46 KiB
46 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | GRBM_COUNT | GRBM_GUI_ACTIVE | SQ_WAVES | SQ_IFETCH | SQ_IFETCH_LEVEL | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 758500 | 758505 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f7559a04180 | 502025 | 502025 | 524288 | 6291456 | 794052 | 101467620 | 12073347399839839 | 12073347643968623 | 12073347644291341 | 12073347644403873 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 758500 | 758505 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f7559a35100 | 28068 | 28068 | 512 | 8192 | 9319 | 1198588 | 12073347659044891 | 12073347659367851 | 12073347659374571 | 12073347659383340 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f76655c5900 | 0x7f7559a35140 | 216739 | 216739 | 65536 | 917504 | 144440 | 18450532 | 12073347659442149 | 12073347659676169 | 12073347659808328 | 12073347659812297 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f76655c5800 | 0x7f7559a35180 | 393393 | 393393 | 65536 | 1245184 | 183278 | 23458684 | 12073347659883419 | 12073347660076167 | 12073347660327525 | 12073347660396092 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f76655c5700 | 0x7f7559a351c0 | 401491 | 401491 | 65536 | 983040 | 137344 | 17545196 | 12073347660427030 | 12073347660624003 | 12073347660879682 | 12073347660944752 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f76655c5600 | 0x7f7559a35200 | 216969 | 216969 | 65536 | 1048576 | 152238 | 19431156 | 12073347660973475 | 12073347661168320 | 12073347661301759 | 12073347661305683 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f76655c5500 | 0x7f7559a35240 | 216019 | 216019 | 65536 | 983040 | 148761 | 19053096 | 12073347661361266 | 12073347661543678 | 12073347661675197 | 12073347661679067 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f76655c5400 | 0x7f7559a35280 | 215673 | 215673 | 65536 | 1048576 | 147489 | 18823360 | 12073347661762512 | 12073347661936796 | 12073347662069275 | 12073347662073580 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f76655c5300 | 0x7f7559a352c0 | 454339 | 454339 | 65536 | 1572864 | 223777 | 28669736 | 12073347662127570 | 12073347662313913 | 12073347662604632 | 12073347662643469 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f76655c5a00 | 0x7f7559a35300 | 403329 | 403329 | 65536 | 1179648 | 157669 | 20247160 | 12073347662678945 | 12073347662865110 | 12073347663121908 | 12073347663187800 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f76655c5900 | 0x7f7559a35340 | 216123 | 216123 | 65536 | 1114112 | 157994 | 20200432 | 12073347663214189 | 12073347663407187 | 12073347663539346 | 12073347663543431 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f76655c5800 | 0x7f7559a35380 | 216945 | 216945 | 65536 | 1114112 | 156564 | 20078500 | 12073347663597181 | 12073347663770865 | 12073347663903664 | 12073347663907478 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f76655c5700 | 0x7f7559a353c0 | 214851 | 214851 | 65536 | 1179648 | 167242 | 21324080 | 12073347663975584 | 12073347664151502 | 12073347664283022 | 12073347664287063 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f76655c5600 | 0x7f7559a35400 | 399865 | 399865 | 65536 | 1835008 | 256467 | 32902108 | 12073347664342496 | 12073347664514860 | 12073347664769899 | 12073347664834400 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f76655c5500 | 0x7f7559a35440 | 396731 | 396731 | 65536 | 1310720 | 178113 | 22838812 | 12073347664861972 | 12073347665050697 | 12073347665304616 | 12073347665370136 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f76655c5400 | 0x7f7559a35480 | 210089 | 210089 | 65536 | 1245184 | 175887 | 22540088 | 12073347665398529 | 12073347665596774 | 12073347665725093 | 12073347665728883 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f76655c5300 | 0x7f7559a354c0 | 220875 | 220875 | 65536 | 1310720 | 181980 | 23252480 | 12073347665783624 | 12073347665954212 | 12073347666090211 | 12073347666094091 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f76655c5a00 | 0x7f7559a35500 | 212185 | 212185 | 65536 | 1310720 | 186822 | 23928536 | 12073347666161066 | 12073347666331489 | 12073347666460769 | 12073347666464640 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f76655c5900 | 0x7f7559a35540 | 398187 | 398187 | 65536 | 2097152 | 292194 | 37370968 | 12073347666519332 | 12073347666689087 | 12073347666943806 | 12073347667021725 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f76655c5800 | 0x7f7559a35580 | 397345 | 397345 | 65536 | 1441792 | 194985 | 24980744 | 12073347667070887 | 12073347667238204 | 12073347667491643 | 12073347667555938 