40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 852721 | 852726 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f6e8fa04180 | 0 | 0 | 0 | 12074902136846207 | 12074902384490777 | 12074902384815895 | 12074902384929407 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 852721 | 852726 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f6e8fa35100 | 0 | 0 | 0 | 12074902399651707 | 12074902399953892 | 12074902399960772 | 12074902399971361 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f6fbfb0d900 | 0x7f6e8fa35140 | 0 | 0 | 0 | 12074902400033135 | 12074902400249250 | 12074902400384129 | 12074902400387534 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f6fbfb0d800 | 0x7f6e8fa35180 | 0 | 0 | 0 | 12074902400454078 | 12074902400627808 | 12074902400885567 | 12074902400955339 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f6fbfb0d700 | 0x7f6e8fa351c0 | 0 | 0 | 0 | 12074902400982059 | 12074902401180605 | 12074902401435004 | 12074902401506163 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f6fbfb0d600 | 0x7f6e8fa35200 | 0 | 0 | 0 | 12074902401535267 | 12074902401724122 | 12074902401851641 | 12074902401854510 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f6fbfb0d500 | 0x7f6e8fa35240 | 0 | 0 | 0 | 12074902401916155 | 12074902402096120 | 12074902402234359 | 12074902402237261 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f6fbfb0d400 | 0x7f6e8fa35280 | 0 | 0 | 0 | 12074902402316439 | 12074902402488598 | 12074902402619317 | 12074902402622437 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f6fbfb0d300 | 0x7f6e8fa352c0 | 0 | 0 | 0 | 12074902402670436 | 12074902402846516 | 12074902403108114 | 12074902403151581 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f6fbfb0da00 | 0x7f6e8fa35300 | 0 | 0 | 0 | 12074902403178851 | 12074902403362513 | 12074902403617552 | 12074902403685934 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f6fbfb0d900 | 0x7f6e8fa35340 | 0 | 0 | 0 | 12074902403711681 | 12074902403909390 | 12074902404043149 | 12074902404046253 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f6fbfb0d800 | 0x7f6e8fa35380 | 0 | 0 | 0 | 12074902404095475 | 12074902404272108 | 12074902404412107 | 12074902404414938 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f6fbfb0d700 | 0x7f6e8fa353c0 | 0 | 0 | 0 | 12074902404475461 | 12074902404645066 | 12074902404776265 | 12074902404778995 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f6fbfb0d600 | 0x7f6e8fa35400 | 0 | 0 | 0 | 12074902404827475 | 12074902404999624 | 12074902405260423 | 12074902405331201 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f6fbfb0d500 | 0x7f6e8fa35440 | 0 | 0 | 0 | 12074902405356679 | 12074902405546501 | 12074902405806980 | 12074902405876995 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f6fbfb0d400 | 0x7f6e8fa35480 | 0 | 0 | 0 | 12074902405903174 | 12074902406094498 | 12074902406222497 | 12074902406225423 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f6fbfb0d300 | 0x7f6e8fa354c0 | 0 | 0 | 0 | 12074902406272651 | 12074902406447616 | 12074902406586176 | 12074902406588928 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f6fbfb0da00 | 0x7f6e8fa35500 | 0 | 0 | 0 | 12074902406648770 | 12074902406816254 | 12074902406949374 | 12074902406952174 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f6fbfb0d900 | 0x7f6e8fa35540 | 0 | 0 | 0 | 12074902407009250 | 12074902407181532 | 12074902407439771 | 12074902407508537 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f6fbfb0d800 | 0x7f6e8fa35580 | 0 | 0 | 0 | 12074902407534155 | 12074902407723609 | 12074902407984728 | 12074902408054753 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f6fbfb0d700 | 