38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 195958 | 195958 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f11ad604280 | 0 | 0 | 0 | 17144144393286 | 17143436477077 | 17144292173346 | 17144292290115 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 195958 | 195958 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f11ad623f80 | 0 | 0 | 0 | 17144297420544 | 17144292173346 | 17144297545660 | 17144297550290 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f11b0705380 | 0x7f11ad623fc0 | 0 | 0 | 0 | 17144297585079 | 17144297545660 | 17144297907260 | 17144297909620 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f11b0705200 | 0x7f11ad624000 | 0 | 0 | 0 | 17144297946799 | 17144297907260 | 17144298315420 | 17144298317709 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f11b0705080 | 0x7f11ad624040 | 0 | 0 | 0 | 17144298350208 | 17144298315420 | 17144298710299 | 17144298712388 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f11ae0d7f00 | 0x7f11ad624080 | 0 | 0 | 0 | 17144298745097 | 17144298710299 | 17144299014619 | 17144299016660 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f11ae0d7d80 | 0x7f11ad6240c0 | 0 | 0 | 0 | 17144299049429 | 17144299014619 | 17144299318459 | 17144299320511 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f11ae0d7c00 | 0x7f11ad624100 | 0 | 0 | 0 | 17144299363190 | 17144299318459 | 17144299620699 | 17144299622733 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f11ae0d7a80 | 0x7f11ad624140 | 0 | 0 | 0 | 17144299654492 | 17144299620699 | 17144300009658 | 17144300011772 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f11ae0d7900 | 0x7f11ad624180 | 0 | 0 | 0 | 17144300043421 | 17144300009658 | 17144300395418 | 17144300397681 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f11ae0d7780 | 0x7f11ad6241c0 | 0 | 0 | 0 | 17144300427501 | 17144300395418 | 17144300708698 | 17144300710943 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f11ae0d7600 | 0x7f11ad624200 | 0 | 0 | 0 | 17144300743822 | 17144300708698 | 17144301009177 | 17144301011354 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f11b0705480 | 0x7f11ad624240 | 0 | 0 | 0 | 17144301051033 | 17144301009177 | 17144301309657 | 17144301311826 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f11b0705300 | 0x7f11ad624280 | 0 | 0 | 0 | 17144301343785 | 17144301309657 | 17144301698617 | 17144301700675 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f11b0705180 | 0x7f11ad6242c0 | 0 | 0 | 0 | 17144301732335 | 17144301698617 | 17144302085977 | 17144302104004 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f11b0705000 | 0x7f11ad624300 | 0 | 0 | 0 | 17144302121174 | 17144302085977 | 17144302400856 | 17144302402946 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f11ae0d7e80 | 0x7f11ad624340 | 0 | 0 | 0 | 17144302435305 | 17144302400856 | 17144302697976 | 17144302700068 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f11ae0d7d00 | 0x7f11ad624380 | 0 | 0 | 0 | 17144302738797 | 17144302697976 | 17144302997976 | 17144303000269 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f11ae0d7b80 | 0x7f11ad6243c0 | 0 | 0 | 0 | 17144303030669 | 17144302997976 | 17144303388376 | 17144303390259 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f11ae0d7a00 | 0x7f11ad624400 | 0 | 0 | 0 | 17144303421908 | 17144303388376 | 17144303749495 | 17144303751219 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f11ae0d7880 | 0x7f11ad624440 | 0 | 0 | 0 | 17144303781928 | 17144303749495 | 17144304025975 | 17144304027501 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f11ae0d7700 | 0x7f11ad624480 | 0 | 0 | 0 | 17144304059140 | 17144304025975 | 17144304297815 | 17144304299303 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f11b0705580 | 0x7f11ad6244c0 | 0 | 0 | 0 | 17144304337932 | 17144304297815 | 17144304569655 | 17144304571146 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f11b0705400 | 0x7f11ad624500 | 0 | 0 | 0 | 17144304602975 | 17144304569655 | 17144304930774 | 17144304932396 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f11b0705280 | 0x7f11ad624540 | 0 | 0 | 0 | 17144304963265 | 17144304930774 | 17144305290294 | 17144305291996 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f11b0705100 | 0x7f11ad624580 | 0 | 0 | 0 | 17144305323855 | 17144305290294 | 17144305560854 | 17144305562328 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f11ae0d7f80 | 0x7f11ad6245c0 | 0 | 0 | 0 | 17144305593648 | 17144305560854 | 17144305831734 | 17144305833381 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f11ae0d7e00 | 0x7f11ad624600 | 0 | 0 | 0 | 17144305871700 | 17144305831734 | 17144306102133 | 17144306103894 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f11ae0d7c80 | 0x7f11ad624640 | 0 | 0 | 0 | 17144306135353 | 17144306102133 | 17144306464853 | 17144306466403 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f11ae0d7b00 | 0x7f11ad624680 | 0 | 0 | 0 | 17144306497453 | 17144306464853 | 17144306826133 | 17144306827723 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f11ae0d7980 | 0x7f11ad6246c0 | 0 | 0 | 0 | 17144306858933 | 17144306826133 | 17144307102773 | 17144307104686 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f11ae0d7800 | 0x7f11ad624700 | 0 | 0 | 0 | 17144307134855 | 17144307102773 | 17144307374772 | 17144307376318 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f11ae0d7680 | 0x7f11ad624740 | 0 | 0 | 0 | 17144307414777 | 17144307374772 | 17144307647092 | 17144307648581 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f11b0705500 | 0x7f11ad624780 | 0 | 0 | 0 | 17144307679620 | 17144307647092 | 17144308016052 | 17144308017621 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f11b0705380 | 0x7f11ad6247c0 | 0 | 0 | 0 | 17144308048810 | 17144308016052 | 17144308377012 | 17144308378561 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f11b0705200 | 0x7f11ad624800 | 0 | 0 | 0 | 17144308409660 | 17144308377012 | 17144308651731 | 17144308653273 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f11b0705080 | 0x7f11ad624840 | 0 | 0 | 0 | 17144308685092 | 17144308651731 | 17144308925171 | 17144308926675 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f11ae0d7f00 | 0x7f11ad624880 | 0 | 0 | 0 | 17144308964874 | 17144308925171 | 17144309196051 | 17144309197488 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f11ae0d7d80 | 0x7f11ad6248c0 | 0 | 0 | 0 | 17144309228567 | 17144309196051 | 17144309555571 | 17144309557118 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f11ae0d7c00 | 0x7f11ad624900 | 0 | 0 | 0 | 17144309590507 | 17144309555571 | 17144309920850 | 17144309922408 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f11ae0d7a80 | 0x7f11ad624940 | 0 | 0 | 0 | 17144309953837 | 17144309920850 | 17144310209330 | 17144310211180 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f11ae0d7900 | 0x7f11ad624980 | 0 | 0 | 0 | 17144310243739 | 17144310209330 | 17144310485170 | 17144310486732 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f11ae0d7780 | 0x7f11ad6249c0 | 0 | 0 | 0 | 17144310525581 | 17144310485170 | 17144310757170 | 17144310758645 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f11ae0d7600 | 0x7f11ad624a00 | 0 | 0 | 0 | 17144310790664 | 17144310757170 | 17144311115569 | 17144311117055 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f11b0705480 | 0x7f11ad624a40 | 0 | 0 | 0 | 17144311149024 | 17144311115569 | 17144311472209 | 17144311473825 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f11b0705300 | 0x7f11ad624a80 | 0 | 0 | 0 | 17144311505104 | 17144311472209 | 17144311744049 | 17144311745497 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f11b0705180 | 0x7f11ad624ac0 | 0 | 0 | 0 | 17144311777196 | 17144311744049 | 17144312016049 | 17144312017660 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f11b0705000 | 0x7f11ad624b00 | 0 | 0 | 0 | 17144312056539 | 17144312016049 | 17144312287728 | 17144312289192 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f11ae0d7e80 | 0x7f11ad624b40 | 0 | 0 | 0 | 17144312321741 | 17144312287728 | 17144312648208 | 17144312649632 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f11ae0d7d00 | 0x7f11ad624b80 | 0 | 0 | 0 | 17144312680731 | 17144312648208 | 17144313009648 | 17144313011202 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f11ae0d7b80 | 0x7f11ad624bc0 | 0 | 0 | 0 | 17144313040951 | 17144313009648 | 17144313281968 | 17144313283425 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f11ae0d7a00 | 0x7f11ad624c00 | 0 | 0 | 0 | 17144313314684 | 17144313281968 | 17144313555567 | 17144313557147 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f11ae0d7880 | 0x7f11ad624c40 | 0 | 0 | 0 | 17144313595136 | 17144313555567 | 17144313829167 | 17144313830680 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f11ae0d7700 | 0x7f11ad624c80 | 0 | 0 | 0 | 17144313862489 | 17144313829167 | 17144314186287 | 17144314188210 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f11b0705580 | 0x7f11ad624cc0 | 0 | 0 | 0 | 17144314220379 | 17144314186287 | 17144314551087 | 17144314552560 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f11b0705400 | 0x7f11ad624d00 | 0 | 0 | 0 | 17144314584249 | 17144314551087 | 17144314822126 | 17144314823632 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f11b0705280 | 0x7f11ad624d40 | 0 | 0 | 0 | 17144314855261 | 17144314822126 | 17144315099886 | 17144315101414 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f11b0705100 | 0x7f11ad624d80 | 0 | 0 | 0 | 17144315140293 | 17144315099886 | 17144315376846 | 17144315378317 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f11ae0d7f80 | 0x7f11ad624dc0 | 0 | 0 | 0 | 17144315410216 | 17144315376846 | 17144315738446 | 17144315740037 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f11ae0d7e00 | 0x7f11ad624e00 | 0 | 0 | 0 | 17144315770536 | 17144315738446 | 17144316097165 | 17144316098777 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f11ae0d7c80 | 0x7f11ad624e40 | 0 | 0 | 0 | 17144316130176 | 17144316097165 | 17144316374925 | 17144316376479 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f11ae0d7b00 | 0x7f11ad624e80 | 0 | 0 | 0 | 17144316407918 | 17144316374925 | 17144316658445 | 17144316660041 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f11ae0d7980 | 0x7f11ad624ec0 | 0 | 0 | 0 | 17144316697790 | 17144316658445 | 17144316931725 | 17144316933364 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f11ae0d7800 | 0x7f11ad624f00 | 0 | 0 | 0 | 17144316964153 | 17144316931725 | 17144317291084 | 17144317292724 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f11ae0d7680 | 0x7f11ad624f40 | 0 | 0 | 0 | 17144317323653 | 17144317291084 | 17144317650284 | 17144317651774 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f11b0705500 | 0x7f11ad624f80 | 0 | 0 | 0 | 17144317682103 | 17144317650284 | 17144317920524 | 17144317922036 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f11b0705380 | 0x7f11ad624fc0 | 0 | 0 | 0 | 17144317953145 | 17144317920524 | 17144318211564 | 17144318213408 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f11b0705200 | 0x7f11ad625000 | 0 | 0 | 0 | 17144318252557 | 17144318211564 | 17144318488523 | 17144318490231 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f11b0705080 | 0x7f11ad625040 | 0 | 0 | 0 | 17144318522270 | 17144318488523 | 17144318852683 | 17144318854231 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f11ae0d7f00 | 0x7f11ad625080 | 0 | 0 | 0 | 17144318886030 | 17144318852683 | 17144319215723 | 17144319217271 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f11ae0d7d80 | 0x7f11ad6250c0 | 0 | 0 | 0 | 17144319249200 | 17144319215723 | 17144319488203 | 17144319489833 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f11ae0d7c00 | 0x7f11ad625100 | 0 | 0 | 0 | 17144319520562 | 17144319488203 | 17144319778762 | 17144319780345 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f11ae0d7a80 | 0x7f11ad625140 | 0 | 0 | 0 | 17144319830444 | 17144319778762 | 17144320055402 | 17144320057067 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f11ae0d7900 | 0x7f11ad625180 | 0 | 0 | 0 | 17144320087716 | 17144320055402 | 17144320421482 | 17144320423017 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f11ae0d7780 | 0x7f11ad6251c0 | 0 | 0 | 0 | 17144320454476 | 17144320421482 | 17144320780361 | 17144320781827 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f11ae0d7600 | 0x7f11ad625200 | 0 | 0 | 0 | 17144320812536 | 17144320780361 | 17144321059241 | 17144321060779 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f11b0705480 | 0x7f11ad625240 | 0 | 0 | 0 | 17144321091999 | 17144321059241 | 17144321358121 | 17144321359661 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f11b0705300 | 0x7f11ad625280 | 0 | 0 | 0 | 17144321397880 | 17144321358121 | 17144321637001 | 17144321638523 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f11b0705180 | 0x7f11ad6252c0 | 0 | 0 | 0 | 17144321668743 | 17144321637001 | 17144321996680 | 17144321998134 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f11b0705000 | 0x7f11ad625300 | 0 | 0 | 0 | 17144322029573 | 17144321996680 | 17144322380200 | 17144322381793 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f11ae0d7e80 | 0x7f11ad625340 | 0 | 0 | 0 | 17144322413552 | 17144322380200 | 17144322654120 | 17144322655625 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f11ae0d7d00 | 0x7f11ad625380 | 0 | 0 | 0 | 17144322686495 | 17144322654120 | 17144322959880 | 17144322961467 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f11ae0d7b80 | 0x7f11ad6253c0 | 0 | 0 | 0 | 17144322999876 | 17144322959880 | 17144323232680 | 17144323234260 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f11ae0d7a00 | 0x7f11ad625400 | 0 | 0 | 0 | 17144323266359 | 17144323232680 | 17144323592999 | 17144323594530 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f11ae0d7880 | 0x7f11ad625440 | 0 | 0 | 0 | 17144323626659 | 17144323592999 | 17144323949319 | 17144323950890 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f11ae0d7700 | 0x7f11ad625480 | 0 | 0 | 0 | 17144323981389 | 17144323949319 | 17144324223239 | 17144324224842 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f11b0705580 | 0x7f11ad6254c0 | 0 | 0 | 0 | 17144324256051 | 17144324223239 | 17144324534598 | 17144324536254 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f11b0705400 | 0x7f11ad625500 | 0 | 0 | 0 | 17144324575023 | 17144324534598 | 17144324811238 | 17144324812946 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f11b0705280 | 0x7f11ad625540 | 0 | 0 | 0 | 17144324844405 | 17144324811238 | 17144325167718 | 17144325169226 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f11b0705100 | 0x7f11ad625580 | 0 | 0 | 0 | 17144325200725 | 17144325167718 | 17144325524518 | 17144325526066 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f11ae0d7f80 | 0x7f11ad6255c0 | 0 | 0 | 0 | 17144325556966 | 17144325524518 | 17144325801317 | 17144325802859 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f11ae0d7e00 | 0x7f11ad625600 | 0 | 0 | 0 | 17144325834778 | 17144325801317 | 17144326119237 | 17144326120790 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f11ae0d7c80 | 0x7f11ad625640 | 0 | 0 | 0 | 17144326159429 | 17144326119237 | 17144326394597 | 17144326396202 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f11ae0d7b00 | 0x7f11ad625680 | 0 | 0 | 0 | 17144326427022 | 17144326394597 | 17144326756197 | 17144326757662 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f11ae0d7980 | 0x7f11ad6256c0 | 0 | 0 | 0 | 17144326788402 | 17144326756197 | 17144327115396 | 17144327116973 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f11ae0d7800 | 0x7f11ad625700 | 0 | 0 | 0 | 