Skip to content

Instantly share code, notes, and snippets.

@lukego
Created March 8, 2016 10:01
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save lukego/062a4c7e4c02cfde92f4 to your computer and use it in GitHub Desktop.
Save lukego/062a4c7e4c02cfde92f4 to your computer and use it in GitHub Desktop.
mp-ring pmu output (second run: showing 1/2/3 process output together)
@@@@ processes 1
@@@@ events l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
PMU report for child #0:
EVENT TOTAL /packet
cycles 518,749,764 51.875
ref_cycles 0 0.000
instructions 587,055,371 58.706
l2_rqsts.all_code_rd 141,671 0.014
l2_rqsts.all_demand_data_rd 1,013,425 0.101
l2_rqsts.all_demand_miss 1,813,018 0.181
l2_rqsts.all_demand_references 2,953,413 0.295
l2_rqsts.all_pf 1,816,785 0.182
l2_rqsts.all_rfo 1,798,316 0.180
l2_rqsts.code_rd_hit 136,865 0.014
l2_rqsts.code_rd_miss 4,777 0.000
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
66.66 Mpps ring throughput per process
@@@@ processes 2
@@@@ events l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
PMU report for child #0:
EVENT TOTAL /packet
cycles 6,662,711,493 666.271
ref_cycles 0 0.000
instructions 593,444,647 59.344
l2_rqsts.all_code_rd 149,164 0.015
l2_rqsts.all_demand_data_rd 39,003,168 3.900
l2_rqsts.all_demand_miss 69,252,570 6.925
l2_rqsts.all_demand_references 80,174,971 8.017
l2_rqsts.all_pf 66,454,003 6.645
l2_rqsts.all_rfo 41,022,638 4.102
l2_rqsts.code_rd_hit 139,881 0.014
l2_rqsts.code_rd_miss 9,221 0.001
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
5.25 Mpps ring throughput per process
@@@@ processes 3
@@@@ events l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
PMU report for child #0:
EVENT TOTAL /packet
cycles 8,060,793,915 806.079
ref_cycles 0 0.000
instructions 572,613,917 57.261
l2_rqsts.all_code_rd 27,037 0.003
l2_rqsts.all_demand_data_rd 41,862,959 4.186
l2_rqsts.all_demand_miss 72,621,732 7.262
l2_rqsts.all_demand_references 82,841,043 8.284
l2_rqsts.all_pf 70,998,318 7.100
l2_rqsts.all_rfo 40,951,047 4.095
l2_rqsts.code_rd_hit 18,422 0.002
l2_rqsts.code_rd_miss 7,656 0.001
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_rqsts
4.34 Mpps ring throughput per process
@@@@ processes 1
@@@@ events l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
PMU report for child #0:
EVENT TOTAL /packet
cycles 514,882,994 51.488
ref_cycles 0 0.000
instructions 587,042,902 58.704
l2_trans.all_pf 2,054,510 0.205
l2_trans.all_requests 14,971,587 1.497
l2_trans.code_rd 138,382 0.014
l2_trans.demand_data_rd 1,331,650 0.133
l2_trans.l1d_wb 515,642 0.052
l2_trans.l2_fill 3,495,905 0.350
l2_trans.l2_wb 1,580 0.000
l2_trans.rfo 1,981,668 0.198
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
67.30 Mpps ring throughput per process
@@@@ processes 2
@@@@ events l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
PMU report for child #0:
EVENT TOTAL /packet
cycles 6,609,444,414 660.944
ref_cycles 0 0.000
instructions 593,112,063 59.311
l2_trans.all_pf 54,269,864 5.427
l2_trans.all_requests 393,628,340 39.363
l2_trans.code_rd 144,216 0.014
l2_trans.demand_data_rd 31,224,906 3.122
l2_trans.l1d_wb 430,806 0.043
l2_trans.l2_fill 108,355,009 10.836
l2_trans.l2_wb 1,880 0.000
l2_trans.rfo 41,737,530 4.174
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
5.29 Mpps ring throughput per process
@@@@ processes 3
@@@@ events l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
PMU report for child #0:
EVENT TOTAL /packet
cycles 7,626,750,487 762.675
ref_cycles 0 0.000
instructions 3,566,455,661 356.646
l2_trans.all_pf 68,552,612 6.855
l2_trans.all_requests 451,124,145 45.112
l2_trans.code_rd 148,487 0.015
l2_trans.demand_data_rd 40,161,392 4.016
l2_trans.l1d_wb 9,546,012 0.955
l2_trans.l2_fill 120,947,897 12.095
l2_trans.l2_wb 2,561 0.000
l2_trans.rfo 44,435,421 4.444
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: l2_trans
4.59 Mpps ring throughput per process
@@@@ processes 1
@@@@ events mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
PMU report for child #0:
EVENT TOTAL /packet
cycles 546,635,716 54.664
ref_cycles 0 0.000
instructions 587,057,747 58.706
