40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 21447 | 21447 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f998ee04280 | 3670016 | 2904094 | 324911544 | 14214097043918 | 14095491412894 | 14214245793171 | 14214245909711 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 21447 | 21447 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f998ee23f80 | 512 | 94148 | 10565528 | 14214251057535 | 14214245793171 | 14214251188702 | 14214251193482 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f9991d71380 | 0x7f998ee23fc0 | 65536 | 639506 | 71642904 | 14214251227932 | 14214251188702 | 14214251559583 | 14214251562255 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f9991d71200 | 0x7f998ee24000 | 65536 | 664010 | 74354736 | 14214251598544 | 14214251559583 | 14214251966304 | 14214251968817 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f9991d71080 | 0x7f998ee24040 | 65536 | 657756 | 73750128 | 14214252002266 | 14214251966304 | 14214252359745 | 14214252362218 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f998f711f00 | 0x7f998ee24080 | 65536 | 692938 | 77578064 | 14214252395358 | 14214252359745 | 14214252663426 | 14214252665802 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f998f711d80 | 0x7f998ee240c0 | 65536 | 633132 | 70852328 | 14214252698702 | 14214252663426 | 14214252969826 | 14214252972236 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f998f711c00 | 0x7f998ee24100 | 131072 | 694200 | 77710408 | 14214253015585 | 14214252969826 | 14214253275427 | 14214253277950 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f998f711a80 | 0x7f998ee24140 | 131072 | 698688 | 78251208 | 14214253310599 | 14214253275427 | 14214253668868 | 14214253671212 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f998f711900 | 0x7f998ee24180 | 65536 | 646328 | 72459720 | 14214253702801 | 14214253668868 | 14214254058149 | 14214254060474 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f998f711780 | 0x7f998ee241c0 | 131072 | 688480 | 77183688 | 14214254094943 | 14214254058149 | 14214254414790 | 14214254417166 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f998f711600 | 0x7f998ee24200 | 131072 | 696100 | 78026296 | 14214254449976 | 14214254414790 | 14214254720550 | 14214254722900 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f9991d71480 | 0x7f998ee24240 | 131072 | 703158 | 78758416 | 14214254763129 | 14214254720550 | 14214255025191 | 14214255027574 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f9991d71300 | 0x7f998ee24280 | 131072 | 699124 | 78206848 | 14214255060793 | 14214255025191 | 14214255418952 | 14214255420916 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f9991d71180 | 0x7f998ee242c0 | 65536 | 658690 | 73754552 | 14214255453325 | 14214255418952 | 14214255794473 | 14214255796098 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f9991d71000 | 0x7f998ee24300 | 131072 | 683326 | 76554480 | 14214255827998 | 14214255794473 | 14214256071433 | 14214256073033 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f998f711e80 | 0x7f998ee24340 | 131072 | 685070 | 76742904 | 14214256105042 | 14214256071433 | 14214256345994 | 14214256347817 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f998f711d00 | 0x7f998ee24380 | 131072 | 719024 | 80446360 | 14214256386896 | 14214256345994 | 14214256622475 | 14214256624312 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f998f711b80 | 0x7f998ee243c0 | 131072 | 697854 | 78174544 | 14214256657381 | 14214256622475 | 14214256986635 | 14214256988554 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f998f711a00 | 0x7f998ee24400 | 65536 | 634282 | 71020728 | 14214257021623 | 14214256986635 | 14214257355436 | 14214257357287 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f998f711880 | 0x7f998ee24440 | 131072 | 693762 | 77763320 | 14214257388616 | 14214257355436 | 14214257632557 | 14214257634421 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f998f711700 | 0x7f998ee24480 | 131072 | 689316 | 77145008 | 14214257665870 | 14214257632557 | 14214257911277 | 14214257913185 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f9991d71580 | 0x7f998ee244c0 | 131072 | 646690 | 72369776 | 14214257952055 | 14214257911277 | 14214258203118 | 14214258205009 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f9991d71400 | 0x7f998ee24500 | 