39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 869055 | 869060 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fe209804180 | 12075298394874174 | 12075298394918942 | 12075298395241339 | 12075298395319412 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 869055 | 869060 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fe209835100 | 12075298410086942 | 12075298410199883 | 12075298410206763 | 12075298410212375 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fe3153ab900 | 0x7fe209835140 | 12075298410303855 | 12075298410323561 | 12075298410454600 | 12075298410457851 |
| 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 | 6 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fe3153ab800 | 0x7fe209835180 | 12075298410504437 | 12075298410524200 | 12075298410768357 | 12075298410837015 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fe3153ab700 | 0x7fe2098351c0 | 12075298410861631 | 12075298410880516 | 12075298411126274 | 12075298411201372 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fe3153ab600 | 0x7fe209835200 | 12075298411227110 | 12075298411248193 | 12075298411373312 | 12075298411376848 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fe3153ab500 | 0x7fe209835240 | 12075298411405632 | 12075298411419872 | 12075298411545310 | 12075298411548387 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fe3153ab400 | 0x7fe209835280 | 12075298411604341 | 12075298411617310 | 12075298411741149 | 12075298411744161 |
| 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 | 16 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fe3153ab300 | 0x7fe2098352c0 | 12075298411774758 | 12075298411787868 | 12075298412073306 | 12075298412142511 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fe3153aba00 | 0x7fe209835300 | 12075298412165854 | 12075298412186585 | 12075298412429942 | 12075298412498442 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fe3153ab900 | 0x7fe209835340 | 12075298412520564 | 12075298412533941 | 12075298412658420 | 12075298412661786 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fe3153ab800 | 0x7fe209835380 | 12075298412687223 | 12075298412698740 | 12075298412824179 | 12075298412827163 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fe3153ab700 | 0x7fe2098353c0 | 12075298412863371 | 12075298412875058 | 12075298412999217 | 12075298413009602 |
| 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 | 26 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fe3153ab600 | 0x7fe209835400 | 12075298413029419 | 12075298413041457 | 12075298413326894 | 12075298413397693 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fe3153ab500 | 0x7fe209835440 | 12075298413417871 | 12075298413434093 | 12075298413679051 | 12075298413748225 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fe3153ab400 | 0x7fe209835480 | 12075298413767541 | 12075298413780490 | 12075298413905289 | 12075298413908693 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fe3153ab300 | 0x7fe2098354c0 | 12075298413932998 | 12075298413944489 | 12075298414069928 | 12075298414073449 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fe3153aba00 | 0x7fe209835500 | 12075298414110378 | 12075298414121447 | 12075298414245926 | 12075298414248755 |
| 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 | 36 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fe3153ab900 | 0x7fe209835540 | 12075298414274362 | 12075298414286246 | 12075298414532963 | 12075298414601951 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fe3153ab800 | 0x7fe209835580 | 12075298414621167 | 12075298414632642 | 12075298414875680 | 12075298414918920 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fe3153ab700 | 0x7fe2098355c0 | 12075298414939709 | 12075298414951520 | 12075298415075678 | 12075298415078847 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fe3153ab600 | 0x7fe209835600 | 12075298415104515 | 12075298415115678 | 12075298415241597 | 12075298415244755 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fe3153ab500 | 0x7fe209835640 | 12075298415280522 | 12075298415291676 | 12075298415415995 | 12075298415419049 |
| 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 | 46 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fe3153ab400 | 0x7fe209835680 | 12075298415444637 | 12075298415456155 | 12075298415704473 | 12075298415769681 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fe3153ab300 | 0x7fe2098356c0 | 12075298415788546 | 12075298415799672 | 12075298416043510 | 12075298416113249 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fe3153aba00 | 0x7fe209835700 | 12075298416132866 | 12075298416143829 | 12075298416267988 | 12075298416271243 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fe3153ab900 | 0x7fe209835740 | 12075298416296991 | 12075298416308467 | 12075298416433426 | 12075298416436620 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fe3153ab800 | 0x7fe209835780 | 12075298416470794 | 12075298416482386 | 12075298416607345 | 12075298416610333 |
