43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 759929 | 759934 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fd40fa04180 | 4194304 | 3210336 | 411223016 | 12073371192092238 | 12073371432548179 | 12073371432871378 | 12073371432980200 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 759929 | 759934 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fd40fa35100 | 512 | 26450 | 3374080 | 12073371447235171 | 12073371447542389 | 12073371447549269 | 12073371447557791 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fd53fc20900 | 0x7fd40fa35140 | 65536 | 197886 | 25315808 | 12073371447611902 | 12073371447832788 | 12073371447965907 | 12073371447969917 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fd53fc20800 | 0x7fd40fa35180 | 65536 | 158334 | 20302064 | 12073371448045457 | 12073371448213106 | 12073371448463665 | 12073371448533384 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fd53fc20700 | 0x7fd40fa351c0 | 65536 | 174294 | 22372568 | 12073371448565033 | 12073371448752144 | 12073371449002223 | 12073371449069891 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fd53fc20600 | 0x7fd40fa35200 | 65536 | 171698 | 21935952 | 12073371449090139 | 12073371449281901 | 12073371449416941 | 12073371449420432 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fd53fc20500 | 0x7fd40fa35240 | 65536 | 175328 | 22513136 | 12073371449463753 | 12073371449640460 | 12073371449779819 | 12073371449783437 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fd53fc20400 | 0x7fd40fa35280 | 131072 | 246944 | 31617904 | 12073371449862714 | 12073371450033738 | 12073371450167657 | 12073371450171428 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fd53fc20300 | 0x7fd40fa352c0 | 131072 | 230588 | 29547872 | 12073371450214368 | 12073371450400616 | 12073371450658695 | 12073371450701213 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fd53fc20a00 | 0x7fd40fa35300 | 65536 | 168520 | 21670296 | 12073371450726860 | 12073371450905894 | 12073371451157893 | 12073371451199909 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fd53fc20900 | 0x7fd40fa35340 | 131072 | 269762 | 34558312 | 12073371451223954 | 12073371451414371 | 12073371451544131 | 12073371451547666 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fd53fc20800 | 0x7fd40fa35380 | 131072 | 269684 | 34373728 | 12073371451596877 | 12073371451765250 | 12073371451899809 | 12073371451903347 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fd53fc20700 | 0x7fd40fa353c0 | 131072 | 271974 | 34968016 | 12073371451965743 | 12073371452134048 | 12073371452267328 | 12073371452270980 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fd53fc20600 | 0x7fd40fa35400 | 131072 | 212746 | 27337128 | 12073371452320412 | 12073371452484447 | 12073371452745085 | 12073371452812336 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fd53fc20500 | 0x7fd40fa35440 | 65536 | 174624 | 22215384 | 12073371452838454 | 12073371453023004 | 12073371453282683 | 12073371453351057 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fd53fc20400 | 0x7fd40fa35480 | 131072 | 262722 | 33812720 | 12073371453375733 | 12073371453560122 | 12073371453688921 | 12073371453692502 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fd53fc20300 | 0x7fd40fa354c0 | 131072 | 273604 | 34963584 | 12073371453742905 | 12073371453902520 | 12073371454040759 | 12073371454044586 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fd53fc20a00 | 0x7fd40fa35500 | 131072 | 251500 | 32245168 | 12073371454105649 | 12073371454269238 | 12073371454442677 | 12073371454446092 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fd53fc20900 | 0x7fd40fa35540 | 131072 | 206496 | 26402056 | 12073371454495814 | 12073371454663796 | 12073371454966035 | 12073371455032943 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fd53fc20800 | 0x7fd40fa35580 | 65536 | 171850 | 21940384 | 12073371455057689 | 12073371455246194 | 12073371455505393 | 12073371455572926 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fd53fc20700 | 0x7fd40fa355c0 | 131072 | 