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 | 919015 | 919020 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fc439e04180 | 12076278471723574 | 12076278471768969 | 12076278472093126 | 12076278472199017 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 919015 | 919020 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fc439e35100 | 12076278486700448 | 12076278486804817 | 12076278486811377 | 12076278486817205 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fc5459af900 | 0x7fc439e35140 | 12076278486860124 | 12076278486872656 | 12076278487011215 | 12076278487014772 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fc5459af800 | 0x7fc439e35180 | 12076278487059174 | 12076278487072814 | 12076278487319532 | 12076278487418302 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fc5459af700 | 0x7fc439e351c0 | 12076278487443408 | 12076278487455210 | 12076278487698088 | 12076278487794791 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fc5459af600 | 0x7fc439e35200 | 12076278487820399 | 12076278487832167 | 12076278487957765 | 12076278487961071 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fc5459af500 | 0x7fc439e35240 | 12076278487988552 | 12076278488000165 | 12076278488125284 | 12076278488128862 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fc5459af400 | 0x7fc439e35280 | 12076278488182783 | 12076278488198883 | 12076278488322722 | 12076278488325748 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fc5459af300 | 0x7fc439e352c0 | 12076278488352358 | 12076278488365761 | 12076278488609919 | 12076278488706325 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fc5459afa00 | 0x7fc439e35300 | 12076278488726844 | 12076278488740957 | 12076278488983515 | 12076278489081713 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fc5459af900 | 0x7fc439e35340 | 12076278489103193 | 12076278489114394 | 12076278489239192 | 12076278489242382 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fc5459af800 | 0x7fc439e35380 | 12076278489269242 | 12076278489280472 | 12076278489405911 | 12076278489409432 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fc5459af700 | 0x7fc439e353c0 | 12076278489444788 | 12076278489456150 | 12076278489580789 | 12076278489584107 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fc5459af600 | 0x7fc439e35400 | 12076278489609915 | 12076278489621589 | 12076278489867666 | 12076278489939537 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fc5459af500 | 0x7fc439e35440 | 12076278489959314 | 12076278489971665 | 12076278490219983 | 12076278490289548 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fc5459af400 | 0x7fc439e35480 | 12076278490309455 | 12076278490321102 | 12076278490445740 | 12076278490448954 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fc5459af300 | 0x7fc439e354c0 | 12076278490473790 | 12076278490485420 | 12076278490610859 | 12076278490613941 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fc5459afa00 | 0x7fc439e35500 | 12076278490650398 | 12076278490662698 | 12076278490786537 | 12076278490789928 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fc5459af900 | 0x7fc439e35540 | 12076278490815315 | 12076278490827016 | 12076278491079014 | 12076278491148765 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fc5459af800 | 0x7fc439e35580 | 12076278491170655 | 12076278491181893 | 12076278491426050 | 12076278491493325 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fc5459af700 | 0x7fc439e355c0 | 12076278491513402 | 12076278491526049 | 12076278491650848 | 12076278491654084 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fc5459af600 | 0x7fc439e35600 | 12076278491679651 | 12076278491691008 | 12076278491815807 | 12076278491818960 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fc5459af500 | 0x7fc439e35640 | 12076278491854126 | 12076278491867646 | 12076278491992125 | 12076278491995118 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fc5459af400 | 0x7fc439e35680 | 12076278492026847 | 12076278492038044 | 12076278492286682 | 12076278492352392 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fc5459af300 | 0x7fc439e356c0 | 12076278492373260 | 12076278492384761 | 12076278492634838 | 12076278492730735 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fc5459afa00 | 0x7fc439e35700 | 12076278492751343 | 12076278492762997 | 12076278492887316 | 12076278492890632 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fc5459af900 | 0x7fc439e35740 | 12076278492916420 | 12076278492927155 | 12076278493051954 | 12076278493055548 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fc5459af800 | 