| 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 | 56 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fe3153ab700 | 0x7fe2098357c0 | 12075298416635550 | 12075298416647344 | 12075298416899022 | 12075298416937431 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fe3153ab600 | 0x7fe209835800 | 12075298416956696 | 12075298416967821 | 12075298417212619 | 12075298417265480 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fe3153ab500 | 0x7fe209835840 | 12075298417285427 | 12075298417297738 | 12075298417422057 | 12075298417425317 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fe3153ab400 | 0x7fe209835880 | 12075298417450133 | 12075298417461897 | 12075298417587816 | 12075298417590835 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fe3153ab300 | 0x7fe2098358c0 | 12075298417626100 | 12075298417637735 | 12075298417763014 | 12075298417765850 |
| 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 | 66 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fe3153aba00 | 0x7fe209835900 | 12075298417790706 | 12075298417801894 | 12075298418053891 | 12075298418077379 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fe3153ab900 | 0x7fe209835940 | 12075298418098608 | 12075298418109891 | 12075298418354529 | 12075298418375563 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fe3153ab800 | 0x7fe209835980 | 12075298418396402 | 12075298418408128 | 12075298418532927 | 12075298418535841 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fe3153ab700 | 0x7fe2098359c0 | 12075298418561068 | 12075298418572767 | 12075298418698526 | 12075298418701378 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fe3153ab600 | 0x7fe209835a00 | 12075298418735221 | 12075298418746525 | 12075298418870524 | 12075298418873538 |
| 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 | 76 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fe3153ab500 | 0x7fe209835a40 | 12075298418897523 | 12075298418908924 | 12075298419158201 | 12075298419217788 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fe3153ab400 | 0x7fe209835a80 | 12075298419238476 | 12075298419257560 | 12075298419504598 | 12075298419527153 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fe3153ab300 | 0x7fe209835ac0 | 12075298419546489 | 12075298419557718 | 12075298419682357 | 12075298419685427 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fe3153aba00 | 0x7fe209835b00 | 12075298419709832 | 12075298419721236 | 12075298419846675 | 12075298419849822 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fe3153ab900 | 0x7fe209835b40 | 12075298419885138 | 12075298419896115 | 12075298420020594 | 12075298420023595 |
| 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 | 86 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fe3153ab800 | 0x7fe209835b80 | 12075298420049143 | 12075298420060593 | 12075298420311311 | 12075298420327780 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fe3153ab700 | 0x7fe209835bc0 | 12075298420351875 | 12075298420362990 | 12075298420609068 | 12075298420629521 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fe3153ab600 | 0x7fe209835c00 | 12075298420647745 | 12075298420659148 | 12075298420783627 | 12075298420786513 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fe3153ab500 | 0x7fe209835c40 | 12075298420811299 | 12075298420822346 | 12075298420949385 | 12075298420952231 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fe3153ab400 | 0x7fe209835c80 | 12075298420987396 | 12075298420998505 | 12075298421123304 | 12075298421126104 |
| 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 | 96 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fe3153ab300 | 0x7fe209835cc0 | 12075298421150860 | 12075298421162023 | 12075298421413701 | 12075298421430279 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fe3153aba00 | 0x7fe209835d00 | 12075298421455205 | 12075298421466180 | 12075298421717058 | 12075298421734134 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fe3153ab900 | 0x7fe209835d40 | 12075298421753570 | 12075298421765058 | 12075298421890017 | 12075298421892999 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fe3153ab800 | 0x7fe209835d80 | 12075298421917414 | 12075298421928896 | 12075298422057215 | 12075298422060310 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fe3153ab700 | 0x7fe209835dc0 | 12075298422095295 | 12075298422106175 | 12075298422231934 | 12075298422234934 |
| 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 | 106 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fe3153ab600 | 0x7fe209835e00 | 12075298422259930 | 12075298422273213 | 12075298422531451 | 12075298422551362 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fe3153ab500 | 0x7fe209835e40 | 12075298422569285 | 12075298422581850 | 12075298422828888 | 12075298422848985 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fe3153ab400 | 0x7fe209835e80 | 12075298422868371 | 12075298422880728 | 12075298423006327 | 12075298423009303 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fe3153ab300 | 0x7fe209835ec0 | 12075298423037225 | 12075298423048566 | 12075298423176565 | 12075298423179449 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fe3153aba00 | 0x7fe209835f00 | 12075298423214444 | 12075298423225525 | 12075298423350643 | 12075298423353603 |
