to VRF port availability system.cpu1.CUs1.wavefronts24.timesBlockedDueWAXDependencies 0 # number of times the wf's instructions are blocked due to WAW or WAR dependencies -system.cpu1.CUs1.wavefronts24.timesBlockedDueRAWDependencies 339 # number of times the wf's instructions are blocked due to RAW dependencies +system.cpu1.CUs1.wavefronts24.timesBlockedDueRAWDependencies 361 # number of times the wf's instructions are blocked due to RAW dependencies system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::samples 34 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::mean 0.852941 # number of executed instructions with N source register operands system.cpu1.CUs1.wavefronts24.src_reg_operand_dist::stdev 0.857493 # number of executed instructions with N source register operands @@ -2274,27 +2274,27 @@ system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::overflows 0 system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::min_value 2 # For each instruction fetch request recieved record how many instructions you got from it system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::max_value 8 # For each instruction fetch request recieved record how many instructions you got from it system.cpu1.CUs1.FetchStage.inst_fetch_instr_returned::total 43 # For each instruction fetch request recieved record how many instructions you got from it -system.cpu1.CUs1.ExecStage.num_cycles_with_no_issue 3228 # number of cycles the CU issues nothing -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_issued 130 # number of cycles the CU issued at least one instruction +system.cpu1.CUs1.ExecStage.num_cycles_with_no_issue 3261 # number of cycles the CU issues nothing +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_issued 99 # number of cycles the CU issued at least one instruction system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU0 30 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU1 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU2 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::ALU3 29 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::GM 18 # Number of cycles at least one instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instrtype_issue::LM 6 # Number of cycles at least one instruction of specific type issued -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU0 778 # Number of cycles no instruction of specific type issued +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU0 777 # Number of cycles no instruction of specific type issued system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU1 472 # Number of cycles no instruction of specific type issued -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU2 447 # Number of cycles no instruction of specific type issued -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU3 411 # Number of cycles no instruction of specific type issued -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::GM 417 # Number of cycles no instruction of specific type issued -system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::LM 26 # Number of cycles no instruction of specific type issued -system.cpu1.CUs1.ExecStage.spc::samples 3358 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::mean 0.041989 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::stdev 0.217686 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU2 444 # Number of cycles no instruction of specific type issued +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::ALU3 416 # Number of cycles no instruction of specific type issued +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::GM 404 # Number of cycles no instruction of specific type issued +system.cpu1.CUs1.ExecStage.num_cycles_with_instr_type_no_issue::LM 22 # Number of cycles no instruction of specific type issued +system.cpu1.CUs1.ExecStage.spc::samples 3360 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.spc::mean 0.041964 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.spc::stdev 0.256550 # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::underflows 0 0.00% 0.