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 | 755525 | 755530 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f5a91804180 | 12073277939439483 | 12073277939480571 | 12073277939805848 | 12073277939922320 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 755525 | 755530 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f5a91835100 | 12073277954440757 | 12073277954543789 | 12073277954550669 | 12073277954557223 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f5b9d52c900 | 0x7f5a91835140 | 12073277954599522 | 12073277954616748 | 12073277954747147 | 12073277954751133 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f5b9d52c800 | 0x7f5a91835180 | 12073277954793362 | 12073277954808906 | 12073277955051784 | 12073277955152139 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f5b9d52c700 | 0x7f5a918351c0 | 12073277955177987 | 12073277955193223 | 12073277955442340 | 12073277955542404 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f5b9d52c600 | 0x7f5a91835200 | 12073277955573171 | 12073277955588419 | 12073277955713858 | 12073277955717399 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f5b9d52c500 | 0x7f5a91835240 | 12073277955752484 | 12073277955767137 | 12073277955892416 | 12073277955896081 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f5b9d52c400 | 0x7f5a91835280 | 12073277955944501 | 12073277955958976 | 12073277956083455 | 12073277956087136 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f5b9d52c300 | 0x7f5a918352c0 | 12073277956115058 | 12073277956130174 | 12073277956384412 | 12073277956484474 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f5b9d52ca00 | 0x7f5a91835300 | 12073277956507978 | 12073277956524890 | 12073277956767928 | 12073277956868177 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f5b9d52c900 | 0x7f5a91835340 | 12073277956891851 | 12073277956911127 | 12073277957035766 | 12073277957039315 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f5b9d52c800 | 0x7f5a91835380 | 12073277957067848 | 12073277957082805 | 12073277957207924 | 12073277957211675 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f5b9d52c700 | 0x7f5a918353c0 | 12073277957248584 | 12073277957263923 | 12073277957388242 | 12073277957391990 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f5b9d52c600 | 0x7f5a91835400 | 12073277957417498 | 12073277957433202 | 12073277957683760 | 12073277957784209 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f5b9d52c500 | 0x7f5a91835440 | 12073277957810047 | 12073277957825358 | 12073277958075596 | 12073277958146312 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f5b9d52c400 | 0x7f5a91835480 | 12073277958175807 | 12073277958192235 | 12073277958317994 | 12073277958321457 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f5b9d52c300 | 0x7f5a918354c0 | 12073277958347095 | 12073277958362313 | 12073277958487432 | 12073277958491173 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f5b9d52ca00 | 0x7f5a91835500 | 12073277958528672 | 12073277958544392 | 12073277958669510 | 12073277958673321 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f5b9d52c900 | 0x7f5a91835540 | 12073277958699440 | 12073277958715590 | 12073277958961188 | 12073277959010899 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f5b9d52c800 | 0x7f5a91835580 | 12073277959035885 | 12073277959052387 | 12073277959295744 | 12073277959364315 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f5b9d52c700 | 0x7f5a918355c0 | 12073277959388360 | 12073277959403903 | 12073277959528222 | 12073277959531987 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f5b9d52c600 | 0x7f5a91835600 | 12073277959558035 | 12073277959572382 | 12073277959697501 | 12073277959701171 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f5b9d52c500 | 0x7f5a91835640 | 12073277959737378 | 12073277959755260 | 12073277959879419 | 12073277959883129 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f5b9d52c400 | 0x7f5a91835680 | 12073277959909097 | 12073277959924219 | 12073277960170776 | 12073277960242036 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f5b9d52c300 | 0x7f5a918356c0 | 12073277960266772 | 12073277960285015 | 12073277960529493 | 12073277960598819 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f5b9d52ca00 | 0x7f5a91835700 | 12073277960623054 | 12073277960639572 | 12073277960763411 | 12073277960767272 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f5b9d52c900 | 0x7f5a91835740 | 12073277960793932 | 12073277960809490 | 12073277960934609 | 12073277960938390 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f5b9d52c800 | 0x7f5a91835780 | 12073277960973225 | 12073277960989489 | 12073277961114608 | 12073277961118374 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f5b9d52c700 | 0x7f5a918357c0 | 12073277961144653 | 12073277961160047 | 12073277961408845 | 12073277961436355 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f5b9d52c600 | 0x7f5a91835800 | 12073277961458637 | 12073277961474764 | 12073277961719082 | 12073277961744929 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f5b9d52c500 | 0x7f5a91835840 | 12073277961768843 | 12073277961784841 | 12073277961908840 | 12073277961912249 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f5b9d52c400 | 0x7f5a91835880 | 12073277961938759 | 12073277961953000 | 12073277962079238 | 12073277962082967 