131072 | 693286 | 77734080 | 14214258237799 | 14214258203118 | 14214258575119 | 14214258576852 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f9991d71280 | 0x7f998ee24540 | 65536 | 651418 | 72929664 | 14214258609061 | 14214258575119 | 14214258943440 | 14214258945244 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f9991d71100 | 0x7f998ee24580 | 131072 | 672198 | 75176760 | 14214258976874 | 14214258943440 | 14214259218160 | 14214259219919 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f998f711f80 | 0x7f998ee245c0 | 131072 | 672238 | 75322696 | 14214259252708 | 14214259218160 | 14214259491601 | 14214259493443 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f998f711e00 | 0x7f998ee24600 | 131072 | 686612 | 76845976 | 14214259531932 | 14214259491601 | 14214259767282 | 14214259768927 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f998f711c80 | 0x7f998ee24640 | 131072 | 666366 | 74624680 | 14214259800707 | 14214259767282 | 14214260128242 | 14214260130070 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f998f711b00 | 0x7f998ee24680 | 65536 | 652018 | 73008624 | 14214260162159 | 14214260128242 | 14214260493203 | 14214260495072 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f998f711980 | 0x7f998ee246c0 | 131072 | 690940 | 77471128 | 14214260525932 | 14214260493203 | 14214260769204 | 14214260771067 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f998f711800 | 0x7f998ee24700 | 131072 | 692986 | 77657368 | 14214260802296 | 14214260769204 | 14214261042805 | 14214261044601 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f998f711680 | 0x7f998ee24740 | 131072 | 700692 | 78443264 | 14214261083750 | 14214261042805 | 14214261327605 | 14214261329505 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f9991d71500 | 0x7f998ee24780 | 131072 | 697990 | 78272224 | 14214261360985 | 14214261327605 | 14214261696246 | 14214261697968 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f9991d71380 | 0x7f998ee247c0 | 65536 | 655246 | 73376184 | 14214261730007 | 14214261696246 | 14214262062327 | 14214262064230 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f9991d71200 | 0x7f998ee24800 | 131072 | 700864 | 78420664 | 14214262096420 | 14214262062327 | 14214262346647 | 14214262348494 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f9991d71080 | 0x7f998ee24840 | 131072 | 687082 | 76943376 | 14214262380494 | 14214262346647 | 14214262626008 | 14214262627679 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f998f711f00 | 0x7f998ee24880 | 131072 | 717420 | 80358576 | 14214262667158 | 14214262626008 | 14214262902649 | 14214262904493 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f998f711d80 | 0x7f998ee248c0 | 131072 | 692184 | 77431192 | 14214262935442 | 14214262902649 | 14214263275610 | 14214263277325 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f998f711c00 | 0x7f998ee24900 | 65536 | 614666 | 68792936 | 14214263309865 | 14214263275610 | 14214263641050 | 14214263642818 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f998f711a80 | 0x7f998ee24940 | 131072 | 691626 | 77426312 | 14214263673917 | 14214263641050 | 14214263914971 | 14214263916852 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f998f711900 | 0x7f998ee24980 | 131072 | 696738 | 77997112 | 14214263947972 | 14214263914971 | 14214264190652 | 14214264192527 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f998f711780 | 0x7f998ee249c0 | 131072 | 694492 | 77804696 | 14214264230196 | 14214264190652 | 14214264469372 | 14214264471121 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f998f711600 | 0x7f998ee24a00 | 131072 | 683892 | 76471752 | 14214264502750 | 14214264469372 | 14214264831133 | 14214264832903 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f9991d71480 | 0x7f998ee24a40 | 65536 | 654486 | 73318504 | 14214264864743 | 14214264831133 | 14214265195454 | 14214265197286 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f9991d71300 | 0x7f998ee24a80 | 131072 | 666066 | 74563560 | 14214265228395 | 14214265195454 | 14214265472094 | 14214265473970 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f9991d71180 | 0x7f998ee24ac0 | 131072 | 652276 | 73076312 | 14214265506220 | 14214265472094 | 14214265749855 | 14214265751705 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f9991d71000 | 0x7f998ee24b00 | 131072 | 