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::0 3228 96.13% 96.13% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::1 120 3.57% 99.70% # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::2 9 0.27% 99.97% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.spc::0 3261 97.05% 97.05% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.spc::1 58 1.73% 98.78% # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.spc::2 40 1.19% 99.97% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::3 1 0.03% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::4 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::5 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) @@ -2302,37 +2302,37 @@ system.cpu1.CUs1.ExecStage.spc::6 0 0.00% 100.00% # Ex system.cpu1.CUs1.ExecStage.spc::overflows 0 0.00% 100.00% # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::min_value 0 # Execution units active per cycle (Exec unit=SIMD,MemPipe) system.cpu1.CUs1.ExecStage.spc::max_value 3 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.spc::total 3358 # Execution units active per cycle (Exec unit=SIMD,MemPipe) -system.cpu1.CUs1.ExecStage.num_transitions_active_to_idle 81 # number of CU transitions from active to idle -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::samples 81 # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::mean 38.617284 # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::stdev 158.076213 # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.spc::total 3360 # Execution units active per cycle (Exec unit=SIMD,MemPipe) +system.cpu1.CUs1.ExecStage.num_transitions_active_to_idle 94 # number of CU transitions from active to idle +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::samples 94 # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::mean 33.585106 # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::stdev 147.747562 # duration of idle periods in cycles system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::underflows 0 0.00% 0.00% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::0-4 60 74.07% 74.07% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::5-9 10 12.35% 86.42% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::10-14 0 0.00% 86.42% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::15-19 2 2.47% 88.89% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::20-24 2 2.47% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::25-29 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::30-34 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::35-39 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::40-44 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::45-49 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::50-54 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::55-59 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::60-64 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::65-69 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::70-74 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::75 0 0.00% 91.36% # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::overflows 7 8.64% 100.00% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::0-4 75 79.79% 79.79% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::5-9 8 8.51% 88.30% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::10-14 0 0.00% 88.30% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::15-19 1 1.06% 89.36% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::20-24 2 2.13% 91.49% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::25-29 1 1.06% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::30-34 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::35-39 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::40-44 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::45-49 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::50-54 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::55-59 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::60-64 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::65-69 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::70-74 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::75 0 0.00% 92.55% # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::overflows 7 7.45% 100.00% # duration of idle periods in cycles system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::min_value 1 # duration of idle periods in cycles system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::max_value 1293 # duration of idle periods in cycles -system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::total 81 # duration of idle periods in cycles +system.cpu1.CUs1.ExecStage.idle_duration_in_cycles::total 94 # duration of idle periods in cycles system.cpu1.CUs1.GlobalMemPipeline.load_vrf_bank_conflict_cycles 0 # total number of cycles GM data are delayed