261936 | 33565792 | 12073371455595087 | 12073371455775791 | 12073371455908911 | 12073371455912457 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fd53fc20600 | 0x7fd40fa35600 | 131072 | 268930 | 34441496 | 12073371455962951 | 12073371456136110 | 12073371456276269 | 12073371456279920 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fd53fc20500 | 0x7fd40fa35640 | 131072 | 250434 | 32030168 | 12073371456340913 | 12073371456509868 | 12073371456648107 | 12073371456651771 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fd53fc20400 | 0x7fd40fa35680 | 131072 | 205492 | 26239560 | 12073371456699670 | 12073371456865866 | 12073371457128745 | 12073371457198207 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fd53fc20300 | 0x7fd40fa356c0 | 65536 | 174160 | 22258536 | 12073371457222802 | 12073371457400744 | 12073371457660263 | 12073371457727470 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fd53fc20a00 | 0x7fd40fa35700 | 131072 | 266490 | 34099608 | 12073371457754701 | 12073371457926661 | 12073371458057381 | 12073371458060960 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fd53fc20900 | 0x7fd40fa35740 | 131072 | 247434 | 31577232 | 12073371458108027 | 12073371458279940 | 12073371458412579 | 12073371458415960 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fd53fc20800 | 0x7fd40fa35780 | 131072 | 243286 | 31288896 | 12073371458477173 | 12073371458637378 | 12073371458768098 | 12073371458771701 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fd53fc20700 | 0x7fd40fa357c0 | 131072 | 220952 | 28157392 | 12073371458820682 | 12073371458992896 | 12073371459248255 | 12073371459316593 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fd53fc20600 | 0x7fd40fa35800 | 65536 | 173596 | 22133848 | 12073371459342231 | 12073371459524734 | 12073371459781213 | 12073371459848392 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fd53fc20500 | 0x7fd40fa35840 | 131072 | 247226 | 31785520 | 12073371459873769 | 12073371460053052 | 12073371460185371 | 12073371460189095 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fd53fc20400 | 0x7fd40fa35880 | 131072 | 243426 | 31208024 | 12073371460233788 | 12073371460406330 | 12073371460536569 | 12073371460539967 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fd53fc20300 | 0x7fd40fa358c0 | 131072 | 256528 | 32628624 | 12073371460600399 | 12073371460759928 | 12073371460894168 | 12073371460897662 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fd53fc20a00 | 0x7fd40fa35900 | 131072 | 235040 | 29896496 | 12073371460945350 | 12073371461120087 | 12073371461375925 | 12073371461444357 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fd53fc20900 | 0x7fd40fa35940 | 65536 | 179142 | 22840824 | 12073371461470656 | 12073371461648404 | 12073371461905363 | 12073371461947262 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fd53fc20800 | 0x7fd40fa35980 | 131072 | 266964 | 34052088 | 12073371461971046 | 12073371462155602 | 12073371462290481 | 12073371462294177 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fd53fc20700 | 0x7fd40fa359c0 | 131072 | 246414 | 31614456 | 12073371462343579 | 12073371462514000 | 12073371462645680 | 12073371462649257 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fd53fc20600 | 0x7fd40fa35a00 | 131072 | 246660 | 31485664 | 12073371462711362 | 12073371462873199 | 12073371463006638 | 12073371463010338 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fd53fc20500 | 0x7fd40fa35a40 | 131072 | 212098 | 27097176 | 12073371463061903 | 12073371463224717 | 12073371463492236 | 12073371463559508 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fd53fc20400 | 0x7fd40fa35a80 | 65536 | 199806 | 25501656 | 12073371463581499 | 12073371463760394 | 12073371464014953 | 12073371464082861 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fd53fc20300 | 0x7fd40fa35ac0 | 131072 | 251738 | 32304312 | 12073371464110963 | 12073371464294632 | 12073371464426151 | 12073371464429816 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fd53fc20a00 | 0x7fd40fa35b00 | 131072 | 265700 | 34084944 | 12073371464482013 | 12073371464642630 | 12073371464779430 | 12073371464783112 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fd53fc20900 | 0x7fd40fa35b40 | 131072 | 246860 | 31537480 | 12073371464842923 | 12073371465001189 | 12073371465132708 | 12073371465136579 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fd53fc20800 | 0x7fd40fa35b80 | 131072 | 224366 | 28647168 | 12073371465185851 | 12073371465354787 | 12073371465620066 | 12073371465687363 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fd53fc20700 | 0x7fd40fa35bc0 | 65536 | 177868 | 22825312 | 12073371465709534 | 12073371465886785 | 12073371466143263 | 12073371466212889 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fd53fc20600 | 0x7fd40fa35c00 | 131072 | 274730 | 35105816 | 12073371466236293 | 12073371466413022 | 12073371466546942 | 12073371466550437 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fd53fc20500 | 0x7fd40fa35c40 | 131072 | 246024 | 31315824 | 12073371466598987 | 12073371466766301 | 12073371466902620 | 12073371466906278 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fd53fc20400 | 0x7fd40fa35c80 | 131072 | 258132 | 32977864 | 12073371466967001 | 12073371467132539 | 12073371467265978 | 12073371467269653 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fd53fc20300 | 0x7fd40fa35cc0 | 131072 | 211716 | 27176712 | 12073371467317562 | 12073371467483257 | 12073371467748856 | 12073371467816830 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fd53fc20a00 | 0x7fd40fa35d00 | 65536 | 185370 | 23606760 | 12073371467843169 | 12073371468014295 | 12073371468269174 | 12073371468336816 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fd53fc20900 | 0x7fd40fa35d40 | 131072 | 253188 | 32537664 | 12073371468360280 | 12073371468537172 | 12073371468664692 | 12073371468668473 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fd53fc20800 | 0x7fd40fa35d80 | 131072 | 272868 | 34876192 | 12073371468723214 | 12073371468879571 | 12073371469016530 | 12073371469020216 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fd53fc20700 | 0x7fd40fa35dc0 | 131072 | 246282 | 31579288 | 12073371469082232 | 12073371469243249 | 12073371469377489 | 12073371469381408 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fd53fc20600 | 0x7fd40fa35e00 | 131072 | 253598 | 32667032 | 12073371469424047 | 12073371469592528 | 12073371469859406 | 12073371469926430 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fd53fc20500 | 0x7fd40fa35e40 | 65536 | 187806 | 24148648 | 12073371469951948 | 12073371470132525 | 12073371470392044 | 12073371470459251 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fd53fc20400 | 0x7fd40fa35e80 | 131072 | 260524 | 33539840 | 12073371470484988 | 12073371470668203 | 12073371470796522 | 12073371470800194 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fd53fc20300 | 0x7fd40fa35ec0 | 131072 | 243490 | 30993216 | 12073371470848935 | 12073371471014281 | 12073371471158760 | 12073371471162538 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fd53fc20a00 | 0x7fd40fa35f00 | 131072 | 244822 | 31362808 | 12073371471224202 | 12073371471386759 | 12073371471518759 | 12073371471522727 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fd53fc20900 | 0x7fd40fa35f40 | 131072 | 257688 | 33017472 | 12073371471571718 | 12073371471733478 | 12073371472000996 | 12073371472068501 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fd53fc20800 | 0x7fd40fa35f80 | 65536 | 196680 | 25139456 | 12073371472091995 | 12073371472268675 | 12073371472526594 | 12073371472593507 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fd53fc20700 | 0x7fd40fa35fc0 | 131072 | 250876 | 31965664 | 12073371472615358 | 12073371472800833 | 12073371472936512 | 12073371472940211 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fd53fc20600 | 0x7fd40fa36000 | 131072 | 255414 | 32771752 | 12073371472989463 | 12073371473156351 | 12073371473295070 | 12073371473298948 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fd53fc20500 | 0x7fd40fa36040 | 131072 | 247922 | 