674736 | 75609568 | 14214265790764 | 14214265749855 | 14214266031776 | 14214266033589 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f998f711e80 | 0x7f998ee24b40 | 131072 | 695542 | 78012688 | 14214266065208 | 14214266031776 | 14214266413057 | 14214266414861 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f998f711d00 | 0x7f998ee24b80 | 65536 | 653020 | 73107240 | 14214266446880 | 14214266413057 | 14214266777857 | 14214266779534 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f998f711b80 | 0x7f998ee24bc0 | 131072 | 693090 | 77735224 | 14214266811213 | 14214266777857 | 14214267056098 | 14214267057788 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f998f711a00 | 0x7f998ee24c00 | 131072 | 689680 | 77211776 | 14214267090597 | 14214267056098 | 14214267334819 | 14214267336552 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f998f711880 | 0x7f998ee24c40 | 131072 | 695678 | 77909208 | 14214267374781 | 14214267334819 | 14214267611939 | 14214267613696 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f998f711700 | 0x7f998ee24c80 | 131072 | 684520 | 76730464 | 14214267644896 | 14214267611939 | 14214267974180 | 14214267975959 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f9991d71580 | 0x7f998ee24cc0 | 65536 | 656446 | 73540072 | 14214268008398 | 14214267974180 | 14214268334981 | 14214268336722 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f9991d71400 | 0x7f998ee24d00 | 131072 | 699528 | 78391856 | 14214268368931 | 14214268334981 | 14214268611462 | 14214268613156 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f9991d71280 | 0x7f998ee24d40 | 131072 | 702374 | 78631736 | 14214268645565 | 14214268611462 | 14214268901382 | 14214268903210 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f9991d71100 | 0x7f998ee24d80 | 131072 | 701210 | 78554048 | 14214268943649 | 14214268901382 | 14214269179783 | 14214269181554 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f998f711f80 | 0x7f998ee24dc0 | 131072 | 667682 | 74796312 | 14214269213164 | 14214269179783 | 14214269543144 | 14214269544897 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f998f711e00 | 0x7f998ee24e00 | 65536 | 659864 | 73962248 | 14214269576836 | 14214269543144 | 14214269905544 | 14214269907309 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f998f711c80 | 0x7f998ee24e40 | 131072 | 694078 | 77740656 | 14214269939029 | 14214269905544 | 14214270190505 | 14214270192484 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f998f711b00 | 0x7f998ee24e80 | 131072 | 694668 | 77884760 | 14214270224673 | 14214270190505 | 14214270478986 | 14214270480758 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f998f711980 | 0x7f998ee24ec0 | 131072 | 657158 | 73663968 | 14214270519677 | 14214270478986 | 14214270755786 | 14214270757652 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f998f711800 | 0x7f998ee24f00 | 131072 | 703118 | 78734464 | 14214270789501 | 14214270755786 | 14214271117707 | 14214271119565 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f998f711680 | 0x7f998ee24f40 | 65536 | 657946 | 73672760 | 14214271151534 | 14214271117707 | 14214271482348 | 14214271483947 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f9991d71500 | 0x7f998ee24f80 | 131072 | 667186 | 74782496 | 14214271515676 | 14214271482348 | 14214271761549 | 14214271763511 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f9991d71380 | 0x7f998ee24fc0 | 131072 | 682540 | 76430552 | 14214271795241 | 14214271761549 | 14214272051949 | 14214272053795 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f9991d71200 | 0x7f998ee25000 | 131072 | 693326 | 77668120 | 14214272092975 | 14214272051949 | 14214272327630 | 14214272329420 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f9991d71080 | 0x7f998ee25040 | 131072 | 705144 | 79044624 | 14214272361739 | 14214272327630 | 14214272692271 | 14214272694062 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f998f711f00 | 0x7f998ee25080 | 65536 | 660416 | 73925016 | 14214272726332 | 14214272692271 | 14214273054991 | 14214273056795 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f998f711d80 | 0x7f998ee250c0 | 131072 | 697326 | 78069912 | 14214273087364 | 14214273054991 | 14214273332112 | 14214273333969 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f998f711c00 | 0x7f998ee25100 | 131072 | 696762 | 78060176 | 14214273365408 | 14214273332112 | 14214273629073 | 14214273630843 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f998f711a80 | 0x7f998ee25140 | 131072 | 695274 | 77785736 | 14214273681002 | 14214273629073 | 14214273908913 | 14214273910687 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f998f711900 | 0x7f998ee25180 | 131072 | 692514 | 77697544 | 14214273941137 | 14214273908913 | 14214274281874 | 14214274283660 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f998f711780 | 0x7f998ee251c0 | 65536 | 657010 | 73644888 | 14214274316129 | 14214274281874 | 14214274651475 | 14214274653422 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f998f711600 | 0x7f998ee25200 | 131072 | 705012 | 79000648 | 14214274684002 | 14214274651475 | 14214274935476 | 14214274937346 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f9991d71480 | 0x7f998ee25240 | 131072 | 707020 | 79168136 | 14214274968626 | 14214274935476 | 14214275237236 | 14214275239120 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f9991d71300 | 0x7f998ee25280 | 131072 | 692710 | 77585264 | 14214275278129 | 14214275237236 | 14214275518357 | 14214275520005 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f9991d71180 | 0x7f998ee252c0 | 131072 | 700072 | 78497856 | 14214275552734 | 14214275518357 | 14214275894198 | 14214275896007 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f9991d71000 | 0x7f998ee25300 | 65536 | 646876 | 72498440 | 14214275928866 | 14214275894198 | 14214276255159 | 14214276256990 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f998f711e80 | 0x7f998ee25340 | 131072 | 681108 | 76242384 | 14214276288869 | 14214276255159 | 14214276533719 | 14214276535504 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f998f711d00 | 0x7f998ee25380 | 131072 | 707966 | 79448016 | 14214276566873 | 14214276533719 | 14214276843800 | 14214276845678 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f998f711b80 | 0x7f998ee253c0 | 131072 | 688286 | 76961720 | 14214276884457 | 14214276843800 | 14214277122361 | 14214277124242 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f998f711a00 | 0x7f998ee25400 | 131072 | 685202 | 76747816 | 14214277155241 | 14214277122361 | 14214277488761 | 14214277490654 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f998f711880 | 0x7f998ee25440 | 65536 | 652824 | 73109480 | 14214277524494 | 14214277488761 | 14214277860282 | 14214277862127 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f998f711700 | 0x7f998ee25480 | 131072 | 662752 | 74221400 | 14214277893786 | 14214277860282 | 14214278138683 | 14214278140751 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f9991d71580 | 0x7f998ee254c0 | 131072 | 672246 | 75172976 | 14214278172791 | 14214278138683 | 14214278458204 | 14214278459945 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f9991d71400 | 0x7f998ee25500 | 131072 | 665324 | 74557288 | 14214278499224 | 14214278458204 | 14214278742204 | 14214278743959 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f9991d71280 | 0x7f998ee25540 | 131072 | 684708 | 76685832 | 14214278775278 | 14214278742204 | 14214279105565 | 14214279107441 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f9991d71100 | 0x7f998ee25580 | 65536 | 666936 | 74662448 | 14214279140011 | 14214279105565 | 14214279467006 | 14214279468854 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f998f711f80 | 0x7f998ee255c0 | 131072 | 698010 | 78093400 | 14214279500103 | 14214279467006 | 14214279745567 | 14214279747518 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f998f711e00 | 0x7f998ee25600 | 131072 | 689228 | 77137272 | 14214279778368 | 14214279745567 | 14214280065567 | 14214280067232 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f998f711c80 | 0x7f998ee25640 | 131072 | 721474 | 80912192 | 14214280105451 | 14214280065567 | 14214280342208 | 14214280343976 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f998f711b00 | 0x7f998ee25680 | 131072 | 692746 | 77571768 | 14214280374685 | 14214280342208 | 14214280710689 | 14214280712469 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f998f711980 | 0x7f998ee256c0 | 65536 | 650258 | 72800224 | 14214280744158 | 14214280710689 | 14214281079490 | 14214281081381 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f998f711800 | 0x7f998ee25700 | 131072 | 680872 | 