41 KiB
41 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 | 217617 | 217617 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f3416804280 | 3670016 | 2900946 | 325288488 | 17519240137891 | 17514040785310 | 17519383484057 | 17519383597957 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 217617 | 217617 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f3416823f80 | 512 | 97956 | 10984232 | 17519388715876 | 17519383484057 | 17519388846306 | 17519388850993 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f3419866380 | 0x7f3416823fc0 | 65536 | 605048 | 67828144 | 17519388884212 | 17519388846306 | 17519389210147 | 17519389212713 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f3419866200 | 0x7f3416824000 | 65536 | 686236 | 76949536 | 17519389249102 | 17519389210147 | 17519389608227 | 17519389610593 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f3419866080 | 0x7f3416824040 | 65536 | 635554 | 71155528 | 17519389641402 | 17519389608227 | 17519389997188 | 17519389999463 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f3417209f00 | 0x7f3416824080 | 65536 | 637536 | 71278024 | 17519390033332 | 17519389997188 | 17519390310629 | 17519390312745 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f3417209d80 | 0x7f34168240c0 | 65536 | 635118 | 71214864 | 17519390344044 | 17519390310629 | 17519390617189 | 17519390619397 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f3417209c00 | 0x7f3416824100 | 131072 | 678968 | 76032888 | 17519390663476 | 17519390617189 | 17519390913190 | 17519390915630 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f3417209a80 | 0x7f3416824140 | 131072 | 686124 | 76875024 | 17519390946949 | 17519390913190 | 17519391303270 | 17519391305680 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f3417209900 | 0x7f3416824180 | 65536 | 653424 | 73416896 | 17519391336179 | 17519391303270 | 17519391692391 | 17519391694560 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f3417209780 | 0x7f34168241c0 | 131072 | 679078 | 76050280 | 17519391724579 | 17519391692391 | 17519392006632 | 17519392008991 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f3417209600 | 0x7f3416824200 | 131072 | 678280 | 75908840 | 17519392040091 | 17519392006632 | 17519392306472 | 17519392308514 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f3419866480 | 0x7f3416824240 | 131072 | 684192 | 76557048 | 17519392347493 | 17519392306472 | 17519392606633 | 17519392608966 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f3419866300 | 0x7f3416824280 | 131072 | 675864 | 75682072 | 17519392640885 | 17519392606633 | 17519392994953 | 17519392997086 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f3419866180 | 0x7f34168242c0 | 65536 | 642208 | 71959256 | 17519393028065 | 17519392994953 | 17519393381514 | 17519393383686 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f3419866000 | 0x7f3416824300 | 131072 | 684260 | 76650992 | 17519393415325 | 17519393381514 | 17519393679115 | 17519393681239 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f3417209e80 | 0x7f3416824340 | 131072 | 717832 | 80234512 | 17519393711478 | 17519393679115 | 17519393975275 | 17519393977471 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f3417209d00 | 0x7f3416824380 | 131072 | 672948 | 75432200 | 17519394016130 | 17519393975275 | 17519394299436 | 17519394301893 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f3417209b80 | 0x7f34168243c0 | 131072 | 679398 | 76146584 | 17519394333032 | 17519394299436 | 17519394691276 | 17519394693383 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f3417209a00 | 0x7f3416824400 | 65536 | 612200 | 68554528 | 17519394724472 | 17519394691276 | 17519395084717 | 17519395086382 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f3417209880 | 0x7f3416824440 | 131072 | 679344 | 76168744 | 17519395116292 | 17519395084717 | 17519395366798 | 17519395368375 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f3417209700 | 0x7f3416824480 | 131072 | 674324 | 75630048 | 17519395399244 | 17519395366798 | 17519395636398 | 17519395638108 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f3419866580 | 0x7f34168244c0 | 131072 | 639414 | 71604664 | 17519395675417 | 17519395636398 | 17519395910159 | 17519395911711 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f3419866400 | 0x7f3416824500 | 131072 | 678208 | 76071328 | 17519395944420 | 17519395910159 | 17519396273999 | 17519396275562 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f3419866280 | 0x7f3416824540 | 65536 | 636568 | 71392280 | 17519396306091 | 17519396273999 | 17519396627440 | 17519396628993 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f3419866100 | 0x7f3416824580 | 131072 | 640370 | 71712240 | 17519396659872 | 17519396627440 | 17519396898160 | 17519396899706 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f3417209f80 | 0x7f34168245c0 | 131072 | 645658 | 72179560 | 17519396930985 | 17519396898160 | 17519397167761 | 17519397169349 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f3417209e00 | 0x7f3416824600 | 131072 | 681986 | 76382616 | 17519397207478 | 17519397167761 | 17519397436721 | 17519397438432 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f3417209c80 | 0x7f3416824640 | 131072 | 642122 | 72003920 | 17519397470001 | 17519397436721 | 17519397792082 | 17519397793693 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f3417209b00 | 0x7f3416824680 | 65536 | 636186 | 71267112 | 17519397824442 | 17519397792082 | 17519398154483 | 17519398156394 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f3417209980 | 0x7f34168246c0 | 131072 | 680290 | 76248008 | 17519398187753 | 17519398154483 | 17519398436243 | 17519398437926 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f3417209800 | 0x7f3416824700 | 131072 | 678234 | 75949256 | 17519398468886 | 17519398436243 | 17519398704564 | 17519398706140 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f3417209680 | 0x7f3416824740 | 131072 | 667486 | 74728136 | 17519398743709 | 17519398704564 | 17519398975124 | 17519398976613 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f3419866500 | 0x7f3416824780 | 131072 | 633924 | 71100144 | 17519399007392 | 17519398975124 | 17519399331285 | 17519399332903 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f3419866380 | 0x7f34168247c0 | 65536 | 642598 | 72062176 | 17519399364613 | 17519399331285 | 17519399689846 | 17519399691474 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f3419866200 | 0x7f3416824800 | 131072 | 711818 | 79728168 | 17519399722473 | 17519399689846 | 17519399959126 | 17519399960817 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f3419866080 | 0x7f3416824840 | 131072 | 682054 | 76326256 | 17519399991986 | 17519399959126 | 17519400229686 | 17519400231380 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f3417209f00 | 0x7f3416824880 | 131072 | 686338 | 76858120 | 17519400269679 | 17519400229686 | 17519400504887 | 17519400506423 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f3417209d80 | 0x7f34168248c0 | 131072 | 685550 | 76655032 | 17519400537592 | 17519400504887 | 17519400871288 | 17519400872844 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f3417209c00 | 0x7f3416824900 | 65536 | 603986 | 67697008 | 17519400904323 | 17519400871288 | 17519401226328 | 17519401227955 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f3417209a80 | 0x7f3416824940 | 131072 | 670882 | 75159416 | 17519401258424 | 17519401226328 | 17519401496889 | 17519401498618 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f3417209900 | 0x7f3416824980 | 131072 | 683226 | 76535920 | 17519401528577 | 17519401496889 | 17519401767769 | 17519401769271 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f3417209780 | 0x7f34168249c0 | 131072 | 676948 | 75933960 | 17519401806360 | 17519401767769 | 17519402036250 | 17519402037764 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f3417209600 | 0x7f3416824a00 | 131072 | 671190 | 75274704 | 17519402068143 | 17519402036250 | 17519402412570 | 17519402414194 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f3419866480 | 0x7f3416824a40 | 65536 | 633458 | 71005344 | 17519402445703 | 17519402412570 | 17519402767771 | 17519402769285 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f3419866300 | 0x7f3416824a80 | 131072 | 644288 | 72117032 | 17519402799814 | 17519402767771 | 17519403034972 | 17519403036578 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f3419866180 | 0x7f3416824ac0 | 131072 | 642102 | 72002928 | 17519403067518 | 17519403034972 | 17519403304892 | 17519403306521 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f3419866000 | 0x7f3416824b00 | 131072 | 639388 | 71637368 | 17519403345470 | 17519403304892 | 17519403585373 | 17519403586864 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f3417209e80 | 0x7f3416824b40 | 131072 | 680836 | 76384784 | 17519403617283 | 17519403585373 | 17519403940573 | 17519403942085 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f3417209d00 | 0x7f3416824b80 | 65536 | 637602 | 71455032 | 17519403973284 | 17519403940573 | 17519404299774 | 17519404301386 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f3417209b80 | 0x7f3416824bc0 | 131072 | 685080 | 76685832 | 17519404331395 | 17519404299774 | 17519404572094 | 17519404573599 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f3417209a00 | 0x7f3416824c00 | 131072 | 670980 | 75106040 | 17519404605058 | 17519404572094 | 17519404845695 | 17519404847242 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f3417209880 | 0x7f3416824c40 | 131072 | 694290 | 77811768 | 17519404884941 | 17519404845695 | 17519405116575 | 17519405118095 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f3417209700 | 0x7f3416824c80 | 131072 | 641310 | 71862008 | 17519405148644 | 17519405116575 | 17519405472896 | 17519405474556 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f3419866580 | 0x7f3416824cc0 | 65536 | 632512 | 70840912 | 17519405505165 | 17519405472896 | 17519405829697 | 17519405831397 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f3419866400 | 0x7f3416824d00 | 131072 | 669926 | 74991280 | 17519405862546 | 17519405829697 | 17519406097857 | 17519406099650 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f3419866280 | 0x7f3416824d40 | 131072 | 676138 | 75645168 | 17519406131579 | 17519406097857 | 17519406381218 | 17519406382842 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f3419866100 | 0x7f3416824d80 | 131072 | 677822 | 75981696 | 17519406421241 | 17519406381218 | 17519406652738 | 17519406654215 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f3417209f80 | 0x7f3416824dc0 | 131072 | 636164 | 71344464 | 17519406685055 | 17519406652738 | 17519407009859 | 17519407011416 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f3417209e00 | 0x7f3416824e00 | 65536 | 606190 | 67901408 | 17519407042235 | 17519407009859 | 17519407365379 | 17519407366787 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f3417209c80 | 0x7f3416824e40 | 131072 | 688256 | 76998752 | 17519407397006 | 17519407365379 | 17519407636580 | 17519407638220 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f3417209b00 | 0x7f3416824e80 | 131072 | 681218 | 76292896 | 17519407669009 | 17519407636580 | 17519407916900 | 17519407918383 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f3417209980 | 0x7f3416824ec0 | 131072 | 645852 | 72455176 | 17519407956082 | 17519407916900 | 17519408195461 | 17519408197016 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f3417209800 | 0x7f3416824f00 | 131072 | 683428 | 76596840 | 17519408227525 | 17519408195461 | 17519408554341 | 17519408556057 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f3417209680 | 0x7f3416824f40 | 65536 | 683556 | 76494504 | 17519408586076 | 17519408554341 | 17519408911942 | 17519408913437 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f3419866500 | 0x7f3416824f80 | 131072 | 640004 | 71710880 | 17519408943757 | 17519408911942 | 17519409189063 | 17519409190870 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f3419866380 | 0x7f3416824fc0 | 131072 | 640254 | 71644880 | 17519409221049 | 17519409189063 | 17519409473703 | 17519409475383 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f3419866200 | 0x7f3416825000 | 131072 | 675692 | 75693640 | 17519409513862 | 17519409473703 | 17519409750344 | 17519409751786 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f3419866080 | 0x7f3416825040 | 131072 | 680810 | 76218824 | 17519409782585 | 17519409750344 | 17519410106504 | 17519410108497 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f3417209f00 | 0x7f3416825080 | 65536 | 702082 | 78686896 | 17519410140316 | 17519410106504 | 17519410469065 | 17519410470807 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f3417209d80 | 0x7f34168250c0 | 131072 | 685450 | 76757016 | 17519410501217 | 17519410469065 | 17519410739465 | 17519410741070 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f3417209c00 | 0x7f3416825100 | 131072 | 680300 | 76140280 | 