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f76655c5700 | 0x7f7559a355c0 | 218003 | 218003 | 65536 | 1376256 | 186852 | 23907344 | 12073347667582658 | 12073347667766681 | 12073347667899800 | 12073347667903734 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f76655c5600 | 0x7f7559a35600 | 210121 | 210121 | 65536 | 1507328 | 208962 | 26708548 | 12073347667958536 | 12073347668135799 | 12073347668264438 | 12073347668268492 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f76655c5500 | 0x7f7559a35640 | 206859 | 206859 | 65536 | 1441792 | 199877 | 25512520 | 12073347668334194 | 12073347668508277 | 12073347668634996 | 12073347668638750 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f76655c5400 | 0x7f7559a35680 | 393689 | 393689 | 65536 | 2359296 | 326512 | 41938188 | 12073347668691979 | 12073347668868274 | 12073347669120273 | 12073347669185036 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f76655c5300 | 0x7f7559a356c0 | 402499 | 402499 | 65536 | 1572864 | 211069 | 27019012 | 12073347669211294 | 12073347669406351 | 12073347669663470 | 12073347669728576 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f76655c5a00 | 0x7f7559a35700 | 213409 | 213409 | 65536 | 1507328 | 207681 | 26627880 | 12073347669753682 | 12073347669944748 | 12073347670075467 | 12073347670079277 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f76655c5900 | 0x7f7559a35740 | 211443 | 211443 | 65536 | 1703936 | 231945 | 29652872 | 12073347670132997 | 12073347670309706 | 12073347670439145 | 12073347670442943 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f76655c5800 | 0x7f7559a35780 | 208841 | 208841 | 65536 | 1572864 | 217348 | 27818868 | 12073347670508675 | 12073347670676264 | 12073347670803943 | 12073347670807851 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f76655c5700 | 0x7f7559a357c0 | 406307 | 406307 | 65536 | 2621440 | 356417 | 45660112 | 12073347670859928 | 12073347671042822 | 12073347671302980 | 12073347671367962 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f76655c5600 | 0x7f7559a35800 | 391481 | 391481 | 65536 | 1703936 | 236072 | 30256252 | 12073347671397467 | 12073347671585858 | 12073347671836257 | 12073347671900342 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f76655c5500 | 0x7f7559a35840 | 208395 | 208395 | 65536 | 1638400 | 236973 | 30356524 | 12073347671927061 | 12073347672115615 | 12073347672243454 | 12073347672247547 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f76655c5400 | 0x7f7559a35880 | 215841 | 215841 | 65536 | 1900544 | 271304 | 34733360 | 12073347672301738 | 12073347672478973 | 12073347672611452 | 12073347672615230 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f76655c5300 | 0x7f7559a358c0 | 214947 | 214947 | 65536 | 1703936 | 234338 | 30009644 | 12073347672680662 | 12073347672848091 | 12073347672979930 | 12073347672983815 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f76655c5a00 | 0x7f7559a35900 | 392825 | 392825 | 65536 | 2883584 | 387560 | 49561232 | 12073347673037936 | 12073347673222809 | 12073347673475447 | 12073347673540610 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f76655c5900 | 0x7f7559a35940 | 396083 | 396083 | 65536 | 1835008 | 247310 | 31796368 | 12073347673566668 | 12073347673751445 | 12073347674005524 | 12073347674070645 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f76655c5800 | 0x7f7559a35980 | 215025 | 215025 | 65536 | 1769472 | 256579 | 32802452 | 12073347674094980 | 12073347674295282 | 12073347674427441 | 12073347674431175 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f76655c5700 | 0x7f7559a359c0 | 214987 | 214987 | 65536 | 2097152 | 303121 | 38867832 | 12073347674487039 | 12073347674655920 | 12073347674788559 | 12073347674792246 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f76655c5600 | 0x7f7559a35a00 | 215377 | 215377 | 65536 | 1835008 | 260612 | 33306764 | 12073347674860573 | 12073347675034318 | 12073347675166157 | 12073347675170148 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f76655c5500 | 0x7f7559a35a40 | 394011 | 394011 | 65536 | 3145728 | 438218 | 56186804 | 12073347675224599 | 12073347675402476 | 12073347675656394 | 12073347675696266 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f76655c5400 | 0x7f7559a35a80 | 399625 | 399625 | 65536 | 1966080 | 269997 | 34510392 | 12073347675727614 | 12073347675903593 | 12073347676160071 | 12073347676230859 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f76655c5300 | 0x7f7559a35ac0 | 207779 | 207779 | 65536 | 1900544 | 259124 | 33159728 | 12073347676254513 | 12073347676450949 | 12073347676578789 | 12073347676582683 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f76655c5a00 | 