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f5b9d52c300 | 0x7f5a918358c0 | 12073277962120707 | 12073277962134918 | 12073277962260037 | 12073277962263512 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f5b9d52ca00 | 0x7f5a91835900 | 12073277962289991 | 12073277962306596 | 12073277962555874 | 12073277962582515 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f5b9d52c900 | 0x7f5a91835940 | 12073277962604987 | 12073277962621313 | 12073277962867551 | 12073277962893623 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f5b9d52c800 | 0x7f5a91835980 | 12073277962916976 | 12073277962934591 | 12073277963059389 | 12073277963063569 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f5b9d52c700 | 0x7f5a918359c0 | 12073277963090980 | 12073277963105789 | 12073277963231868 | 12073277963235548 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f5b9d52c600 | 0x7f5a91835a00 | 12073277963271916 | 12073277963286747 | 12073277963410906 | 12073277963414621 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f5b9d52c500 | 0x7f5a91835a40 | 12073277963441210 | 12073277963455706 | 12073277963702903 | 12073277963725308 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f5b9d52c400 | 0x7f5a91835a80 | 12073277963746878 | 12073277963762583 | 12073277964008180 | 12073277964035555 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f5b9d52c300 | 0x7f5a91835ac0 | 12073277964062194 | 12073277964078260 | 12073277964202899 | 12073277964206963 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f5b9d52ca00 | 0x7f5a91835b00 | 12073277964233994 | 12073277964248978 | 12073277964374897 | 12073277964378612 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f5b9d52c900 | 0x7f5a91835b40 | 12073277964415451 | 12073277964430097 | 12073277964555215 | 12073277964558687 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f5b9d52c800 | 0x7f5a91835b80 | 12073277964585477 | 12073277964600175 | 12073277964850093 | 12073277964871448 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f5b9d52c700 | 0x7f5a91835bc0 | 12073277964895322 | 12073277964910892 | 12073277965156170 | 12073277965183217 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f5b9d52c600 | 0x7f5a91835c00 | 12073277965206040 | 12073277965223369 | 12073277965348328 | 12073277965352061 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f5b9d52c500 | 0x7f5a91835c40 | 12073277965378741 | 12073277965393608 | 12073277965519686 | 12073277965523129 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f5b9d52c400 | 0x7f5a91835c80 | 12073277965561480 | 12073277965576646 | 12073277965701925 | 12073277965705398 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f5b9d52c300 | 0x7f5a91835cc0 | 12073277965732217 | 12073277965747844 | 12073277966004802 | 12073277966031113 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f5b9d52ca00 | 0x7f5a91835d00 | 12073277966054346 | 12073277966071201 | 12073277966315039 | 12073277966345066 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f5b9d52c900 | 0x7f5a91835d40 | 12073277966367768 | 12073277966385438 | 12073277966510557 | 12073277966514331 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f5b9d52c800 | 0x7f5a91835d80 | 12073277966540629 | 12073277966555677 | 12073277966685115 | 12073277966688915 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f5b9d52c700 | 0x7f5a91835dc0 | 12073277966726174 | 12073277966740315 | 12073277966865754 | 12073277966869571 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f5b9d52c600 | 0x7f5a91835e00 | 12073277966896120 | 12073277966910873 | 12073277967168151 | 12073277967198983 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f5b9d52c500 | 0x7f5a91835e40 | 12073277967221505 | 12073277967237270 | 12073277967481908 | 12073277967510712 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f5b9d52c400 | 0x7f5a91835e80 | 12073277967537462 | 12073277967554067 | 12073277967679506 | 12073277967683042 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f5b9d52c300 | 0x7f5a91835ec0 | 12073277967710423 | 12073277967725586 | 12073277967855825 | 12073277967859560 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f5b9d52ca00 | 0x7f5a91835f00 | 12073277967896469 | 12073277967912624 | 12073277968038063 | 12073277968041669 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f5b9d52c900 | 0x7f5a91835f40 | 12073277968069931 | 12073277968085262 | 12073277968338700 | 12073277968361383 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f5b9d52c800 | 0x7f5a91835f80 | 12073277968384295 | 12073277968399819 | 12073277968646377 | 12073277968671008 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f5b9d52c700 | 0x7f5a91835fc0 | 12073277968693550 | 12073277968709417 | 12073277968835655 | 12073277968839130 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f5b9d52c600 | 0x7f5a91836000 | 12073277968864918 | 12073277968879655 | 12073277969017094 | 12073277969021028 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f5b9d52c500 | 0x7f5a91836040 | 12073277969060652 | 12073277969075013 | 12073277969200452 | 12073277969204529 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f5b9d52c400 | 0x7f5a91836080 | 12073277969231229 | 12073277969246852 | 12073277969502529 | 12073277969524333 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f5b9d52c300 | 0x7f5a918360c0 | 12073277969546795 | 