before updating the VRF system.cpu1.CUs1.LocalMemPipeline.load_vrf_bank_conflict_cycles 0 # total number of cycles LDS data are delayed before updating the VRF system.cpu1.CUs1.tlb_requests 769 # number of uncoalesced requests -system.cpu1.CUs1.tlb_cycles -452466433000 # total number of cycles for all uncoalesced requests -system.cpu1.CUs1.avg_translation_latency -588382877.763329 # Avg. translation latency for data translations +system.cpu1.CUs1.tlb_cycles -452459838000 # total number of cycles for all uncoalesced requests +system.cpu1.CUs1.avg_translation_latency -588374301.690507 # Avg. translation latency for data translations system.cpu1.CUs1.TLB_hits_distribution::page_table 769 # TLB hits distribution (0 for page table, x for Lx-TLB system.cpu1.CUs1.TLB_hits_distribution::L1_TLB 0 # TLB hits distribution (0 for page table, x for Lx-TLB system.cpu1.CUs1.TLB_hits_distribution::L2_TLB 0 # TLB hits distribution (0 for page table, x for Lx-TLB @@ -2408,23 +2408,23 @@ system.cpu1.CUs1.local_mem_instr_cnt 6 # dy system.cpu1.CUs1.wg_blocked_due_lds_alloc 0 # Workgroup blocked due to LDS capacity system.cpu1.CUs1.num_instr_executed 141 # number of instructions executed system.cpu1.CUs1.inst_exec_rate::samples 141 # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::mean 85.666667 # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::stdev 230.212531 # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::mean 85.553191 # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::stdev 230.829913 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.inst_exec_rate::underflows 0 0.00% 0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::0-1 1 0.71% 0.71% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::2-3 12 8.51% 9.22% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::0-1 0 0.00% 0.00% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::2-3 13 9.22% 9.22% # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.inst_exec_rate::4-5 52 36.88% 46.10% # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.inst_exec_rate::6-7 33 23.40% 69.50% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::8-9 4 2.84% 72.34% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::10 1 0.71% 73.05% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::overflows 38 26.95% 100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle -system.cpu1.CUs1.inst_exec_rate::min_value 1 # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::8-9 6 4.26% 73.76% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::10 0 0.00% 73.76% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::overflows 37 26.24% 100.00% # Instruction Execution Rate: Number of executed vector instructions per cycle +system.cpu1.CUs1.inst_exec_rate::min_value 2 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.inst_exec_rate::max_value 1299 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.inst_exec_rate::total 141 # Instruction Execution Rate: Number of executed vector instructions per cycle system.cpu1.CUs1.num_vec_ops_executed 6762 # number of vec ops executed (e.g. VSZ/inst) -system.cpu1.CUs1.num_total_cycles 3358 # number of cycles the CU ran for -system.cpu1.CUs1.vpc 2.013699 # Vector Operations per cycle (this CU only) -system.cpu1.CUs1.ipc 0.041989 # Instructions per cycle (this CU only) +system.cpu1.CUs1.num_total_cycles 3360 # number of cycles the CU ran for +system.cpu1.CUs1.vpc 2.012500 # Vector Operations per cycle (this CU only) +system.cpu1.CUs1.ipc 0.041964 # Instructions per cycle (this CU only) system.cpu1.CUs1.warp_execution_dist::samples 141 # number of lanes active per instruction (oval all instructions) system.cpu1.CUs1.warp_execution_dist::mean 47.957447 # number of lanes active per instruction (oval all instructions) system.cpu1.CUs1.warp_execution_dist::stdev 23.818022 # number of lanes active per instruction (oval all instructions) @@ -2659,13 +2659,12 @@ system.ruby.network.ext_links1.int_node.msg_bytes.Unblock_Control::4 1228 system.tcp_cntrl0.L1cache.demand_hits 0 # Number of cache demand hits system.tcp_cntrl0.L1cache.demand_misses 0 # Number of cache demand misses system.tcp_cntrl0.L1cache.demand_accesses 0 # Number of cache demand accesses -system.tcp_cntrl0.L1cache.num_data_array_reads 10 # number of data array reads +system.tcp_cntrl0.L1cache.num_data_array_reads 9 # number of data array reads system.tcp_cntrl0.L1cache.num_data_array_writes 11 # number of data array writes -system.tcp_cntrl0.L1cache.num_tag_array_reads 