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 | 820647 | 820652 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f2e0de04180 | 12074318637769159 | 12074318637816165 | 12074318638140962 | 12074318638250614 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 820647 | 820652 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f2e0de35100 | 12074318652600197 | 12074318652705076 | 12074318652712756 | 12074318652718486 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f2f19a4a900 | 0x7f2e0de35140 | 12074318652763109 | 12074318652775956 | 12074318652910994 | 12074318652914310 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f2f19a4a800 | 0x7f2e0de35180 | 12074318652957541 | 12074318652971314 | 12074318653214512 | 12074318653313963 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f2f19a4a700 | 0x7f2e0de351c0 | 12074318653340502 | 12074318653352591 | 12074318653595948 | 12074318653691815 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f2f19a4a600 | 0x7f2e0de35200 | 12074318653719426 | 12074318653730827 | 12074318653856586 | 12074318653859877 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f2f19a4a500 | 0x7f2e0de35240 | 12074318653887849 | 12074318653899946 | 12074318654024905 | 12074318654028140 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f2f19a4a400 | 0x7f2e0de35280 | 12074318654084104 | 12074318654097704 | 12074318654221703 | 12074318654224715 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f2f19a4a300 | 0x7f2e0de352c0 | 12074318654254510 | 12074318654266663 | 12074318654511461 | 12074318654608198 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f2f19a4aa00 | 0x7f2e0de35300 | 12074318654629627 | 12074318654640899 | 12074318654884737 | 12074318654980790 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f2f19a4a900 | 0x7f2e0de35340 | 12074318655008411 | 12074318655020576 | 12074318655145055 | 12074318655148592 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f2f19a4a800 | 0x7f2e0de35380 | 12074318655176914 | 12074318655188735 | 12074318655313534 | 12074318655317095 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f2f19a4a700 | 0x7f2e0de353c0 | 12074318655355777 | 12074318655367933 | 12074318655492892 | 12074318655496027 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f2f19a4a600 | 0x7f2e0de35400 | 12074318655522627 | 12074318655534172 | 12074318655781050 | 12074318655853982 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f2f19a4a500 | 0x7f2e0de35440 | 12074318655876494 | 12074318655887609 | 12074318656132407 | 12074318656202500 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f2f19a4a400 | 0x7f2e0de35480 | 12074318656226054 | 12074318656237846 | 12074318656363285 | 12074318656366395 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f2f19a4a300 | 0x7f2e0de354c0 | 12074318656393555 | 12074318656405044 | 12074318656530643 | 12074318656533585 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f2f19a4aa00 | 0x7f2e0de35500 | 12074318656572768 | 12074318656583603 | 12074318656707762 | 12074318656711045 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f2f19a4a900 | 0x7f2e0de35540 | 12074318656737534 | 12074318656749681 | 12074318656994479 | 12074318657038283 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f2f19a4a800 | 0x7f2e0de35580 | 12074318657060815 | 12074318657074159 | 12074318657317836 | 12074318657383404 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f2f19a4a700 | 0x7f2e0de355c0 | 12074318657406086 | 12074318657419276 | 12074318657544074 | 12074318657547139 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f2f19a4a600 | 0x7f2e0de35600 | 12074318657573618 | 12074318657585994 | 12074318657711433 | 12074318657714389 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f2f19a4a500 | 0x7f2e0de35640 | 12074318657751709 | 12074318657764233 | 12074318657888712 | 12074318657891889 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f2f19a4a400 | 0x7f2e0de35680 | 12074318657919000 | 12074318657932391 | 12074318658181349 | 12074318658280852 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f2f19a4a300 | 0x7f2e0de356c0 | 12074318658302963 | 12074318658314148 | 12074318658557506 | 12074318658653745 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f2f19a4aa00 | 0x7f2e0de35700 | 12074318658675515 | 12074318658687265 | 12074318658811424 | 12074318658814654 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f2f19a4a900 | 0x7f2e0de35740 | 12074318658841554 | 12074318658852543 | 12074318658977342 | 12074318658980782 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f2f19a4a800 | 