17519410771220 | 17519410739465 | 17519411030826 | 17519411032423 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f3417209a80 | 0x7f3416825140 | 131072 | 678520 | 76070080 | 17519411083592 | 17519411030826 | 17519411306986 | 17519411308596 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f3417209900 | 0x7f3416825180 | 131072 | 680952 | 76289664 | 17519411339285 | 17519411306986 | 17519411666187 | 17519411667857 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f3417209780 | 0x7f34168251c0 | 65536 | 644418 | 72182360 | 17519411698866 | 17519411666187 | 17519412026508 | 17519412028287 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f3417209600 | 0x7f3416825200 | 131072 | 670870 | 75216496 | 17519412058987 | 17519412026508 | 17519412299468 | 17519412301080 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f3419866480 | 0x7f3416825240 | 131072 | 676612 | 75772744 | 17519412331300 | 17519412299468 | 17519412596749 | 17519412598433 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f3419866300 | 0x7f3416825280 | 131072 | 669904 | 75030520 | 17519412636572 | 17519412596749 | 17519412866989 | 17519412868606 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f3419866180 | 0x7f34168252c0 | 131072 | 672972 | 75558552 | 17519412898865 | 17519412866989 | 17519413223630 | 17519413225127 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f3419866000 | 0x7f3416825300 | 65536 | 631734 | 70631912 | 17519413256016 | 17519413223630 | 17519413578031 | 17519413579458 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f3417209e80 | 0x7f3416825340 | 131072 | 677848 | 75927808 | 17519413609297 | 17519413578031 | 17519413846511 | 17519413848011 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f3417209d00 | 0x7f3416825380 | 131072 | 683532 | 76514608 | 17519413877920 | 17519413846511 | 17519414146192 | 17519414147683 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f3417209b80 | 0x7f34168253c0 | 131072 | 669074 | 74980680 | 17519414185682 | 17519414146192 | 17519414427952 | 17519414429556 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f3417209a00 | 0x7f3416825400 | 131072 | 643518 | 72023560 | 17519414460055 | 17519414427952 | 17519414791153 | 17519414792766 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f3417209880 | 0x7f3416825440 | 65536 | 641246 | 71890064 | 17519414823256 | 17519414791153 | 17519415145713 | 17519415147397 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f3417209700 | 0x7f3416825480 | 131072 | 643986 | 72105304 | 17519415177207 | 17519415145713 | 17519415415954 | 17519415417620 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f3419866580 | 0x7f34168254c0 | 131072 | 634026 | 70921264 | 17519415447460 | 17519415415954 | 17519415721714 | 17519415723183 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f3419866400 | 0x7f3416825500 | 131072 | 635876 | 71145120 | 17519415762562 | 17519415721714 | 17519415996275 | 17519415997825 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f3419866280 | 0x7f3416825540 | 131072 | 673734 | 75516520 | 17519416028545 | 17519415996275 | 17519416351636 | 17519416353376 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f3419866100 | 0x7f3416825580 | 65536 | 637576 | 71418952 | 17519416384256 | 17519416351636 | 17519416706836 | 17519416708337 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f3417209f80 | 0x7f34168255c0 | 131072 | 681748 | 76296512 | 17519416738856 | 17519416706836 | 17519416978037 | 17519416979730 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f3417209e00 | 0x7f3416825600 | 131072 | 668848 | 75066200 | 17519417009789 | 17519416978037 | 17519417291957 | 17519417293482 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f3417209c80 | 0x7f3416825640 | 131072 | 676336 | 75737088 | 17519417330711 | 17519417291957 | 17519417567318 | 17519417568975 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f3417209b00 | 0x7f3416825680 | 131072 | 683724 | 76747240 | 17519417599634 | 17519417567318 | 17519417927318 | 17519417929096 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f3417209980 | 0x7f34168256c0 | 65536 | 642266 | 71967872 | 17519417958675 | 17519417927318 | 17519418290519 | 17519418292407 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f3417209800 | 0x7f3416825700 | 131072 | 672538 | 75418296 | 17519418322346 | 