| 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 | 116 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fe3153ab900 | 0x7fe209835f40 | 12075298423377547 | 12075298423388723 | 12075298423642641 | 12075298423663328 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fe3153ab800 | 0x7fe209835f80 | 12075298423682283 | 12075298423694320 | 12075298423941998 | 12075298423962254 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fe3153ab700 | 0x7fe209835fc0 | 12075298423980007 | 12075298423992558 | 12075298424117836 | 12075298424121039 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fe3153ab600 | 0x7fe209836000 | 12075298424147718 | 12075298424160076 | 12075298424296875 | 12075298424299891 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fe3153ab500 | 0x7fe209836040 | 12075298424335086 | 12075298424346154 | 12075298424471113 | 12075298424473834 |
| 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 | 126 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fe3153ab400 | 0x7fe209836080 | 12075298424497679 | 12075298424509193 | 12075298424767431 | 12075298424784371 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fe3153ab300 | 0x7fe2098360c0 | 12075298424805671 | 12075298424818790 | 12075298425068388 | 12075298425092664 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fe3153aba00 | 0x7fe209836100 | 12075298425111449 | 12075298425123747 | 12075298425248226 | 12075298425251309 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fe3153ab900 | 0x7fe209836140 | 12075298425276556 | 12075298425289186 | 12075298425431745 | 12075298425434840 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fe3153ab800 | 0x7fe209836180 | 12075298425468783 | 12075298425479744 | 12075298425605183 | 12075298425608442 |
| 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 | 136 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fe3153ab700 | 0x7fe2098361c0 | 12075298425632106 | 12075298425643423 | 12075298425902620 | 12075298425919731 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fe3153ab600 | 0x7fe209836200 | 12075298425942734 | 12075298425953820 | 12075298426197818 | 12075298426220810 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fe3153ab500 | 0x7fe209836240 | 12075298426240637 | 12075298426251737 | 12075298426376696 | 12075298426379706 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fe3153ab400 | 0x7fe209836280 | 12075298426405293 | 12075298426416536 | 12075298426566454 | 12075298426569488 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fe3153ab300 | 0x7fe2098362c0 | 12075298426618109 | 12075298426630614 | 12075298426756213 | 12075298426759391 |
| 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 | 146 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fe3153aba00 | 0x7fe209836300 | 12075298426783666 | 12075298426795252 | 12075298427049010 | 12075298427072232 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fe3153ab900 | 0x7fe209836340 | 12075298427092520 | 12075298427103889 | 12075298427348847 | 12075298427374284 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fe3153ab800 | 0x7fe209836380 | 12075298427392107 | 12075298427403567 | 12075298427529166 | 12075298427532347 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fe3153ab700 | 0x7fe2098363c0 | 12075298427556021 | 12075298427568525 | 12075298427725964 | 12075298427728933 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fe3153ab600 | 0x7fe209836400 | 12075298427762375 | 12075298427773803 | 12075298427898602 | 12075298427901603 |
| 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 | 156 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fe3153ab500 | 0x7fe209836440 | 12075298427925478 | 12075298427936522 | 12075298428189480 | 12075298428210738 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fe3153ab400 | 0x7fe209836480 | 12075298428231236 | 12075298428242119 | 12075298428486757 | 12075298428507459 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fe3153ab300 | 0x7fe2098364c0 | 12075298428526715 | 12075298428537956 | 12075298428663395 | 12075298428666545 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fe3153aba00 | 0x7fe209836500 | 12075298428690700 | 12075298428701955 | 12075298428867553 | 12075298428870524 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fe3153ab900 | 0x7fe209836540 | 12075298428905559 | 12075298428916673 | 12075298429042752 | 12075298429045749 |