0x7fc439e35780 | 12076278493090283 | 12076278493103954 | 12076278493228592 | 12076278493231896 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fc5459af700 | 0x7fc439e357c0 | 12076278493256562 | 12076278493269392 | 12076278493514349 | 12076278493591645 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fc5459af600 | 0x7fc439e35800 | 12076278493610550 | 12076278493622028 | 12076278493868746 | 12076278493945743 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fc5459af500 | 0x7fc439e35840 | 12076278493964447 | 12076278493976265 | 12076278494101064 | 12076278494104598 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fc5459af400 | 0x7fc439e35880 | 12076278494129985 | 12076278494141063 | 12076278494267462 | 12076278494270897 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fc5459af300 | 0x7fc439e358c0 | 12076278494306443 | 12076278494318341 | 12076278494442820 | 12076278494445762 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fc5459afa00 | 0x7fc439e35900 | 12076278494471450 | 12076278494485060 | 12076278494736577 | 12076278494789471 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fc5459af900 | 0x7fc439e35940 | 12076278494808566 | 12076278494828096 | 12076278495074974 | 12076278495157435 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fc5459af800 | 0x7fc439e35980 | 12076278495179105 | 12076278495190173 | 12076278495315451 | 12076278495319015 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fc5459af700 | 0x7fc439e359c0 | 12076278495344152 | 12076278495355291 | 12076278495480890 | 12076278495484202 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fc5459af600 | 0x7fc439e35a00 | 12076278495519628 | 12076278495530809 | 12076278495655288 | 12076278495658386 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fc5459af500 | 0x7fc439e35a40 | 12076278495683101 | 12076278495694648 | 12076278495948405 | 12076278495975966 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fc5459af400 | 0x7fc439e35a80 | 12076278495995141 | 12076278496006324 | 12076278496251122 | 12076278496277847 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fc5459af300 | 0x7fc439e35ac0 | 12076278496299257 | 12076278496312881 | 12076278496437680 | 12076278496441040 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fc5459afa00 | 0x7fc439e35b00 | 12076278496468581 | 12076278496482160 | 12076278496608078 | 12076278496611266 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fc5459af900 | 0x7fc439e35b40 | 12076278496646261 | 12076278496658958 | 12076278496783437 | 12076278496786682 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fc5459af800 | 0x7fc439e35b80 | 12076278496812420 | 12076278496823436 | 12076278497084714 | 12076278497113530 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fc5459af700 | 0x7fc439e35bc0 | 12076278497133667 | 12076278497146313 | 12076278497394951 | 12076278497418677 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fc5459af600 | 0x7fc439e35c00 | 12076278497436901 | 12076278497449190 | 12076278497573829 | 12076278497576871 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fc5459af500 | 0x7fc439e35c40 | 12076278497601877 | 12076278497614788 | 12076278497741187 | 12076278497744252 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fc5459af400 | 0x7fc439e35c80 | 12076278497779988 | 12076278497791587 | 12076278497916865 | 12076278497919858 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fc5459af300 | 0x7fc439e35cc0 | 12076278497944935 | 12076278497957825 | 12076278498212862 | 12076278498244492 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fc5459afa00 | 0x7fc439e35d00 | 12076278498264369 | 12076278498277342 | 12076278498520379 | 12076278498543788 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fc5459af900 | 0x7fc439e35d40 | 12076278498563344 | 12076278498576219 | 12076278498701817 | 12076278498705068 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fc5459af800 | 0x7fc439e35d80 | 12076278498730435 | 12076278498741817 | 12076278498869016 | 12076278498872108 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fc5459af700 | 0x7fc439e35dc0 | 12076278498908476 | 12076278498921655 | 12076278499046294 | 12076278499049458 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fc5459af600 | 0x7fc439e35e00 | 12076278499075136 | 12076278499086614 | 12076278499342931 | 12076278499369743 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fc5459af500 | 0x7fc439e35e40 | 12076278499388358 | 12076278499401010 | 12076278499652048 | 12076278499674790 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fc5459af400 | 0x7fc439e35e80 | 12076278499695799 | 12076278499708367 | 12076278499833166 | 12076278499836370 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fc5459af300 | 0x7fc439e35ec0 | 12076278499861707 | 12076278499874766 | 12076278500004044 | 12076278500007368 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fc5459afa00 | 0x7fc439e35f00 | 12076278500042684 | 12076278500054124 | 12076278500179083 | 12076278500182083 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fc5459af900 | 0x7fc439e35f40 | 12076278500207209 | 12076278500220042 | 12076278500472680 | 12076278500492069 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fc5459af800 | 0x7fc439e35f80 | 12076278500511795 | 12076278500524359 | 12076278500768037 | 12076278500790874 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fc5459af700 | 0x7fc439e35fc0 | 12076278500810611 | 12076278500823396 | 12076278500948995 | 12076278500952074 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fc5459af600 | 0x7fc439e36000 | 12076278500976980 | 12076278500988354 | 12076278501125793 | 12076278501128922 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fc5459af500 | 0x7fc439e36040 | 12076278501167093 | 12076278501178753 | 12076278501303231 | 12076278501306422 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fc5459af400 | 0x7fc439e36080 | 12076278501332330 | 12076278501343551 | 12076278501594908 | 12076278501615557 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fc5459af300 | 0x7fc439e360c0 | 12076278501639191 | 12076278501650748 | 12076278501895225 | 12076278501917959 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fc5459afa00 | 0x7fc439e36100 | 12076278501938086 | 12076278501949145 | 12076278502073304 | 12076278502076844 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fc5459af900 | 0x7fc439e36140 | 12076278502102902 | 12076278502116023 | 12076278502257142 | 12076278502260405 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fc5459af800 | 0x7fc439e36180 | 12076278502296853 | 12076278502307701 | 12076278502433140 | 12076278502436272 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fc5459af700 | 0x7fc439e361c0 | 12076278502462100 | 12076278502475059 | 12076278502727377 | 12076278502746819 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fc5459af600 | 0x7fc439e36200 | 12076278502766436 | 12076278502779536 | 12076278503024814 | 12076278503054481 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fc5459af500 | 0x7fc439e36240 | 12076278503077444 | 12076278503090733 | 12076278503216172 | 12076278503219558 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fc5459af400 | 0x7fc439e36280 | 12076278503244915 | 12076278503256652 | 12076278503406250 | 12076278503409411 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fc5459af300 | 0x7fc439e362c0 | 12076278503462579 | 12076278503473609 | 12076278503598568 | 12076278503601868 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fc5459afa00 | 0x7fc439e36300 | 12076278503626394 | 12076278503641928 | 12076278503907685 | 12076278503935268 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fc5459af900 | 0x7fc439e36340 | 12076278503955335 | 12076278503968325 | 12076278504219202 | 12076278504247488 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fc5459af800 | 0x7fc439e36380 | 12076278504267335 | 12076278504279841 | 12076278504405440 | 12076278504408788 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fc5459af700 | 0x7fc439e363c0 | 12076278504434606 | 12076278504447040 | 12076278504604958 | 12076278504608309 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fc5459af600 | 0x7fc439e36400 | 12076278504644396 | 12076278504657118 | 12076278504782396 | 12076278504785598 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fc5459af500 | 0x7fc439e36440 | 12076278504811336 | 12076278504823676 | 12076278505080313 | 12076278505114069 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fc5459af400 | 0x7fc439e36480 | 12076278505133485 | 12076278505146233 | 12076278505390870 | 12076278505413365 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fc5459af300 | 0x7fc439e364c0 | 12076278505434845 | 12076278505447830 | 12076278505573588 | 12076278505576859 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fc5459afa00 | 0x7fc439e36500 | 12076278505600973 | 12076278505613108 | 12076278505777426 | 12076278505780627 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fc5459af900 | 0x7fc439e36540 | 12076278505816133 | 12076278505827986 | 12076278505954065 | 12076278505957406 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fc5459af800 | 0x7fc439e36580 | 