0x7f6e8fa355c0 | 0 | 0 | 0 | 12074902408080370 | 12074902408268566 | 12074902408402166 | 12074902408405033 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f6fbfb0d600 | 0x7f6e8fa35600 | 0 | 0 | 0 | 12074902408455327 | 12074902408620084 | 12074902408752884 | 12074902408755615 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f6fbfb0d500 | 0x7f6e8fa35640 | 0 | 0 | 0 | 12074902408815687 | 12074902408982642 | 12074902409112402 | 12074902409115564 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f6fbfb0d400 | 0x7f6e8fa35680 | 0 | 0 | 0 | 12074902409163613 | 12074902409338961 | 12074902409607279 | 12074902409676536 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f6fbfb0d300 | 0x7f6e8fa356c0 | 0 | 0 | 0 | 12074902409703627 | 12074902409883598 | 12074902410140716 | 12074902410209727 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f6fbfb0da00 | 0x7f6e8fa35700 | 0 | 0 | 0 | 12074902410236848 | 12074902410420395 | 12074902410554474 | 12074902410557433 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f6fbfb0d900 | 0x7f6e8fa35740 | 0 | 0 | 0 | 12074902410605052 | 12074902410778793 | 12074902410916072 | 12074902410918975 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f6fbfb0d800 | 0x7f6e8fa35780 | 0 | 0 | 0 | 12074902410978907 | 12074902411153831 | 12074902411291430 | 12074902411294683 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f6fbfb0d700 | 0x7f6e8fa357c0 | 0 | 0 | 0 | 12074902411343484 | 12074902411516869 | 12074902411777987 | 12074902411847371 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f6fbfb0d600 | 0x7f6e8fa35800 | 0 | 0 | 0 | 12074902411871566 | 12074902412073506 | 12074902412325664 | 12074902412396421 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f6fbfb0d500 | 0x7f6e8fa35840 | 0 | 0 | 0 | 12074902412419814 | 12074902412612063 | 12074902412743422 | 12074902412746291 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f6fbfb0d400 | 0x7f6e8fa35880 | 0 | 0 | 0 | 12074902412793799 | 12074902412964701 | 12074902413104380 | 12074902413107492 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f6fbfb0d300 | 0x7f6e8fa358c0 | 0 | 0 | 0 | 12074902413168015 | 12074902413336379 | 12074902413469658 | 12074902413472451 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f6fbfb0da00 | 0x7f6e8fa35900 | 0 | 0 | 0 | 12074902413519157 | 12074902413697177 | 12074902413956535 | 12074902414027412 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f6fbfb0d900 | 0x7f6e8fa35940 | 0 | 0 | 0 | 12074902414051627 | 12074902414239734 | 12074902414499092 | 12074902414542369 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f6fbfb0d800 | 0x7f6e8fa35980 | 0 | 0 | 0 | 12074902414568097 | 12074902414745651 | 12074902414925810 | 12074902414928657 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f6fbfb0d700 | 0x7f6e8fa359c0 | 0 | 0 | 0 | 12074902414977007 | 12074902415160049 | 12074902415298768 | 12074902415301620 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f6fbfb0d600 | 0x7f6e8fa35a00 | 0 | 0 | 0 | 12074902415362944 | 12074902415533487 | 12074902415665166 | 12074902415668141 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f6fbfb0d500 | 0x7f6e8fa35a40 | 0 | 0 | 0 | 12074902415715248 | 12074902415892685 | 12074902416145003 | 12074902416214266 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f6fbfb0d400 | 0x7f6e8fa35a80 | 0 | 0 | 0 | 12074902416238391 | 12074902416423882 | 12074902416685960 | 12074902416754931 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f6fbfb0d300 | 0x7f6e8fa35ac0 | 0 | 0 | 0 | 12074902416781650 | 12074902416970279 | 12074902417104838 | 12074902417108107 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f6fbfb0da00 | 0x7f6e8fa35b00 | 0 | 0 | 0 | 12074902417156016 | 12074902417333477 | 12074902417473796 | 12074902417476592 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f6fbfb0d900 | 0x7f6e8fa35b40 | 0 | 0 | 0 | 12074902417538938 | 12074902417704675 | 12074902417835714 | 12074902417838604 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f6fbfb0d800 | 0x7f6e8fa35b80 | 0 | 0 | 0 | 12074902417885512 | 12074902418075393 | 12074902418346431 | 12074902418391261 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f6fbfb0d700 | 0x7f6e8fa35bc0 | 0 | 0 | 0 | 12074902418415376 | 12074902418600030 | 12074902418858909 | 12074902418903203 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f6fbfb0d600 | 0x7f6e8fa35c00 | 0 | 0 | 0 | 12074902418923921 | 12074902419118267 | 12074902419253147 | 12074902419256780 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f6fbfb0d500 | 0x7f6e8fa35c40 | 0 | 0 | 0 | 12074902419304178 | 12074902419479065 | 12074902419618265 | 12074902419621097 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f6fbfb0d400 | 0x7f6e8fa35c80 | 0 | 0 | 0 | 12074902419680858 | 12074902419844983 | 12074902419984983 | 12074902419987949 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f6fbfb0d300 | 0x7f6e8fa35cc0 | 0 | 0 | 0 | 12074902420036509 | 12074902420216181 | 12074902420486900 | 12074902420555513 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f6fbfb0da00 | 0x7f6e8fa35d00 | 0 | 0 | 0 | 12074902420579308 | 12074902420760818 | 12074902421011217 | 12074902421061874 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f6fbfb0d900 | 0x7f6e8fa35d40 | 0 | 0 | 0 | 12074902421083264 | 12074902421270096 | 12074902421407215 | 12074902421410142 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f6fbfb0d800 | 0x7f6e8fa35d80 | 0 | 0 | 0 | 12074902421461036 | 12074902421623694 | 12074902421769933 | 12074902421772766 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f6fbfb0d700 | 0x7f6e8fa35dc0 | 0 | 0 | 0 | 12074902421834160 | 12074902421996652 | 12074902422133131 | 12074902422136361 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f6fbfb0d600 | 0x7f6e8fa35e00 | 0 | 0 | 0 | 12074902422183839 | 12074902422360810 | 12074902422619208 | 12074902422662990 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f6fbfb0d500 | 0x7f6e8fa35e40 | 0 | 0 | 0 | 12074902422688618 | 12074902422869127 | 12074902423124485 | 12074902423170493 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f6fbfb0d400 | 0x7f6e8fa35e80 | 0 | 0 | 0 | 12074902423197283 | 12074902423376164 | 12074902423514563 | 12074902423517478 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f6fbfb0d300 | 0x7f6e8fa35ec0 | 0 | 0 | 0 | 12074902423564746 | 12074902423735202 | 12074902423873121 | 12074902423876084 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f6fbfb0da00 | 0x7f6e8fa35f00 | 0 | 0 | 0 | 12074902423938240 | 12074902424116320 | 12074902424251519 | 12074902424254598 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f6fbfb0d900 | 0x7f6e8fa35f40 | 0 | 0 | 0 | 12074902424302036 | 12074902424476638 | 12074902424736957 | 12074902424806984 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f6fbfb0d800 | 0x7f6e8fa35f80 | 0 | 0 | 0 | 12074902424830979 | 12074902425013595 | 12074902425270554 | 12074902425342449 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f6fbfb0d700 | 0x7f6e8fa35fc0 | 0 | 0 | 0 | 12074902425367105 | 12074902425554872 | 12074902425683351 | 12074902425686318 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f6fbfb0d600 | 0x7f6e8fa36000 | 0 | 0 | 0 | 12074902425733606 | 12074902425905270 | 12074902426045270 | 12074902426048511 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f6fbfb0d500 | 0x7f6e8fa36040 | 0 | 0 | 0 | 12074902426110416 | 12074902426277268 | 12074902426407988 | 12074902426411055 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f6fbfb0d400 | 0x7f6e8fa36080 | 0 | 0 | 0 | 12074902426457421 | 12074902426629906 | 12074902426897265 | 12074902426967319 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f6fbfb0d300 | 0x7f6e8fa360c0 | 0 | 0 | 0 | 12074902426989971 | 12074902427180783 | 12074902427431822 | 12074902427501371 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f6fbfb0da00 | 0x7f6e8fa36100 | 0 | 0 | 0 | 12074902427525496 | 12074902427714220 | 12074902427849580 | 12074902427852534 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f6fbfb0d900 | 0x7f6e8fa36140 | 0 | 0 | 0 | 12074902427899912 | 12074902428091818 | 12074902428236138 | 12074902428239152 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f6fbfb0d800 | 0x7f6e8fa36180 | 0 | 0 | 0 | 12074902428299975 | 12074902428465576 | 12074902428599496 | 12074902428602568 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f6fbfb0d700 | 0x7f6e8fa361c0 | 0 | 0 | 0 | 12074902428650587 | 12074902428823974 | 12074902429090053 | 12074902429142531 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f6fbfb0d600 | 0x7f6e8fa36200 | 0 | 0 | 0 | 12074902429169952 | 12074902429351971 | 12074902429604610 | 12074902429654683 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f6fbfb0d500 | 0x7f6e8fa36240 | 0 | 0 | 0 | 12074902429681563 | 12074902429859649 | 12074902430000288 | 12074902430006357 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f6fbfb0d400 | 0x7f6e8fa36280 | 0 | 0 | 0 | 12074902430051060 | 12074902430224447 | 12074902430376446 | 12074902430379440 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f6fbfb0d300 | 0x7f6e8fa362c0 | 0 | 0 | 0 | 12074902430460010 | 12074902430624925 | 12074902430755804 | 12074902430758745 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f6fbfb0da00 | 0x7f6e8fa36300 | 0 | 0 | 0 | 12074902430805251 | 12074902430976763 | 12074902431247001 | 12074902431298738 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f6fbfb0d900 | 0x7f6e8fa36340 | 0 | 0 | 0 | 12074902431323625 | 12074902431506520 | 12074902431768438 | 12074902431818845 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f6fbfb0d800 | 0x7f6e8fa36380 | 0 | 0 | 0 | 12074902431841667 | 12074902432035797 | 12074902432173236 | 12074902432176229 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f6fbfb0d700 | 0x7f6e8fa363c0 | 0 | 0 | 0 | 12074902432224158 | 12074902432398835 | 12074902432557874 | 12074902432560834 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f6fbfb0d600 | 0x7f6e8fa36400 | 0 | 0 | 0 | 12074902432620675 | 12074902432782353 | 12074902432918512 | 12074902432921554 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f6fbfb0d500 | 0x7f6e8fa36440 | 0 | 0 | 0 | 12074902432968702 | 12074902433156911 | 12074902433428909 | 12074902433482366 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f6fbfb0d400 | 0x7f6e8fa36480 | 0 | 0 | 0 | 12074902433505469 | 12074902433689708 | 12074902433950666 | 12074902434005979 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f6fbfb0d300 | 0x7f6e8fa364c0 | 0 | 0 | 0 | 12074902434033931 | 12074902434215625 | 12074902434358344 | 12074902434361700 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f6fbfb0da00 | 0x7f6e8fa36500 | 0 | 0 | 0 | 12074902434407666 | 12074902434579303 | 12074902434746502 | 12074902434749892 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f6fbfb0d900 | 0x7f6e8fa36540 | 0 | 0 | 0 | 12074902434810484 | 12074902434974181 | 12074902435110340 | 12074902435114099 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f6fbfb0d800 | 0x7f6e8fa36580 | 0 | 0 | 0 | 