76262144 | 14214281112500 | 14214281079490 | 14214281359650 | 14214281361245 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f998f711680 | 0x7f998ee25740 | 131072 | 686048 | 76845792 | 14214281393845 | 14214281359650 | 14214281687491 | 14214281689398 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f9991d71500 | 0x7f998ee25780 | 131072 | 707692 | 79239544 | 14214281728298 | 14214281687491 | 14214281969092 | 14214281970803 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f9991d71380 | 0x7f998ee257c0 | 131072 | 694222 | 77754912 | 14214282003342 | 14214281969092 | 14214282341732 | 14214282343565 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f9991d71200 | 0x7f998ee25800 | 65536 | 661668 | 74129600 | 14214282376024 | 14214282341732 | 14214282712133 | 14214282714027 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f9991d71080 | 0x7f998ee25840 | 131072 | 696724 | 77994928 | 14214282745997 | 14214282712133 | 14214282997414 | 14214282999332 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f998f711f00 | 0x7f998ee25880 | 131072 | 664800 | 74351672 | 14214283031851 | 14214282997414 | 14214283336135 | 14214283337825 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f998f711d80 | 0x7f998ee258c0 | 131072 | 1038520 | 115943216 | 14214283377334 | 14214283336135 | 14214283624615 | 14214283626459 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f998f711c00 | 0x7f998ee25900 | 131072 | 654080 | 73194984 | 14214283657828 | 14214283624615 | 14214283988136 | 14214283990021 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f998f711a80 | 0x7f998ee25940 | 65536 | 654306 | 73260736 | 14214284021831 | 14214283988136 | 14214284351177 | 14214284352974 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f998f711900 | 0x7f998ee25980 | 131072 | 695550 | 77897920 | 14214284384223 | 14214284351177 | 14214284641578 | 14214284643398 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f998f711780 | 0x7f998ee259c0 | 131072 | 691980 | 77487432 | 14214284674807 | 14214284641578 | 14214284995818 | 14214284997581 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f998f711600 | 0x7f998ee25a00 | 131072 | 1015956 | 113767976 | 14214285037200 | 14214284995818 | 14214285276779 | 14214285278675 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f9991d71480 | 0x7f998ee25a40 | 131072 | 691616 | 77415520 | 14214285310394 | 14214285276779 | 14214285641100 | 14214285642897 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f9991d71300 | 0x7f998ee25a80 | 65536 | 650204 | 72768920 | 14214285675217 | 14214285641100 | 14214286006221 | 14214286008050 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f9991d71180 | 0x7f998ee25ac0 | 131072 | 688498 | 77156824 | 14214286040419 | 14214286006221 | 14214286304301 | 14214286306104 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f9991d71000 | 0x7f998ee25b00 | 131072 | 665318 | 74536184 | 14214286338263 | 14214286304301 | 14214286676942 | 14214286678756 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f998f711e80 | 0x7f998ee25b40 | 131072 | 998174 | 111825960 | 14214286718065 | 14214286676942 | 14214286963503 | 14214286965160 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f998f711d00 | 0x7f998ee25b80 | 131072 | 696060 | 77961168 | 14214286996920 | 14214286963503 | 14214287331344 | 14214287333123 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f998f711b80 | 0x7f998ee25bc0 | 65536 | 656200 | 73579680 | 14214287364472 | 14214287331344 | 14214287698384 | 14214287700185 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f998f711a00 | 0x7f998ee25c00 | 131072 | 671346 | 75213632 | 14214287732135 | 14214287698384 | 14214288005425 | 14214288007249 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f998f711880 | 0x7f998ee25c40 | 131072 | 674930 | 75509048 | 14214288039908 | 14214288005425 | 14214288396306 | 14214288442140 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f998f711700 | 0x7f998ee25c80 | 131072 | 1029970 | 115296224 | 14214288462190 | 14214288396306 | 14214288724467 | 14214288726254 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f9991d71580 | 0x7f998ee25cc0 | 131072 | 689622 | 77318032 | 14214288758424 | 14214288724467 | 14214289091348 | 14214289093277 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f9991d71400 | 0x7f998ee25d00 | 65536 | 653952 | 