27 # number of tag array reads +system.tcp_cntrl0.L1cache.num_tag_array_reads 26 # number of tag array reads system.tcp_cntrl0.L1cache.num_tag_array_writes 18 # number of tag array writes -system.tcp_cntrl0.L1cache.num_tag_array_stalls 2 # number of stalls caused by tag array system.tcp_cntrl0.L1cache.num_data_array_stalls 2 # number of stalls caused by data array -system.tcp_cntrl0.coalescer.gpu_tcp_ld_hits 3 # loads that hit in the TCP +system.tcp_cntrl0.coalescer.gpu_tcp_ld_hits 2 # loads that hit in the TCP system.tcp_cntrl0.coalescer.gpu_tcp_ld_transfers 0 # TCP to TCP load transfers system.tcp_cntrl0.coalescer.gpu_tcc_ld_hits 0 # loads that hit in the TCC system.tcp_cntrl0.coalescer.gpu_ld_misses 2 # loads that miss in the GPU @@ -2732,7 +2731,7 @@ system.sqc_cntrl0.L1cache.num_data_array_reads 86 system.sqc_cntrl0.L1cache.num_data_array_writes 5 # number of data array writes system.sqc_cntrl0.L1cache.num_tag_array_reads 86 # number of tag array reads system.sqc_cntrl0.L1cache.num_tag_array_writes 5 # number of tag array writes -system.sqc_cntrl0.L1cache.num_data_array_stalls 44 # number of stalls caused by data array +system.sqc_cntrl0.L1cache.num_data_array_stalls 47 # number of stalls caused by data array system.sqc_cntrl0.sequencer.load_waiting_on_load 120 # Number of times a load aliased with a pending load system.tcc_cntrl0.L2cache.demand_hits 0 # Number of cache demand hits system.tcc_cntrl0.L2cache.demand_misses 0 # Number of cache demand misses @@ -2755,16 +2754,16 @@ system.ruby.network.msg_byte.Unblock_Control 24968 system.sqc_coalescer.clk_domain.voltage_domain.voltage 1 # Voltage in Volts system.sqc_coalescer.clk_domain.clock 1000 # Clock period in ticks system.sqc_coalescer.uncoalesced_accesses 86 # Number of uncoalesced TLB accesses -system.sqc_coalescer.coalesced_accesses 63 # Number of coalesced TLB accesses -system.sqc_coalescer.queuing_cycles 100000 # Number of cycles spent in queue -system.sqc_coalescer.local_queuing_cycles 100000 # Number of cycles spent in queue for all incoming reqs -system.sqc_coalescer.local_latency 1162.790698 # Avg. latency over all incoming pkts +system.sqc_coalescer.coalesced_accesses 60 # Number of coalesced TLB accesses +system.sqc_coalescer.queuing_cycles 108000 # Number of cycles spent in queue +system.sqc_coalescer.local_queuing_cycles 108000 # Number of cycles spent in queue for all incoming reqs +system.sqc_coalescer.local_latency 1255.813953 # Avg. latency over all incoming pkts system.sqc_tlb.clk_domain.voltage_domain.voltage 1 # Voltage in Volts system.sqc_tlb.clk_domain.clock 1000 # Clock period in ticks -system.sqc_tlb.local_TLB_accesses 63 # Number of TLB accesses -system.sqc_tlb.local_TLB_hits 62 # Number of TLB hits +system.sqc_tlb.local_TLB_accesses 60 # Number of TLB accesses +system.sqc_tlb.local_TLB_hits 59 # Number of TLB hits system.sqc_tlb.local_TLB_misses 1 # Number of TLB misses -system.sqc_tlb.local_TLB_miss_rate 1.587302 # TLB miss rate +system.sqc_tlb.local_TLB_miss_rate 1.666667 # TLB miss rate system.sqc_tlb.global_TLB_accesses 86 # Number of TLB accesses system.sqc_tlb.global_TLB_hits 78 # Number of TLB hits system.sqc_tlb.global_TLB_misses 8 # Number of TLB misses @@ -2772,8 +2771,8 @@ system.sqc_tlb.global_TLB_miss_rate 9.302326 # TL system.sqc_tlb.access_cycles 86008 # Cycles spent accessing this TLB level system.sqc_tlb.page_table_cycles 0 # Cycles spent accessing the page table system.sqc_tlb.unique_pages 1 # Number of unique pages touched -system.sqc_tlb.local_cycles 63001 # Number of cycles spent in queue for all incoming reqs -system.sqc_tlb.local_latency 1000.015873 # Avg. latency over incoming coalesced reqs +system.sqc_tlb.local_cycles 60001 # Number of cycles spent in queue for all incoming reqs +system.sqc_tlb.local_latency 1000.016667 # Avg. latency over incoming coalesced reqs system.sqc_tlb.avg_reuse_distance 0 # avg. reuse distance over all pages (in ticks) system.ruby.network.ext_links0.int_node.throttle0.link_utilization 0.005592 system.ruby.network.ext_links0.int_node.throttle0.msg_count.Request_Control::0 1551 @@ -2897,22 +2896,22 @@ system.ruby.Directory_Controller.CoreUnblock 1551 0.00% 0.00% system.ruby.Directory_Controller.U.RdBlkS 1039 0.00% 0.00% system.ruby.Directory_Controller.U.RdBlkM 335 0.00% 0.00% system.ruby.Directory_Controller.U.RdBlk 177 0.00% 0.00% -system.ruby.Directory_Controller.BS_M.MemData 29 0.00% 0.00% -system.ruby.Directory_Controller.BM_M.MemData 12 0.00% 