12074902435160735 | 12074902435334019 | 12074902435599137 | 12074902435648943 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f6fbfb0d700 | 0x7f6e8fa365c0 | 0 | 0 | 0 | 12074902435673208 | 12074902435856256 | 12074902436108255 | 12074902436159271 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f6fbfb0d600 | 0x7f6e8fa36600 | 0 | 0 | 0 | 12074902436185540 | 12074902436371133 | 12074902436514652 | 12074902436517657 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f6fbfb0d500 | 0x7f6e8fa36640 | 0 | 0 | 0 | 12074902436564865 | 12074902436736571 | 12074902436910490 | 12074902436913422 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f6fbfb0d400 | 0x7f6e8fa36680 | 0 | 0 | 0 | 12074902436973394 | 12074902437145049 | 12074902437283928 | 12074902437287177 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f6fbfb0d300 | 0x7f6e8fa366c0 | 0 | 0 | 0 | 12074902437334876 | 12074902437508887 | 12074902437773046 | 12074902437823003 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f6fbfb0da00 | 0x7f6e8fa36700 | 0 | 0 | 0 | 12074902437846136 | 12074902438034324 | 12074902438293363 | 12074902438345243 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f6fbfb0d900 | 0x7f6e8fa36740 | 0 | 0 | 0 | 12074902438367595 | 12074902438554321 | 12074902438694161 | 12074902438697177 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f6fbfb0d800 | 0x7f6e8fa36780 | 0 | 0 | 0 | 12074902438743834 | 12074902438914319 | 12074902439097998 | 12074902439101729 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f6fbfb0d700 | 0x7f6e8fa367c0 | 0 | 0 | 0 | 12074902439165498 | 12074902439330637 | 12074902439475116 | 12074902439478018 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f6fbfb0d600 | 0x7f6e8fa36800 | 0 | 0 | 0 | 12074902439524455 | 12074902439695435 | 12074902439961194 | 12074902440019294 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f6fbfb0d500 | 0x7f6e8fa36840 | 0 | 0 | 0 | 12074902440042958 | 12074902440233832 | 12074902440493351 | 12074902440516809 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f6fbfb0d400 | 0x7f6e8fa36880 | 0 | 0 | 0 | 12074902440555872 | 12074902440717350 | 12074902440857509 | 12074902440860508 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f6fbfb0d300 | 0x7f6e8fa368c0 | 0 | 0 | 0 | 12074902440907094 | 12074902441085668 | 12074902441277987 | 12074902441329890 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f6fbfb0da00 | 0x7f6e8fa36900 | 0 | 0 | 0 | 12074902441367269 | 12074902441530145 | 12074902441671904 | 12074902441674981 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f6fbfb0d900 | 0x7f6e8fa36940 | 0 | 0 | 0 | 12074902441725555 | 12074902441888223 | 12074902442172222 | 12074902442222659 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f6fbfb0d800 | 0x7f6e8fa36980 | 0 | 0 | 0 | 12074902442249128 | 12074902442430460 | 12074902442693339 | 12074902442743327 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f6fbfb0d700 | 0x7f6e8fa369c0 | 0 | 0 | 0 | 12074902442771198 | 12074902442949817 | 12074902443086457 | 12074902443090422 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f6fbfb0d600 | 0x7f6e8fa36a00 | 0 | 0 | 0 | 12074902443137760 | 12074902443308215 | 12074902443520534 | 12074902443569833 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f6fbfb0d500 | 0x7f6e8fa36a40 | 0 | 0 | 0 | 12074902443607593 | 12074902443773493 | 12074902443916052 | 12074902443919202 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f6fbfb0d400 | 0x7f6e8fa36a80 | 0 | 0 | 0 | 12074902443968574 | 12074902444148371 | 12074902444456689 | 12074902444507205 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f6fbfb0d300 | 0x7f6e8fa36ac0 | 0 | 0 | 0 | 12074902444532021 | 12074902444716368 | 12074902444981966 | 12074902445033402 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f6fbfb0da00 | 0x7f6e8fa36b00 | 0 | 0 | 0 | 12074902445057888 | 12074902445240525 | 12074902445381804 | 12074902445385036 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f6fbfb0d900 | 0x7f6e8fa36b40 | 0 | 0 | 0 | 12074902445432394 | 12074902445604043 | 12074902445832522 | 12074902445882280 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f6fbfb0d800 | 0x7f6e8fa36b80 | 0 | 0 | 0 | 12074902445922344 | 12074902446094760 | 12074902446238600 | 12074902446242169 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f6fbfb0d700 | 0x7f6e8fa36bc0 | 0 | 0 | 0 | 12074902446291350 | 12074902446467238 | 12074902446797956 | 12074902446847173 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f6fbfb0d600 | 0x7f6e8fa36c00 | 0 | 0 | 0 | 12074902446873252 | 12074902447053155 | 12074902447314754 | 12074902447338957 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f6fbfb0d500 | 0x7f6e8fa36c40 | 0 | 0 | 0 | 12074902447378601 | 12074902447540814 | 12074902447680494 | 12074902447687445 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f6fbfb0d400 | 0x7f6e8fa36c80 | 0 | 0 | 0 | 12074902447730314 | 12074902447903531 | 12074902448151050 | 12074902448201730 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f6fbfb0d300 | 0x7f6e8fa36cc0 | 0 | 0 | 0 | 12074902448237928 | 12074902448414569 | 12074902448550088 | 12074902448552532 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f6fbfb0da00 | 0x7f6e8fa36d00 | 0 | 0 | 0 | 12074902448599259 | 12074902448770567 | 12074902449173286 | 12074902449225012 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f6fbfb0d900 | 0x7f6e8fa36d40 | 0 | 0 | 0 | 12074902449249497 | 12074902449435204 | 12074902449700963 | 12074902449750539 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f6fbfb0d800 | 0x7f6e8fa36d80 | 0 | 0 | 0 | 12074902449773331 | 12074902449963682 | 12074902450106401 | 12074902450108965 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f6fbfb0d700 | 0x7f6e8fa36dc0 | 0 | 0 | 0 | 12074902450156212 | 12074902450334400 | 12074902450614079 | 12074902450664467 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f6fbfb0d600 | 0x7f6e8fa36e00 | 0 | 0 | 0 | 12074902450702979 | 12074902450871038 | 12074902451012477 | 12074902451015389 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f6fbfb0d500 | 0x7f6e8fa36e40 | 0 | 0 | 0 | 12074902451062457 | 12074902451239196 | 12074902451663834 | 12074902451686937 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f6fbfb0d400 | 0x7f6e8fa36e80 | 0 | 0 | 0 | 12074902451725970 | 12074902451890713 | 12074902452159832 | 12074902452209438 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f6fbfb0d300 | 0x7f6e8fa36ec0 | 0 | 0 | 0 | 12074902452233102 | 12074902452424950 | 12074902452563350 | 12074902452565921 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f6fbfb0da00 | 0x7f6e8fa36f00 | 0 | 0 | 0 | 12074902452613068 | 12074902452785269 | 12074902453101747 | 12074902453152731 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f6fbfb0d900 | 0x7f6e8fa36f40 | 0 | 0 | 0 | 12074902453189409 | 12074902453365906 | 12074902453517745 | 12074902453520284 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f6fbfb0d800 | 0x7f6e8fa36f80 | 0 | 0 | 0 | 12074902453566750 | 12074902453740304 | 12074902454260782 | 12074902454311625 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f6fbfb0d700 | 0x7f6e8fa36fc0 | 0 | 0 | 0 | 12074902454335309 | 12074902454527021 | 12074902454822859 | 12074902454872337 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f6fbfb0d600 | 0x7f6e8fa37000 | 0 | 0 | 0 | 12074902454894488 | 12074902455088298 | 12074902455244777 | 12074902455247654 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f6fbfb0d500 | 0x7f6e8fa37040 | 0 | 0 | 0 | 12074902455294391 | 12074902455471016 | 12074902455858214 | 12074902455881292 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f6fbfb0d400 | 0x7f6e8fa37080 | 0 | 0 | 0 | 12074902455934170 | 12074902456115333 | 12074902456291652 | 12074902456294630 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f6fbfb0d300 | 0x7f6e8fa370c0 | 0 | 0 | 0 | 12074902456343330 | 12074902456516931 | 12074902457128448 | 12074902457179013 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f6fbfb0da00 | 0x7f6e8fa37100 | 0 | 0 | 0 | 12074902457202868 | 12074902457386207 | 12074902457715486 | 12074902457765062 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f6fbfb0d900 | 0x7f6e8fa37140 | 0 | 0 | 0 | 12074902457791411 | 12074902457977084 | 12074902458156764 | 12074902458159976 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f6fbfb0d800 | 0x7f6e8fa37180 | 0 | 0 | 0 | 12074902458208296 | 12074902458385403 | 12074902458843160 | 12074902458892868 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f6fbfb0d700 | 0x7f6e8fa371c0 | 0 | 0 | 0 | 12074902458931741 | 12074902459106519 | 12074902459306678 | 12074902459357872 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f6fbfb0d600 | 0x7f6e8fa37200 | 0 | 0 | 0 | 12074902459383821 | 12074902459564437 | 12074902460269074 | 12074902460320401 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f6fbfb0d500 | 0x7f6e8fa37240 | 0 | 0 | 0 | 12074902460344396 | 12074902460529713 | 12074902460904591 | 12074902460954389 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f6fbfb0d400 | 0x7f6e8fa37280 | 0 | 0 | 0 | 12074902460976851 | 12074902461170670 | 12074902461373709 | 12074902461423712 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f6fbfb0d300 | 0x7f6e8fa372c0 | 0 | 0 | 0 | 12074902461447796 | 12074902461630187 | 12074902462156105 | 12074902462207628 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f6fbfb0da00 | 0x7f6e8fa37300 | 0 | 0 | 0 | 12074902462248254 | 12074902462415144 | 12074902462640423 | 12074902462690416 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f6fbfb0d900 | 0x7f6e8fa37340 | 0 | 0 | 0 | 12074902462713949 | 12074902462896421 | 12074902463695618 | 12074902463747460 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f6fbfb0d800 | 0x7f6e8fa37380 | 0 | 0 | 0 | 12074902463774099 | 12074902463955297 | 12074902464400574 | 12074902464450937 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f6fbfb0d700 | 0x7f6e8fa373c0 | 0 | 0 | 0 | 12074902464475743 | 12074902464663773 | 12074902464890812 | 12074902464940457 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f6fbfb0d600 | 0x7f6e8fa37400 | 0 | 0 | 0 | 12074902464964922 | 12074902465153531 | 12074902465750808 | 12074902465820733 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f6fbfb0d500 | 0x7f6e8fa37440 | 0 | 0 | 0 | 12074902465859715 | 12074902466037047 | 12074902466307286 | 12074902466377447 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f6fbfb0d400 | 0x7f6e8fa37480 | 0 | 0 | 0 | 12074902466402223 | 12074902466585684 | 12074902467571600 | 12074902467641416 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f6fbfb0d300 | 0x7f6e8fa374c0 | 0 | 0 | 0 | 12074902467671823 | 12074902467857038 | 12074902468373516 | 12074902468444980 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f6fbfb0da00 | 0x7f6e8fa37500 | 0 | 0 | 0 | 12074902468469545 | 12074902468658315 | 12074902468930953 | 12074902468973752 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f6fbfb0d900 | 0x7f6e8fa37540 | 0 | 0 | 0 | 12074902469005792 | 