17519418290519 | 17519418565560 | 17519418567200 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f3417209680 | 0x7f3416825740 | 131072 | 668900 | 75035040 | 17519418597879 | 17519418565560 | 17519418885560 | 17519418887231 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f3419866500 | 0x7f3416825780 | 131072 | 704834 | 79077352 | 17519418924690 | 17519418885560 | 17519419155161 | 17519419156824 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f3419866380 | 0x7f34168257c0 | 131072 | 676906 | 75824552 | 17519419186934 | 17519419155161 | 17519419510841 | 17519419512535 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f3419866200 | 0x7f3416825800 | 65536 | 643876 | 72056928 | 17519419542544 | 17519419510841 | 17519419867002 | 17519419868566 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f3419866080 | 0x7f3416825840 | 131072 | 641924 | 71775616 | 17519419899465 | 17519419867002 | 17519420143002 | 17519420144399 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f3417209f00 | 0x7f3416825880 | 131072 | 655588 | 73465992 | 17519420175328 | 17519420143002 | 17519420472443 | 17519420474211 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f3417209d80 | 0x7f34168258c0 | 131072 | 1028508 | 115186720 | 17519420512290 | 17519420472443 | 17519420755323 | 17519420756913 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f3417209c00 | 0x7f3416825900 | 131072 | 636396 | 71240024 | 17519420787872 | 17519420755323 | 17519421118044 | 17519421119634 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f3417209a80 | 0x7f3416825940 | 65536 | 637110 | 71369072 | 17519421149883 | 17519421118044 | 17519421477245 | 17519421478915 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f3417209900 | 0x7f3416825980 | 131072 | 695350 | 77849480 | 17519421508124 | 17519421477245 | 17519421761405 | 17519421762927 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f3417209780 | 0x7f34168259c0 | 131072 | 672688 | 75413424 | 17519421792867 | 17519421761405 | 17519422105566 | 17519422107469 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f3417209600 | 0x7f3416825a00 | 131072 | 1012642 | 113150608 | 17519422146378 | 17519422105566 | 17519422380926 | 17519422382622 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f3419866480 | 0x7f3416825a40 | 131072 | 682594 | 76378992 | 17519422412991 | 17519422380926 | 17519422739327 | 17519422740952 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f3419866300 | 0x7f3416825a80 | 65536 | 637738 | 71349560 | 17519422771292 | 17519422739327 | 17519423096288 | 17519423098003 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f3419866180 | 0x7f3416825ac0 | 131072 | 636172 | 71247512 | 17519423128312 | 17519423096288 | 17519423382688 | 17519423384326 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f3419866000 | 0x7f3416825b00 | 131072 | 709566 | 79544336 | 17519423415015 | 17519423382688 | 17519423748129 | 17519423749576 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f3417209e80 | 0x7f3416825b40 | 131072 | 962082 | 107825840 | 17519423787955 | 17519423748129 | 17519424034369 | 17519424036029 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f3417209d00 | 0x7f3416825b80 | 131072 | 679624 | 76099304 | 17519424066268 | 17519424034369 | 17519424397570 | 17519424399300 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f3417209b80 | 0x7f3416825bc0 | 65536 | 642720 | 71958672 | 17519424429379 | 17519424397570 | 17519424759971 | 17519424761560 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f3417209a00 | 0x7f3416825c00 | 131072 | 633012 | 70925024 | 17519424791580 | 17519424759971 | 17519425059331 | 17519425060963 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f3417209880 | 0x7f3416825c40 | 131072 | 630424 | 70638072 | 17519425091372 | 17519425059331 | 17519425444932 | 17519425463322 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f3417209700 | 0x7f3416825c80 | 131072 | 993604 | 111335024 | 17519425485002 | 17519425444932 | 17519425740292 | 17519425741815 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f3419866580 | 0x7f3416825cc0 | 131072 | 641522 | 71796888 | 17519425772024 | 17519425740292 | 17519426098693 | 17519426100246 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f3419866400 | 0x7f3416825d00 | 65536 | 643306 | 71940752 | 17519426131215 | 17519426098693 | 17519426462694 | 17519426464267 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f3419866280 | 0x7f3416825d40 | 131072 | 632888 | 70876584 | 17519426495086 | 17519426462694 | 17519426777254 | 17519426778879 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f3419866100 | 0x7f3416825d80 | 131072 | 640914 | 71705408 | 17519426809368 | 17519426777254 | 17519427186855 | 17519427207558 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f3417209f80 | 0x7f3416825dc0 | 131072 | 950078 | 106452360 | 17519427226347 | 17519427186855 | 17519427499656 | 17519427501290 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f3417209e00 | 0x7f3416825e00 | 131072 | 669842 | 74961776 | 17519427531849 | 17519427499656 | 17519427867336 | 17519427887740 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f3417209c80 | 0x7f3416825e40 | 65536 | 650164 | 72798520 | 17519427899150 | 17519427867336 | 17519428250697 | 17519428270290 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f3417209b00 | 0x7f3416825e80 | 131072 | 637580 | 71480696 | 17519428281590 | 17519428250697 | 17519428593578 | 17519428595302 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f3417209980 | 0x7f3416825ec0 | 131072 | 637436 | 71439272 | 17519428625861 | 17519428593578 | 17519429056458 | 17519429078030 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f3417209800 | 0x7f3416825f00 | 131072 | 1002566 | 112086912 | 17519429096989 | 17519429056458 | 17519429394059 | 17519429395641 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f3417209680 | 0x7f3416825f40 | 131072 | 934696 | 104574160 | 17519429425551 | 17519429394059 | 17519429783340 | 17519429800271 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f3419866500 | 0x7f3416825f80 | 65536 | 636914 | 71495832 | 17519429814681 | 17519429783340 | 17519430177100 | 17519430221230 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f3419866380 | 0x7f3416825fc0 | 131072 | 643212 | 72053928 | 17519430231860 | 17519430177100 | 17519430583501 | 17519430585231 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f3419866200 | 0x7f3416826000 | 131072 | 651086 | 73055080 | 17519430617120 | 17519430583501 | 17519431094382 | 17519431135997 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f3419866080 | 0x7f3416826040 | 131072 | 994106 | 111408760 | 17519431155146 | 17519431094382 | 17519431467343 | 17519431469048 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f3417209f00 | 0x7f3416826080 | 131072 | 1000676 | 112171840 | 17519431499707 | 17519431467343 | 17519431875664 | 17519431917097 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f3417209d80 | 0x7f34168260c0 | 65536 | 639500 | 71611232 | 17519431929686 | 17519431875664 | 17519432318064 | 17519432359625 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f3417209c00 | 0x7f3416826100 | 131072 | 634906 | 71151176 | 17519432370365 | 17519432318064 | 17519432742865 | 17519432761575 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f3417209a80 | 0x7f3416826140 | 131072 | 645354 | 72299968 | 17519432775025 | 17519432742865 | 17519433313266 | 17519433330990 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f3417209900 | 0x7f3416826180 | 131072 | 1006948 | 112638312 | 17519433352890 | 17519433313266 | 17519433688787 | 17519433690461 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f3417209780 | 0x7f34168261c0 | 131072 | 1025318 | 114711392 | 17519433719790 | 17519433688787 | 17519434124148 | 17519434147619 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f3417209600 | 0x7f3416826200 | 65536 | 640444 | 71775736 | 17519434158759 | 17519434124148 | 17519434565588 | 17519434586398 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f3419866480 | 0x7f3416826240 | 131072 | 636174 | 71225848 | 17519434598038 | 17519434565588 | 17519434986069 | 17519435003417 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f3419866300 | 0x7f3416826280 | 131072 | 1007948 | 112987928 | 17519435018307 | 17519434986069 | 17519435619990 | 17519435636641 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f3419866180 | 0x7f34168262c0 | 131072 | 1008646 | 113112072 | 17519435660131 | 17519435619990 | 17519436024151 | 17519436040531 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f3419866000 | 0x7f3416826300 | 131072 | 960540 | 107746152 | 17519436056230 | 17519436024151 | 17519436505752 | 17519436523918 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f3417209e80 | 0x7f3416826340 | 65536 | 639638 | 71642688 | 17519436537568 | 17519436505752 | 17519436986873 | 17519437003206 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f3417209d00 | 0x7f3416826380 | 131072 | 959596 | 107570640 | 17519437018836 | 17519436986873 | 17519437466074 | 17519437487234 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f3417209b80 | 0x7f34168263c0 | 131072 | 1003232 | 112449488 | 17519437498013 | 17519437466074 | 17519438209275 | 17519438229975 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f3417209a00 | 0x7f3416826400 | 131072 | 960298 | 107547624 | 17519438249064 | 17519438209275 | 17519438667836 | 17519438685063 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f3417209880 | 0x7f3416826440 | 131072 | 988800 | 110620952 | 17519438698983 | 17519438667836 | 17519439202397 | 17519439244059 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f3417209700 | 0x7f3416826480 | 65536 | 639750 | 71656832 | 17519439254098 | 17519439202397 | 17519439757118 | 17519439798694 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f3419866580 | 0x7f34168264c0 | 131072 | 972148 | 108972248 | 17519439809144 | 17519439757118 | 17519440309919 | 17519440327691 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f3419866400 | 0x7f3416826500 | 131072 | 993684 | 111326032 | 17519440342860 | 17519440309919 | 17519441146080 | 17519441162369 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f3419866280 | 0x7f3416826540 | 131072 | 1061904 | 119159008 | 17519441185889 | 17519441146080 | 17519441771841 | 17519441788713 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f3419866100 | 0x7f3416826580 | 131072 | 990592 | 110760640 | 17519441804253 | 17519441771841 | 17519442419043 | 17519442437827 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f3417209f80 | 0x7f34168265c0 | 65536 | 643744 | 72134968 | 17519442451636 | 17519442419043 | 17519443066884 | 17519443108909 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f3417209e00 | 0x7f3416826600 | 131072 | 1000876 | 112085552 | 17519443118919 | 17519443066884 | 17519443722405 | 17519443765152 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f3417209c80 | 0x7f3416826640 | 131072 | 1010654 | 113220672 | 17519443775082 | 17519443722405 | 17519444801607 | 17519444844345 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f3417209b00 | 0x7f3416826680 | 131072 | 1005672 | 112527552 | 17519444862274 | 17519444801607 | 17519445861289 | 17519445909907 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f3417209980 | 0x7f34168266c0 | 131072 | 1003684 | 112487480 | 17519445919697 | 17519445861048 | 17519446958649 | 17519447026289 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f3417209800 | 0x7f3416826700 | 65536 | 643980 | 72224000 | 17519447038338 | 17519446958649 | 17519448084410 | 17519448150690 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f3417209680 | 0x7f3416826740 | 131072 | 1012622 | 113019928 | 17519448161530 | 17519448084410 | 17519449190171 | 17519449255521 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f3419866500 | 0x7f3416826780 | 131072 | 1034416 | 115930872 | 17519449266681 | 17519449190171 | 17519451130814 | 17519451200512 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f3419866380 | 0x7f34168267c0 | 131072 | 1005214 | 112775432 | 17519451220441 | 17519451130814 | 17519453049216 | 17519453115742 |
| 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 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f3419866200 | 0x7f3416826800 | 131072 | 994016 | 111533640 | 17519453126602 | 17519453049216 | 17519455017059 | 17519455090162 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f3419866080 | 0x7f3416826840 | 65536 | 642730 | 72073344 | 17519455101171 | 17519455017059 | 17519456992582 | 17519457060401 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f3417209f00 | 0x7f3416826880 | 131072 | 1012610 | 113463328 | 17519457070931 | 17519456992582 | 17519458923464 | 17519458992241 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 217617 | 217617 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f3417209d80 | 0x7f34168268c0 | 131072 | 1012086 | 113448344 | 17519459003761 | 17519458923464 | 17519462538509 | 17519462609109 |