0x7f2e0de35780 | 12074318659026978 | 12074318659040062 | 12074318659164541 | 12074318659167780 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f2f19a4a700 | 0x7f2e0de357c0 | 12074318659198627 | 12074318659213020 | 12074318659463578 | 12074318659541274 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f2f19a4a600 | 0x7f2e0de35800 | 12074318659563906 | 12074318659575737 | 12074318659818775 | 12074318659895452 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f2f19a4a500 | 0x7f2e0de35840 | 12074318659916691 | 12074318659927414 | 12074318660052213 | 12074318660055820 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f2f19a4a400 | 0x7f2e0de35880 | 12074318660083321 | 12074318660097173 | 12074318660222611 | 12074318660225886 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f2f19a4a300 | 0x7f2e0de358c0 | 12074318660263285 | 12074318660276531 | 12074318660401010 | 12074318660404448 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f2f19a4aa00 | 0x7f2e0de35900 | 12074318660431227 | 12074318660444370 | 12074318660696367 | 12074318660774876 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f2f19a4a900 | 0x7f2e0de35940 | 12074318660794643 | 12074318660812526 | 12074318661057004 | 12074318661118334 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f2f19a4a800 | 0x7f2e0de35980 | 12074318661140215 | 12074318661151563 | 12074318661276362 | 12074318661279804 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f2f19a4a700 | 0x7f2e0de359c0 | 12074318661307856 | 12074318661319562 | 12074318661445481 | 12074318661448708 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f2f19a4a600 | 0x7f2e0de35a00 | 12074318661485506 | 12074318661498600 | 12074318661622599 | 12074318661625647 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f2f19a4a500 | 0x7f2e0de35a40 | 12074318661652316 | 12074318661663719 | 12074318661915717 | 12074318661942065 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f2f19a4a400 | 0x7f2e0de35a80 | 12074318661966981 | 12074318661978276 | 12074318662221314 | 12074318662249476 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f2f19a4a300 | 0x7f2e0de35ac0 | 12074318662272389 | 12074318662283714 | 12074318662409633 | 12074318662412629 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f2f19a4aa00 | 0x7f2e0de35b00 | 12074318662441102 | 12074318662452672 | 12074318662578911 | 12074318662581793 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f2f19a4a900 | 0x7f2e0de35b40 | 12074318662619103 | 12074318662630751 | 12074318662756350 | 12074318662759423 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f2f19a4a800 | 0x7f2e0de35b80 | 12074318662787536 | 12074318662799229 | 12074318663061627 | 12074318663086952 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f2f19a4a700 | 0x7f2e0de35bc0 | 12074318663111768 | 12074318663123706 | 12074318663367864 | 12074318663396026 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f2f19a4a600 | 0x7f2e0de35c00 | 12074318663416915 | 12074318663428344 | 12074318663552663 | 12074318663555663 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f2f19a4a500 | 0x7f2e0de35c40 | 12074318663582763 | 12074318663594262 | 12074318663721141 | 12074318663724026 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f2f19a4a400 | 0x7f2e0de35c80 | 12074318663761205 | 12074318663773461 | 12074318663898900 | 12074318663901806 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f2f19a4a300 | 0x7f2e0de35cc0 | 12074318663929417 | 12074318663940819 | 12074318664203857 | 12074318664236338 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f2f19a4aa00 | 0x7f2e0de35d00 | 12074318664259421 | 12074318664270417 | 12074318664515535 | 12074318664538389 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f2f19a4a900 | 0x7f2e0de35d40 | 12074318664560300 | 12074318664573294 | 12074318664698733 | 12074318664701662 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f2f19a4a800 | 0x7f2e0de35d80 | 12074318664729865 | 12074318664740973 | 12074318664870091 | 12074318664873141 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f2f19a4a700 | 0x7f2e0de35dc0 | 12074318664910781 | 12074318664922251 | 12074318665047210 | 12074318665050370 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f2f19a4a600 | 0x7f2e0de35e00 | 12074318665078402 | 12074318665090250 | 12074318665344807 | 12074318665368171 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f2f19a4a500 | 0x7f2e0de35e40 | 12074318665390212 | 12074318665402087 | 12074318665648485 | 12074318665671164 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f2f19a4a400 | 0x7f2e0de35e80 | 12074318665692273 | 12074318665704804 | 12074318665830403 | 12074318665833526 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f2f19a4a300 | 0x7f2e0de35ec0 | 12074318665860496 | 12074318665872163 | 12074318666001122 | 12074318666005736 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f2f19a4aa00 | 0x7f2e0de35f00 | 12074318666042524 | 12074318666054561 | 12074318666179680 | 12074318666182594 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f2f19a4a900 | 0x7f2e0de35f40 | 12074318666210516 | 12074318666226240 | 12074318666486878 | 12074318666514982 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f2f19a4a800 | 0x7f2e0de35f80 | 12074318666539668 | 12074318666552957 | 12074318666796955 | 12074318666823856 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f2f19a4a700 | 0x7f2e0de35fc0 | 12074318666845566 | 12074318666858714 | 12074318666983833 | 12074318666987039 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f2f19a4a600 | 0x7f2e0de36000 | 12074318667020952 | 12074318667032633 | 12074318667168632 | 12074318667171912 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f2f19a4a500 | 0x7f2e0de36040 | 12074318667209592 | 12074318667221431 | 12074318667345750 | 12074318667348681 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f2f19a4a400 | 0x7f2e0de36080 | 12074318667375891 | 12074318667387830 | 12074318667641588 | 12074318667661412 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f2f19a4a300 | 0x7f2e0de360c0 | 12074318667683503 | 12074318667695027 | 12074318667942225 | 12074318667966068 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f2f19a4aa00 | 0x7f2e0de36100 | 12074318667987378 | 12074318668000465 | 12074318668124943 | 12074318668128480 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f2f19a4a900 | 0x7f2e0de36140 | 12074318668157914 | 12074318668171183 | 12074318668313582 | 12074318668316910 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f2f19a4a800 | 0x7f2e0de36180 | 12074318668353889 | 12074318668367501 | 12074318668492300 | 12074318668495622 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f2f19a4a700 | 0x7f2e0de361c0 | 12074318668523293 | 12074318668536140 | 12074318668790378 | 12074318668810407 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f2f19a4a600 | 0x7f2e0de36200 | 12074318668832237 | 12074318668846057 | 12074318669092295 | 12074318669119651 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f2f19a4a500 | 0x7f2e0de36240 | 12074318669139729 | 12074318669152615 | 12074318669277894 | 12074318669281041 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f2f19a4a400 | 0x7f2e0de36280 | 12074318669308613 | 12074318669319973 | 12074318669470212 | 12074318669473148 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f2f19a4a300 | 0x7f2e0de362c0 | 12074318669530996 | 12074318669542531 | 12074318669668130 | 12074318669671387 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f2f19a4aa00 | 0x7f2e0de36300 | 12074318669698407 | 12074318669711010 | 12074318669964928 | 12074318669988336 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f2f19a4a900 | 0x7f2e0de36340 | 12074318670018111 | 12074318670030367 | 12074318670278845 | 12074318670309883 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f2f19a4a800 | 0x7f2e0de36380 | 12074318670331814 | 12074318670344444 | 12074318670470043 | 12074318670473327 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f2f19a4a700 | 0x7f2e0de363c0 | 12074318670500237 | 12074318670513403 | 12074318670670842 | 12074318670674160 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f2f19a4a600 | 0x7f2e0de36400 | 12074318670711459 | 12074318670724761 | 12074318670892440 | 12074318670895541 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f2f19a4a500 | 0x7f2e0de36440 | 12074318670923884 | 12074318670937559 | 12074318671193077 | 12074318671218421 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f2f19a4a400 | 0x7f2e0de36480 | 12074318671240342 | 12074318671254037 | 12074318671500114 | 12074318671527696 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f2f19a4a300 | 0x7f2e0de364c0 | 12074318671551019 | 12074318671563794 | 12074318671690193 | 12074318671693324 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f2f19a4aa00 | 0x7f2e0de36500 | 12074318671722638 | 12074318671733872 | 12074318671899151 | 12074318671902242 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f2f19a4a900 | 0x7f2e0de36540 | 12074318671940262 | 12074318671952751 | 12074318672078669 | 12074318672081996 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f2f19a4a800 | 0x7f2e0de36580 | 