| 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 | 166 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fe3153ab800 | 0x7fe209836580 | 12075298429072589 | 12075298429083871 | 12075298429341309 | 12075298429364031 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fe3153ab700 | 0x7fe2098365c0 | 12075298429383146 | 12075298429395869 | 12075298429643866 | 12075298429660682 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fe3153ab600 | 0x7fe209836600 | 12075298429682563 | 12075298429695226 | 12075298429820185 | 12075298429823164 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fe3153ab500 | 0x7fe209836640 | 12075298429848271 | 12075298429859384 | 12075298430032183 | 12075298430035489 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fe3153ab400 | 0x7fe209836680 | 12075298430071566 | 12075298430083062 | 12075298430209461 | 12075298430212457 |
| 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 | 176 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fe3153ab300 | 0x7fe2098366c0 | 12075298430236953 | 12075298430248181 | 12075298430506899 | 12075298430527934 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fe3153aba00 | 0x7fe209836700 | 12075298430546167 | 12075298430558738 | 12075298430809616 | 12075298430830205 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fe3153ab900 | 0x7fe209836740 | 12075298430850813 | 12075298430862735 | 12075298430988014 | 12075298430991024 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fe3153ab800 | 0x7fe209836780 | 12075298431021821 | 12075298431032494 | 12075298431215052 | 12075298431218046 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fe3153ab700 | 0x7fe2098367c0 | 12075298431252139 | 12075298431263212 | 12075298431388811 | 12075298431391899 |
| 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 | 186 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fe3153ab600 | 0x7fe209836800 | 12075298431416805 | 12075298431428010 | 12075298431691368 | 12075298431712174 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fe3153ab500 | 0x7fe209836840 | 12075298431733223 | 12075298431747367 | 12075298431998885 | 12075298432024655 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fe3153ab400 | 0x7fe209836880 | 12075298432043870 | 12075298432056484 | 12075298432182083 | 12075298432185083 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fe3153ab300 | 0x7fe2098368c0 | 12075298432209198 | 12075298432220323 | 12075298432411361 | 12075298432415020 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fe3153aba00 | 0x7fe209836900 | 12075298432447961 | 12075298432458881 | 12075298432584800 | 12075298432587801 |
| 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 | 196 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fe3153ab900 | 0x7fe209836940 | 12075298432611796 | 12075298432623039 | 12075298432905597 | 12075298432926300 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fe3153ab800 | 0x7fe209836980 | 12075298432944805 | 12075298432955996 | 12075298433207834 | 12075298433238170 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fe3153ab700 | 0x7fe2098369c0 | 12075298433256454 | 12075298433267673 | 12075298433392792 | 12075298433395963 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fe3153ab600 | 0x7fe209836a00 | 12075298433422642 | 12075298433433592 | 12075298433643030 | 12075298433663330 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fe3153ab500 | 0x7fe209836a40 | 12075298433692474 | 12075298433703350 | 12075298433830548 | 12075298433833726 |
| 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 | 206 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fe3153ab400 | 0x7fe209836a80 | 12075298433858412 | 12075298433869748 | 12075298434175825 | 12075298434200888 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fe3153ab300 | 0x7fe209836ac0 | 12075298434220605 | 12075298434231665 | 12075298434479822 | 12075298434504112 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fe3153aba00 | 0x7fe209836b00 | 12075298434523207 | 12075298434534062 | 12075298434661261 | 12075298434664560 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fe3153ab900 | 0x7fe209836b40 | 12075298434689216 | 12075298434700300 | 12075298434927018 | 12075298434947836 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fe3153ab800 | 0x7fe209836b80 | 12075298434977291 | 12075298434989578 | 12075298435116137 | 12075298435119455 |
| 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 | 216 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fe3153ab700 | 0x7fe209836bc0 | 12075298435144422 | 12075298435155656 | 12075298435483973 | 12075298435504861 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fe3153ab600 | 0x7fe209836c00 | 12075298435526031 | 12075298435536773 | 12075298435790691 | 12075298435811271 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fe3153ab500 | 0x7fe209836c40 | 12075298435830006 | 12075298435841090 | 12075298435969409 | 12075298435972460 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fe3153ab400 | 0x7fe209836c80 | 12075298435997136 | 12075298436012289 | 12075298436256126 | 12075298436277327 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fe3153ab300 | 0x7fe209836cc0 | 12075298436306932 | 12075298436318046 | 12075298436447965 | 12075298436451290 |