12076278505982452 | 12076278505993904 | 12076278506251022 | 12076278506277952 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fc5459af700 | 0x7fc439e365c0 | 12076278506298049 | 12076278506310541 | 12076278506559018 | 12076278506581726 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fc5459af600 | 0x7fc439e36600 | 12076278506603286 | 12076278506616138 | 12076278506741577 | 12076278506744909 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fc5459af500 | 0x7fc439e36640 | 12076278506770427 | 12076278506783176 | 12076278506955975 | 12076278506959268 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fc5459af400 | 0x7fc439e36680 | 12076278506995746 | 12076278507007174 | 12076278507132613 | 12076278507136136 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fc5459af300 | 0x7fc439e366c0 | 12076278507163277 | 12076278507174692 | 12076278507427170 | 12076278507452044 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fc5459afa00 | 0x7fc439e36700 | 12076278507471440 | 12076278507482369 | 12076278507729727 | 12076278507752472 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fc5459af900 | 0x7fc439e36740 | 12076278507772860 | 12076278507783806 | 12076278507910365 | 12076278507913501 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fc5459af800 | 0x7fc439e36780 | 12076278507938648 | 12076278507951645 | 12076278508133563 | 12076278508137337 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fc5459af700 | 0x7fc439e367c0 | 12076278508175197 | 12076278508187482 | 12076278508314361 | 12076278508317562 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fc5459af600 | 0x7fc439e36800 | 12076278508342278 | 12076278508353560 | 12076278508615158 | 12076278508638248 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fc5459af500 | 0x7fc439e36840 | 12076278508657534 | 12076278508668437 | 12076278508919955 | 12076278508942463 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fc5459af400 | 0x7fc439e36880 | 12076278508961058 | 12076278508972434 | 12076278509098193 | 12076278509101669 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fc5459af300 | 0x7fc439e368c0 | 12076278509128579 | 12076278509139953 | 12076278509331631 | 12076278509355180 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fc5459afa00 | 0x7fc439e36900 | 12076278509384635 | 12076278509398190 | 12076278509524109 | 12076278509527320 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fc5459af900 | 0x7fc439e36940 | 12076278509552207 | 12076278509564268 | 12076278509845865 | 12076278509865128 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fc5459af800 | 0x7fc439e36980 | 12076278509884975 | 12076278509897865 | 12076278510149222 | 12076278510176597 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fc5459af700 | 0x7fc439e369c0 | 12076278510196624 | 12076278510209382 | 12076278510335141 | 12076278510338458 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fc5459af600 | 0x7fc439e36a00 | 12076278510363705 | 12076278510376580 | 12076278510585058 | 12076278510607478 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fc5459af500 | 0x7fc439e36a40 | 12076278510637564 | 12076278510649857 | 12076278510778336 | 12076278510781631 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fc5459af400 | 0x7fc439e36a80 | 12076278510806638 | 12076278510818176 | 12076278511124093 | 12076278511151990 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fc5459af300 | 0x7fc439e36ac0 | 12076278511173029 | 12076278511183932 | 12076278511434810 | 12076278511459802 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fc5459afa00 | 0x7fc439e36b00 | 12076278511480220 | 12076278511493049 | 12076278511620248 | 12076278511623506 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fc5459af900 | 0x7fc439e36b40 | 12076278511649034 | 12076278511662327 | 12076278511888885 | 12076278511908135 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fc5459af800 | 0x7fc439e36b80 | 12076278511940235 | 12076278511952884 | 12076278512079443 | 12076278512082790 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fc5459af700 | 0x7fc439e36bc0 | 12076278512109299 | 12076278512120243 | 12076278512448399 | 12076278512471512 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fc5459af600 | 0x7fc439e36c00 | 12076278512491860 | 12076278512504559 | 12076278512751596 | 12076278512774455 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fc5459af500 | 0x7fc439e36c40 | 12076278512794532 | 12076278512805516 | 12076278512933834 | 12076278512937017 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fc5459af400 | 0x7fc439e36c80 | 12076278512962044 | 