31815544 | 12073371473359000 | 12073371473519069 | 12073371473653149 | 12073371473656873 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fd53fc20400 | 0x7fd40fa36080 | 131072 | 229140 | 29387240 | 12073371473708609 | 12073371473864348 | 12073371474132507 | 12073371474182269 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fd53fc20300 | 0x7fd40fa360c0 | 65536 | 173812 | 22318960 | 12073371474205132 | 12073371474388185 | 12073371474646104 | 12073371474694902 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fd53fc20a00 | 0x7fd40fa36100 | 131072 | 267428 | 34289032 | 12073371474717875 | 12073371474902743 | 12073371475040662 | 12073371475044231 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fd53fc20900 | 0x7fd40fa36140 | 131072 | 209742 | 26868592 | 12073371475093102 | 12073371475263701 | 12073371475407541 | 12073371475411123 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fd53fc20800 | 0x7fd40fa36180 | 131072 | 243654 | 31137024 | 12073371475471315 | 12073371475633140 | 12073371475773459 | 12073371475777584 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fd53fc20700 | 0x7fd40fa361c0 | 131072 | 205848 | 26381648 | 12073371475825413 | 12073371475984978 | 12073371476256177 | 12073371476283715 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fd53fc20600 | 0x7fd40fa36200 | 65536 | 200228 | 25541240 | 12073371476325052 | 12073371476497936 | 12073371476755055 | 12073371476802248 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fd53fc20500 | 0x7fd40fa36240 | 131072 | 252806 | 31967392 | 12073371476829729 | 12073371477002893 | 12073371477134733 | 12073371477138533 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fd53fc20400 | 0x7fd40fa36280 | 131072 | 226126 | 28961688 | 12073371477188787 | 12073371477357452 | 12073371477506571 | 12073371477510214 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fd53fc20300 | 0x7fd40fa362c0 | 131072 | 249910 | 32018856 | 12073371477588920 | 12073371477747050 | 12073371477879369 | 12073371477882997 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fd53fc20a00 | 0x7fd40fa36300 | 131072 | 230512 | 29642816 | 12073371477936636 | 12073371478117128 | 12073371478384007 | 12073371478410587 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fd53fc20900 | 0x7fd40fa36340 | 65536 | 200348 | 25593848 | 12073371478451563 | 12073371478610086 | 12073371478873765 | 12073371478897743 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fd53fc20800 | 0x7fd40fa36380 | 131072 | 269640 | 34331312 | 12073371478941834 | 12073371479110884 | 12073371479249443 | 12073371479253253 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fd53fc20700 | 0x7fd40fa363c0 | 131072 | 246518 | 31624240 | 12073371479302585 | 12073371479461442 | 12073371479618561 | 12073371479622119 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fd53fc20600 | 0x7fd40fa36400 | 131072 | 264198 | 33741816 | 12073371479682952 | 12073371479842880 | 12073371479974880 | 12073371479978812 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fd53fc20500 | 0x7fd40fa36440 | 131072 | 207770 | 26531376 | 12073371480032000 | 12073371480195519 | 12073371480464797 | 12073371480490242 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fd53fc20400 | 0x7fd40fa36480 | 65536 | 200532 | 25616576 | 12073371480533442 | 12073371480690556 | 12073371480948475 | 12073371480969483 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fd53fc20300 | 0x7fd40fa364c0 | 131072 | 244574 | 31289016 | 12073371481016089 | 12073371481182714 | 12073371481320473 | 12073371481324673 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fd53fc20a00 | 0x7fd40fa36500 | 131072 | 272506 | 34980032 | 12073371481367713 | 12073371481552632 | 12073371481719672 | 12073371481723294 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fd53fc20900 | 0x7fd40fa36540 | 131072 | 249178 | 31940736 | 12073371481784187 | 12073371481942391 | 12073371482073430 | 12073371482077822 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fd53fc20800 | 0x7fd40fa36580 | 131072 | 207512 | 26562752 | 12073371482122175 | 12073371482317269 | 12073371482580788 | 12073371482606545 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fd53fc20700 | 0x7fd40fa365c0 | 65536 | 171500 | 22024776 | 12073371482647090 | 12073371482803667 | 12073371483061585 | 12073371483086828 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fd53fc20600 | 0x7fd40fa36600 | 131072 | 267438 | 34198128 | 12073371483131380 | 12073371483290704 | 12073371483424304 | 12073371483428222 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fd53fc20500 | 0x7fd40fa36640 | 131072 | 269506 | 34159656 | 12073371483476251 | 12073371483639983 | 12073371483814222 | 12073371483817946 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fd53fc20400 | 0x7fd40fa36680 | 131072 | 246050 | 31519144 | 12073371483877948 | 12073371484041421 | 12073371484176940 | 12073371484181181 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fd53fc20300 | 0x7fd40fa366c0 | 131072 | 235226 | 30119560 | 12073371484229561 | 12073371484398059 | 12073371484659818 | 12073371484684386 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fd53fc20a00 | 0x7fd40fa36700 | 65536 | 180702 | 23190304 | 12073371484723229 | 12073371484878857 | 12073371485137736 | 12073371485165270 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fd53fc20900 | 0x7fd40fa36740 | 131072 | 259174 | 33240024 | 12073371485202980 | 12073371485365255 | 12073371485507814 | 12073371485511804 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fd53fc20800 | 0x7fd40fa36780 | 131072 | 284224 | 36133408 | 12073371485560685 | 12073371485725413 | 12073371485907812 | 12073371485911537 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fd53fc20700 | 0x7fd40fa367c0 | 131072 | 242898 | 30967216 | 12073371485971358 | 12073371486136131 | 12073371486278531 | 12073371486282546 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fd53fc20600 | 0x7fd40fa36800 | 131072 | 247242 | 31712936 | 12073371486330626 | 12073371486495010 | 12073371486761248 | 12073371486785200 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fd53fc20500 | 0x7fd40fa36840 | 65536 | 174134 | 22257552 | 12073371486832669 | 12073371486991647 | 12073371487252126 | 12073371487277395 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fd53fc20400 | 0x7fd40fa36880 | 131072 | 268286 | 34427736 | 12073371487320996 | 12073371487481245 | 12073371487657564 | 12073371487661469 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fd53fc20300 | 0x7fd40fa368c0 | 131072 | 277470 | 35709120 | 12073371487713295 | 12073371487878523 | 12073371488070202 | 12073371488095365 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fd53fc20a00 | 0x7fd40fa36900 | 131072 | 248250 | 31856984 | 12073371488150558 | 12073371488308761 | 12073371488451481 | 12073371488455274 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fd53fc20900 | 0x7fd40fa36940 | 131072 | 256854 | 32788056 | 12073371488502271 | 12073371488667320 | 12073371488950998 | 12073371488970772 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fd53fc20800 | 0x7fd40fa36980 | 65536 | 170812 | 21872232 | 12073371489012049 | 12073371489182357 | 12073371489446036 | 12073371489472565 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fd53fc20700 | 0x7fd40fa369c0 | 131072 | 247164 | 31439776 | 12073371489514042 | 12073371489671795 | 12073371489813874 | 12073371489817546 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fd53fc20600 | 0x7fd40fa36a00 | 131072 | 244378 | 31343528 | 12073371489859423 | 12073371490038513 | 12073371490247792 | 12073371490271950 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fd53fc20500 | 0x7fd40fa36a40 | 131072 | 249124 | 31941096 | 12073371490331501 | 12073371490494671 | 12073371490628431 | 12073371490632180 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fd53fc20400 | 0x7fd40fa36a80 | 131072 | 239592 | 30880968 | 12073371490679137 | 12073371490840270 | 12073371491150028 | 12073371491174618 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fd53fc20300 | 0x7fd40fa36ac0 | 65536 | 167080 | 21449064 | 