| 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 | 226 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fe3153aba00 | 0x7fe209836d00 | 12075298436475455 | 12075298436487004 | 12075298436861881 | 12075298436887631 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fe3153ab900 | 0x7fe209836d40 | 12075298436905774 | 12075298436917080 | 12075298437175958 | 12075298437201093 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fe3153ab800 | 0x7fe209836d80 | 12075298437220499 | 12075298437231318 | 12075298437359956 | 12075298437363074 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fe3153ab700 | 0x7fe209836dc0 | 12075298437388902 | 12075298437399636 | 12075298437677394 | 12075298437698417 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fe3153ab600 | 0x7fe209836e00 | 12075298437727040 | 12075298437737873 | 12075298437873552 | 12075298437876739 |
| 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 | 236 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fe3153ab500 | 0x7fe209836e40 | 12075298437900332 | 12075298437911311 | 12075298438333548 | 12075298438364856 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fe3153ab400 | 0x7fe209836e80 | 12075298438385173 | 12075298438397547 | 12075298438659945 | 12075298438684469 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fe3153ab300 | 0x7fe209836ec0 | 12075298438702864 | 12075298438715304 | 12075298438851143 | 12075298438854495 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fe3153aba00 | 0x7fe209836f00 | 12075298438878901 | 12075298438890183 | 12075298439233219 | 12075298439257805 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fe3153ab900 | 0x7fe209836f40 | 12075298439287640 | 12075298439298659 | 12075298439449377 | 12075298439453208 |
| 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 | 246 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fe3153ab800 | 0x7fe209836f80 | 12075298439477824 | 12075298439489857 | 12075298440006492 | 12075298440031793 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fe3153ab700 | 0x7fe209836fc0 | 12075298440054114 | 12075298440066172 | 12075298440364889 | 12075298440389588 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fe3153ab600 | 0x7fe209837000 | 12075298440408273 | 12075298440420569 | 12075298440575287 | 12075298440578479 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fe3153ab500 | 0x7fe209837040 | 12075298440603595 | 12075298440615767 | 12075298441000243 | 12075298441025359 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fe3153ab400 | 0x7fe209837080 | 12075298441054754 | 12075298441067123 | 12075298441242001 | 12075298441245478 |
| 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 | 256 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fe3153ab300 | 0x7fe2098370c0 | 12075298441269222 | 12075298441280241 | 12075298441889675 | 12075298441913700 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fe3153aba00 | 0x7fe209837100 | 12075298441932685 | 12075298441945035 | 12075298442275752 | 12075298442305277 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fe3153ab900 | 0x7fe209837140 | 12075298442323692 | 12075298442336071 | 12075298442514470 | 12075298442517712 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fe3153ab800 | 0x7fe209837180 | 12075298442544071 | 12075298442555109 | 12075298443010465 | 12075298443038009 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fe3153ab700 | 0x7fe2098371c0 | 12075298443068496 | 12075298443079745 | 12075298443279263 | 12075298443303673 |
| 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 | 266 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fe3153ab600 | 0x7fe209837200 | 12075298443321205 | 12075298443332222 | 12075298444036056 | 12075298444061861 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fe3153ab500 | 0x7fe209837240 | 12075298444081448 | 12075298444093495 | 12075298444466132 | 12075298444490758 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fe3153ab400 | 0x7fe209837280 | 12075298444509353 | 12075298444521651 | 12075298444723730 | 12075298444747986 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fe3153ab300 | 0x7fe2098372c0 | 12075298444767292 | 12075298444779409 | 12075298445304844 | 12075298445329837 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fe3153aba00 | 0x7fe209837300 | 12075298445358731 | 12075298445370924 | 12075298445594602 | 12075298445618854 |
