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 | 810647 | 810652 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7ff1ef204180 | 12074163422799658 | 12074163422846673 | 12074163423172110 | 12074163423264713 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 810647 | 810652 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7ff1ef235100 | 12074163437610889 | 12074163437710941 | 12074163437717501 | 12074163437723238 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7ff31f3f0900 | 0x7ff1ef235140 | 12074163437764394 | 12074163437778781 | 12074163437909500 | 12074163437912670 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7ff31f3f0800 | 0x7ff1ef235180 | 12074163437952023 | 12074163437965499 | 12074163438212697 | 12074163438294359 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7ff31f3f0700 | 0x7ff1ef2351c0 | 12074163438316310 | 12074163438329176 | 12074163438575734 | 12074163438654619 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7ff31f3f0600 | 0x7ff1ef235200 | 12074163438675698 | 12074163438687573 | 12074163438813492 | 12074163438816640 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7ff31f3f0500 | 0x7ff1ef235240 | 12074163438843189 | 12074163438855251 | 12074163438980530 | 12074163438983570 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7ff31f3f0400 | 0x7ff1ef235280 | 12074163439043892 | 12074163439056850 | 12074163439181329 | 12074163439184153 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7ff31f3f0300 | 0x7ff1ef2352c0 | 12074163439206534 | 12074163439217968 | 12074163439461006 | 12074163439539453 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7ff31f3f0a00 | 0x7ff1ef235300 | 12074163439560031 | 12074163439573165 | 12074163439816843 | 12074163439893941 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7ff31f3f0900 | 0x7ff1ef235340 | 12074163439914950 | 12074163439926602 | 12074163440051561 | 12074163440054961 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7ff31f3f0800 | 0x7ff1ef235380 | 12074163440082722 | 12074163440094761 | 12074163440220519 | 12074163440223504 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7ff31f3f0700 | 0x7ff1ef2353c0 | 12074163440261785 | 12074163440273639 | 12074163440398758 | 12074163440401805 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7ff31f3f0600 | 0x7ff1ef235400 | 12074163440429727 | 12074163440441797 | 12074163440689635 | 12074163440743300 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7ff31f3f0500 | 0x7ff1ef235440 | 12074163440764228 | 12074163440775075 | 12074163441020512 | 12074163441070207 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7ff31f3f0400 | 0x7ff1ef235480 | 12074163441092268 | 12074163441104352 | 12074163441229791 | 12074163441232709 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7ff31f3f0300 | 0x7ff1ef2354c0 | 12074163441258938 | 12074163441270910 | 12074163441395549 | 12074163441398517 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7ff31f3f0a00 | 0x7ff1ef235500 | 12074163441435997 | 12074163441447869 | 12074163441572828 | 12074163441575907 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7ff31f3f0900 | 0x7ff1ef235540 | 12074163441602606 | 12074163441614907 | 12074163441861625 | 12074163441909717 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7ff31f3f0800 | 0x7ff1ef235580 | 12074163441931367 | 12074163441943704 | 12074163442189462 | 12074163442239940 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7ff31f3f0700 | 0x7ff1ef2355c0 | 12074163442261390 | 12074163442273941 | 12074163442398260 | 12074163442401080 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7ff31f3f0600 | 0x7ff1ef235600 | 12074163442427549 | 12074163442439220 | 12074163442564499 | 12074163442567619 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7ff31f3f0500 | 0x7ff1ef235640 | 12074163442603746 | 12074163442617778 | 12074163442741617 | 12074163442744919 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7ff31f3f0400 | 0x7ff1ef235680 | 12074163442771047 | 12074163442784497 | 12074163443032015 | 12074163443068500 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7ff31f3f0300 | 0x7ff1ef2356c0 | 12074163443089189 | 12074163443100814 | 12074163443383372 | 12074163443460739 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7ff31f3f0a00 | 0x7ff1ef235700 | 12074163443481187 | 12074163443493931 | 12074163443618250 | 12074163443621538 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7ff31f3f0900 | 0x7ff1ef235740 | 12074163443647756 | 12074163443659529 | 12074163443784648 | 12074163443787696 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7ff31f3f0800 | 