0x7f7559a35b00 | 220833 | 220833 | 65536 | 2293760 | 313116 | 40043400 | 12073347676639449 | 12073347676813187 | 12073347676949666 | 12073347676953432 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f76655c5900 | 0x7f7559a35b40 | 208315 | 208315 | 65536 | 1966080 | 292633 | 37417348 | 12073347677023452 | 12073347677194465 | 12073347677322304 | 12073347677326205 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f76655c5800 | 0x7f7559a35b80 | 413361 | 413361 | 65536 | 3407872 | 460495 | 58919700 | 12073347677380456 | 12073347677559103 | 12073347677825021 | 12073347677890554 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f76655c5700 | 0x7f7559a35bc0 | 393995 | 393995 | 65536 | 2097152 | 279096 | 35631048 | 12073347677921852 | 12073347678110620 | 12073347678363418 | 12073347678428544 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f76655c5600 | 0x7f7559a35c00 | 211097 | 211097 | 65536 | 2031616 | 286964 | 36787444 | 12073347678452769 | 12073347678640056 | 12073347678769816 | 12073347678773695 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f76655c5500 | 0x7f7559a35c40 | 220315 | 220315 | 65536 | 2490368 | 365128 | 46619044 | 12073347678826213 | 12073347678998614 | 12073347679135254 | 12073347679139445 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f76655c5400 | 0x7f7559a35c80 | 212705 | 212705 | 65536 | 2097152 | 281989 | 36130676 | 12073347679206149 | 12073347679375732 | 12073347679505971 | 12073347679509893 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f76655c5300 | 0x7f7559a35cc0 | 400099 | 400099 | 65536 | 3670016 | 489609 | 62663108 | 12073347679564555 | 12073347679742770 | 12073347680001168 | 12073347680039888 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f76655c5a00 | 0x7f7559a35d00 | 395193 | 395193 | 65536 | 2228224 | 300954 | 38658696 | 12073347680073731 | 12073347680252847 | 12073347680506765 | 12073347680570965 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f76655c5900 | 0x7f7559a35d40 | 208523 | 208523 | 65536 | 2162688 | 303547 | 38871448 | 12073347680594278 | 12073347680779884 | 12073347680908043 | 12073347680911939 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f76655c5800 | 0x7f7559a35d80 | 222745 | 222745 | 65536 | 2686976 | 383631 | 49172584 | 12073347680965638 | 12073347681147882 | 12073347681285641 | 12073347681289891 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f76655c5700 | 0x7f7559a35dc0 | 213195 | 213195 | 65536 | 2228224 | 327427 | 41857136 | 12073347681355493 | 12073347681524999 | 12073347681656039 | 12073347681659999 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f76655c5600 | 0x7f7559a35e00 | 407625 | 407625 | 65536 | 3932160 | 522507 | 67010644 | 12073347681714600 | 12073347681884677 | 12073347682147236 | 12073347682213277 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f76655c5500 | 0x7f7559a35e40 | 396995 | 396995 | 65536 | 2359296 | 309622 | 39590416 | 12073347682238554 | 12073347682426434 | 12073347682681632 | 12073347682746267 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f76655c5400 | 0x7f7559a35e80 | 211929 | 211929 | 65536 | 2293760 | 326198 | 41786372 | 12073347682769951 | 12073347682960671 | 12073347683090430 | 12073347683094384 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f76655c5300 | 0x7f7559a35ec0 | 228915 | 228915 | 65536 | 2883584 | 426079 | 54633484 | 12073347683147814 | 12073347683331389 | 12073347683473788 | 12073347683477717 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f76655c5a00 | 0x7f7559a35f00 | 213097 | 213097 | 65536 | 2359296 | 325972 | 41714420 | 12073347683544180 | 12073347683710746 | 12073347683841626 | 12073347683845570 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f76655c5900 | 0x7f7559a35f40 | 405539 | 405539 | 65536 | 4194304 | 561629 | 71973796 | 12073347683897787 | 12073347684072344 | 12073347684333783 | 12073347684401824 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f76655c5800 | 0x7f7559a35f80 | 387769 | 387769 | 65536 | 2490368 | 330261 | 42299612 | 12073347684429676 | 12073347684612981 | 12073347684862420 | 12073347684927240 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f76655c5700 | 0x7f7559a35fc0 | 214531 | 214531 | 65536 | 2424832 | 355598 | 45526152 | 12073347684951586 | 12073347685142578 | 12073347685274897 | 12073347685279004 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f76655c5600 | 0x7f7559a36000 | 229705 | 229705 | 65536 | 3080192 | 480666 | 61663888 | 12073347685332624 | 12073347685509136 | 12073347685652015 | 12073347685656005 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f76655c5500 | 0x7f7559a36040 | 214371 | 214371 | 65536 | 