73210432 | 14214289124956 | 14214289091348 | 14214289457428 | 14214289459189 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f9991d71280 | 0x7f998ee25d40 | 131072 | 664034 | 74329160 | 14214289491769 | 14214289457428 | 14214289782549 | 14214289784273 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f9991d71100 | 0x7f998ee25d80 | 131072 | 723092 | 81001144 | 14214289815602 | 14214289782549 | 14214290198870 | 14214290226853 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f998f711f80 | 0x7f998ee25dc0 | 131072 | 996022 | 111521184 | 14214290248013 | 14214290198870 | 14214290532151 | 14214290533977 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f998f711e00 | 0x7f998ee25e00 | 131072 | 682834 | 76427888 | 14214290565146 | 14214290532151 | 14214290907032 | 14214290952959 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f998f711c80 | 0x7f998ee25e40 | 65536 | 659022 | 73765544 | 14214290966218 | 14214290907032 | 14214291316633 | 14214291362350 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f998f711b00 | 0x7f998ee25e80 | 131072 | 664788 | 74456208 | 14214291374300 | 14214291316633 | 14214291697113 | 14214291698863 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f998f711980 | 0x7f998ee25ec0 | 131072 | 674382 | 75538512 | 14214291731313 | 14214291697113 | 14214292163354 | 14214292208873 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f998f711800 | 0x7f998ee25f00 | 131072 | 1017782 | 113921136 | 14214292229002 | 14214292163354 | 14214292527675 | 14214292529376 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f998f711680 | 0x7f998ee25f40 | 131072 | 986142 | 110382192 | 14214292562476 | 14214292527675 | 14214292919996 | 14214292962617 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f9991d71500 | 0x7f998ee25f80 | 65536 | 655824 | 73349264 | 14214292974077 | 14214292919996 | 14214293342717 | 14214293361119 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f9991d71380 | 0x7f998ee25fc0 | 131072 | 656764 | 73555248 | 14214293377019 | 14214293342717 | 14214293717438 | 14214293719382 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f9991d71200 | 0x7f998ee26000 | 131072 | 663396 | 74244552 | 14214293751291 | 14214293717438 | 14214294234399 | 14214294253601 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f9991d71080 | 0x7f998ee26040 | 131072 | 1019138 | 114184064 | 14214294276570 | 14214294234399 | 14214294598240 | 14214294600054 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f998f711f00 | 0x7f998ee26080 | 131072 | 1023494 | 114526928 | 14214294632653 | 14214294598240 | 14214295010881 | 14214295053365 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f998f711d80 | 0x7f998ee260c0 | 65536 | 655712 | 73528408 | 14214295066434 | 14214295010881 | 14214295452482 | 14214295494676 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f998f711c00 | 0x7f998ee26100 | 131072 | 669892 | 75092680 | 14214295506965 | 14214295452482 | 14214295878403 | 14214295920347 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f998f711a80 | 0x7f998ee26140 | 131072 | 678968 | 76001888 | 14214295932917 | 14214295878403 | 14214296483844 | 14214296526545 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f998f711900 | 0x7f998ee26180 | 131072 | 1026606 | 114962488 | 14214296545864 | 14214296483844 | 14214296882245 | 14214296884037 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f998f711780 | 0x7f998ee261c0 | 131072 | 1012822 | 113220592 | 14214296916657 | 14214296882245 | 14214297318086 | 14214297360368 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f998f711600 | 0x7f998ee26200 | 65536 | 658872 | 73829744 | 14214297372457 | 14214297318086 | 14214297783207 | 14214297801439 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f9991d71480 | 0x7f998ee26240 | 131072 | 681512 | 76287672 | 14214297818028 | 14214297783207 | 14214298208328 | 14214298256839 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f9991d71300 | 0x7f998ee26280 | 131072 | 1030716 | 115699504 | 14214298269799 | 14214298208328 | 14214298884330 | 14214298929006 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f9991d71180 | 0x7f998ee262c0 | 131072 | 1022286 | 114373656 | 14214298949165 | 14214298884330 | 14214299335211 | 14214299378356 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f9991d71000 | 0x7f998ee26300 | 131072 | 