| 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 | 276 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fe3153ab900 | 0x7fe209837340 | 12075298445637098 | 12075298445649641 | 12075298446448194 | 12075298446474154 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fe3153ab800 | 0x7fe209837380 | 12075298446495864 | 12075298446507873 | 12075298446927710 | 12075298446952102 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fe3153ab700 | 0x7fe2098373c0 | 12075298446971077 | 12075298446982429 | 12075298447209147 | 12075298447239857 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fe3153ab600 | 0x7fe209837400 | 12075298447259663 | 12075298447270907 | 12075298447866741 | 12075298447892519 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fe3153ab500 | 0x7fe209837440 | 12075298447921202 | 12075298447933781 | 12075298448201618 | 12075298448226650 |
| 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 | 286 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fe3153ab400 | 0x7fe209837480 | 12075298448245245 | 12075298448257618 | 12075298449242409 | 12075298449268606 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fe3153ab300 | 0x7fe2098374c0 | 12075298449286409 | 12075298449298408 | 12075298449812964 | 12075298449837443 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fe3153aba00 | 0x7fe209837500 | 12075298449857280 | 12075298449868323 | 12075298450139041 | 12075298450167577 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fe3153ab900 | 0x7fe209837540 | 12075298450188816 | 12075298450201280 | 12075298450938553 | 12075298450962914 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fe3153ab800 | 0x7fe209837580 | 12075298450991357 | 12075298451002393 | 12075298451347030 | 12075298451372025 |
| 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 | 296 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fe3153ab700 | 0x7fe2098375c0 | 12075298451391922 | 12075298451403349 | 12075298452573898 | 12075298452600217 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fe3153ab600 | 0x7fe209837600 | 12075298452619102 | 12075298452631338 | 12075298453241732 | 12075298453267497 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fe3153ab500 | 0x7fe209837640 | 12075298453286863 | 12075298453299172 | 12075298453617409 | 12075298453638496 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fe3153ab400 | 0x7fe209837680 | 12075298453657481 | 12075298453669729 | 12075298454546521 | 12075298454571950 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fe3153ab300 | 0x7fe2098376c0 | 12075298454601295 | 12075298454612280 | 12075298455022676 | 12075298455048346 |
| 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 | 306 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fe3153aba00 | 0x7fe209837700 | 12075298455068984 | 12075298455080596 | 12075298456629222 | 12075298456675229 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fe3153ab900 | 0x7fe209837740 | 12075298456697420 | 12075298456709221 | 12075298457504734 | 12075298457550255 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fe3153ab800 | 0x7fe209837780 | 12075298457569971 | 12075298457582807 | 12075298457995924 | 12075298458045244 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fe3153ab700 | 0x7fe2098377c0 | 12075298458065061 | 12075298458078162 | 12075298459235913 | 12075298459281010 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fe3153ab600 | 0x7fe209837800 | 12075298459311006 | 12075298459323913 | 12075298460111267 | 12075298460156347 |
| 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 | 316 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fe3153ab500 | 0x7fe209837840 | 12075298460175402 | 12075298460188226 | 12075298463238443 | 12075298463284089 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fe3153ab400 | 0x7fe209837880 | 12075298463302563 | 12075298463315722 | 12075298464856991 | 12075298464902596 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fe3153ab300 | 0x7fe2098378c0 | 12075298464922673 | 12075298464934110 | 12075298465722744 | 12075298465772132 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fe3153aba00 | 0x7fe209837900 | 12075298465794363 | 12075298465807383 | 12075298468089286 | 12075298468141194 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fe3153ab900 | 0x7fe209837940 | 12075298468171230 | 12075298468184325 | 12075298469719834 | 12075298469764931 |
| 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 | 326 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fe3153ab800 | 0x7fe209837980 | 12075298469784768 | 12075298469798233 | 12075298475856107 | 12075298475922983 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fe3153ab700 | 0x7fe2098379c0 | 12075298475942800 | 12075298475955626 | 12075298478998643 | 12075298479047569 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fe3153ab600 | 0x7fe209837a00 | 12075298479068408 | 12075298479081362 | 12075298480620071 | 12075298480666918 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 869055 | 869060 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fe3153ab500 | 0x7fe209837a40 | 12075298480685092 | 12075298480698310 | 12075298485224356 | 12075298485270272 |