0x7ff1ef235780 | 12074163443822762 | 12074163443837768 | 12074163443962087 | 12074163443965146 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7ff31f3f0700 | 0x7ff1ef2357c0 | 12074163443991966 | 12074163444005926 | 12074163444260964 | 12074163444339462 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7ff31f3f0600 | 0x7ff1ef235800 | 12074163444359649 | 12074163444374083 | 12074163444622081 | 12074163444699801 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7ff31f3f0500 | 0x7ff1ef235840 | 12074163444722964 | 12074163444734720 | 12074163444859359 | 12074163444862493 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7ff31f3f0400 | 0x7ff1ef235880 | 12074163444888832 | 12074163444900478 | 12074163445025597 | 12074163445028883 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7ff31f3f0300 | 0x7ff1ef2358c0 | 12074163445066011 | 12074163445077917 | 12074163445203036 | 12074163445205761 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7ff31f3f0a00 | 0x7ff1ef235900 | 12074163445228193 | 12074163445239995 | 12074163445486553 | 12074163445540173 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7ff31f3f0900 | 0x7ff1ef235940 | 12074163445561021 | 12074163445580632 | 12074163445825910 | 12074163445903217 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7ff31f3f0800 | 0x7ff1ef235980 | 12074163445923455 | 12074163445934229 | 12074163446059828 | 12074163446063114 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7ff31f3f0700 | 0x7ff1ef2359c0 | 12074163446084514 | 12074163446096148 | 12074163446221427 | 12074163446224494 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7ff31f3f0600 | 0x7ff1ef235a00 | 12074163446260611 | 12074163446273106 | 12074163446397745 | 12074163446400521 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7ff31f3f0500 | 0x7ff1ef235a40 | 12074163446423283 | 12074163446434705 | 12074163446680463 | 12074163446703775 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7ff31f3f0400 | 0x7ff1ef235a80 | 12074163446724964 | 12074163446738702 | 12074163446981580 | 12074163447013861 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7ff31f3f0300 | 0x7ff1ef235ac0 | 12074163447035651 | 12074163447049259 | 12074163447174378 | 12074163447177194 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7ff31f3f0a00 | 0x7ff1ef235b00 | 12074163447200097 | 12074163447213258 | 12074163447339497 | 12074163447342301 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7ff31f3f0900 | 0x7ff1ef235b40 | 12074163447378619 | 12074163447389896 | 12074163447514855 | 12074163447517577 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7ff31f3f0800 | 0x7ff1ef235b80 | 12074163447544236 | 12074163447556615 | 12074163447810053 | 12074163447831991 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7ff31f3f0700 | 0x7ff1ef235bc0 | 12074163447854012 | 12074163447865732 | 12074163448109890 | 12074163448136387 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7ff31f3f0600 | 0x7ff1ef235c00 | 12074163448155672 | 12074163448169090 | 12074163448293728 | 12074163448296715 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7ff31f3f0500 | 0x7ff1ef235c40 | 12074163448323464 | 12074163448335328 | 12074163448461407 | 12074163448464196 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7ff31f3f0400 | 0x7ff1ef235c80 | 12074163448501906 | 12074163448513886 | 12074163448639645 | 12074163448642497 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7ff31f3f0300 | 0x7ff1ef235cc0 | 12074163448668976 | 12074163448681885 | 12074163448937403 | 12074163448962932 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7ff31f3f0a00 | 0x7ff1ef235d00 | 12074163448983000 | 12074163448995642 | 12074163449242840 | 12074163449270173 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7ff31f3f0900 | 0x7ff1ef235d40 | 12074163449290661 | 12074163449304440 | 12074163449430038 | 12074163449432856 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7ff31f3f0800 | 0x7ff1ef235d80 | 12074163449459425 | 12074163449472118 | 12074163449600277 | 12074163449603112 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7ff31f3f0700 | 0x7ff1ef235dc0 | 12074163449638728 | 12074163449652436 | 12074163449777555 | 12074163449780632 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7ff31f3f0600 | 0x7ff1ef235e00 | 12074163449802132 | 12074163449814835 | 12074163450078353 | 12074163450108902 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7ff31f3f0500 | 0x7ff1ef235e40 | 12074163450129380 | 12074163450143312 | 12074163450389070 | 12074163450419519 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7ff31f3f0400 | 0x7ff1ef235e80 | 12074163450443263 | 12074163450456429 | 12074163450581548 | 12074163450584395 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7ff31f3f0300 | 0x7ff1ef235ec0 | 12074163450610323 | 12074163450622188 | 12074163450752587 | 12074163450755383 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7ff31f3f0a00 | 0x7ff1ef235f00 | 12074163450791450 | 12074163450803306 | 12074163450928425 | 12074163450931240 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7ff31f3f0900 | 0x7ff1ef235f40 | 12074163450958160 | 12074163450969865 | 12074163451226503 | 12074163451256805 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7ff31f3f0800 | 0x7ff1ef235f80 | 12074163451277263 | 12074163451290342 | 12074163451534500 | 12074163451559427 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7ff31f3f0700 | 0x7ff1ef235fc0 | 12074163451579815 | 12074163451592899 | 12074163451718018 | 12074163451720957 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7ff31f3f0600 | 0x7ff1ef236000 | 12074163451748689 | 12074163451761058 | 12074163451898337 | 12074163451901372 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7ff31f3f0500 | 0x7ff1ef236040 | 12074163451939664 | 12074163451952256 | 12074163452076735 | 12074163452079644 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7ff31f3f0400 | 0x7ff1ef236080 | 12074163452102155 | 12074163452114975 | 12074163452368093 | 12074163452396863 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7ff31f3f0300 | 0x7ff1ef2360c0 | 12074163452417341 | 12074163452430812 | 12074163452677530 | 12074163452705787 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7ff31f3f0a00 | 0x7ff1ef236100 | 12074163452725674 | 12074163452738329 | 12074163452863288 | 12074163452866195 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7ff31f3f0900 | 0x7ff1ef236140 | 12074163452893416 | 12074163452905528 | 12074163453048407 | 12074163453051429 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7ff31f3f0800 | 0x7ff1ef236180 | 12074163453088799 | 12074163453100566 | 12074163453225525 | 12074163453228508 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7ff31f3f0700 | 0x7ff1ef2361c0 | 12074163453250229 | 12074163453261845 | 12074163453516083 | 12074163453541199 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7ff31f3f0600 | 0x7ff1ef236200 | 12074163453562018 | 12074163453575442 | 12074163453823600 | 12074163453847749 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7ff31f3f0500 | 0x7ff1ef236240 | 12074163453870521 | 12074163453883919 | 12074163454009678 | 12074163454012756 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7ff31f3f0400 | 0x7ff1ef236280 | 12074163454039495 | 12074163454050958 | 12074163454201516 | 12074163454204632 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7ff31f3f0300 | 0x7ff1ef2362c0 | 12074163454259865 | 12074163454271596 | 12074163454396715 | 12074163454399865 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7ff31f3f0a00 | 0x7ff1ef236300 | 12074163454426835 | 12074163454438634 | 12074163454696872 | 12074163454718367 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7ff31f3f0900 | 0x7ff1ef236340 | 12074163454740438 | 12074163454752872 | 12074163455000389 | 12074163455027100 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7ff31f3f0800 | 0x7ff1ef236380 | 12074163455046446 | 12074163455057989 | 12074163455183908 | 12074163455186797 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7ff31f3f0700 | 0x7ff1ef2363c0 | 12074163455213807 | 12074163455225987 | 12074163455384226 | 12074163455387249 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7ff31f3f0600 | 0x7ff1ef236400 | 12074163455424248 | 12074163455435266 | 12074163455560065 | 12074163455563076 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7ff31f3f0500 | 0x7ff1ef236440 | 12074163455589315 | 12074163455601984 | 12074163455856702 | 12074163455885335 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7ff31f3f0400 | 0x7ff1ef236480 | 12074163455904701 | 12074163455916061 | 12074163456159739 | 12074163456192396 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7ff31f3f0300 | 0x7ff1ef2364c0 | 12074163456213385 | 12074163456229339 | 12074163456355578 | 12074163456358484 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7ff31f3f0a00 | 0x7ff1ef236500 | 12074163456380375 | 12074163456392377 | 12074163456557496 | 12074163456560479 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7ff31f3f0900 | 0x7ff1ef236540 | 12074163456596697 | 12074163456608215 | 12074163456733334 | 12074163456736396 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7ff31f3f0800 | 0x7ff1ef236580 | 