39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 913999 | 914004 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fc2bb204180 | 12076182316331086 | 12076182316374996 | 12076182316698353 | 12076182316803594 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 913999 | 914004 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fc2bb235100 | 12076182331718924 | 12076182331822481 | 12076182331829361 | 12076182331835510 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fc3eb372900 | 0x7fc2bb235140 | 12076182331879292 | 12076182331892560 | 12076182332025999 | 12076182332030022 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fc3eb372800 | 0x7fc2bb235180 | 12076182332077390 | 12076182332092238 | 12076182332338796 | 12076182332435155 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fc3eb372700 | 0x7fc2bb2351c0 | 12076182332460923 | 12076182332472394 | 12076182332715272 | 12076182332811264 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fc3eb372600 | 0x7fc2bb235200 | 12076182332838815 | 12076182332850951 | 12076182332976709 | 12076182332980228 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fc3eb372500 | 0x7fc2bb235240 | 12076182333014752 | 12076182333026149 | 12076182333151748 | 12076182333155103 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fc3eb372400 | 0x7fc2bb235280 | 12076182333207931 | 12076182333219907 | 12076182333343906 | 12076182333347220 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fc3eb372300 | 0x7fc2bb2352c0 | 12076182333375392 | 12076182333386785 | 12076182333635743 | 12076182333731965 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fc3eb372a00 | 0x7fc2bb235300 | 12076182333753845 | 12076182333765982 | 12076182334015099 | 12076182334111460 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fc3eb372900 | 0x7fc2bb235340 | 12076182334139192 | 12076182334150938 | 12076182334276056 | 12076182334279643 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fc3eb372800 | 0x7fc2bb235380 | 12076182334311121 | 12076182334323256 | 12076182334448375 | 12076182334451652 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fc3eb372700 | 0x7fc2bb2353c0 | 12076182334495774 | 12076182334507894 | 12076182334632533 | 12076182334635795 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fc3eb372600 | 0x7fc2bb235400 | 12076182334667173 | 12076182334678932 | 12076182334933810 | 12076182335014108 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fc3eb372500 | 0x7fc2bb235440 | 12076182335037651 | 12076182335049329 | 12076182335294126 | 12076182335363727 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fc3eb372400 | 0x7fc2bb235480 | 12076182335386269 | 12076182335398125 | 12076182335522924 | 12076182335526179 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fc3eb372300 | 0x7fc2bb2354c0 | 12076182335552358 | 12076182335565964 | 12076182335691082 | 12076182335694542 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fc3eb372a00 | 0x7fc2bb235500 | 12076182335733374 | 12076182335745642 | 12076182335870121 | 12076182335873405 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fc3eb372900 | 0x7fc2bb235540 | 12076182335899784 | 12076182335913000 | 12076182336160038 | 12076182336225880 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fc3eb372800 | 0x7fc2bb235580 | 12076182336248472 | 12076182336260197 | 12076182336508834 | 12076182336574758 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fc3eb372700 | 0x7fc2bb2355c0 | 12076182336596328 | 12076182336609953 | 12076182336734752 | 12076182336737801 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fc3eb372600 | 0x7fc2bb235600 | 12076182336765873 | 12076182336779072 | 12076182336904670 | 12076182336908027 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fc3eb372500 | 0x7fc2bb235640 | 12076182336946218 | 12076182336960190 | 12076182337084669 | 12076182337087912 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fc3eb372400 | 0x7fc2bb235680 | 12076182337115964 | 12076182337128988 | 12076182337380826 | 12076182337447049 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fc3eb372300 | 0x7fc2bb2356c0 | 12076182337470132 | 12076182337482425 | 12076182337726262 | 12076182337822857 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fc3eb372a00 | 0x7fc2bb235700 | 12076182337843867 | 12076182337855221 | 12076182337979220 | 12076182337982674 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fc3eb372900 | 0x7fc2bb235740 | 12076182338015766 | 12076182338027539 | 12076182338153298 | 12076182338156848 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fc3eb372800 | 