17144327148382 | 17144327115396 | 17144327388516 | 17144327390165 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f11ae0d7680 | 0x7f11ad625740 | 0 | 0 | 0 | 17144327421924 | 17144327388516 | 17144327716196 | 17144327717826 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f11b0705500 | 0x7f11ad625780 | 0 | 0 | 0 | 17144327755815 | 17144327716196 | 17144327989796 | 17144327991448 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f11b0705380 | 0x7f11ad6257c0 | 0 | 0 | 0 | 17144328022437 | 17144327989796 | 17144328347715 | 17144328349218 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f11b0705200 | 0x7f11ad625800 | 0 | 0 | 0 | 17144328381098 | 17144328347715 | 17144328704675 | 17144328706109 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f11b0705080 | 0x7f11ad625840 | 0 | 0 | 0 | 17144328737138 | 17144328704675 | 17144328981795 | 17144328983411 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f11ae0d7f00 | 0x7f11ad625880 | 0 | 0 | 0 | 17144329015060 | 17144328981795 | 17144329315075 | 17144329316582 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f11ae0d7d80 | 0x7f11ad6258c0 | 0 | 0 | 0 | 17144329354851 | 17144329315075 | 17144329588354 | 17144329589894 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f11ae0d7c00 | 0x7f11ad625900 | 0 | 0 | 0 | 17144329620413 | 17144329588354 | 17144329946434 | 17144329948024 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f11ae0d7a80 | 0x7f11ad625940 | 0 | 0 | 0 | 17144329978693 | 17144329946434 | 17144330313634 | 17144330315514 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f11ae0d7900 | 0x7f11ad625980 | 0 | 0 | 0 | 17144330345973 | 17144330313634 | 17144330601634 | 17144330603236 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f11ae0d7780 | 0x7f11ad6259c0 | 0 | 0 | 0 | 17144330633255 | 17144330601634 | 17144330956513 | 17144330958066 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f11ae0d7600 | 0x7f11ad625a00 | 0 | 0 | 0 | 17144330996505 | 17144330956513 | 17144331232673 | 17144331234229 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f11b0705480 | 0x7f11ad625a40 | 0 | 0 | 0 | 17144331266768 | 17144331232673 | 17144331592513 | 17144331594139 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f11b0705300 | 0x7f11ad625a80 | 0 | 0 | 0 | 17144331625198 | 17144331592513 | 17144331950432 | 17144331951899 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f11b0705180 | 0x7f11ad625ac0 | 0 | 0 | 0 | 17144331984048 | 17144331950432 | 17144332241792 | 17144332243411 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f11b0705000 | 0x7f11ad625b00 | 0 | 0 | 0 | 17144332274980 | 17144332241792 | 17144332602112 | 17144332603701 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f11ae0d7e80 | 0x7f11ad625b40 | 0 | 0 | 0 | 17144332642110 | 17144332602112 | 17144332881792 | 17144332883233 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f11ae0d7d00 | 0x7f11ad625b80 | 0 | 0 | 0 | 17144332913862 | 17144332881792 | 17144333243551 | 17144333245233 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f11ae0d7b80 | 0x7f11ad625bc0 | 0 | 0 | 0 | 17144333275832 | 17144333243551 | 17144333604511 | 17144333605993 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f11ae0d7a00 | 0x7f11ad625c00 | 0 | 0 | 0 | 17144333637512 | 17144333604511 | 17144333910591 | 17144333912184 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f11ae0d7880 | 0x7f11ad625c40 | 0 | 0 | 0 | 17144333943544 | 17144333910591 | 17144334304511 | 17144334328113 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f11ae0d7700 | 0x7f11ad625c80 | 0 | 0 | 0 | 17144334348352 | 17144334304511 | 17144334617310 | 17144334618855 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f11b0705580 | 0x7f11ad625cc0 | 0 | 0 | 0 | 17144334650624 | 17144334617310 | 17144334984830 | 17144334986355 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f11b0705400 | 0x7f11ad625d00 | 0 | 0 | 0 | 17144335017644 | 17144334984830 | 17144335346270 | 17144335347705 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f11b0705280 | 0x7f11ad625d40 | 0 | 0 | 0 | 17144335378524 | 17144335346270 | 17144335660509 | 17144335661966 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f11b0705100 | 0x7f11ad625d80 | 0 | 0 | 0 | 17144335693065 | 17144335660509 | 17144336074109 | 17144336095794 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f11ae0d7f80 | 0x7f11ad625dc0 | 0 | 0 | 0 | 17144336114313 | 17144336074109 | 17144336390749 | 17144336392336 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f11ae0d7e00 | 0x7f11ad625e00 | 0 | 0 | 0 | 17144336422375 | 17144336390749 | 17144336762749 | 17144336764305 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f11ae0d7c80 | 0x7f11ad625e40 | 0 | 0 | 0 | 17144336795155 | 17144336762749 | 17144337138268 | 17144337140065 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f11ae0d7b00 | 0x7f11ad625e80 | 0 | 0 | 0 | 17144337170214 | 17144337138268 | 17144337491548 | 17144337493065 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f11ae0d7980 | 0x7f11ad625ec0 | 0 | 0 | 0 | 17144337523754 | 17144337491548 | 17144337958108 | 17144337975522 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f11ae0d7800 | 0x7f11ad625f00 | 0 | 0 | 0 | 17144337998461 | 17144337958108 | 17144338302587 | 17144338304083 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f11ae0d7680 | 0x7f11ad625f40 | 0 | 0 | 0 | 17144338336722 | 17144338302587 | 17144338699707 | 17144338721681 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f11b0705500 | 0x7f11ad625f80 | 0 | 0 | 0 | 17144338733421 | 17144338699707 | 17144339096987 | 17144339118240 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f11b0705380 | 0x7f11ad625fc0 | 0 | 0 | 0 | 17144339128750 | 17144339096987 | 17144339477786 | 17144339479310 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f11b0705200 | 0x7f11ad626000 | 0 | 0 | 0 | 17144339510759 | 17144339477786 | 17144339992026 | 17144340013995 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f11b0705080 | 0x7f11ad626040 | 0 | 0 | 0 | 17144340032875 | 17144339992026 | 17144340350106 | 17144340351566 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f11ae0d7f00 | 0x7f11ad626080 | 0 | 0 | 0 | 17144340382445 | 17144340350106 | 17144340763225 | 17144340780054 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f11ae0d7d80 | 0x7f11ad6260c0 | 0 | 0 | 0 | 17144340794484 | 17144340763225 | 17144341185625 | 17144341202933 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f11ae0d7c00 | 0x7f11ad626100 | 0 | 0 | 0 | 17144341217222 | 17144341185625 | 17144341582105 | 17144341598922 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f11ae0d7a80 | 0x7f11ad626140 | 0 | 0 | 0 | 17144341615381 | 17144341582105 | 17144342150584 | 17144342179006 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f11ae0d7900 | 0x7f11ad626180 | 0 | 0 | 0 | 17144342197985 | 17144342150584 | 17144342538104 | 17144342539656 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f11ae0d7780 | 0x7f11ad6261c0 | 0 | 0 | 0 | 17144342569635 | 17144342538104 | 17144342968824 | 17144342986763 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f11ae0d7600 | 0x7f11ad626200 | 0 | 0 | 0 | 17144343000583 | 17144342968824 | 17144343402743 | 17144343419661 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f11b0705480 | 0x7f11ad626240 | 0 | 0 | 0 | 17144343435851 | 17144343402743 | 17144343826423 | 17144343842830 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f11b0705300 | 0x7f11ad626280 | 0 | 0 | 0 | 17144343858799 | 17144343826423 | 17144344462262 | 17144344479342 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f11b0705180 | 0x7f11ad6262c0 | 0 | 0 | 0 | 17144344502631 | 17144344462262 | 17144344872982 | 17144344889571 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f11b0705000 | 0x7f11ad626300 | 0 | 0 | 0 | 17144344907420 | 