12074163456763457 | 12074163456774774 | 12074163457032692 | 12074163457062382 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7ff31f3f0700 | 0x7ff1ef2365c0 | 12074163457081988 | 12074163457094931 | 12074163457344369 | 12074163457372398 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7ff31f3f0600 | 0x7ff1ef236600 | 12074163457395190 | 12074163457408368 | 12074163457533807 | 12074163457536784 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7ff31f3f0500 | 0x7ff1ef236640 | 12074163457564415 | 12074163457576207 | 12074163457748525 | 12074163457751472 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7ff31f3f0400 | 0x7ff1ef236680 | 12074163457788431 | 12074163457799885 | 12074163457925324 | 12074163457928191 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7ff31f3f0300 | 0x7ff1ef2366c0 | 12074163457951003 | 12074163457962283 | 12074163458214921 | 12074163458244799 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7ff31f3f0a00 | 0x7ff1ef236700 | 12074163458264085 | 12074163458275561 | 12074163458522918 | 12074163458546910 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7ff31f3f0900 | 0x7ff1ef236740 | 12074163458567248 | 12074163458580198 | 12074163458705957 | 12074163458708911 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7ff31f3f0800 | 0x7ff1ef236780 | 12074163458735020 | 12074163458746757 | 12074163458928515 | 12074163458931425 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7ff31f3f0700 | 0x7ff1ef2367c0 | 12074163458968764 | 12074163458980674 | 12074163459106913 | 12074163459110087 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7ff31f3f0600 | 0x7ff1ef236800 | 12074163459130865 | 12074163459141793 | 12074163459405631 | 12074163459426876 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7ff31f3f0500 | 0x7ff1ef236840 | 12074163459449327 | 12074163459462430 | 12074163459707708 | 12074163459732313 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7ff31f3f0400 | 0x7ff1ef236880 | 12074163459752310 | 12074163459765468 | 12074163459891546 | 12074163459894665 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7ff31f3f0300 | 0x7ff1ef2368c0 | 12074163459920493 | 12074163459933306 | 12074163460124344 | 12074163460127507 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7ff31f3f0a00 | 0x7ff1ef236900 | 12074163460164496 | 12074163460177464 | 12074163460304503 | 12074163460307522 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7ff31f3f0900 | 0x7ff1ef236940 | 12074163460330354 | 12074163460342103 | 12074163460624660 | 12074163460653465 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7ff31f3f0800 | 0x7ff1ef236980 | 12074163460674784 | 12074163460687859 | 12074163460941617 | 12074163460969702 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7ff31f3f0700 | 0x7ff1ef2369c0 | 12074163460991543 | 12074163461004817 | 12074163461130576 | 12074163461133887 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7ff31f3f0600 | 0x7ff1ef236a00 | 12074163461161208 | 12074163461172975 | 12074163461382093 | 12074163461411924 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7ff31f3f0500 | 0x7ff1ef236a40 | 12074163461442200 | 12074163461454413 | 12074163461581612 | 12074163461584765 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7ff31f3f0400 | 0x7ff1ef236a80 | 12074163461607006 | 12074163461618411 | 12074163461924649 | 12074163461952128 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7ff31f3f0300 | 0x7ff1ef236ac0 | 12074163461972916 | 12074163461986248 | 12074163462234566 | 12074163462270760 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7ff31f3f0a00 | 0x7ff1ef236b00 | 12074163462290557 | 12074163462303205 | 12074163462431364 | 12074163462434775 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7ff31f3f0900 | 0x7ff1ef236b40 | 12074163462465001 | 12074163462480484 | 12074163462707202 | 12074163462736205 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7ff31f3f0800 | 0x7ff1ef236b80 | 12074163462768475 | 12074163462781441 | 12074163462908800 | 12074163462912162 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7ff31f3f0700 | 0x7ff1ef236bc0 | 12074163462932900 | 12074163462944640 | 12074163463271997 | 12074163463298299 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7ff31f3f0600 | 0x7ff1ef236c00 | 12074163463319338 | 12074163463332316 | 12074163463585274 | 12074163463609758 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7ff31f3f0500 | 0x7ff1ef236c40 | 12074163463630536 | 12074163463643513 | 12074163463770552 | 12074163463773552 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7ff31f3f0400 | 0x7ff1ef236c80 | 12074163463799400 | 12074163463811192 | 12074163464054550 | 12074163464079851 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7ff31f3f0300 | 0x7ff1ef236cc0 | 12074163464110859 | 12074163464123509 | 12074163464253428 | 12074163464256409 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7ff31f3f0a00 | 0x7ff1ef236d00 | 12074163464285093 | 12074163464296788 | 12074163464672784 | 12074163464697088 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7ff31f3f0900 | 0x7ff1ef236d40 | 12074163464718257 | 12074163464730064 | 12074163464986862 | 12074163465018515 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7ff31f3f0800 | 0x7ff1ef236d80 | 12074163465041648 | 12074163465054541 | 12074163465183660 | 12074163465186748 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7ff31f3f0700 | 0x7ff1ef236dc0 | 12074163465214510 | 12074163465227020 | 12074163465505417 | 12074163465529715 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7ff31f3f0600 | 0x7ff1ef236e00 | 12074163465560352 | 12074163465573097 | 12074163465707975 | 12074163465710982 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7ff31f3f0500 | 0x7ff1ef236e40 | 12074163465733604 | 12074163465746055 | 12074163466168611 | 12074163466200071 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7ff31f3f0400 | 0x7ff1ef236e80 | 12074163466220118 | 12074163466232611 | 12074163466494048 | 12074163466522189 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7ff31f3f0300 | 0x7ff1ef236ec0 | 12074163466542697 | 12074163466556448 | 12074163466692287 | 12074163466695401 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7ff31f3f0a00 | 0x7ff1ef236f00 | 12074163466722992 | 12074163466734686 | 12074163467077883 | 12074163467107286 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7ff31f3f0900 | 0x7ff1ef236f40 | 12074163467140158 | 12074163467153083 | 12074163467305241 | 12074163467308741 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7ff31f3f0800 | 0x7ff1ef236f80 | 12074163467335090 | 12074163467348121 | 12074163467864116 | 12074163467892265 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7ff31f3f0700 | 0x7ff1ef236fc0 | 12074163467912172 | 12074163467925076 | 12074163468224753 | 12074163468259287 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7ff31f3f0600 | 0x7ff1ef237000 | 12074163468280667 | 12074163468293713 | 12074163468449391 | 12074163468452406 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7ff31f3f0500 | 0x7ff1ef237040 | 12074163468474737 | 12074163468486031 | 12074163468871308 | 12074163468899897 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7ff31f3f0400 | 0x7ff1ef237080 | 12074163468931286 | 12074163468942987 | 12074163469118665 | 12074163469122281 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7ff31f3f0300 | 0x7ff1ef2370c0 | 12074163469143750 | 12074163469157225 | 12074163469778980 | 12074163469807233 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7ff31f3f0a00 | 0x7ff1ef237100 | 12074163469828924 | 12074163469841699 | 12074163470169216 | 12074163470199091 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7ff31f3f0900 | 0x7ff1ef237140 | 12074163470221673 | 12074163470235296 | 12074163470413534 | 12074163470416586 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7ff31f3f0800 | 0x7ff1ef237180 | 12074163470444588 | 12074163470455774 | 12074163470932569 | 12074163470960757 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7ff31f3f0700 | 0x7ff1ef2371c0 | 12074163470992546 | 12074163471006009 | 12074163471206167 | 12074163471239304 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7ff31f3f0600 | 0x7ff1ef237200 | 12074163471259682 | 12074163471273046 | 12074163471975440 | 12074163472007161 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7ff31f3f0500 | 0x7ff1ef237240 | 12074163472028290 | 12074163472040720 | 12074163472412076 | 12074163472441658 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7ff31f3f0400 | 0x7ff1ef237280 | 12074163472461726 | 12074163472474956 | 12074163472676234 | 12074163472704697 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7ff31f3f0300 | 0x7ff1ef2372c0 | 12074163472724855 | 12074163472737834 | 12074163473263109 | 12074163473291988 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7ff31f3f0a00 | 0x7ff1ef237300 | 12074163473325220 | 12074163473338468 | 12074163473560866 | 12074163473589090 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7ff31f3f0900 | 0x7ff1ef237340 | 12074163473609639 | 12074163473622626 | 12074163474420859 | 12074163474450501 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7ff31f3f0800 | 0x7ff1ef237380 | 12074163474471660 | 12074163474483098 | 12074163474902774 | 12074163474927006 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7ff31f3f0700 | 0x7ff1ef2373c0 | 12074163474950109 | 12074163474962934 | 12074163475187732 | 12074163475219019 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7ff31f3f0600 | 0x7ff1ef237400 | 12074163475241551 | 12074163475257171 | 12074163475853646 | 12074163475879045 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7ff31f3f0500 | 0x7ff1ef237440 | 12074163475913890 | 12074163475927085 | 12074163476195243 | 12074163476220530 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7ff31f3f0400 | 0x7ff1ef237480 | 12074163476244855 | 12074163476257803 | 12074163477242274 | 12074163477271563 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7ff31f3f0300 | 0x7ff1ef2374c0 | 12074163477291049 | 12074163477304193 | 12074163477817789 | 12074163477845780 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7ff31f3f0a00 | 0x7ff1ef237500 | 12074163477869694 | 12074163477882908 | 12074163478154266 | 12074163478186112 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7ff31f3f0900 | 0x7ff1ef237540 | 12074163478208283 | 12074163478221145 | 12074163478958099 | 12074163478986209 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7ff31f3f0800 | 0x7ff1ef237580 | 12074163479028137 | 12074163479042258 | 12074163479357455 | 12074163479385911 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7ff31f3f0700 | 0x7ff1ef2375c0 | 12074163479412000 | 12074163479424815 | 12074163480595684 | 12074163480625515 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7ff31f3f0600 | 0x7ff1ef237600 | 12074163480647486 | 12074163480660324 | 12074163481272318 | 12074163481302593 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7ff31f3f0500 | 0x7ff1ef237640 | 12074163481324964 | 12074163481337758 | 12074163481655995 | 12074163481684713 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7ff31f3f0400 | 0x7ff1ef237680 | 12074163481706764 | 12074163481718395 | 12074163482595347 | 12074163482626192 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7ff31f3f0300 | 0x7ff1ef2376c0 | 12074163482659725 | 12074163482672946 | 12074163483105262 | 12074163483136030 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7ff31f3f0a00 | 0x7ff1ef237700 | 12074163483156528 | 12074163483169422 | 12074163484717728 | 12074163484771919 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7ff31f3f0900 | 0x7ff1ef237740 | 12074163484793950 | 12074163484806687 | 12074163485600120 | 12074163485658036 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7ff31f3f0800 | 0x7ff1ef237780 | 12074163485679556 | 12074163485692295 | 12074163486105092 | 12074163486162293 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7ff31f3f0700 | 0x7ff1ef2377c0 | 12074163486182610 | 12074163486195810 | 12074163487353081 | 12074163487406975 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7ff31f3f0600 | 0x7ff1ef237800 | 12074163487438564 | 12074163487451320 | 12074163488236114 | 12074163488289265 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7ff31f3f0500 | 0x7ff1ef237840 | 12074163488310905 | 12074163488323633 | 12074163491373689 | 12074163491427376 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7ff31f3f0400 | 0x7ff1ef237880 | 12074163491448645 | 12074163491459929 | 12074163492999757 | 12074163493054138 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7ff31f3f0300 | 0x7ff1ef2378c0 | 12074163493077532 | 12074163493091116 | 12074163493879910 | 12074163493931198 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7ff31f3f0a00 | 0x7ff1ef237900 | 12074163493953850 | 12074163493967109 | 12074163496248211 | 12074163496305109 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7ff31f3f0900 | 0x7ff1ef237940 | 12074163496335375 | 12074163496349170 | 12074163497884038 | 12074163497937031 |
| 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 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7ff31f3f0800 | 0x7ff1ef237980 | 12074163497958561 | 12074163497971557 | 12074163504027830 | 12074163504084945 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7ff31f3f0700 | 0x7ff1ef2379c0 | 12074163504106395 | 12074163504119189 | 12074163507161725 | 12074163507215572 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7ff31f3f0600 | 0x7ff1ef237a00 | 12074163507236952 | 12074163507250844 | 12074163508789392 | 12074163508841794 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 810647 | 810652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7ff31f3f0500 | 0x7ff1ef237a40 | 12074163508864987 | 12074163508876911 | 12074163513402796 | 12074163513460135 |