0x7fc2bb235780 | 12076182338199337 | 12076182338210897 | 12076182338335856 | 12076182338339157 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fc3eb372700 | 0x7fc2bb2357c0 | 12076182338370155 | 12076182338381456 | 12076182338630093 | 12076182338726246 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fc3eb372600 | 0x7fc2bb235800 | 12076182338750361 | 12076182338761612 | 12076182339005129 | 12076182339083380 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fc3eb372500 | 0x7fc2bb235840 | 12076182339105782 | 12076182339117608 | 12076182339242247 | 12076182339246002 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fc3eb372400 | 0x7fc2bb235880 | 12076182339272321 | 12076182339289287 | 12076182339414405 | 12076182339417732 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fc3eb372300 | 0x7fc2bb2358c0 | 12076182339455402 | 12076182339466725 | 12076182339591364 | 12076182339594560 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fc3eb372a00 | 0x7fc2bb235900 | 12076182339621210 | 12076182339634083 | 12076182339881441 | 12076182339932578 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fc3eb372900 | 0x7fc2bb235940 | 12076182339953708 | 12076182339966880 | 12076182340212477 | 12076182340268022 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fc3eb372800 | 0x7fc2bb235980 | 12076182340290914 | 12076182340302556 | 12076182340427195 | 12076182340430684 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fc3eb372700 | 0x7fc2bb2359c0 | 12076182340457193 | 12076182340468475 | 12076182340594554 | 12076182340597915 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fc3eb372600 | 0x7fc2bb235a00 | 12076182340634523 | 12076182340646073 | 12076182340770712 | 12076182340773742 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fc3eb372500 | 0x7fc2bb235a40 | 12076182340799630 | 12076182340811191 | 12076182341061269 | 12076182341122029 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fc3eb372400 | 0x7fc2bb235a80 | 12076182341144010 | 12076182341155348 | 12076182341402706 | 12076182341428238 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fc3eb372300 | 0x7fc2bb235ac0 | 12076182341451501 | 12076182341463185 | 12076182341587824 | 12076182341590890 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fc3eb372a00 | 0x7fc2bb235b00 | 12076182341617610 | 12076182341629103 | 12076182341754862 | 12076182341758051 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fc3eb372900 | 0x7fc2bb235b40 | 12076182341797765 | 12076182341811981 | 12076182341936620 | 12076182341939799 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fc3eb372800 | 0x7fc2bb235b80 | 12076182341966789 | 12076182341979820 | 12076182342230857 | 12076182342255495 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fc3eb372700 | 0x7fc2bb235bc0 | 12076182342278448 | 12076182342291177 | 12076182342536454 | 12076182342559460 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fc3eb372600 | 0x7fc2bb235c00 | 12076182342579728 | 12076182342592294 | 12076182342716612 | 12076182342719919 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fc3eb372500 | 0x7fc2bb235c40 | 12076182342746738 | 12076182342759492 | 12076182342886211 | 12076182342889363 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fc3eb372400 | 0x7fc2bb235c80 | 12076182342927675 | 12076182342938850 | 12076182343064289 | 12076182343067374 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fc3eb372300 | 0x7fc2bb235cc0 | 12076182343096218 | 12076182343110689 | 12076182343371966 | 12076182343396215 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fc3eb372a00 | 0x7fc2bb235d00 | 12076182343418296 | 12076182343431325 | 12076182343675163 | 12076182343701312 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fc3eb372900 | 0x7fc2bb235d40 | 12076182343722191 | 12076182343733882 | 12076182343859001 | 12076182343862171 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fc3eb372800 | 0x7fc2bb235d80 | 12076182343888781 | 12076182343900441 | 12076182344028119 | 12076182344031246 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fc3eb372700 | 0x7fc2bb235dc0 | 12076182344070489 | 12076182344082039 | 12076182344207798 | 12076182344210960 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fc3eb372600 | 0x7fc2bb235e00 | 12076182344237759 | 12076182344250997 | 12076182344508915 | 12076182344535112 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fc3eb372500 | 0x7fc2bb235e40 | 12076182344556963 | 12076182344569714 | 12076182344817712 | 12076182344839628 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fc3eb372400 | 0x7fc2bb235e80 | 12076182344864174 | 12076182344876911 | 12076182345002030 | 12076182345006548 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fc3eb372300 | 0x7fc2bb235ec0 | 12076182345033799 | 12076182345046349 | 12076182345174828 | 12076182345178097 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fc3eb372a00 | 0x7fc2bb235f00 | 12076182345215757 | 12076182345228267 | 12076182345353546 | 12076182345356729 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fc3eb372900 | 0x7fc2bb235f40 | 12076182345383529 | 12076182345394826 | 12076182345648263 | 12076182345667386 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fc3eb372800 | 0x7fc2bb235f80 | 12076182345689507 | 12076182345702023 | 12076182345947940 | 12076182345969969 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fc3eb372700 | 0x7fc2bb235fc0 | 12076182345990747 | 12076182346003300 | 12076182346128578 | 12076182346131990 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fc3eb372600 | 0x7fc2bb236000 | 12076182346160282 | 12076182346172738 | 12076182346310177 | 12076182346313267 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fc3eb372500 | 0x7fc2bb236040 | 12076182346352139 | 12076182346364256 | 12076182346488895 | 12076182346491959 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fc3eb372400 | 0x7fc2bb236080 | 12076182346518929 | 12076182346532094 | 12076182346788412 | 12076182346807044 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fc3eb372300 | 0x7fc2bb2360c0 | 12076182346828725 | 12076182346839931 | 12076182347086969 | 12076182347113394 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fc3eb372a00 | 0x7fc2bb236100 | 12076182347135815 | 12076182347146648 | 12076182347271767 | 12076182347275124 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fc3eb372900 | 0x7fc2bb236140 | 12076182347301102 | 12076182347312247 | 12076182347454965 | 12076182347458555 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fc3eb372800 | 0x7fc2bb236180 | 12076182347496275 | 12076182347507445 | 12076182347632083 | 12076182347635304 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fc3eb372700 | 0x7fc2bb2361c0 | 12076182347660410 | 12076182347673843 | 12076182347927761 | 12076182347947364 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fc3eb372600 | 0x7fc2bb236200 | 12076182347969795 | 12076182347982320 | 12076182348231758 | 12076182348256047 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fc3eb372500 | 0x7fc2bb236240 | 12076182348280182 | 12076182348292877 | 12076182348417676 | 12076182348420833 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fc3eb372400 | 0x7fc2bb236280 | 12076182348448144 | 12076182348459435 | 12076182348608554 | 12076182348611768 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fc3eb372300 | 0x7fc2bb2362c0 | 12076182348662062 | 12076182348672873 | 12076182348798472 | 12076182348801761 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fc3eb372a00 | 0x7fc2bb236300 | 12076182348828251 | 12076182348841351 | 12076182349103909 | 12076182349133388 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fc3eb372900 | 0x7fc2bb236340 | 12076182349155769 | 12076182349168068 | 12076182349413986 | 12076182349438495 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fc3eb372800 | 0x7fc2bb236380 | 12076182349460085 | 12076182349472865 | 12076182349598464 | 12076182349601648 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fc3eb372700 | 0x7fc2bb2363c0 | 12076182349629440 | 12076182349642303 | 12076182349798622 | 12076182349801980 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fc3eb372600 | 0x7fc2bb236400 | 12076182349841263 | 12076182349853341 | 12076182349977820 | 12076182349980943 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fc3eb372500 | 0x7fc2bb236440 | 12076182350013173 | 12076182350025820 | 12076182350289817 | 12076182350313611 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fc3eb372400 | 0x7fc2bb236480 | 12076182350336163 | 12076182350348856 | 12076182350592534 | 12076182350615171 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fc3eb372300 | 0x7fc2bb2364c0 | 12076182350636842 | 12076182350649333 | 12076182350774772 | 12076182350778214 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fc3eb372a00 | 0x7fc2bb236500 | 12076182350803912 | 12076182350816852 | 12076182350981330 | 12076182350984738 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fc3eb372900 | 0x7fc2bb236540 | 12076182351027678 | 12076182351041010 | 12076182351166768 | 12076182351169962 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fc3eb372800 | 0x7fc2bb236580 | 