982320 | 109981832 | 14214299390416 | 14214299335211 | 14214299848172 | 14214299890096 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f998f711e80 | 0x7f998ee26340 | 65536 | 648336 | 72521416 | 14214299903746 | 14214299848172 | 14214300360173 | 14214300402545 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f998f711d00 | 0x7f998ee26380 | 131072 | 992336 | 111249128 | 14214300414705 | 14214300360173 | 14214300872014 | 14214300913215 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f998f711b80 | 0x7f998ee263c0 | 131072 | 1023794 | 114688224 | 14214300926385 | 14214300872014 | 14214301640496 | 14214301682359 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f998f711a00 | 0x7f998ee26400 | 131072 | 986102 | 110436928 | 14214301701639 | 14214301640496 | 14214302118737 | 14214302141840 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f998f711880 | 0x7f998ee26440 | 131072 | 1017496 | 114417400 | 14214302154330 | 14214302118737 | 14214302674258 | 14214302716968 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f998f711700 | 0x7f998ee26480 | 65536 | 656706 | 73649400 | 14214302729498 | 14214302674258 | 14214303244019 | 14214303285356 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f9991d71580 | 0x7f998ee264c0 | 131072 | 991660 | 111013080 | 14214303297866 | 14214303244019 | 14214303806581 | 14214303847075 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f9991d71400 | 0x7f998ee26500 | 131072 | 1025722 | 114555184 | 14214303859685 | 14214303806581 | 14214304676663 | 14214304718007 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f9991d71280 | 0x7f998ee26540 | 131072 | 1023618 | 114627208 | 14214304737807 | 14214304676663 | 14214305335864 | 14214305376563 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f9991d71100 | 0x7f998ee26580 | 131072 | 1017582 | 114017376 | 14214305388653 | 14214305335864 | 14214306008026 | 14214306024360 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f998f711f80 | 0x7f998ee265c0 | 65536 | 651150 | 72886696 | 14214306042450 | 14214306008026 | 14214306658747 | 14214306708256 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f998f711e00 | 0x7f998ee26600 | 131072 | 1029150 | 115382912 | 14214306720106 | 14214306658747 | 14214307337149 | 14214307381262 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f998f711c80 | 0x7f998ee26640 | 131072 | 1032734 | 115823304 | 14214307394132 | 14214307337008 | 14214308437970 | 14214308484410 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f998f711b00 | 0x7f998ee26680 | 131072 | 1024224 | 114752216 | 14214308504509 | 14214308437970 | 14214309534612 | 14214309575877 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f998f711980 | 0x7f998ee266c0 | 131072 | 1021236 | 114229048 | 14214309589057 | 14214309534612 | 14214310648054 | 14214310693084 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f998f711800 | 0x7f998ee26700 | 65536 | 646576 | 72467872 | 14214310705274 | 14214310648054 | 14214311759736 | 14214311804202 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f998f711680 | 0x7f998ee26740 | 131072 | 1025492 | 114701320 | 14214311817741 | 14214311759736 | 14214312848378 | 14214312893309 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f9991d71500 | 0x7f998ee26780 | 131072 | 1030016 | 115124752 | 14214312905809 | 14214312848378 | 14214314775742 | 14214314828650 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f9991d71380 | 0x7f998ee267c0 | 131072 | 1032718 | 115459776 | 14214314850049 | 14214314775742 | 14214316685346 | 14214316753011 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f9991d71200 | 0x7f998ee26800 | 131072 | 1028806 | 115245048 | 14214316764910 | 14214316685346 | 14214318661990 | 14214318735350 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f9991d71080 | 0x7f998ee26840 | 65536 | 653722 | 73189064 | 14214318747980 | 14214318661990 | 14214320641193 | 14214320705990 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f998f711f00 | 0x7f998ee26880 | 131072 | 1029700 | 115521320 | 14214320717780 | 14214320641193 | 14214322562797 | 14214322633650 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 21447 | 21447 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f998f711d80 | 0x7f998ee268c0 | 131072 | 1016644 | 113980256 | 14214322646540 | 14214322562797 | 14214326191124 | 14214326264276 |