2490368 | 353344 | 45201888 | 12073347685721436 | 12073347685888013 | 12073347686020013 | 12073347686024379 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f76655c5400 | 0x7f7559a36080 | 410169 | 410169 | 65536 | 4456448 | 593184 | 75825536 | 12073347686077348 | 12073347686261771 | 12073347686526250 | 12073347686592074 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f76655c5300 | 0x7f7559a360c0 | 389795 | 389795 | 65536 | 2621440 | 347067 | 44470896 | 12073347686615789 | 12073347686803848 | 12073347687055207 | 12073347687124304 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f76655c5a00 | 0x7f7559a36100 | 211713 | 211713 | 65536 | 2555904 | 369884 | 47356676 | 12073347687148308 | 12073347687340645 | 12073347687471044 | 12073347687474845 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f76655c5900 | 0x7f7559a36140 | 231515 | 231515 | 65536 | 3276800 | 525233 | 67187656 | 12073347687530008 | 12073347687702083 | 12073347687845762 | 12073347687849732 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f76655c5800 | 0x7f7559a36180 | 213569 | 213569 | 65536 | 2621440 | 379167 | 48585672 | 12073347687915103 | 12073347688090720 | 12073347688222080 | 12073347688225951 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f76655c5700 | 0x7f7559a361c0 | 415779 | 415779 | 65536 | 4718592 | 647425 | 83020856 | 12073347688280873 | 12073347688451198 | 12073347688720477 | 12073347688785100 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f76655c5600 | 0x7f7559a36200 | 395769 | 395769 | 65536 | 2752512 | 380145 | 48826120 | 12073347688808363 | 12073347688994715 | 12073347689249754 | 12073347689316538 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f76655c5500 | 0x7f7559a36240 | 219499 | 219499 | 65536 | 2686976 | 418224 | 53512268 | 12073347689341223 | 12073347689529432 | 12073347689665111 | 12073347689669153 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f76655c5400 | 0x7f7559a36280 | 244361 | 244361 | 65536 | 3473408 | 530346 | 67671696 | 12073347689723754 | 12073347689895190 | 12073347690047829 | 12073347690052275 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f76655c5300 | 0x7f7559a362c0 | 210443 | 210443 | 65536 | 2752512 | 379052 | 48557024 | 12073347690138565 | 12073347690313587 | 12073347690443346 | 12073347690447159 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f76655c5a00 | 0x7f7559a36300 | 407185 | 407185 | 65536 | 4980736 | 663960 | 85237640 | 12073347690498574 | 12073347690673585 | 12073347690937264 | 12073347690956866 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f76655c5900 | 0x7f7559a36340 | 389291 | 389291 | 65536 | 2883584 | 375751 | 48156104 | 12073347691012098 | 12073347691173422 | 12073347691424781 | 12073347691470971 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f76655c5800 | 0x7f7559a36380 | 217257 | 217257 | 65536 | 2818048 | 442340 | 56605276 | 12073347691494585 | 12073347691685259 | 12073347691819178 | 12073347691823466 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f76655c5700 | 0x7f7559a363c0 | 253259 | 253259 | 65536 | 3670016 | 569180 | 72683572 | 12073347691875263 | 12073347692055657 | 12073347692214376 | 12073347692218831 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f76655c5600 | 0x7f7559a36400 | 212201 | 212201 | 65536 | 2883584 | 388116 | 49732576 | 12073347692285084 | 12073347692452775 | 12073347692583174 | 12073347692587105 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f76655c5500 | 0x7f7559a36440 | 408043 | 408043 | 65536 | 5177344 | 692815 | 88850700 | 12073347692642048 | 12073347692811652 | 12073347693076291 | 12073347693123572 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f76655c5400 | 0x7f7559a36480 | 388777 | 388777 | 65536 | 3014656 | 424387 | 54254156 | 12073347693147928 | 12073347693337889 | 12073347693588768 | 12073347693634452 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f76655c5300 | 0x7f7559a364c0 | 220795 | 220795 | 65536 | 2949120 | 499963 | 64080020 | 12073347693657364 | 12073347693845086 | 12073347693981725 | 12073347693985755 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f76655c5a00 | 0x7f7559a36500 | 263465 | 263465 | 65536 | 3866624 | 558106 | 71050356 | 12073347694041779 | 12073347694214524 | 12073347694379803 | 12073347694384035 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f76655c5900 | 0x7f7559a36540 | 213755 | 213755 | 65536 | 3014656 | 429571 | 54973180 | 12073347694448805 | 12073347694615002 | 12073347694747001 | 12073347694751157 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f76655c5800 | 0x7f7559a36580 | 406721 | 406721 | 65536 | 5439488 | 724766 | 92902300 | 12073347694803635 | 12073347694980120 | 12073347695243478 | 12073347695290740 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f76655c5700 | 0x7f7559a365c0 | 394595 | 394595 | 65536 | 3145728 | 415657 | 53183048 | 12073347695314103 | 12073347695502196 | 12073347695757235 | 12073347695802311 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f76655c5600 | 0x7f7559a36600 | 213985 | 213985 | 65536 | 3080192 | 435756 | 55739168 | 12073347695829641 | 12073347696015313 | 12073347696146833 | 12073347696151189 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f76655c5500 | 0x7f7559a36640 | 276315 | 276315 | 65536 | 4063232 | 569062 | 72751632 | 12073347696204488 | 12073347696379311 | 12073347696553710 | 12073347696557905 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f76655c5400 | 0x7f7559a36680 | 216729 | 216729 | 65536 | 3145728 | 422904 | 54138568 | 12073347696623537 | 12073347696791469 | 12073347696925228 | 12073347696929305 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f76655c5300 | 0x7f7559a366c0 | 401747 | 401747 | 65536 | 5701632 | 767556 | 98516388 | 12073347696983125 | 12073347697161387 | 12073347697422025 | 12073347697469729 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f76655c5a00 | 0x7f7559a36700 | 395785 | 395785 | 65536 | 3276800 | 440201 | 56486736 | 12073347697498122 | 12073347697681224 | 12073347697937062 | 12073347697956203 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f76655c5900 | 0x7f7559a36740 | 223283 | 223283 | 65536 | 3211264 | 489326 | 62491140 | 12073347698014702 | 12073347698179141 | 12073347698317700 | 12073347698321913 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f76655c5800 | 0x7f7559a36780 | 289769 | 289769 | 65536 | 4259840 | 591364 | 75803232 | 12073347698376324 | 12073347698552098 | 12073347698734977 | 12073347698739459 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f76655c5700 | 0x7f7559a367c0 | 220683 | 220683 | 65536 | 3276800 | 555498 | 71073424 | 12073347698811202 | 12073347698981856 | 12073347699118815 | 12073347699122741 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f76655c5600 | 0x7f7559a36800 | 410609 | 410609 | 65536 | 7733248 | 978336 | 125363124 | 12073347699178244 | 12073347699349214 | 12073347699615932 | 12073347699660831 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f76655c5500 | 0x7f7559a36840 | 393627 | 393627 | 65536 | 3407872 | 445701 | 57114904 | 12073347699685657 | 12073347699868731 | 12073347700122969 | 12073347700170709 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f76655c5400 | 0x7f7559a36880 | 221961 | 221961 | 65536 | 3342336 | 480525 | 61414688 | 12073347700194333 | 12073347700385527 | 12073347700522807 | 12073347700526700 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f76655c5300 | 0x7f7559a368c0 | 302099 | 302099 | 65536 | 4456448 | 642156 | 81734772 | 12073347700580971 | 12073347700748085 | 12073347700940084 | 12073347700959675 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f76655c5a00 | 0x7f7559a36900 | 222321 | 222321 | 65536 | 3538944 | 569802 | 72981140 | 12073347701028202 | 12073347701199283 | 12073347701336402 | 12073347701340943 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f76655c5900 | 0x7f7559a36940 | 434267 | 434267 | 65536 | 8978432 | 1127442 | 144345868 | 12073347701396968 | 12073347701569520 | 12073347701852719 | 12073347701897568 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f76655c5800 | 0x7f7559a36980 | 394665 | 394665 | 65536 | 3670016 | 528731 | 67674216 | 12073347701920460 | 12073347702112557 | 12073347702367436 | 12073347702412785 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f76655c5700 | 0x7f7559a369c0 | 212291 | 212291 | 65536 | 3604480 | 508378 | 65136164 | 12073347702437281 | 12073347702629354 | 12073347702760873 | 12073347702764940 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f76655c5600 | 0x7f7559a36a00 | 329281 | 329281 | 65536 | 4849664 | 699621 | 89547480 | 12073347702818820 | 12073347702993512 | 12073347703203591 | 12073347703249941 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f76655c5500 | 0x7f7559a36a40 | 227635 | 227635 | 65536 | 3801088 | 612103 | 78338780 | 12073347703292741 | 12073347703457829 | 12073347703599268 | 12073347703603408 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f76655c5400 | 0x7f7559a36a80 | 470521 | 470521 | 65536 | 14548992 | 1827570 | 234030932 | 12073347703659512 | 12073347703837187 | 12073347704144385 | 12073347704191271 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f76655c5300 | 0x7f7559a36ac0 | 384635 | 384635 | 65536 | 3932160 | 517110 | 66049496 | 12073347704219032 | 12073347704401184 | 