12076182351196642 | 12076182351212368 | 12076182351467885 | 12076182351488494 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fc3eb372700 | 0x7fc2bb2365c0 | 12076182351509564 | 12076182351523405 | 12076182351768362 | 12076182351790927 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fc3eb372600 | 0x7fc2bb236600 | 12076182351814460 | 12076182351827402 | 12076182351953160 | 12076182351956444 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fc3eb372500 | 0x7fc2bb236640 | 12076182351982012 | 12076182351994600 | 12076182352167558 | 12076182352171033 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fc3eb372400 | 0x7fc2bb236680 | 12076182352208984 | 12076182352221478 | 12076182352347557 | 12076182352350747 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fc3eb372300 | 0x7fc2bb2366c0 | 12076182352378258 | 12076182352390916 | 12076182352644034 | 12076182352667145 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fc3eb372a00 | 0x7fc2bb236700 | 12076182352687092 | 12076182352697953 | 12076182352948671 | 12076182352971511 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fc3eb372900 | 0x7fc2bb236740 | 12076182352992991 | 12076182353004350 | 12076182353129469 | 12076182353133251 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fc3eb372800 | 0x7fc2bb236780 | 12076182353160612 | 12076182353171548 | 12076182353354426 | 12076182353357648 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fc3eb372700 | 0x7fc2bb2367c0 | 12076182353395939 | 12076182353408506 | 12076182353534745 | 12076182353538054 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fc3eb372600 | 0x7fc2bb236800 | 12076182353563270 | 12076182353576504 | 12076182353839062 | 12076182353862396 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fc3eb372500 | 0x7fc2bb236840 | 12076182353883646 | 12076182353896181 | 12076182354140819 | 12076182354169016 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fc3eb372400 | 0x7fc2bb236880 | 12076182354189865 | 12076182354202578 | 12076182354328177 | 12076182354331448 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fc3eb372300 | 0x7fc2bb2368c0 | 12076182354357737 | 12076182354370416 | 12076182354561294 | 12076182354566475 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fc3eb372a00 | 0x7fc2bb236900 | 12076182354600588 | 12076182354612814 | 12076182354739053 | 12076182354742542 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fc3eb372900 | 0x7fc2bb236940 | 12076182354769192 | 12076182354782092 | 12076182355064329 | 12076182355091451 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fc3eb372800 | 0x7fc2bb236980 | 12076182355112600 | 12076182355124009 | 12076182355371846 | 12076182355398261 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fc3eb372700 | 0x7fc2bb2369c0 | 12076182355420141 | 12076182355431686 | 12076182355556965 | 12076182355560312 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fc3eb372600 | 0x7fc2bb236a00 | 12076182355587152 | 12076182355598244 | 12076182355806402 | 12076182355828370 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fc3eb372500 | 0x7fc2bb236a40 | 12076182355860730 | 12076182355871681 | 12076182356000160 | 12076182356005619 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fc3eb372400 | 0x7fc2bb236a80 | 12076182356032229 | 12076182356045440 | 12076182356383196 | 12076182356409059 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fc3eb372300 | 0x7fc2bb236ac0 | 12076182356431821 | 12076182356445116 | 12076182356691513 | 12076182356714026 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fc3eb372a00 | 0x7fc2bb236b00 | 12076182356735095 | 12076182356748633 | 12076182356875671 | 12076182356879023 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fc3eb372900 | 0x7fc2bb236b40 | 12076182356905502 | 12076182356918391 | 12076182357145109 | 12076182357170434 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fc3eb372800 | 0x7fc2bb236b80 | 12076182357204848 | 12076182357215828 | 12076182357342227 | 12076182357345399 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fc3eb372700 | 0x7fc2bb236bc0 | 12076182357371828 | 12076182357383346 | 12076182357740463 | 12076182357759539 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fc3eb372600 | 0x7fc2bb236c00 | 12076182357781630 | 12076182357794382 | 12076182358049420 | 12076182358076428 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fc3eb372500 | 0x7fc2bb236c40 | 12076182358098068 | 12076182358110859 | 12076182358238378 | 12076182358241695 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fc3eb372400 | 0x7fc2bb236c80 | 12076182358267753 | 