12074902469187432 | 12074902469925989 | 12074902469994710 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f6fbfb0d800 | 0x7f6e8fa37580 | 0 | 0 | 0 | 12074902470040144 | 12074902470208227 | 12074902470525666 | 12074902470595195 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f6fbfb0d700 | 0x7f6e8fa375c0 | 0 | 0 | 0 | 12074902470618930 | 12074902470801985 | 12074902471974299 | 12074902472045851 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f6fbfb0d600 | 0x7f6e8fa37600 | 0 | 0 | 0 | 12074902472078031 | 12074902472259738 | 12074902472869815 | 12074902472939883 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f6fbfb0d500 | 0x7f6e8fa37640 | 0 | 0 | 0 | 12074902472963747 | 12074902473154294 | 12074902473501652 | 12074902473573049 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f6fbfb0d400 | 0x7f6e8fa37680 | 0 | 0 | 0 | 12074902473598487 | 12074902473781651 | 12074902474660047 | 12074902474729759 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f6fbfb0d300 | 0x7f6e8fa376c0 | 0 | 0 | 0 | 12074902474771807 | 12074902474939725 | 12074902475349323 | 12074902475420493 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f6fbfb0da00 | 0x7f6e8fa37700 | 0 | 0 | 0 | 12074902475447262 | 12074902475628682 | 12074902477176675 | 12074902477247598 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f6fbfb0d900 | 0x7f6e8fa37740 | 0 | 0 | 0 | 12074902477280108 | 12074902477465793 | 12074902478261310 | 12074902478330871 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f6fbfb0d800 | 0x7f6e8fa37780 | 0 | 0 | 0 | 12074902478361618 | 12074902478546428 | 12074902478961946 | 12074902479032545 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f6fbfb0d700 | 0x7f6e8fa377c0 | 0 | 0 | 0 | 12074902479064605 | 12074902479247545 | 12074902480406900 | 12074902480476899 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f6fbfb0d600 | 0x7f6e8fa37800 | 0 | 0 | 0 | 12074902480517805 | 12074902480686578 | 12074902481472815 | 12074902481542399 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f6fbfb0d500 | 0x7f6e8fa37840 | 0 | 0 | 0 | 12074902481572856 | 12074902481754253 | 12074902484803679 | 12074902484873450 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f6fbfb0d400 | 0x7f6e8fa37880 | 0 | 0 | 0 | 12074902484906090 | 12074902485263197 | 12074902486805590 | 12074902486878876 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f6fbfb0d300 | 0x7f6e8fa378c0 | 0 | 0 | 0 | 12074902486953475 | 12074902487326827 | 12074902488116584 | 12074902488188090 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f6fbfb0da00 | 0x7f6e8fa37900 | 0 | 0 | 0 | 12074902488245576 | 12074902488508422 | 12074902490790811 | 12074902490861959 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f6fbfb0d900 | 0x7f6e8fa37940 | 0 | 0 | 0 | 12074902490940905 | 12074902491194809 | 12074902492730322 | 12074902492801092 |
| 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 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f6fbfb0d800 | 0x7f6e8fa37980 | 0 | 0 | 0 | 12074902492854612 | 12074902493117680 | 12074902499175572 | 12074902499249576 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f6fbfb0d700 | 0x7f6e8fa379c0 | 0 | 0 | 0 | 12074902499301643 | 12074902499553650 | 12074902502599076 | 12074902502670253 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f6fbfb0d600 | 0x7f6e8fa37a00 | 0 | 0 | 0 | 12074902502723762 | 12074902502973794 | 12074902504513947 | 12074902504585011 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 852721 | 852726 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f6fbfb0d500 | 0x7f6e8fa37a40 | 0 | 0 | 0 | 12074902504639963 | 12074902504879545 | 12074902509408804 | 12074902509479677 |