12073347704650462 | 12073347704668578 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f76655c5a00 | 0x7f7559a36b00 | 216993 | 216993 | 65536 | 3866624 | 563625 | 72021788 | 12073347704717468 | 12073347704881821 | 12073347705016220 | 12073347705020612 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f76655c5900 | 0x7f7559a36b40 | 356395 | 356395 | 65536 | 5242880 | 800499 | 102882768 | 12073347705074802 | 12073347705253019 | 12073347705481657 | 12073347705528746 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f76655c5800 | 0x7f7559a36b80 | 218873 | 218873 | 65536 | 4063232 | 604969 | 77522900 | 12073347705570093 | 12073347705733496 | 12073347705868695 | 12073347705872635 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f76655c5700 | 0x7f7559a36bc0 | 506603 | 506603 | 65536 | 10027008 | 1259065 | 161364496 | 12073347705924922 | 12073347706109334 | 12073347706441332 | 12073347706487738 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f76655c5600 | 0x7f7559a36c00 | 389497 | 389497 | 65536 | 4194304 | 617254 | 79123172 | 12073347706515660 | 12073347706698558 | 12073347706950557 | 12073347706998588 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f76655c5500 | 0x7f7559a36c40 | 227419 | 227419 | 65536 | 4128768 | 679205 | 86947068 | 12073347707032731 | 12073347707214074 | 12073347707355354 | 12073347707359148 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f76655c5400 | 0x7f7559a36c80 | 382385 | 382385 | 65536 | 5636096 | 782626 | 99998088 | 12073347707413939 | 12073347707592952 | 12073347707838391 | 12073347707882480 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f76655c5300 | 0x7f7559a36cc0 | 227139 | 227139 | 65536 | 4587520 | 724669 | 92713880 | 12073347707922324 | 12073347708095830 | 12073347708237429 | 12073347708241407 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f76655c5a00 | 0x7f7559a36d00 | 577161 | 577161 | 65536 | 11075584 | 1390248 | 177986740 | 12073347708298082 | 12073347708471348 | 12073347708850546 | 12073347708895813 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f76655c5900 | 0x7f7559a36d40 | 398355 | 398355 | 65536 | 4718592 | 685237 | 87531752 | 12073347708921060 | 12073347709104624 | 12073347709363663 | 12073347709410129 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f76655c5800 | 0x7f7559a36d80 | 220969 | 220969 | 65536 | 4653056 | 665192 | 85091864 | 12073347709435456 | 12073347709623021 | 12073347709760141 | 12073347709763746 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f76655c5700 | 0x7f7559a36dc0 | 433451 | 433451 | 65536 | 6422528 | 900758 | 115858104 | 12073347709817085 | 12073347709987499 | 12073347710268458 | 12073347710313257 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f76655c5600 | 0x7f7559a36e00 | 226225 | 226225 | 65536 | 5111808 | 803164 | 102676556 | 12073347710354664 | 12073347710519657 | 12073347710660616 | 12073347710664340 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f76655c5500 | 0x7f7559a36e40 | 644619 | 644619 | 65536 | 15007744 | 1887251 | 241467988 | 12073347710717449 | 12073347710889575 | 12073347711315812 | 12073347711361405 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f76655c5400 | 0x7f7559a36e80 | 401313 | 401313 | 65536 | 5242880 | 698241 | 89520456 | 12073347711389357 | 12073347711579651 | 12073347711840289 | 12073347711884888 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f76655c5300 | 0x7f7559a36ec0 | 223371 | 223371 | 65536 | 5177344 | 864478 | 110793676 | 12073347711910686 | 12073347712098688 | 12073347712238047 | 12073347712242062 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f76655c5a00 | 0x7f7559a36f00 | 486729 | 486729 | 65536 | 7208960 | 1003025 | 128560680 | 12073347712297124 | 12073347712464126 | 12073347712779644 | 12073347712798716 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f76655c5900 | 0x7f7559a36f40 | 242667 | 242667 | 65536 | 6160384 | 910233 | 116572968 | 12073347712860862 | 12073347713032763 | 12073347713185402 | 12073347713189372 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f76655c5800 | 0x7f7559a36f80 | 784633 | 784633 | 65536 | 17104896 | 2143519 | 274471676 | 12073347713244174 | 12073347713422681 | 12073347713942038 | 12073347713987305 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f76655c5700 | 0x7f7559a36fc0 | 461587 | 461587 | 65536 | 6291456 | 948114 | 121499216 | 12073347714017972 | 12073347714206837 | 12073347714510035 | 12073347714554640 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f76655c5600 | 0x7f7559a37000 | 245593 | 245593 | 65536 | 6225920 | 900491 | 115249668 | 12073347714582862 | 12073347714764434 | 12073347714918833 | 