12076182358280297 | 12076182358524295 | 12076182358546502 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fc3eb372300 | 0x7fc2bb236cc0 | 12076182358577980 | 12076182358590214 | 12076182358720293 | 12076182358723651 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fc3eb372a00 | 0x7fc2bb236d00 | 12076182358750040 | 12076182358762853 | 12076182359137729 | 12076182359164881 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fc3eb372900 | 0x7fc2bb236d40 | 12076182359186892 | 12076182359199328 | 12076182359453566 | 12076182359480067 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fc3eb372800 | 0x7fc2bb236d80 | 12076182359504161 | 12076182359517085 | 12076182359647324 | 12076182359650613 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fc3eb372700 | 0x7fc2bb236dc0 | 12076182359677423 | 12076182359689723 | 12076182359967961 | 12076182359994092 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fc3eb372600 | 0x7fc2bb236e00 | 12076182360053853 | 12076182360066840 | 12076182360201558 | 12076182360205124 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fc3eb372500 | 0x7fc2bb236e40 | 12076182360233086 | 12076182360249398 | 12076182360695633 | 12076182360722746 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fc3eb372400 | 0x7fc2bb236e80 | 12076182360744577 | 12076182360755793 | 12076182361011630 | 12076182361039495 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fc3eb372300 | 0x7fc2bb236ec0 | 12076182361062417 | 12076182361075470 | 12076182361211308 | 12076182361214670 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fc3eb372a00 | 0x7fc2bb236f00 | 12076182361241350 | 12076182361254028 | 12076182361567465 | 12076182361593124 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fc3eb372900 | 0x7fc2bb236f40 | 12076182361627457 | 12076182361638504 | 12076182361790182 | 12076182361793566 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fc3eb372800 | 0x7fc2bb236f80 | 12076182361819745 | 12076182361832742 | 12076182362347137 | 12076182362379906 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fc3eb372700 | 0x7fc2bb236fc0 | 12076182362401666 | 12076182362412736 | 12076182362710813 | 12076182362736899 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fc3eb372600 | 0x7fc2bb237000 | 12076182362758089 | 12076182362769053 | 12076182362922651 | 12076182362926051 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fc3eb372500 | 0x7fc2bb237040 | 12076182362952480 | 12076182362965371 | 12076182363349847 | 12076182363379353 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fc3eb372400 | 0x7fc2bb237080 | 12076182363412575 | 12076182363425046 | 12076182363601204 | 12076182363604542 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fc3eb372300 | 0x7fc2bb2370c0 | 12076182363631412 | 12076182363644244 | 12076182364252878 | 12076182364280969 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fc3eb372a00 | 0x7fc2bb237100 | 12076182364303421 | 12076182364315917 | 12076182364671434 | 12076182364699316 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fc3eb372900 | 0x7fc2bb237140 | 12076182364723541 | 12076182364736233 | 12076182364913991 | 12076182364917652 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fc3eb372800 | 0x7fc2bb237180 | 12076182364944121 | 12076182364956711 | 12076182365410466 | 12076182365444471 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fc3eb372700 | 0x7fc2bb2371c0 | 12076182365477282 | 12076182365489826 | 12076182365687904 | 12076182365711227 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fc3eb372600 | 0x7fc2bb237200 | 12076182365731996 | 12076182365744703 | 12076182366445496 | 12076182366474205 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fc3eb372500 | 0x7fc2bb237240 | 12076182366497668 | 12076182366509975 | 12076182366882612 | 12076182366908722 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fc3eb372400 | 0x7fc2bb237280 | 12076182366931585 | 12076182366943891 | 12076182367145809 | 12076182367177352 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fc3eb372300 | 0x7fc2bb2372c0 | 12076182367201697 | 12076182367214448 | 12076182367739243 | 12076182367765685 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fc3eb372a00 | 0x7fc2bb237300 | 12076182367800510 | 12076182367812523 | 12076182368034920 | 12076182368062907 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fc3eb372900 | 0x7fc2bb237340 | 12076182368086972 | 12076182368099720 | 12076182368896352 | 12076182368926232 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fc3eb372800 | 0x7fc2bb237380 | 12076182368946990 | 12076182368959871 | 12076182369376187 | 12076182369408398 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fc3eb372700 | 0x7fc2bb2373c0 | 12076182369429547 | 12076182369441466 | 12076182369666424 | 12076182369692446 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fc3eb372600 | 0x7fc2bb237400 | 12076182369714046 | 12076182369726583 | 12076182370322898 | 12076182370350469 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fc3eb372500 | 0x7fc2bb237440 | 12076182370382839 | 12076182370395857 | 12076182370662894 | 12076182370689268 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fc3eb372400 | 0x7fc2bb237480 | 12076182370712692 | 12076182370725134 | 12076182371708004 | 12076182371735312 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fc3eb372300 | 0x7fc2bb2374c0 | 12076182371757985 | 12076182371770403 | 12076182372284798 | 12076182372313807 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fc3eb372a00 | 0x7fc2bb237500 | 12076182372338313 | 12076182372351517 | 12076182372623035 | 12076182372645664 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fc3eb372900 | 0x7fc2bb237540 | 12076182372670140 | 12076182372682554 | 12076182373419187 | 12076182373447995 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fc3eb372800 | 0x7fc2bb237580 | 12076182373480155 | 12076182373492626 | 12076182373806543 | 12076182373832981 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fc3eb372700 | 0x7fc2bb2375c0 | 12076182373855653 | 12076182373868622 | 12076182375038211 | 12076182375071673 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fc3eb372600 | 0x7fc2bb237600 | 12076182375093714 | 12076182375106210 | 12076182375715164 | 12076182375741588 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fc3eb372500 | 0x7fc2bb237640 | 12076182375764280 | 12076182375776603 | 12076182376094520 | 12076182376122476 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fc3eb372400 | 0x7fc2bb237680 | 12076182376146190 | 12076182376158519 | 12076182377035151 | 12076182377064356 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fc3eb372300 | 0x7fc2bb2376c0 | 12076182377098430 | 12076182377111150 | 12076182377542666 | 12076182377569856 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fc3eb372a00 | 0x7fc2bb237700 | 12076182377592498 | 12076182377604585 | 12076182379151930 | 12076182379201949 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fc3eb372900 | 0x7fc2bb237740 | 12076182379224721 | 12076182379238335 | 12076182380030168 | 12076182380105578 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fc3eb372800 | 0x7fc2bb237780 | 12076182380124954 | 12076182380137526 | 12076182380550963 | 12076182380621938 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fc3eb372700 | 0x7fc2bb2377c0 | 12076182380644339 | 12076182380656722 | 12076182381814472 | 12076182381885145 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fc3eb372600 | 0x7fc2bb237800 | 12076182381918497 | 12076182381931270 | 12076182382716224 | 12076182382790237 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fc3eb372500 | 0x7fc2bb237840 | 12076182382815514 | 12076182382829023 | 12076182385876036 | 12076182385950681 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fc3eb372400 | 0x7fc2bb237880 | 12076182385971910 | 12076182385984835 | 12076182387523541 | 12076182387597752 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fc3eb372300 | 0x7fc2bb2378c0 | 12076182387624141 | 12076182387636020 | 12076182388424654 | 12076182388496532 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fc3eb372a00 | 0x7fc2bb237900 | 12076182388518894 | 12076182388531213 | 12076182390811353 | 12076182390882677 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fc3eb372900 | 0x7fc2bb237940 | 12076182390915398 | 12076182390928152 | 12076182392463178 | 12076182392537132 |
| 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 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fc3eb372800 | 0x7fc2bb237980 | 12076182392561687 | 12076182392575337 | 12076182398626644 | 12076182398698412 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fc3eb372700 | 0x7fc2bb2379c0 | 12076182398720934 | 12076182398733843 | 12076182401771737 | 12076182401842736 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fc3eb372600 | 0x7fc2bb237a00 | 12076182401866129 | 12076182401879256 | 12076182403417482 | 12076182403493203 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 913999 | 914004 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fc3eb372500 | 0x7fc2bb237a40 | 12076182403516667 | 12076182403530761 | 12076182408056321 | 12076182408135340 |