12074318672110519 | 12074318672122189 | 12074318672387627 | 12074318672411177 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f2f19a4a700 | 0x7f2e0de365c0 | 12074318672433619 | 12074318672446506 | 12074318672691464 | 12074318672714100 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f2f19a4a600 | 0x7f2e0de36600 | 12074318672735480 | 12074318672746824 | 12074318672872103 | 12074318672875190 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f2f19a4a500 | 0x7f2e0de36640 | 12074318672901909 | 12074318672913382 | 12074318673086021 | 12074318673089247 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f2f19a4a400 | 0x7f2e0de36680 | 12074318673127128 | 12074318673138980 | 12074318673264579 | 12074318673267749 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f2f19a4a300 | 0x7f2e0de366c0 | 12074318673294308 | 12074318673305859 | 12074318673558657 | 12074318673586301 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f2f19a4aa00 | 0x7f2e0de36700 | 12074318673609494 | 12074318673621376 | 12074318673865854 | 12074318673892750 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f2f19a4a900 | 0x7f2e0de36740 | 12074318673913870 | 12074318673926654 | 12074318674052412 | 12074318674055833 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f2f19a4a800 | 0x7f2e0de36780 | 12074318674083004 | 12074318674094492 | 12074318674276571 | 12074318674279880 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f2f19a4a700 | 0x7f2e0de367c0 | 12074318674317369 | 12074318674329530 | 12074318674454969 | 12074318674458231 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f2f19a4a600 | 0x7f2e0de36800 | 12074318674485542 | 12074318674497049 | 12074318674760566 | 12074318674784547 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f2f19a4a500 | 0x7f2e0de36840 | 12074318674804935 | 12074318674816566 | 12074318675063924 | 12074318675091187 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f2f19a4a400 | 0x7f2e0de36880 | 12074318675113318 | 12074318675124563 | 12074318675250162 | 12074318675253369 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f2f19a4a300 | 0x7f2e0de368c0 | 12074318675283434 | 12074318675296722 | 12074318675487440 | 12074318675490679 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f2f19a4aa00 | 0x7f2e0de36900 | 12074318675528139 | 12074318675540400 | 12074318675666959 | 12074318675670323 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f2f19a4a900 | 0x7f2e0de36940 | 12074318675697033 | 12074318675709838 | 12074318675991436 | 12074318676015835 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f2f19a4a800 | 0x7f2e0de36980 | 12074318676037816 | 12074318676050475 | 12074318676298153 | 12074318676321223 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f2f19a4a700 | 0x7f2e0de369c0 | 12074318676342112 | 12074318676353673 | 12074318676479592 | 12074318676482723 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f2f19a4a600 | 0x7f2e0de36a00 | 12074318676509893 | 12074318676521191 | 12074318676730629 | 12074318676757273 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f2f19a4a500 | 0x7f2e0de36a40 | 12074318676790174 | 12074318676801829 | 12074318676928068 | 12074318676931266 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f2f19a4a400 | 0x7f2e0de36a80 | 12074318676958296 | 12074318676969507 | 12074318677275425 | 12074318677303869 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f2f19a4a300 | 0x7f2e0de36ac0 | 12074318677327132 | 12074318677338144 | 12074318677590142 | 12074318677617311 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f2f19a4aa00 | 0x7f2e0de36b00 | 12074318677639342 | 12074318677650781 | 12074318677776860 | 12074318677779933 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f2f19a4a900 | 0x7f2e0de36b40 | 12074318677807214 | 12074318677818620 | 12074318678045978 | 12074318678074491 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f2f19a4a800 | 0x7f2e0de36b80 | 12074318678106881 | 12074318678117657 | 12074318678244056 | 12074318678247322 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f2f19a4a700 | 0x7f2e0de36bc0 | 12074318678274743 | 12074318678286776 | 12074318678615573 | 12074318678638929 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f2f19a4a600 | 0x7f2e0de36c00 | 12074318678660389 | 12074318678671253 | 12074318678922451 | 12074318678949316 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f2f19a4a500 | 0x7f2e0de36c40 | 12074318678970926 | 12074318678983570 | 12074318679112529 | 12074318679116126 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f2f19a4a400 | 0x7f2e0de36c80 | 12074318679145120 | 