mem_trans_retired.load_latency_gt_128 0 0.000
mem_trans_retired.load_latency_gt_16 0 0.000
mem_trans_retired.load_latency_gt_256 0 0.000
mem_trans_retired.load_latency_gt_32 0 0.000
mem_trans_retired.load_latency_gt_4 0 0.000
mem_trans_retired.load_latency_gt_512 0 0.000
mem_trans_retired.load_latency_gt_64 0 0.000
mem_trans_retired.load_latency_gt_8 0 0.000
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
63.43 Mpps ring throughput per process
@@@@ processes 2
@@@@ events mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
PMU report for child #0:
EVENT TOTAL /packet
cycles 6,671,960,431 667.196
ref_cycles 0 0.000
instructions 593,401,545 59.340
mem_trans_retired.load_latency_gt_128 0 0.000
mem_trans_retired.load_latency_gt_16 0 0.000
mem_trans_retired.load_latency_gt_256 0 0.000
mem_trans_retired.load_latency_gt_32 0 0.000
mem_trans_retired.load_latency_gt_4 0 0.000
mem_trans_retired.load_latency_gt_512 0 0.000
mem_trans_retired.load_latency_gt_64 0 0.000
mem_trans_retired.load_latency_gt_8 0 0.000
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
5.24 Mpps ring throughput per process
@@@@ processes 3
@@@@ events mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
PMU report for child #0:
EVENT TOTAL /packet
cycles 7,752,190,598 775.219
ref_cycles 0 0.000
instructions 596,138,869 59.614
mem_trans_retired.load_latency_gt_128 0 0.000
mem_trans_retired.load_latency_gt_16 0 0.000
mem_trans_retired.load_latency_gt_256 0 0.000
mem_trans_retired.load_latency_gt_32 0 0.000
mem_trans_retired.load_latency_gt_4 0 0.000
mem_trans_retired.load_latency_gt_512 0 0.000
mem_trans_retired.load_latency_gt_64 0 0.000
mem_trans_retired.load_latency_gt_8 0 0.000
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: mem_trans_retired[.]load_latency_gt_
4.51 Mpps ring throughput per process
@@@@ processes 1
@@@@ events cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
PMU report for child #0:
EVENT TOTAL /packet
cycles 551,134,994 55.113
ref_cycles 0 0.000
instructions 587,461,069 58.746
cycle_activity.cycles_l1d_pending 0 0.000
cycle_activity.cycles_l2_pending 1,709,020 0.171
cycle_activity.cycles_ldm_pending 513,246,736 51.325
cycle_activity.cycles_no_execute 1,283,608,212 128.361
cycle_activity.stalls_l1d_pending 1,283,608,220 128.361
cycle_activity.stalls_l2_pending 1,285,317,240 128.532
cycle_activity.stalls_ldm_pending 1,796,854,956 179.685
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 1
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
62.98 Mpps ring throughput per process
@@@@ processes 2
@@@@ events cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
PMU report for child #0:
EVENT TOTAL /packet
cycles 6,539,607,131 653.961
ref_cycles 0 0.000
instructions 593,000,407 59.300
cycle_activity.cycles_l1d_pending 0 0.000
cycle_activity.cycles_l2_pending 3,760,645,024 376.065
cycle_activity.cycles_ldm_pending 8,785,157,244 878.516
cycle_activity.cycles_no_execute 24,078,009,752 2407.801
cycle_activity.stalls_l1d_pending 24,078,009,760 2407.801
cycle_activity.stalls_l2_pending 27,838,654,784 2783.865
cycle_activity.stalls_ldm_pending 32,863,167,004 3286.317
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 2
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
5.35 Mpps ring throughput per process
@@@@ processes 3
@@@@ events cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
PMU report for child #0:
EVENT TOTAL /packet
cycles 7,558,957,039 755.896
ref_cycles 0 0.000
instructions 596,832,860 59.683
cycle_activity.cycles_l1d_pending 0 0.000
cycle_activity.cycles_l2_pending 3,631,162,469 363.116
cycle_activity.cycles_ldm_pending 11,592,599,692 1159.260
cycle_activity.cycles_no_execute 28,343,776,764 2834.378
cycle_activity.stalls_l1d_pending 28,343,776,764 2834.378
cycle_activity.stalls_l2_pending 31,974,939,233 3197.494
cycle_activity.stalls_ldm_pending 39,936,376,456 3993.638
packet 10,000,000 1.000
Benchmark configuration:
burst: 100
writebytes: 0
processes: 3
readbytes: 0
packets: 10000000
mode: basic
pmuevents: cycle_activity
4.63 Mpps ring throughput per process
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment