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 | 760546 | 760551 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f3c31e04180 | 12073376112529333 | 12073376112577260 | 12073376112901737 | 12073376113022259 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 760546 | 760551 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f3c31e35100 | 12073376127807245 | 12073376127912772 | 12073376127919491 | 12073376127924924 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f3d3d9a9900 | 0x7f3c31e35140 | 12073376127971200 | 12073376127985571 | 12073376128118210 | 12073376128121519 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f3d3d9a9800 | 0x7f3c31e35180 | 12073376128168136 | 12073376128180129 | 12073376128427487 | 12073376128525109 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f3d3d9a9700 | 0x7f3c31e351c0 | 12073376128551418 | 12073376128564446 | 12073376128809404 | 12073376128904625 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f3d3d9a9600 | 0x7f3c31e35200 | 12073376128930773 | 12073376128942683 | 12073376129067802 | 12073376129071264 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f3d3d9a9500 | 0x7f3c31e35240 | 12073376129101090 | 12073376129113402 | 12073376129238841 | 12073376129241881 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f3d3d9a9400 | 0x7f3c31e35280 | 12073376129294880 | 12073376129306840 | 12073376129430999 | 12073376129433948 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f3d3d9a9300 | 0x7f3c31e352c0 | 12073376129461239 | 12073376129474199 | 12073376129720277 | 12073376129816058 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f3d3d9a9a00 | 0x7f3c31e35300 | 12073376129839873 | 12073376129851955 | 12073376130134033 | 12073376130230348 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f3d3d9a9900 | 0x7f3c31e35340 | 12073376130251979 | 12073376130265232 | 12073376130390671 | 12073376130394183 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f3d3d9a9800 | 0x7f3c31e35380 | 12073376130420632 | 12073376130433231 | 12073376130559150 | 12073376130562215 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f3d3d9a9700 | 0x7f3c31e353c0 | 12073376130599695 | 12073376130611309 | 12073376130735148 | 12073376130737932 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f3d3d9a9600 | 0x7f3c31e35400 | 12073376130765012 | 12073376130777708 | 12073376131022186 | 12073376131118369 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f3d3d9a9500 | 0x7f3c31e35440 | 12073376131145269 | 12073376131157385 | 12073376131402663 | 12073376131469932 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f3d3d9a9400 | 0x7f3c31e35480 | 12073376131496912 | 12073376131509222 | 12073376131633861 | 12073376131636932 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f3d3d9a9300 | 0x7f3c31e354c0 | 12073376131664353 | 12073376131676580 | 12073376131801699 | 12073376131804814 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f3d3d9a9a00 | 0x7f3c31e35500 | 12073376131843286 | 12073376131856739 | 12073376131981058 | 12073376131984198 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f3d3d9a9900 | 0x7f3c31e35540 | 12073376132016828 | 12073376132028897 | 12073376132273855 | 12073376132339568 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f3d3d9a9800 | 0x7f3c31e35580 | 12073376132371367 | 12073376132383294 | 12073376132628732 | 12073376132668630 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f3d3d9a9700 | 0x7f3c31e355c0 | 12073376132693466 | 12073376132706172 | 12073376132830651 | 12073376132833486 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f3d3d9a9600 | 0x7f3c31e35600 | 12073376132860236 | 12073376132872410 | 12073376132998009 | 12073376133006397 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f3d3d9a9500 | 0x7f3c31e35640 | 12073376133040731 | 12073376133053049 | 12073376133176728 | 12073376133179539 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f3d3d9a9400 | 0x7f3c31e35680 | 12073376133207030 | 12073376133218807 | 12073376133506645 | 12073376133571708 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f3d3d9a9300 | 0x7f3c31e356c0 | 12073376133593869 | 12073376133606324 | 12073376133851762 | 12073376133917290 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f3d3d9a9a00 | 0x7f3c31e35700 | 12073376133940002 | 12073376133952241 | 12073376134076400 | 12073376134079391 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f3d3d9a9900 | 0x7f3c31e35740 | 12073376134107444 | 12073376134119440 | 12073376134244559 | 12073376134247724 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f3d3d9a9800 | 0x7f3c31e35780 | 12073376134284242 | 12073376134297838 | 12073376134422317 | 12073376134425274 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f3d3d9a9700 | 0x7f3c31e357c0 | 12073376134451874 | 12073376134465837 | 12073376134715435 | 12073376134761058 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f3d3d9a9600 | 0x7f3c31e35800 | 12073376134782678 | 12073376134794154 | 12073376135037512 | 12073376135086142 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f3d3d9a9500 | 0x7f3c31e35840 | 12073376135108484 | 12073376135120872 | 12073376135245831 | 12073376135248664 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f3d3d9a9400 | 0x7f3c31e35880 | 12073376135278630 | 12073376135290150 | 12073376135415749 | 12073376135418470 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f3d3d9a9300 | 0x7f3c31e358c0 | 12073376135456230 | 12073376135467749 | 12073376135592708 | 12073376135595609 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f3d3d9a9a00 | 0x7f3c31e35900 | 12073376135622639 | 12073376135634467 | 12073376135885185 | 12073376135906537 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f3d3d9a9900 | 0x7f3c31e35940 | 12073376135928247 | 12073376135940545 | 12073376136186303 | 12073376136234146 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f3d3d9a9800 | 0x7f3c31e35980 | 12073376136256678 | 12073376136269022 | 12073376136393821 | 12073376136396748 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f3d3d9a9700 | 0x7f3c31e359c0 | 12073376136423608 | 12073376136435421 | 12073376136561340 | 12073376136564379 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f3d3d9a9600 | 0x7f3c31e35a00 | 12073376136602410 | 12073376136615099 | 12073376136739578 | 12073376136742400 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f3d3d9a9500 | 0x7f3c31e35a40 | 12073376136769741 | 12073376136782298 | 12073376137027576 | 12073376137062315 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f3d3d9a9400 | 0x7f3c31e35a80 | 12073376137083865 | 12073376137095895 | 12073376137341973 | 12073376137421592 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f3d3d9a9300 | 0x7f3c31e35ac0 | 12073376137444225 | 12073376137456532 | 12073376137581331 | 12073376137584555 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f3d3d9a9a00 | 0x7f3c31e35b00 | 12073376137610554 | 12073376137622131 | 12073376137748370 | 12073376137751486 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f3d3d9a9900 | 0x7f3c31e35b40 | 12073376137788074 | 12073376137799889 | 12073376137925168 | 12073376137928444 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f3d3d9a9800 | 0x7f3c31e35b80 | 12073376137955064 | 12073376137967568 | 12073376138226446 | 12073376138303942 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f3d3d9a9700 | 0x7f3c31e35bc0 | 12073376138326715 | 12073376138341165 | 12073376138585963 | 12073376138638504 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f3d3d9a9600 | 0x7f3c31e35c00 | 12073376138662308 | 12073376138680522 | 12073376138805321 | 12073376138808720 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f3d3d9a9500 | 0x7f3c31e35c40 | 12073376138837193 | 12073376138849321 | 12073376138975559 | 12073376138978636 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f3d3d9a9400 | 0x7f3c31e35c80 | 12073376139020574 | 12073376139032359 | 12073376139156998 | 12073376139160193 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f3d3d9a9300 | 0x7f3c31e35cc0 | 12073376139185931 | 12073376139197958 | 12073376139460355 | 12073376139483384 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f3d3d9a9a00 | 0x7f3c31e35d00 | 12073376139504944 | 12073376139516835 | 12073376139760513 | 12073376139781037 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f3d3d9a9900 | 0x7f3c31e35d40 | 12073376139802838 | 12073376139814592 | 12073376139939711 | 12073376139942648 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f3d3d9a9800 | 0x7f3c31e35d80 | 12073376139969267 | 12073376139981151 | 12073376140109310 | 12073376140112363 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f3d3d9a9700 | 0x7f3c31e35dc0 | 12073376140152638 | 12073376140166270 | 12073376140291389 | 12073376140294341 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f3d3d9a9600 | 0x7f3c31e35e00 | 12073376140321031 | 12073376140333468 | 12073376140590746 | 12073376140611080 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f3d3d9a9500 | 0x7f3c31e35e40 | 12073376140631999 | 12073376140643866 | 12073376140888344 | 12073376140908493 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f3d3d9a9400 | 0x7f3c31e35e80 | 12073376140930293 | 12073376140941943 | 12073376141067542 | 12073376141071185 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f3d3d9a9300 | 0x7f3c31e35ec0 | 12073376141099037 | 12073376141110902 | 12073376141238901 | 12073376141241892 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f3d3d9a9a00 | 0x7f3c31e35f00 | 12073376141279963 | 12073376141291540 | 12073376141416339 | 12073376141419362 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f3d3d9a9900 | 0x7f3c31e35f40 | 12073376141446302 | 12073376141459699 | 12073376141717937 | 12073376141738375 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f3d3d9a9800 | 0x7f3c31e35f80 | 12073376141759414 | 12073376141771056 | 12073376142015214 | 12073376142036128 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f3d3d9a9700 | 0x7f3c31e35fc0 | 12073376142060834 | 12073376142072814 | 12073376142198253 | 12073376142201305 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f3d3d9a9600 | 0x7f3c31e36000 | 12073376142228185 | 12073376142240172 | 12073376142376331 | 12073376142379216 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f3d3d9a9500 | 0x7f3c31e36040 | 12073376142416134 | 12073376142427851 | 12073376142552330 | 12073376142555313 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f3d3d9a9400 | 0x7f3c31e36080 | 12073376142581772 | 12073376142594089 | 12073376142848647 | 12073376142868765 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f3d3d9a9300 | 0x7f3c31e360c0 | 12073376142891157 | 12073376142904167 | 12073376143184484 | 12073376143238563 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f3d3d9a9a00 | 0x7f3c31e36100 | 12073376143260754 | 12073376143274404 | 12073376143399363 | 12073376143402878 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f3d3d9a9900 | 0x7f3c31e36140 | 12073376143430349 | 12073376143442722 | 12073376143584961 | 12073376143588403 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f3d3d9a9800 | 0x7f3c31e36180 | 12073376143627345 | 12073376143639361 | 12073376143764800 | 12073376143768007 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f3d3d9a9700 | 0x7f3c31e361c0 | 12073376143794907 | 12073376143807519 | 12073376144067357 | 12073376144124239 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f3d3d9a9600 | 0x7f3c31e36200 | 12073376144146951 | 12073376144159196 | 12073376144439674 | 12073376144490559 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f3d3d9a9500 | 0x7f3c31e36240 | 12073376144512260 | 12073376144523673 | 12073376144649752 | 12073376144653412 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f3d3d9a9400 | 0x7f3c31e36280 | 12073376144680623 | 12073376144692632 | 12073376144842551 | 12073376144845679 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f3d3d9a9300 | 0x7f3c31e362c0 | 12073376144898758 | 12073376144910550 | 12073376145035669 | 12073376145038778 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f3d3d9a9a00 | 0x7f3c31e36300 | 12073376145067101 | 12073376145079189 | 12073376145337427 | 12073376145390161 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f3d3d9a9900 | 0x7f3c31e36340 | 12073376145411751 | 12073376145423826 | 12073376145668624 | 12073376145719072 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f3d3d9a9800 | 0x7f3c31e36380 | 12073376145744339 | 12073376145756463 | 12073376145881902 | 12073376145884931 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f3d3d9a9700 | 0x7f3c31e363c0 | 12073376145910819 | 12073376145923022 | 12073376146081420 | 12073376146084712 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f3d3d9a9600 | 0x7f3c31e36400 | 12073376146122101 | 12073376146134540 | 12073376146259819 | 12073376146263083 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f3d3d9a9500 | 0x7f3c31e36440 | 12073376146291156 | 12073376146302698 | 12073376146562376 | 12073376146583729 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f3d3d9a9400 | 0x7f3c31e36480 | 12073376146603606 | 12073376146615496 | 12073376146859174 | 12073376146905327 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f3d3d9a9300 | 0x7f3c31e364c0 | 12073376146926246 | 12073376146938213 | 12073376147063332 | 12073376147066737 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f3d3d9a9a00 | 0x7f3c31e36500 | 12073376147093366 | 12073376147105732 | 12073376147270050 | 12073376147273271 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f3d3d9a9900 | 0x7f3c31e36540 | 12073376147310730 | 12073376147323490 | 12073376147449249 | 12073376147452394 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f3d3d9a9800 | 0x7f3c31e36580 | 12073376147479213 | 12073376147491809 | 12073376147753566 | 12073376147774883 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f3d3d9a9700 | 0x7f3c31e365c0 | 12073376147795421 | 12073376147807486 | 12073376148055964 | 12073376148083667 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f3d3d9a9600 | 0x7f3c31e36600 | 12073376148102582 | 12073376148114523 | 12073376148240282 | 12073376148243464 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f3d3d9a9500 | 0x7f3c31e36640 | 12073376148269191 | 12073376148280922 | 12073376148453561 | 12073376148456469 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f3d3d9a9400 | 0x7f3c31e36680 | 12073376148492196 | 12073376148503640 | 12073376148630039 | 12073376148632977 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f3d3d9a9300 | 0x7f3c31e366c0 | 12073376148659497 | 12073376148670999 | 12073376148923157 | 12073376148943014 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f3d3d9a9a00 | 0x7f3c31e36700 | 12073376148963091 | 12073376148975956 | 12073376149220594 | 12073376149248622 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f3d3d9a9900 | 0x7f3c31e36740 | 12073376149272526 | 12073376149285394 | 12073376149410833 | 12073376149413839 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f3d3d9a9800 | 0x7f3c31e36780 | 12073376149434457 | 12073376149445872 | 12073376149629071 | 12073376149632265 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f3d3d9a9700 | 0x7f3c31e367c0 | 12073376149669975 | 12073376149681550 | 12073376149809069 | 12073376149811999 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f3d3d9a9600 | 0x7f3c31e36800 | 12073376149837927 | 12073376149850029 | 12073376150113067 | 12073376150137444 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f3d3d9a9500 | 0x7f3c31e36840 | 12073376150159975 | 12073376150172266 | 12073376150455144 | 12073376150478928 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f3d3d9a9400 | 0x7f3c31e36880 | 12073376150498975 | 12073376150512103 | 12073376150637702 | 12073376150641260 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f3d3d9a9300 | 0x7f3c31e368c0 | 12073376150668500 | 12073376150680902 | 12073376150871940 | 12073376150895382 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f3d3d9a9a00 | 0x7f3c31e36900 | 12073376150926350 | 12073376150938020 | 12073376151063619 | 12073376151066610 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f3d3d9a9900 | 0x7f3c31e36940 | 12073376151094232 | 12073376151106339 | 12073376151388096 | 12073376151414567 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f3d3d9a9800 | 0x7f3c31e36980 | 12073376151434925 | 12073376151446976 | 12073376151692734 | 12073376151716308 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f3d3d9a9700 | 0x7f3c31e369c0 | 12073376151737116 | 12073376151748413 | 12073376151875132 | 12073376151878239 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f3d3d9a9600 | 0x7f3c31e36a00 | 12073376151903866 | 12073376151915292 | 12073376152124250 | 12073376152150655 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f3d3d9a9500 | 0x7f3c31e36a40 | 12073376152183045 | 12073376152197689 | 12073376152325688 | 12073376152328766 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f3d3d9a9400 | 0x7f3c31e36a80 | 12073376152356097 | 12073376152369208 | 12073376152675765 | 12073376152698463 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f3d3d9a9300 | 0x7f3c31e36ac0 | 12073376152719302 | 12073376152732245 | 12073376152987923 | 12073376153021293 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f3d3d9a9a00 | 0x7f3c31e36b00 | 12073376153045047 | 12073376153058002 | 12073376153185041 | 12073376153188113 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f3d3d9a9900 | 0x7f3c31e36b40 | 12073376153214742 | 12073376153226161 | 12073376153452879 | 12073376153480196 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f3d3d9a9800 | 0x7f3c31e36b80 | 12073376153510251 | 12073376153522158 | 12073376153649357 | 12073376153652426 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f3d3d9a9700 | 0x7f3c31e36bc0 | 12073376153679015 | 12073376153690477 | 12073376154048074 | 12073376154075742 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f3d3d9a9600 | 0x7f3c31e36c00 | 12073376154098334 | 12073376154110314 | 12073376154393991 | 12073376154421525 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f3d3d9a9500 | 0x7f3c31e36c40 | 12073376154444778 | 12073376154456711 | 12073376154584390 | 12073376154587443 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f3d3d9a9400 | 0x7f3c31e36c80 | 12073376154615125 | 