12073347714922513 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f76655c5500 | 0x7f7559a37040 | 592547 | 592547 | 65536 | 8781824 | 1238234 | 159404152 | 12073347714978157 | 12073347715163311 | 12073347715549229 | 12073347715593801 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f76655c5400 | 0x7f7559a37080 | 278009 | 278009 | 65536 | 7208960 | 1060057 | 135594848 | 12073347715634306 | 12073347715799628 | 12073347715976107 | 12073347715979848 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f76655c5300 | 0x7f7559a370c0 | 943171 | 943171 | 65536 | 19202048 | 2414169 | 308152328 | 12073347716034039 | 12073347716214826 | 12073347716838982 | 12073347716885451 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f76655c5a00 | 0x7f7559a37100 | 501897 | 501897 | 65536 | 7340032 | 974537 | 125283736 | 12073347716908113 | 12073347717098181 | 12073347717426819 | 12073347717472953 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f76655c5900 | 0x7f7559a37140 | 281459 | 281459 | 65536 | 7274496 | 1055744 | 135197644 | 12073347717500193 | 12073347717682498 | 12073347717861217 | 12073347717865052 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f76655c5800 | 0x7f7559a37180 | 697761 | 697761 | 65536 | 10354688 | 1515852 | 193346704 | 12073347717921036 | 12073347718095936 | 12073347718552093 | 12073347718596030 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f76655c5700 | 0x7f7559a371c0 | 315171 | 315171 | 65536 | 8257536 | 1284756 | 164258532 | 12073347718640162 | 12073347718804732 | 12073347719006971 | 12073347719051066 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f76655c5600 | 0x7f7559a37200 | 1065369 | 1065369 | 65536 | 21299200 | 2671643 | 341917964 | 12073347719079829 | 12073347719261209 | 12073347719966166 | 12073347719984540 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f76655c5500 | 0x7f7559a37240 | 566443 | 566443 | 65536 | 8388608 | 1132207 | 145087048 | 12073347720042458 | 12073347720211284 | 12073347720585202 | 12073347720632054 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f76655c5400 | 0x7f7559a37280 | 317449 | 317449 | 65536 | 8323072 | 1247790 | 159617424 | 12073347720655597 | 12073347720871601 | 12073347721074640 | 12073347721121724 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f76655c5300 | 0x7f7559a372c0 | 803499 | 803499 | 65536 | 11927552 | 1667484 | 214038800 | 12073347721153052 | 12073347721333518 | 12073347721860875 | 12073347721907534 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f76655c5a00 | 0x7f7559a37300 | 349897 | 349897 | 65536 | 9306112 | 1425958 | 182507588 | 12073347721948039 | 12073347722119914 | 12073347722344553 | 12073347722390331 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f76655c5900 | 0x7f7559a37340 | 1208275 | 1208275 | 65536 | 29163520 | 3653393 | 467568488 | 12073347722416039 | 12073347722598471 | 12073347723399267 | 12073347723446133 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f76655c5800 | 0x7f7559a37380 | 638889 | 638889 | 65536 | 9437184 | 1321991 | 168933604 | 12073347723470228 | 12073347723656866 | 12073347724078463 | 12073347724143549 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f76655c5700 | 0x7f7559a373c0 | 354795 | 354795 | 65536 | 9371648 | 1448280 | 185418052 | 12073347724169397 | 12073347724359422 | 12073347724587901 | 12073347724653046 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f76655c5600 | 0x7f7559a37400 | 911321 | 911321 | 65536 | 13500416 | 1917031 | 245947608 | 12073347724680928 | 12073347724863419 | 12073347725461816 | 12073347725531990 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f76655c5500 | 0x7f7559a37440 | 420171 | 420171 | 65536 | 11403264 | 1795756 | 229995564 | 12073347725569149 | 12073347725747414 | 12073347726018453 | 12073347726083715 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f76655c5400 | 0x7f7559a37480 | 1486921 | 1486921 | 65536 | 33357824 | 4179033 | 534697652 | 12073347726107870 | 12073347726297331 | 12073347727283086 | 12073347727349527 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f76655c5300 | 0x7f7559a374c0 | 777219 | 777219 | 65536 | 11534336 | 1563872 | 199586848 | 12073347727376537 | 12073347727564525 | 12073347728080682 | 12073347728146528 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f76655c5a00 | 0x7f7559a37500 | 423033 | 423033 | 65536 | 11534336 | 1840335 | 235514376 | 12073347728177055 | 12073347728365000 | 12073347728638439 | 12073347728704265 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f76655c5900 | 0x7f7559a37540 | 1126963 | 1126963 | 65536 | 19267584 | 2416378 | 309659660 | 12073347728727488 | 12073347728917317 | 12073347729656513 | 12073347729727226 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f76655c5800 | 0x7f7559a37580 | 490289 | 490289 | 65536 | 13500416 | 2100598 | 268859580 | 12073347729765337 | 12073347729936832 | 12073347730254750 | 12073347730320418 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f76655c5700 | 0x7f7559a375c0 | 1768675 | 1768675 | 65536 | 37552128 | 4693690 | 601646632 | 12073347730346256 | 12073347730530589 | 12073347731702742 | 12073347731769862 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f76655c5600 | 0x7f7559a37600 | 919617 | 919617 | 65536 | 13631488 | 1900053 | 242493460 | 12073347731799187 | 12073347731987861 | 12073347732598257 | 12073347732664845 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f76655c5500 | 0x7f7559a37640 | 493675 | 493675 | 65536 | 13631488 | 2066480 | 264526536 | 12073347732690533 | 12073347732891056 | 12073347733211374 | 12073347733281551 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f76655c5400 | 0x7f7559a37680 | 1336353 | 1336353 | 65536 | 21692416 | 2738958 | 350679312 | 12073347733305917 | 12073347733490573 | 12073347734369928 | 12073347734436007 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f76655c5300 | 0x7f7559a376c0 | 630867 | 630867 | 65536 | 17694720 | 2767280 | 354183264 | 12073347734478035 | 12073347734644006 | 12073347735056644 | 12073347735123374 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f76655c5a00 | 0x7f7559a37700 | 2331817 | 2331817 | 65536 | 57475072 | 7193720 | 920867752 | 12073347735152628 | 12073347735338403 | 12073347736889594 | 12073347736956010 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f76655c5900 | 0x7f7559a37740 | 1199771 | 1199771 | 65536 | 19660800 | 2476450 | 316578196 | 12073347736986026 | 12073347737177273 | 12073347737974548 | 12073347738040155 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f76655c5800 | 0x7f7559a37780 | 640729 | 640729 | 65536 | 20381696 | 2569700 | 328641688 | 12073347738064620 | 12073347738252947 | 12073347738668305 | 12073347738732091 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f76655c5700 | 0x7f7559a377c0 | 1758379 | 1758379 | 65536 | 28704768 | 3619147 | 462900416 | 12073347738760814 | 12073347738939983 | 12073347740099657 | 12073347740169732 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f76655c5600 | 0x7f7559a37800 | 1197041 | 1197041 | 65536 | 36634624 | 4655726 | 595918124 | 12073347740213674 | 12073347740383175 | 12073347741168771 | 12073347741235823 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f76655c5500 | 0x7f7559a37840 | 4583971 | 4583971 | 65536 | 105840640 | 13238761 | 1694738132 | 12073347741262733 | 12073347741456770 | 12073347744510353 | 12073347744577233 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f76655c5400 | 0x7f7559a37880 | 2323777 | 2323777 | 65536 | 38535168 | 4840251 | 618482452 | 12073347744608842 | 12073347744789232 | 12073347746331623 | 12073347746400341 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f76655c5300 | 0x7f7559a378c0 | 1204467 | 1204467 | 65536 | 39124992 | 4914677 | 629249996 | 12073347746429706 | 12073347746619622 | 12073347747409858 | 12073347747477142 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f76655c5a00 | 0x7f7559a37900 | 3444041 | 3444041 | 65536 | 55771136 | 7011594 | 897013724 | 12073347747505846 | 12073347747692896 | 12073347749977044 | 12073347750050074 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f76655c5900 | 0x7f7559a37940 | 2323371 | 2323371 | 65536 | 72548352 | 9114747 | 1166783340 | 12073347750095638 | 12073347750262802 | 12073347751798154 | 12073347751865437 |
| 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 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f76655c5800 | 0x7f7559a37980 | 9086745 | 9086745 | 65536 | 210698240 | 26348616 | 3372627536 | 12073347751896866 | 12073347752089992 | 12073347758145960 | 12073347758214526 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f76655c5700 | 0x7f7559a379c0 | 4574691 | 4574691 | 65536 | 76283904 | 9564348 | 1223226516 | 12073347758247858 | 12073347758429958 | 12073347761474742 | 12073347761542000 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f76655c5600 | 0x7f7559a37a00 | 2328633 | 2328633 | 65536 | 77398016 | 9705092 | 1242371212 | 12073347761573238 | 12073347761766580 | 12073347763306892 | 12073347763374085 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 758500 | 758505 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f76655c5500 | 0x7f7559a37a40 | 6812043 | 6812043 | 65536 | 110821376 | 13885302 | 1777046536 | 12073347763404151 | 12073347763590730 | 12073347768118066 | 12073347768186889 |