0.00% +system.ruby.Directory_Controller.BS_M.MemData 30 0.00% 0.00% +system.ruby.Directory_Controller.BM_M.MemData 11 0.00% 0.00% system.ruby.Directory_Controller.B_M.MemData 1 0.00% 0.00% -system.ruby.Directory_Controller.BS_PM.CPUPrbResp 29 0.00% 0.00% -system.ruby.Directory_Controller.BS_PM.ProbeAcksComplete 29 0.00% 0.00% -system.ruby.Directory_Controller.BS_PM.MemData 1010 0.00% 0.00% -system.ruby.Directory_Controller.BM_PM.CPUPrbResp 12 0.00% 0.00% -system.ruby.Directory_Controller.BM_PM.ProbeAcksComplete 12 0.00% 0.00% -system.ruby.Directory_Controller.BM_PM.MemData 323 0.00% 0.00% +system.ruby.Directory_Controller.BS_PM.CPUPrbResp 30 0.00% 0.00% +system.ruby.Directory_Controller.BS_PM.ProbeAcksComplete 30 0.00% 0.00% +system.ruby.Directory_Controller.BS_PM.MemData 1009 0.00% 0.00% +system.ruby.Directory_Controller.BM_PM.CPUPrbResp 11 0.00% 0.00% +system.ruby.Directory_Controller.BM_PM.ProbeAcksComplete 11 0.00% 0.00% +system.ruby.Directory_Controller.BM_PM.MemData 324 0.00% 0.00% system.ruby.Directory_Controller.B_PM.CPUPrbResp 1 0.00% 0.00% system.ruby.Directory_Controller.B_PM.ProbeAcksComplete 1 0.00% 0.00% system.ruby.Directory_Controller.B_PM.MemData 176 0.00% 0.00% -system.ruby.Directory_Controller.BS_Pm.CPUPrbResp 1010 0.00% 0.00% -system.ruby.Directory_Controller.BS_Pm.ProbeAcksComplete 1010 0.00% 0.00% -system.ruby.Directory_Controller.BM_Pm.CPUPrbResp 323 0.00% 0.00% -system.ruby.Directory_Controller.BM_Pm.ProbeAcksComplete 323 0.00% 0.00% +system.ruby.Directory_Controller.BS_Pm.CPUPrbResp 1009 0.00% 0.00% +system.ruby.Directory_Controller.BS_Pm.ProbeAcksComplete 1009 0.00% 0.00% +system.ruby.Directory_Controller.BM_Pm.CPUPrbResp 324 0.00% 0.00% +system.ruby.Directory_Controller.BM_Pm.ProbeAcksComplete 324 0.00% 0.00% system.ruby.Directory_Controller.B_Pm.CPUPrbResp 176 0.00% 0.00% system.ruby.Directory_Controller.B_Pm.ProbeAcksComplete 176 0.00% 0.00% system.ruby.Directory_Controller.B.CoreUnblock 1551 0.00% 0.00% @@ -2926,12 +2925,12 @@ system.ruby.LD.latency_hist_seqr | 16160 98.93% 98.93% | system.ruby.LD.latency_hist_seqr::total 16335 system.ruby.LD.latency_hist_coalsr::bucket_size 64 system.ruby.LD.latency_hist_coalsr::max_bucket 639 -system.ruby.LD.latency_hist_coalsr::samples 10 -system.ruby.LD.latency_hist_coalsr::mean 119.100000 -system.ruby.LD.latency_hist_coalsr::gmean 16.830524 -system.ruby.LD.latency_hist_coalsr::stdev 153.079827 -system.ruby.LD.latency_hist_coalsr | 6 60.00% 60.00% | 0 0.00% 60.00% | 0 0.00% 60.00% | 2 20.00% 80.00% | 0 0.00% 80.00% | 2 20.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.LD.latency_hist_coalsr::total 10 +system.ruby.LD.latency_hist_coalsr::samples 9 +system.ruby.LD.latency_hist_coalsr::mean 133 +system.ruby.LD.latency_hist_coalsr::gmean 19.809210 +system.ruby.LD.latency_hist_coalsr::stdev 158.221364 +system.ruby.LD.latency_hist_coalsr | 5 55.56% 55.56% | 0 0.00% 55.56% | 0 0.00% 55.56% | 2 22.22% 77.78% | 0 0.00% 77.78% | 2 22.22% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.LD.latency_hist_coalsr::total 9 system.ruby.LD.hit_latency_hist_seqr::bucket_size 32 system.ruby.LD.hit_latency_hist_seqr::max_bucket 319 system.ruby.LD.hit_latency_hist_seqr::samples 175 @@ -2950,12 +2949,12 @@ system.ruby.LD.miss_latency_hist_seqr | 16155 99.97% 99.97% | system.ruby.LD.miss_latency_hist_seqr::total 16160 system.ruby.LD.miss_latency_hist_coalsr::bucket_size 64 system.ruby.LD.miss_latency_hist_coalsr::max_bucket 639 -system.ruby.LD.miss_latency_hist_coalsr::samples 10 -system.ruby.LD.miss_latency_hist_coalsr::mean 119.100000 -system.ruby.LD.miss_latency_hist_coalsr::gmean 16.830524 -system.ruby.LD.miss_latency_hist_coalsr::stdev 153.079827 -system.ruby.LD.miss_latency_hist_coalsr | 6 60.00% 60.00% | 0 0.00% 60.00% | 0 0.00% 60.00% | 2 20.00% 80.00% | 0 0.00% 80.00% | 2 20.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.LD.miss_latency_hist_coalsr::total 10 +system.ruby.LD.miss_latency_hist_coalsr::samples 9 +system.ruby.LD.miss_latency_hist_coalsr::mean 133 +system.ruby.LD.miss_latency_hist_coalsr::gmean 19.809210 +system.ruby.LD.miss_latency_hist_coalsr::stdev 158.221364 +system.ruby.LD.miss_latency_hist_coalsr | 5 55.56% 55.56% | 0 0.00% 55.56% | 0 0.00% 55.56% | 2 22.22% 77.78% | 0 0.00% 77.78% | 2 22.22% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.LD.miss_latency_hist_coalsr::total 9 system.ruby.ST.latency_hist_seqr::bucket_size 64 system.ruby.ST.latency_hist_seqr::max_bucket 639 system.ruby.ST.latency_hist_seqr::samples 10412 @@ -2967,9 +2966,9 @@ system.ruby.ST.latency_hist_seqr::total 10412 system.ruby.ST.latency_hist_coalsr::bucket_size 32 system.ruby.ST.latency_hist_coalsr::max_bucket 319 system.ruby.ST.latency_hist_coalsr::samples 16 -system.ruby.ST.latency_hist_coalsr::mean 125.375000 -system.ruby.ST.latency_hist_coalsr::gmean 15.803091 -system.ruby.ST.latency_hist_coalsr::stdev 128.466792 +system.ruby.ST.latency_hist_coalsr::mean 124.937500 +system.ruby.ST.latency_hist_coalsr::gmean 15.775436 +system.ruby.ST.latency_hist_coalsr::stdev 128.013264 system.ruby.ST.latency_hist_coalsr | 8 50.