12073371491218389 | 12073371491377707 | 12073371491638186 | 12073371491661452 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fd53fc20a00 | 0x7fd40fa36b00 | 131072 | 244648 | 31387176 | 12073371491707809 | 12073371491866985 | 12073371492007944 | 12073371492011944 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fd53fc20900 | 0x7fd40fa36b40 | 131072 | 268900 | 34489808 | 12073371492060734 | 12073371492226663 | 12073371492454182 | 12073371492478300 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fd53fc20800 | 0x7fd40fa36b80 | 131072 | 252894 | 32196984 | 12073371492534695 | 12073371492693381 | 12073371492834020 | 12073371492837879 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fd53fc20700 | 0x7fd40fa36bc0 | 131072 | 247188 | 31489512 | 12073371492885938 | 12073371493067299 | 12073371493398818 | 12073371493425561 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fd53fc20600 | 0x7fd40fa36c00 | 65536 | 172324 | 21985016 | 12073371493466687 | 12073371493627457 | 12073371493886815 | 12073371493909861 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fd53fc20500 | 0x7fd40fa36c40 | 131072 | 271198 | 34746032 | 12073371493954414 | 12073371494118334 | 12073371494255134 | 12073371494259190 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fd53fc20400 | 0x7fd40fa36c80 | 131072 | 248996 | 31717248 | 12073371494307530 | 12073371494466493 | 12073371494711452 | 12073371494735114 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fd53fc20300 | 0x7fd40fa36cc0 | 131072 | 247610 | 31595992 | 12073371494794375 | 12073371494955771 | 12073371495094970 | 12073371495098680 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fd53fc20a00 | 0x7fd40fa36d00 | 131072 | 247586 | 31576744 | 12073371495147701 | 12073371495316627 | 12073371495694546 | 12073371495720916 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fd53fc20900 | 0x7fd40fa36d40 | 65536 | 173298 | 22132712 | 12073371495759288 | 12073371495917904 | 12073371496186543 | 12073371496209725 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fd53fc20800 | 0x7fd40fa36d80 | 131072 | 275770 | 35221392 | 12073371496251292 | 12073371496409262 | 12073371496547022 | 12073371496549677 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fd53fc20700 | 0x7fd40fa36dc0 | 131072 | 245616 | 31393488 | 12073371496591404 | 12073371496763821 | 12073371497043340 | 12073371497067829 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fd53fc20600 | 0x7fd40fa36e00 | 131072 | 248906 | 31942000 | 12073371497125306 | 12073371497284779 | 12073371497423179 | 12073371497426045 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fd53fc20500 | 0x7fd40fa36e40 | 131072 | 251108 | 32188952 | 12073371497473814 | 12073371497640138 | 12073371498064297 | 12073371498087985 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fd53fc20400 | 0x7fd40fa36e80 | 65536 | 169634 | 21755496 | 12073371498131506 | 12073371498292136 | 12073371498553575 | 12073371498575972 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fd53fc20300 | 0x7fd40fa36ec0 | 131072 | 267002 | 34362592 | 12073371498623440 | 12073371498784934 | 12073371498922534 | 12073371498925211 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fd53fc20a00 | 0x7fd40fa36f00 | 131072 | 250758 | 31963464 | 12073371498972970 | 12073371499149253 | 12073371499464292 | 12073371499490051 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fd53fc20900 | 0x7fd40fa36f40 | 131072 | 266126 | 34111080 | 12073371499543310 | 12073371499705091 | 12073371499857571 | 12073371499860269 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fd53fc20800 | 0x7fd40fa36f80 | 131072 | 251238 | 31917312 | 12073371499908318 | 12073371500069730 | 12073371500586528 | 12073371500609902 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fd53fc20700 | 0x7fd40fa36fc0 | 65536 | 191392 | 24483720 | 12073371500651600 | 12073371500810208 | 12073371501107487 | 12073371501134367 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fd53fc20600 | 0x7fd40fa37000 | 131072 | 244696 | 31404808 | 