12076278512973354 | 12076278513217032 | 12076278513240651 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fc5459af300 | 0x7fc439e36cc0 | 12076278513271920 | 12076278513283111 | 12076278513412870 | 12076278513416128 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fc5459afa00 | 0x7fc439e36d00 | 12076278513441034 | 12076278513452069 | 12076278513826786 | 12076278513849453 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fc5459af900 | 0x7fc439e36d40 | 12076278513868468 | 12076278513879265 | 12076278514130782 | 12076278514157465 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fc5459af800 | 0x7fc439e36d80 | 12076278514179556 | 12076278514192222 | 12076278514320861 | 12076278514324255 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fc5459af700 | 0x7fc439e36dc0 | 12076278514349142 | 12076278514361980 | 12076278514640217 | 12076278514662764 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fc5459af600 | 0x7fc439e36e00 | 12076278514692029 | 12076278514704217 | 12076278514838615 | 12076278514842198 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fc5459af500 | 0x7fc439e36e40 | 12076278514866643 | 12076278514879415 | 12076278515300691 | 12076278515328652 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fc5459af400 | 0x7fc439e36e80 | 12076278515349701 | 12076278515362130 | 12076278515620208 | 12076278515642866 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fc5459af300 | 0x7fc439e36ec0 | 12076278515662182 | 12076278515674447 | 12076278515810446 | 12076278515813824 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fc5459afa00 | 0x7fc439e36f00 | 12076278515838920 | 12076278515851565 | 12076278516195402 | 12076278516219257 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fc5459af900 | 0x7fc439e36f40 | 12076278516251587 | 12076278516264521 | 12076278516415400 | 12076278516419399 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fc5459af800 | 0x7fc439e36f80 | 12076278516445467 | 12076278516457159 | 12076278516971714 | 12076278516994227 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fc5459af700 | 0x7fc439e36fc0 | 12076278517019294 | 12076278517030113 | 12076278517327870 | 12076278517351431 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fc5459af600 | 0x7fc439e37000 | 12076278517370617 | 12076278517381470 | 12076278517535068 | 12076278517538499 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fc5459af500 | 0x7fc439e37040 | 12076278517563555 | 12076278517574588 | 12076278517958904 | 12076278517981763 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fc5459af400 | 0x7fc439e37080 | 12076278518018932 | 12076278518030743 | 12076278518206102 | 12076278518209546 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fc5459af300 | 0x7fc439e370c0 | 12076278518239972 | 12076278518251221 | 12076278518859535 | 12076278518882286 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fc5459afa00 | 0x7fc439e37100 | 12076278518906271 | 12076278518917294 | 12076278519245931 | 12076278519272862 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fc5459af900 | 0x7fc439e37140 | 12076278519296185 | 12076278519308810 | 12076278519486889 | 12076278519490286 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fc5459af800 | 0x7fc439e37180 | 12076278519515653 | 12076278519527848 | 12076278519982404 | 12076278520008609 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fc5459af700 | 0x7fc439e371c0 | 12076278520042272 | 12076278520055043 | 12076278520254881 | 12076278520281657 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fc5459af600 | 0x7fc439e37200 | 12076278520301123 | 12076278520312000 | 12076278521020313 | 12076278521048562 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fc5459af500 | 0x7fc439e37240 | 12076278521069110 | 12076278521081273 | 12076278521453109 | 12076278521479663 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fc5459af400 | 0x7fc439e37280 | 12076278521499811 | 12076278521511348 | 12076278521713906 | 12076278521740147 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fc5459af300 | 0x7fc439e372c0 | 12076278521759393 | 12076278521770226 | 12076278522295980 | 12076278522323281 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fc5459afa00 | 0x7fc439e37300 | 12076278522355681 | 12076278522368300 | 12076278522592458 | 12076278522618720 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fc5459af900 | 0x7fc439e37340 | 12076278522640280 | 12076278522651177 | 12076278523448449 | 12076278523475492 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fc5459af800 | 0x7fc439e37380 | 12076278523496592 | 12076278523507488 | 12076278523926844 | 12076278523952830 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fc5459af700 | 0x7fc439e373c0 | 12076278523974309 | 12076278523985884 | 12076278524210361 | 12076278524242518 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fc5459af600 | 0x7fc439e37400 | 12076278524265220 | 12076278524276441 | 12076278524871795 | 12076278524899259 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fc5459af500 | 0x7fc439e37440 | 12076278524930436 | 12076278524941074 | 12076278525209071 | 12076278525236325 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fc5459af400 | 0x7fc439e37480 | 12076278525258135 | 12076278525271471 | 12076278526254821 | 12076278526282138 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fc5459af300 | 0x7fc439e374c0 | 12076278526301524 | 12076278526313700 | 12076278526826335 | 12076278526848251 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fc5459afa00 | 0x7fc439e37500 | 12076278526873728 | 12076278526886814 | 12076278527158012 | 12076278527184195 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fc5459af900 | 0x7fc439e37540 | 12076278527208139 | 12076278527219291 | 12076278527955764 | 12076278527978301 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fc5459af800 | 0x7fc439e37580 | 12076278528022753 | 12076278528034643 | 12076278528377999 | 12076278528401517 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fc5459af700 | 0x7fc439e375c0 | 12076278528429018 | 12076278528441679 | 12076278529611427 | 12076278529636072 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fc5459af600 | 0x7fc439e37600 | 12076278529662851 | 12076278529675906 | 12076278530284860 | 12076278530313270 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fc5459af500 | 0x7fc439e37640 | 12076278530334640 | 12076278530345660 | 12076278530664216 | 12076278530691914 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fc5459af400 | 0x7fc439e37680 | 12076278530713494 | 12076278530724856 | 12076278531602127 | 12076278531631290 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fc5459af300 | 0x7fc439e376c0 | 12076278531664401 | 12076278531675566 | 12076278532084362 | 12076278532112985 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fc5459afa00 | 0x7fc439e37700 | 12076278532135547 | 12076278532146442 | 12076278533694586 | 12076278533765867 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fc5459af900 | 0x7fc439e37740 | 12076278533786645 | 12076278533798105 | 12076278534591057 | 12076278534666370 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fc5459af800 | 0x7fc439e37780 | 12076278534686568 | 12076278534698441 | 12076278535112197 | 12076278535187068 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fc5459af700 | 0x7fc439e377c0 | 12076278535208047 | 12076278535219715 | 12076278536377306 | 12076278536448242 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fc5459af600 | 0x7fc439e37800 | 12076278536479921 | 12076278536493945 | 12076278537279858 | 12076278537350408 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fc5459af500 | 0x7fc439e37840 | 12076278537372519 | 12076278537386257 | 12076278540437112 | 12076278540508157 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fc5459af400 | 0x7fc439e37880 | 12076278540529657 | 12076278540542391 | 12076278542083019 | 12076278542153635 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fc5459af300 | 0x7fc439e378c0 | 12076278542176137 | 12076278542189898 | 12076278542979491 | 12076278543050742 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fc5459afa00 | 0x7fc439e37900 | 12076278543071431 | 12076278543082690 | 12076278545363631 | 12076278545435334 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fc5459af900 | 0x7fc439e37940 | 12076278545465901 | 12076278545479631 | 12076278547014178 | 12076278547085140 |
| 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 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fc5459af800 | 0x7fc439e37980 | 12076278547107672 | 12076278547121217 | 12076278553173967 | 12076278553245328 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fc5459af700 | 0x7fc439e379c0 | 12076278553264444 | 12076278553277966 | 12076278556318741 | 12076278556390183 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fc5459af600 | 0x7fc439e37a00 | 12076278556411012 | 12076278556422740 | 12076278557961448 | 12076278558033487 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 919015 | 919020 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fc5459af500 | 0x7fc439e37a40 | 12076278558053334 | 12076278558066567 | 12076278562591649 | 12076278562663892 |