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 8 50.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.ST.latency_hist_coalsr::total 16 system.ruby.ST.hit_latency_hist_seqr::bucket_size 64 @@ -2990,9 +2989,9 @@ system.ruby.ST.miss_latency_hist_seqr::total 10090 system.ruby.ST.miss_latency_hist_coalsr::bucket_size 32 system.ruby.ST.miss_latency_hist_coalsr::max_bucket 319 system.ruby.ST.miss_latency_hist_coalsr::samples 16 -system.ruby.ST.miss_latency_hist_coalsr::mean 125.375000 -system.ruby.ST.miss_latency_hist_coalsr::gmean 15.803091 -system.ruby.ST.miss_latency_hist_coalsr::stdev 128.466792 +system.ruby.ST.miss_latency_hist_coalsr::mean 124.937500 +system.ruby.ST.miss_latency_hist_coalsr::gmean 15.775436 +system.ruby.ST.miss_latency_hist_coalsr::stdev 128.013264 system.ruby.ST.miss_latency_hist_coalsr | 8 50.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 0 0.00% 50.00% | 8 50.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.ST.miss_latency_hist_coalsr::total 16 system.ruby.ATOMIC.latency_hist_coalsr::bucket_size 64 @@ -3014,17 +3013,17 @@ system.ruby.ATOMIC.miss_latency_hist_coalsr::total 2 system.ruby.IFETCH.latency_hist_seqr::bucket_size 64 system.ruby.IFETCH.latency_hist_seqr::max_bucket 639 system.ruby.IFETCH.latency_hist_seqr::samples 87095 -system.ruby.IFETCH.latency_hist_seqr::mean 4.462093 +system.ruby.IFETCH.latency_hist_seqr::mean 4.462070 system.ruby.IFETCH.latency_hist_seqr::gmean 2.116390 -system.ruby.IFETCH.latency_hist_seqr::stdev 22.435279 +system.ruby.IFETCH.latency_hist_seqr::stdev 22.434900 system.ruby.IFETCH.latency_hist_seqr | 86061 98.81% 98.81% | 0 0.00% 98.81% | 0 0.00% 98.81% | 1011 1.16% 99.97% | 16 0.02% 99.99% | 7 0.01% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.IFETCH.latency_hist_seqr::total 87095 system.ruby.IFETCH.hit_latency_hist_seqr::bucket_size 64 system.ruby.IFETCH.hit_latency_hist_seqr::max_bucket 639 system.ruby.IFETCH.hit_latency_hist_seqr::samples 1034 -system.ruby.IFETCH.hit_latency_hist_seqr::mean 208.444874 -system.ruby.IFETCH.hit_latency_hist_seqr::gmean 207.968565 -system.ruby.IFETCH.hit_latency_hist_seqr::stdev 16.462617 +system.ruby.IFETCH.hit_latency_hist_seqr::mean 208.442940 +system.ruby.IFETCH.hit_latency_hist_seqr::gmean 207.967489 +system.ruby.IFETCH.hit_latency_hist_seqr::stdev 16.443135 system.ruby.IFETCH.hit_latency_hist_seqr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 1011 97.78% 97.78% | 16 1.55% 99.32% | 7 0.68% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.IFETCH.hit_latency_hist_seqr::total 1034 system.ruby.IFETCH.miss_latency_hist_seqr::bucket_size 4 @@ -3102,33 +3101,33 @@ system.ruby.L2Cache.miss_mach_latency_hist_seqr::total 59 system.ruby.Directory.hit_mach_latency_hist_seqr::bucket_size 64 system.ruby.Directory.hit_mach_latency_hist_seqr::max_bucket 639 system.ruby.Directory.hit_mach_latency_hist_seqr::samples 1535 -system.ruby.Directory.hit_mach_latency_hist_seqr::mean 208.449511 -system.ruby.Directory.hit_mach_latency_hist_seqr::gmean 208.002927 -system.ruby.Directory.hit_mach_latency_hist_seqr::stdev 15.847049 +system.ruby.Directory.hit_mach_latency_hist_seqr::mean 208.448208 +system.ruby.Directory.hit_mach_latency_hist_seqr::gmean 208.002202 +system.ruby.Directory.hit_mach_latency_hist_seqr::stdev 15.833423 system.ruby.Directory.hit_mach_latency_hist_seqr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 1506 98.11% 98.11% | 19 1.24% 99.35% | 10 0.65% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.Directory.hit_mach_latency_hist_seqr::total 1535 system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::bucket_size 64 system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::max_bucket 639 system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::samples 3 -system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::mean 342 -system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::gmean 341.902506 -system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::stdev 10 +system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::mean 345.333333 +system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::gmean 345.301362 +system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::stdev 5.773503 system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 3 100.