12073371501174732 | 12073371501334366 | 12073371501490205 | 12073371501492963 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fd53fc20500 | 0x7fd40fa37040 | 131072 | 230170 | 29572824 | 12073371501541704 | 12073371501719805 | 12073371502104923 | 12073371502128725 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fd53fc20400 | 0x7fd40fa37080 | 131072 | 264734 | 33984104 | 12073371502188345 | 12073371502350202 | 12073371502526682 | 12073371502529600 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fd53fc20300 | 0x7fd40fa370c0 | 131072 | 237718 | 30196272 | 12073371502575816 | 12073371502745721 | 12073371503355639 | 12073371503379459 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fd53fc20a00 | 0x7fd40fa37100 | 65536 | 171628 | 21959648 | 12073371503427538 | 12073371503588118 | 12073371503915957 | 12073371503939129 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fd53fc20900 | 0x7fd40fa37140 | 131072 | 239440 | 30451328 | 12073371503989182 | 12073371504157876 | 12073371504336116 | 12073371504339523 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fd53fc20800 | 0x7fd40fa37180 | 131072 | 248790 | 31774872 | 12073371504382343 | 12073371504561235 | 12073371505038513 | 12073371505062937 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fd53fc20700 | 0x7fd40fa371c0 | 131072 | 248070 | 31812776 | 12073371505123841 | 12073371505287153 | 12073371505486832 | 12073371505508976 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fd53fc20600 | 0x7fd40fa37200 | 131072 | 244784 | 31199824 | 12073371505552577 | 12073371505709231 | 12073371506413389 | 12073371506438113 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fd53fc20500 | 0x7fd40fa37240 | 65536 | 172372 | 22161800 | 12073371506482856 | 12073371506645548 | 12073371507018347 | 12073371507042196 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fd53fc20400 | 0x7fd40fa37280 | 131072 | 248594 | 31894040 | 12073371507090525 | 12073371507251306 | 12073371507454825 | 12073371507476904 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fd53fc20300 | 0x7fd40fa372c0 | 131072 | 269618 | 34458448 | 12073371507526987 | 12073371507686665 | 12073371508213063 | 12073371508237447 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fd53fc20a00 | 0x7fd40fa37300 | 131072 | 255524 | 32772800 | 12073371508293301 | 12073371508453382 | 12073371508677541 | 12073371508696610 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fd53fc20900 | 0x7fd40fa37340 | 131072 | 238172 | 30541792 | 12073371508739931 | 12073371508897221 | 12073371509697058 | 12073371509724911 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fd53fc20800 | 0x7fd40fa37380 | 65536 | 173752 | 22108096 | 12073371509765467 | 12073371509927457 | 12073371510371136 | 12073371510398082 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fd53fc20700 | 0x7fd40fa373c0 | 131072 | 274438 | 35252560 | 12073371510437686 | 12073371510596095 | 12073371510823134 | 12073371510846215 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fd53fc20600 | 0x7fd40fa37400 | 131072 | 247860 | 31668784 | 12073371510889876 | 12073371511052893 | 12073371511650011 | 12073371511674474 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fd53fc20500 | 0x7fd40fa37440 | 131072 | 245374 | 31579408 | 12073371511730969 | 12073371511893531 | 12073371512163610 | 12073371512191265 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fd53fc20400 | 0x7fd40fa37480 | 131072 | 257436 | 32812704 | 12073371512235547 | 12073371512400249 | 12073371513386806 | 12073371513431520 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fd53fc20300 | 0x7fd40fa374c0 | 65536 | 204950 | 26176280 | 12073371513462347 | 12073371513644565 | 12073371514160723 | 12073371514228521 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fd53fc20a00 | 0x7fd40fa37500 | 131072 | 240438 | 31009224 | 12073371514261051 | 12073371514427442 | 12073371514700081 | 12073371514767542 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fd53fc20900 | 0x7fd40fa37540 | 131072 | 257802 | 32954400 | 12073371514797588 | 12073371514975920 | 12073371515714158 | 12073371515783030 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fd53fc20800 | 0x7fd40fa37580 | 131072 | 241404 | 31099552 | 12073371515820018 | 12073371515981197 | 12073371516299116 | 12073371516366474 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fd53fc20700 | 0x7fd40fa375c0 | 131072 | 247626 | 31685512 | 12073371516389056 | 12073371516575595 | 12073371517747111 | 12073371517814735 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fd53fc20600 | 0x7fd40fa37600 | 65536 | 169610 | 21605896 | 12073371517846564 | 12073371518026310 | 12073371518637028 | 12073371518705110 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fd53fc20500 | 0x7fd40fa37640 | 131072 | 258318 | 33249352 | 12073371518737079 | 12073371518910627 | 12073371519231266 | 12073371519300927 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fd53fc20400 | 0x7fd40fa37680 | 131072 | 272314 | 34845320 | 12073371519328158 | 12073371519508225 | 12073371520387102 | 12073371520454621 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fd53fc20300 | 0x7fd40fa376c0 | 131072 | 269660 | 34556320 | 12073371520499865 | 12073371520661661 | 12073371521096060 | 12073371521163839 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fd53fc20a00 | 0x7fd40fa37700 | 131072 | 281912 | 36095016 | 12073371521194015 | 12073371521370939 | 12073371522919254 | 12073371522987238 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fd53fc20900 | 0x7fd40fa37740 | 65536 | 173644 | 22407960 | 12073371523016763 | 12073371523204053 | 12073371524000850 | 12073371524070080 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fd53fc20800 | 0x7fd40fa37780 | 131072 | 258342 | 32986248 | 12073371524100767 | 12073371524273329 | 12073371524688528 | 12073371524755504 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fd53fc20700 | 0x7fd40fa377c0 | 131072 | 272880 | 34845136 | 12073371524773167 | 12073371524956367 | 12073371526115403 | 12073371526184009 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fd53fc20600 | 0x7fd40fa37800 | 131072 | 288878 | 36843488 | 12073371526220286 | 12073371526385802 | 12073371527171080 | 12073371527238909 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fd53fc20500 | 0x7fd40fa37840 | 131072 | 262784 | 33895640 | 12073371527269386 | 12073371527446759 | 12073371530494909 | 12073371530562375 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fd53fc20400 | 0x7fd40fa37880 | 65536 | 185540 | 23644256 | 12073371530592692 | 12073371530769148 | 12073371532312023 | 12073371532379913 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fd53fc20300 | 0x7fd40fa378c0 | 131072 | 294662 | 37351416 | 12073371532410750 | 12073371532590422 | 12073371533380019 | 12073371533447547 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fd53fc20a00 | 0x7fd40fa37900 | 131072 | 244094 | 31157512 | 12073371533477603 | 12073371533657618 | 12073371535939051 | 12073371536017583 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fd53fc20900 | 0x7fd40fa37940 | 131072 | 246688 | 31834264 | 12073371536061174 | 12073371536226890 | 12073371537762405 | 12073371537831244 |
| 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 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fd53fc20800 | 0x7fd40fa37980 | 131072 | 246124 | 31693024 | 12073371537860919 | 12073371538044164 | 12073371544097743 | 12073371544167619 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fd53fc20700 | 0x7fd40fa379c0 | 65536 | 171790 | 22003808 | 12073371544198456 | 12073371544373103 | 12073371547413092 | 12073371547481367 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fd53fc20600 | 0x7fd40fa37a00 | 131072 | 279656 | 35458264 | 12073371547510692 | 12073371547690212 | 12073371549230366 | 12073371549298795 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 759929 | 759934 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fd53fc20500 | 0x7fd40fa37a40 | 131072 | 250340 | 32173976 | 12073371549329191 | 12073371549507325 | 12073371554034670 | 12073371554102552 |