12074318679156369 | 12074318679399886 | 12074318679427685 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f2f19a4a300 | 0x7f2e0de36cc0 | 12074318679460005 | 12074318679470606 | 12074318679599405 | 12074318679602470 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f2f19a4aa00 | 0x7f2e0de36d00 | 12074318679628638 | 12074318679642124 | 12074318680017641 | 12074318680042557 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f2f19a4a900 | 0x7f2e0de36d40 | 12074318680062955 | 12074318680075241 | 12074318680333638 | 12074318680356090 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f2f19a4a800 | 0x7f2e0de36d80 | 12074318680377560 | 12074318680390118 | 12074318680518757 | 12074318680521938 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f2f19a4a700 | 0x7f2e0de36dc0 | 12074318680547886 | 12074318680560516 | 12074318680839714 | 12074318680862170 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f2f19a4a600 | 0x7f2e0de36e00 | 12074318680893879 | 12074318680904833 | 12074318681040352 | 12074318681043567 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f2f19a4a500 | 0x7f2e0de36e40 | 12074318681070868 | 12074318681082272 | 12074318681504828 | 12074318681533418 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f2f19a4a400 | 0x7f2e0de36e80 | 12074318681557512 | 12074318681569948 | 12074318681835065 | 12074318681861948 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f2f19a4a300 | 0x7f2e0de36ec0 | 12074318681883648 | 12074318681894905 | 12074318682028504 | 12074318682031854 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f2f19a4aa00 | 0x7f2e0de36f00 | 12074318682059265 | 12074318682071063 | 12074318682384501 | 12074318682415336 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f2f19a4a900 | 0x7f2e0de36f40 | 12074318682446494 | 12074318682458100 | 12074318682609299 | 12074318682612513 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f2f19a4a800 | 0x7f2e0de36f80 | 12074318682638391 | 12074318682649778 | 12074318683165934 | 12074318683194384 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f2f19a4a700 | 0x7f2e0de36fc0 | 12074318683216545 | 12074318683229613 | 12074318683526251 | 12074318683552670 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f2f19a4a600 | 0x7f2e0de37000 | 12074318683575863 | 12074318683588330 | 12074318683742729 | 12074318683745949 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f2f19a4a500 | 0x7f2e0de37040 | 12074318683774963 | 12074318683787849 | 12074318684172005 | 12074318684200493 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f2f19a4a400 | 0x7f2e0de37080 | 12074318684232022 | 12074318684245285 | 12074318684421283 | 12074318684424399 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f2f19a4a300 | 0x7f2e0de370c0 | 12074318684449977 | 12074318684463043 | 12074318685072958 | 12074318685101097 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f2f19a4aa00 | 0x7f2e0de37100 | 12074318685122496 | 12074318685135197 | 12074318685463514 | 12074318685490109 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f2f19a4a900 | 0x7f2e0de37140 | 12074318685513082 | 12074318685526394 | 12074318685704792 | 12074318685708345 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f2f19a4a800 | 0x7f2e0de37180 | 12074318685734744 | 12074318685747352 | 12074318686202388 | 12074318686230535 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f2f19a4a700 | 0x7f2e0de371c0 | 12074318686263286 | 12074318686276467 | 12074318686474866 | 12074318686501158 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f2f19a4a600 | 0x7f2e0de37200 | 12074318686521366 | 12074318686533905 | 12074318687236299 | 12074318687266991 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f2f19a4a500 | 0x7f2e0de37240 | 12074318687291837 | 12074318687304618 | 12074318687676295 | 12074318687703212 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f2f19a4a400 | 0x7f2e0de37280 | 12074318687726445 | 12074318687739815 | 12074318687941413 | 12074318687967673 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f2f19a4a300 | 0x7f2e0de372c0 | 12074318687989013 | 12074318688001732 | 12074318688526848 | 12074318688559062 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f2f19a4aa00 | 0x7f2e0de37300 | 12074318688591953 | 12074318688603647 | 12074318688828445 | 12074318688854821 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f2f19a4a900 | 0x7f2e0de37340 | 12074318688877934 | 12074318688888925 | 12074318689687798 | 12074318689716432 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f2f19a4a800 | 0x7f2e0de37380 | 12074318689737481 | 12074318689748597 | 12074318690191314 | 12074318690218956 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f2f19a4a700 | 0x7f2e0de373c0 | 12074318690242009 | 12074318690253713 | 12074318690478031 | 12074318690504737 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f2f19a4a600 | 0x7f2e0de37400 | 12074318690529413 | 12074318690541231 | 12074318691136905 | 12074318691165665 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f2f19a4a500 | 0x7f2e0de37440 | 12074318691197454 | 12074318691209065 | 12074318691478023 | 12074318691504665 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f2f19a4a400 | 0x7f2e0de37480 | 12074318691526846 | 12074318691538022 | 12074318692522014 | 12074318692550619 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f2f19a4a300 | 0x7f2e0de374c0 | 12074318692571197 | 12074318692583933 | 12074318693100249 | 12074318693128853 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f2f19a4aa00 | 0x7f2e0de37500 | 12074318693151936 | 12074318693164248 | 12074318693435926 | 12074318693462753 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f2f19a4a900 | 0x7f2e0de37540 | 12074318693486457 | 12074318693498325 | 12074318694235119 | 12074318694263501 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f2f19a4a800 | 0x7f2e0de37580 | 12074318694297134 | 12074318694308878 | 12074318694625035 | 12074318694652093 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f2f19a4a700 | 0x7f2e0de375c0 | 12074318694675727 | 12074318694687115 | 12074318695858785 | 12074318695887559 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f2f19a4a600 | 0x7f2e0de37600 | 12074318695911974 | 12074318695922784 | 12074318696531419 | 12074318696563866 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f2f19a4a500 | 0x7f2e0de37640 | 12074318696586618 | 12074318696598138 | 12074318696916216 | 12074318696946547 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f2f19a4a400 | 0x7f2e0de37680 | 12074318696970902 | 12074318696981975 | 12074318697859088 | 12074318697889378 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f2f19a4a300 | 0x7f2e0de376c0 | 12074318697921278 | 12074318697932687 | 12074318698343403 | 12074318698373358 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f2f19a4aa00 | 0x7f2e0de37700 | 12074318698395309 | 12074318698406123 | 12074318699956350 | 12074318700029174 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f2f19a4a900 | 0x7f2e0de37740 | 12074318700053720 | 12074318700065370 | 12074318700859284 | 12074318700933605 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f2f19a4a800 | 0x7f2e0de37780 | 12074318700952380 | 12074318700965522 | 12074318701379279 | 12074318701453621 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f2f19a4a700 | 0x7f2e0de377c0 | 12074318701479620 | 12074318701491118 | 12074318702648869 | 12074318702721978 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f2f19a4a600 | 0x7f2e0de37800 | 12074318702754378 | 12074318702765989 | 12074318703551263 | 12074318703623243 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f2f19a4a500 | 0x7f2e0de37840 | 12074318703645875 | 12074318703657822 | 12074318706708999 | 12074318706782182 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f2f19a4a400 | 0x7f2e0de37880 | 12074318706805756 | 12074318706816998 | 12074318708358906 | 12074318708434332 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f2f19a4a300 | 0x7f2e0de378c0 | 12074318708458196 | 12074318708469945 | 12074318709260339 | 12074318709332681 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f2f19a4aa00 | 0x7f2e0de37900 | 12074318709355464 | 12074318709366578 | 12074318711648001 | 12074318711721109 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f2f19a4a900 | 0x7f2e0de37940 | 12074318711753610 | 12074318711766080 | 12074318713301588 | 12074318713374241 |
| 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 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f2f19a4a800 | 0x7f2e0de37980 | 12074318713397514 | 12074318713409108 | 12074318719466342 | 12074318719538675 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f2f19a4a700 | 0x7f2e0de379c0 | 12074318719562890 | 12074318719574341 | 12074318722619278 | 12074318722692766 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f2f19a4a600 | 0x7f2e0de37a00 | 12074318722715227 | 12074318722728717 | 12074318724267585 | 12074318724340047 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 820647 | 820652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f2f19a4a500 | 0x7f2e0de37a40 | 12074318724361837 | 12074318724374464 | 12074318728900510 | 12074318728973115 |