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.L1Cache_wCC.miss_mach_latency_hist_coalsr::total 3 system.ruby.TCP.miss_mach_latency_hist_coalsr::bucket_size 1 system.ruby.TCP.miss_mach_latency_hist_coalsr::max_bucket 9 -system.ruby.TCP.miss_mach_latency_hist_coalsr::samples 14 -system.ruby.TCP.miss_mach_latency_hist_coalsr::mean 1.714286 -system.ruby.TCP.miss_mach_latency_hist_coalsr::gmean 1.485994 -system.ruby.TCP.miss_mach_latency_hist_coalsr::stdev 1.069045 -system.ruby.TCP.miss_mach_latency_hist_coalsr | 0 0.00% 0.00% | 8 57.14% 57.14% | 4 28.57% 85.71% | 0 0.00% 85.71% | 2 14.29% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.TCP.miss_mach_latency_hist_coalsr::total 14 +system.ruby.TCP.miss_mach_latency_hist_coalsr::samples 13 +system.ruby.TCP.miss_mach_latency_hist_coalsr::mean 1.538462 +system.ruby.TCP.miss_mach_latency_hist_coalsr::gmean 1.377009 +system.ruby.TCP.miss_mach_latency_hist_coalsr::stdev 0.877058 +system.ruby.TCP.miss_mach_latency_hist_coalsr | 0 0.00% 0.00% | 8 61.54% 61.54% | 4 30.77% 92.31% | 0 0.00% 92.31% | 1 7.69% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.TCP.miss_mach_latency_hist_coalsr::total 13 system.ruby.TCCdir.miss_mach_latency_hist_coalsr::bucket_size 32 system.ruby.TCCdir.miss_mach_latency_hist_coalsr::max_bucket 319 system.ruby.TCCdir.miss_mach_latency_hist_coalsr::samples 11 -system.ruby.TCCdir.miss_mach_latency_hist_coalsr::mean 251.454545 -system.ruby.TCCdir.miss_mach_latency_hist_coalsr::gmean 251.396753 -system.ruby.TCCdir.miss_mach_latency_hist_coalsr::stdev 5.733474 +system.ruby.TCCdir.miss_mach_latency_hist_coalsr::mean 250.818182 +system.ruby.TCCdir.miss_mach_latency_hist_coalsr::gmean 250.757089 +system.ruby.TCCdir.miss_mach_latency_hist_coalsr::stdev 5.896070 system.ruby.TCCdir.miss_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 10 90.91% 90.91% | 1 9.09% 100.00% | 0 0.00% 100.00% system.ruby.TCCdir.miss_mach_latency_hist_coalsr::total 11 system.ruby.LD.L1Cache.miss_type_mach_latency_hist_seqr::bucket_size 1 @@ -3156,19 +3155,18 @@ system.ruby.LD.Directory.hit_type_mach_latency_hist_seqr::total 175 system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::bucket_size 64 system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::max_bucket 639 system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::samples 2 -system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::mean 337 -system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::gmean 336.962906 -system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::stdev 7.071068 +system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::mean 342 +system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::gmean 342.000000 system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 2 100.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.LD.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::total 2 system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::bucket_size 1 system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::max_bucket 9 -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::samples 6 -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::mean 2.666667 -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::gmean 2.519842 -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::stdev 1.032796 -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 4 66.67% 66.67% | 0 0.00% 66.67% | 2 33.33% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% -system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::total 6 +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::samples 5 +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::mean 2.400000 +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::gmean 2.297397 +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::stdev 0.894427 +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 4 80.00% 80.00% | 0 0.00% 80.00% | 1 20.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% +system.ruby.LD.TCP.miss_type_mach_latency_hist_coalsr::total 5 system.ruby.LD.TCCdir.miss_type_mach_latency_hist_coalsr::bucket_size 32 system.ruby.LD.TCCdir.miss_type_mach_latency_hist_coalsr::max_bucket 319 system.ruby.LD.TCCdir.miss_type_mach_latency_hist_coalsr::samples 2 @@ -3202,9 +3200,9 @@ system.ruby.ST.TCP.miss_type_mach_latency_hist_coalsr::total 8 system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::bucket_size 32 system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::max_bucket 319 system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::samples 8 -system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::mean 249.750000 -system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::gmean 249.737699 -system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::stdev 2.659216 +system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::mean 248.875000 +system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::gmean 248.864382 +system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::stdev 2.474874 system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 8 100.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.ST.TCCdir.miss_type_mach_latency_hist_coalsr::total 8 system.ruby.ATOMIC.L1Cache_wCC.miss_type_mach_latency_hist_coalsr::bucket_size 64 @@ -3240,9 +3238,9 @@ system.ruby.IFETCH.L2Cache.miss_type_mach_latency_hist_seqr::total 54 system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::bucket_size 64 system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::max_bucket 639 system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::samples 1034 -system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::mean 208.444874 -system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::gmean 207.968565 -system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::stdev 16.462617 +system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::mean 208.442940 +system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::gmean 207.967489 +system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::stdev 16.443135 system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr | 0 0.00% 0.00% | 0 0.00% 0.00% | 0 0.00% 0.00% | 1011 97.78% 97.78% | 16 1.55% 99.32% | 7 0.68% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% | 0 0.00% 100.00% system.ruby.IFETCH.Directory.hit_type_mach_latency_hist_seqr::total 1034 system.ruby.RMW_Read.L1Cache.miss_type_mach_latency_hist_seqr::bucket_size 1 @@ -3278,7 +3276,7 @@ system.ruby.SQC_Controller.TCC_AckS 5 0.00% 0.00% system.ruby.SQC_Controller.I.Fetch 5 0.00% 0.00% system.ruby.SQC_Controller.S.Fetch 81 0.00% 0.00% system.ruby.SQC_Controller.I_S.TCC_AckS 5 0.00% 0.00% -system.ruby.TCCdir_Controller.RdBlk 53 0.00% 0.00% +system.ruby.TCCdir_Controller.RdBlk 54 0.00% 0.00% system.ruby.TCCdir_Controller.RdBlkM 36 0.00% 0.00% system.ruby.TCCdir_Controller.RdBlkS 5 0.00% 0.00% system.ruby.TCCdir_Controller.CPUPrbResp 14 0.00% 0.00% @@ -3313,12 +3311,12 @@ system.ruby.TCCdir_Controller.BBM_M.CPUPrbResp 1 0.00% 0.00 system.ruby.TCCdir_Controller.BBM_M.ProbeAcksComplete 1 0.00% 0.00% system.ruby.TCCdir_Controller.BB_M.CoreUnblock 1 0.00% 0.00% system.ruby.TCCdir_Controller.BB_S.LastCoreUnblock 2 0.00% 0.00% -system.ruby.TCCdir_Controller.BBB_S.RdBlk 8 0.00% 0.00% +system.ruby.TCCdir_Controller.BBB_S.RdBlk 9 0.00% 0.00% system.ruby.TCCdir_Controller.BBB_S.CoreUnblock 7 0.00% 0.00% system.ruby.TCCdir_Controller.BBB_M.RdBlkM 4 0.00% 0.00% system.ruby.TCCdir_Controller.BBB_M.CoreUnblock 9 0.00% 0.00% -system.ruby.TCP_Controller.Load | 5 50.00% 50.00% | 5 50.00% 100.00% -system.ruby.TCP_Controller.Load::total 10 +system.ruby.TCP_Controller.Load | 4 44.44% 44.44% | 5 55.56% 100.00% +system.ruby.TCP_Controller.Load::total 9 system.ruby.TCP_Controller.Store | 9 50.00% 50.00% | 9 50.00% 100.00% system.ruby.TCP_Controller.Store::total 18 system.ruby.TCP_Controller.TCC_AckS | 2 50.00% 50.00% | 2 50.00% 100.00% @@ -3333,8 +3331,8 @@ system.ruby.TCP_Controller.I.Load | 2 50.00% 50.00% | system.ruby.TCP_Controller.I.Load::total 4 system.ruby.TCP_Controller.I.Store | 5 50.00% 50.00% | 5 50.00% 100.00% system.ruby.TCP_Controller.I.Store::total 10 -system.ruby.TCP_Controller.S.Load | 3 50.00% 50.00% | 3 50.00% 100.00% -system.ruby.TCP_Controller.S.Load::total 6 +system.ruby.TCP_Controller.S.Load | 2 40.00% 40.00% | 3 60.00% 100.00% +system.ruby.TCP_Controller.S.Load::total 5 system.ruby.TCP_Controller.S.PrbInvData | 1 50.00% 50.00% | 1 50.00% 100.00% system.ruby.TCP_Controller.S.PrbInvData::total 2 system.ruby.TCP_Controller.S.PrbShrData | 2 100.00% 100.00% | 0 0.00% 100.00%