17144344872982 | 17144345356022 | 17144345372207 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f11ae0d7e80 | 0x7f11ad626340 | 0 | 0 | 0 | 17144345388727 | 17144345356022 | 17144345842901 | 17144345859464 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f11ae0d7d00 | 0x7f11ad626380 | 0 | 0 | 0 | 17144345873903 | 17144345842901 | 17144346322901 | 17144346344270 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f11ae0d7b80 | 0x7f11ad6263c0 | 0 | 0 | 0 | 17144346355030 | 17144346322901 | 17144347072500 | 17144347089110 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f11ae0d7a00 | 0x7f11ad626400 | 0 | 0 | 0 | 17144347112169 | 17144347072500 | 17144347521460 | 17144347537597 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f11ae0d7880 | 0x7f11ad626440 | 0 | 0 | 0 | 17144347553517 | 17144347521460 | 17144348052339 | 17144348068833 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f11ae0d7700 | 0x7f11ad626480 | 0 | 0 | 0 | 17144348085202 | 17144348052339 | 17144348592179 | 17144348609938 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f11b0705580 | 0x7f11ad6264c0 | 0 | 0 | 0 | 17144348624137 | 17144348592179 | 17144349123219 | 17144349140053 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f11b0705400 | 0x7f11ad626500 | 0 | 0 | 0 | 17144349156012 | 17144349123219 | 17144349963058 | 17144349979840 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f11b0705280 | 0x7f11ad626540 | 0 | 0 | 0 | 17144350003609 | 17144349963058 | 17144350604977 | 17144350632792 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f11b0705100 | 0x7f11ad626580 | 0 | 0 | 0 | 17144350643321 | 17144350604977 | 17144351265137 | 17144351308343 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f11ae0d7f80 | 0x7f11ad6265c0 | 0 | 0 | 0 | 17144351319853 | 17144351265137 | 17144351938896 | 17144351980915 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f11ae0d7e00 | 0x7f11ad626600 | 0 | 0 | 0 | 17144351991334 | 17144351938896 | 17144352601296 | 17144352643356 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f11ae0d7c80 | 0x7f11ad626640 | 0 | 0 | 0 | 17144352654136 | 17144352601296 | 17144353679215 | 17144353721097 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f11ae0d7b00 | 0x7f11ad626680 | 0 | 0 | 0 | 17144353739706 | 17144353679215 | 17144354741614 | 17144354789927 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f11ae0d7980 | 0x7f11ad6266c0 | 0 | 0 | 0 | 17144354801267 | 17144354741366 | 17144355843763 | 17144355910426 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f11ae0d7800 | 0x7f11ad626700 | 0 | 0 | 0 | 17144355921196 | 17144355843763 | 17144356977682 | 17144357042015 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f11ae0d7680 | 0x7f11ad626740 | 0 | 0 | 0 | 17144357053254 | 17144356977682 | 17144358084560 | 17144358138664 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f11b0705500 | 0x7f11ad626780 | 0 | 0 | 0 | 17144358150894 | 17144358084560 | 17144360022478 | 17144360089370 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f11b0705380 | 0x7f11ad6267c0 | 0 | 0 | 0 | 17144360108380 | 17144360022478 | 17144361937355 | 17144362003947 |
| 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 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f11b0705200 | 0x7f11ad626800 | 0 | 0 | 0 | 17144362015037 | 17144361937355 | 17144363922633 | 17144364000002 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f11b0705080 | 0x7f11ad626840 | 0 | 0 | 0 | 17144364010742 | 17144363922633 | 17144365900230 | 17144365966758 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f11ae0d7f00 | 0x7f11ad626880 | 0 | 0 | 0 | 17144365978427 | 17144365900230 | 17144367831588 | 17144367902514 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 195958 | 195958 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f11ae0d7d80 | 0x7f11ad6268c0 | 0 | 0 | 0 | 17144367913334 | 17144367831588 | 17144371446143 | 17144371522054 |