12073376154626789 | 12073376154871107 | 12073376154898431 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f3d3d9a9300 | 0x7f3c31e36cc0 | 12073376154931332 | 12073376154943747 | 12073376155073185 | 12073376155076682 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f3d3d9a9a00 | 0x7f3c31e36d00 | 12073376155102811 | 12073376155114945 | 12073376155490142 | 12073376155519415 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f3d3d9a9900 | 0x7f3c31e36d40 | 12073376155540434 | 12073376155552062 | 12073376155803579 | 12073376155831465 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f3d3d9a9800 | 0x7f3c31e36d80 | 12073376155851082 | 12073376155863099 | 12073376155993018 | 12073376155996221 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f3d3d9a9700 | 0x7f3c31e36dc0 | 12073376156026928 | 12073376156038297 | 12073376156316855 | 12073376156345500 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f3d3d9a9600 | 0x7f3c31e36e00 | 12073376156376969 | 12073376156390935 | 12073376156525653 | 12073376156528711 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f3d3d9a9500 | 0x7f3c31e36e40 | 12073376156554990 | 12073376156566773 | 12073376156989810 | 12073376157014494 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f3d3d9a9400 | 0x7f3c31e36e80 | 12073376157036424 | 12073376157050289 | 12073376157313327 | 12073376157340199 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f3d3d9a9300 | 0x7f3c31e36ec0 | 12073376157365225 | 12073376157378446 | 12073376157514285 | 12073376157517418 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f3d3d9a9a00 | 0x7f3c31e36f00 | 12073376157543427 | 12073376157554765 | 12073376157868522 | 12073376157891243 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f3d3d9a9900 | 0x7f3c31e36f40 | 12073376157922902 | 12073376157934442 | 12073376158085800 | 12073376158089141 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f3d3d9a9800 | 0x7f3c31e36f80 | 12073376158118085 | 12073376158130440 | 12073376158646756 | 12073376158673587 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f3d3d9a9700 | 0x7f3c31e36fc0 | 12073376158694486 | 12073376158706435 | 12073376159001473 | 12073376159028697 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f3d3d9a9600 | 0x7f3c31e37000 | 12073376159051840 | 12073376159063872 | 12073376159218591 | 12073376159221716 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f3d3d9a9500 | 0x7f3c31e37040 | 12073376159246452 | 12073376159257791 | 12073376159668187 | 12073376159695306 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f3d3d9a9400 | 0x7f3c31e37080 | 12073376159728377 | 12073376159741147 | 12073376159916665 | 12073376159920083 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f3d3d9a9300 | 0x7f3c31e370c0 | 12073376159946122 | 12073376159959065 | 12073376160568660 | 12073376160600348 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f3d3d9a9a00 | 0x7f3c31e37100 | 12073376160623220 | 12073376160636659 | 12073376160960176 | 12073376160986776 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f3d3d9a9900 | 0x7f3c31e37140 | 12073376161014026 | 12073376161027056 | 12073376161204494 | 12073376161207877 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f3d3d9a9800 | 0x7f3c31e37180 | 12073376161234827 | 12073376161246574 | 12073376161702090 | 12073376161728614 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f3d3d9a9700 | 0x7f3c31e371c0 | 12073376161766364 | 12073376161778250 | 12073376161976968 | 12073376162006781 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f3d3d9a9600 | 0x7f3c31e37200 | 12073376162026869 | 12073376162038408 | 12073376162741282 | 12073376162769278 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f3d3d9a9500 | 0x7f3c31e37240 | 12073376162797641 | 12073376162809121 | 12073376163181758 | 12073376163215788 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f3d3d9a9400 | 0x7f3c31e37280 | 12073376163240734 | 12073376163254557 | 12073376163456956 | 12073376163478757 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f3d3d9a9300 | 0x7f3c31e372c0 | 12073376163498964 | 12073376163511675 | 12073376164037271 | 12073376164065437 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f3d3d9a9a00 | 0x7f3c31e37300 | 12073376164098609 | 12073376164111830 | 12073376164334868 | 12073376164365184 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f3d3d9a9900 | 0x7f3c31e37340 | 12073376164386474 | 12073376164399828 | 12073376165197741 | 12073376165229620 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f3d3d9a9800 | 0x7f3c31e37380 | 12073376165250740 | 12073376165264621 | 12073376165685897 | 12073376165712368 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f3d3d9a9700 | 0x7f3c31e373c0 | 12073376165732214 | 12073376165745897 | 12073376165971975 | 12073376165997968 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f3d3d9a9600 | 0x7f3c31e37400 | 12073376166026972 | 12073376166038694 | 12073376166635969 | 12073376166666350 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f3d3d9a9500 | 0x7f3c31e37440 | 12073376166699953 | 12073376166711969 | 12073376166980606 | 12073376167009558 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f3d3d9a9400 | 0x7f3c31e37480 | 12073376167032100 | 12073376167043806 | 12073376168028118 | 12073376168055753 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f3d3d9a9300 | 0x7f3c31e374c0 | 12073376168076211 | 12073376168089397 | 12073376168621713 | 12073376168647913 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f3d3d9a9a00 | 0x7f3c31e37500 | 12073376168670295 | 12073376168684272 | 12073376168955950 | 12073376168978447 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f3d3d9a9900 | 0x7f3c31e37540 | 12073376168999767 | 12073376169017549 | 12073376169754183 | 12073376169781820 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f3d3d9a9800 | 0x7f3c31e37580 | 12073376169816174 | 12073376169829383 | 12073376170145700 | 12073376170168629 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f3d3d9a9700 | 0x7f3c31e375c0 | 12073376170194347 | 12073376170207140 | 12073376171378650 | 12073376171406039 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f3d3d9a9600 | 0x7f3c31e37600 | 12073376171428170 | 12073376171441369 | 12073376172048724 | 12073376172076414 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f3d3d9a9500 | 0x7f3c31e37640 | 12073376172100008 | 12073376172113204 | 12073376172431921 | 12073376172458745 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f3d3d9a9400 | 0x7f3c31e37680 | 12073376172481597 | 12073376172494320 | 12073376173371273 | 12073376173399553 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f3d3d9a9300 | 0x7f3c31e376c0 | 12073376173430781 | 12073376173444553 | 12073376173856869 | 12073376173885456 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f3d3d9a9a00 | 0x7f3c31e37700 | 12073376173909972 | 12073376173923269 | 12073376175472696 | 12073376175546363 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f3d3d9a9900 | 0x7f3c31e37740 | 12073376175568123 | 12073376175581762 | 12073376176376796 | 12073376176452186 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f3d3d9a9800 | 0x7f3c31e37780 | 12073376176473316 | 12073376176484954 | 12073376176899031 | 12073376176942588 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f3d3d9a9700 | 0x7f3c31e377c0 | 12073376176964689 | 12073376176977271 | 12073376178135342 | 12073376178208590 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f3d3d9a9600 | 0x7f3c31e37800 | 12073376178241932 | 12073376178255981 | 12073376179040936 | 12073376179113011 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f3d3d9a9500 | 0x7f3c31e37840 | 12073376179137196 | 12073376179150535 | 12073376182204113 | 12073376182275368 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f3d3d9a9400 | 0x7f3c31e37880 | 12073376182297168 | 12073376182309392 | 12073376183851141 | 12073376183922158 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f3d3d9a9300 | 0x7f3c31e378c0 | 12073376183943979 | 12073376183956100 | 12073376184744734 | 12073376184812974 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f3d3d9a9a00 | 0x7f3c31e37900 | 12073376184840285 | 12073376184852253 | 12073376187133837 | 12073376187206262 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f3d3d9a9900 | 0x7f3c31e37940 | 12073376187239583 | 12073376187252396 | 12073376188787265 | 12073376188858622 |
| 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 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f3d3d9a9800 | 0x7f3c31e37980 | 12073376188880543 | 12073376188893824 | 12073376194949460 | 12073376195026334 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f3d3d9a9700 | 0x7f3c31e379c0 | 12073376195049217 | 12073376195061299 | 12073376198103677 | 12073376198175386 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f3d3d9a9600 | 0x7f3c31e37a00 | 12073376198200423 | 12073376198214076 | 12073376199752945 | 12073376199824210 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 760546 | 760551 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f3d3d9a9500 | 0x7f3c31e37a40 | 12073376199845941 | 12073376199858064 | 12073376204384112 | 12073376204459725 |