12073277969562529 | 12073277969807326 | 12073277969828929 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f5b9d52ca00 | 0x7f5a91836100 | 12073277969849808 | 12073277969866366 | 12073277969991005 | 12073277969994597 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f5b9d52c900 | 0x7f5a91836140 | 12073277970029262 | 12073277970044604 | 12073277970187803 | 12073277970191613 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f5b9d52c800 | 0x7f5a91836180 | 12073277970228221 | 12073277970242682 | 12073277970368281 | 12073277970371989 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f5b9d52c700 | 0x7f5a918361c0 | 12073277970399249 | 12073277970413881 | 12073277970666678 | 12073277970692163 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f5b9d52c600 | 0x7f5a91836200 | 12073277970714274 | 12073277970729878 | 12073277970976435 | 12073277971006708 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f5b9d52c500 | 0x7f5a91836240 | 12073277971029981 | 12073277971046035 | 12073277971171154 | 12073277971174890 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f5b9d52c400 | 0x7f5a91836280 | 12073277971201189 | 12073277971215953 | 12073277971364112 | 12073277971367979 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f5b9d52c300 | 0x7f5a918362c0 | 12073277971424023 | 12073277971439631 | 12073277971564750 | 12073277971568602 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f5b9d52ca00 | 0x7f5a91836300 | 12073277971594710 | 12073277971609229 | 12073277971871467 | 12073277971896902 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f5b9d52c900 | 0x7f5a91836340 | 12073277971919504 | 12073277971934666 | 12073277972181544 | 12073277972208621 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f5b9d52c800 | 0x7f5a91836380 | 12073277972232465 | 12073277972248103 | 12073277972374342 | 12073277972378036 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f5b9d52c700 | 0x7f5a918363c0 | 12073277972404776 | 12073277972419622 | 12073277972577700 | 12073277972581604 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f5b9d52c600 | 0x7f5a91836400 | 12073277972618593 | 12073277972632900 | 12073277972758019 | 12073277972761528 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f5b9d52c500 | 0x7f5a91836440 | 12073277972787757 | 12073277972802658 | 12073277973063776 | 12073277973091101 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f5b9d52c400 | 0x7f5a91836480 | 12073277973114334 | 12073277973130175 | 12073277973375133 | 12073277973400075 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f5b9d52c300 | 0x7f5a918364c0 | 12073277973421956 | 12073277973440092 | 12073277973567131 | 12073277973570752 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f5b9d52ca00 | 0x7f5a91836500 | 12073277973595819 | 12073277973610811 | 12073277973776729 | 12073277973780321 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f5b9d52c900 | 0x7f5a91836540 | 12073277973817180 | 12073277973831929 | 12073277973957368 | 12073277973961017 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f5b9d52c800 | 0x7f5a91836580 | 12073277973987526 | 12073277974001847 | 12073277974260405 | 12073277974289417 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f5b9d52c700 | 0x7f5a918365c0 | 12073277974312621 | 12073277974328084 | 12073277974578482 | 12073277974603611 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f5b9d52c600 | 0x7f5a91836600 | 12073277974627726 | 12073277974643441 | 12073277974769200 | 12073277974772846 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f5b9d52c500 | 0x7f5a91836640 | 12073277974799635 | 12073277974814800 | 12073277974987758 | 12073277974991672 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f5b9d52c400 | 0x7f5a91836680 | 12073277975035594 | 12073277975050317 | 12073277975176076 | 12073277975180323 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f5b9d52c300 | 0x7f5a918366c0 | 12073277975206522 | 12073277975221036 | 12073277975475913 | 12073277975497402 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f5b9d52ca00 | 0x7f5a91836700 | 12073277975519613 | 12073277975536393 | 12073277975781190 | 12073277975806296 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f5b9d52c900 | 0x7f5a91836740 | 12073277975829038 | 12073277975844710 | 12073277975971109 | 12073277975975009 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f5b9d52c800 | 0x7f5a91836780 | 12073277976007810 | 12073277976022628 | 12073277976205667 | 12073277976209375 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f5b9d52c700 | 0x7f5a918367c0 | 12073277976247886 | 12073277976262626 | 12073277976389185 | 12073277976392766 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f5b9d52c600 | 0x7f5a91836800 | 12073277976418874 | 12073277976433504 | 12073277976696862 | 12073277976718501 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f5b9d52c500 | 0x7f5a91836840 | 12073277976740352 | 12073277976755421 | 12073277977004219 | 12073277977029849 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f5b9d52c400 | 0x7f5a91836880 | 12073277977051941 | 12073277977069018 | 12073277977194457 | 12073277977198353 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f5b9d52c300 | 0x7f5a918368c0 | 12073277977223589 | 12073277977238617 | 12073277977430135 | 12073277977458897 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f5b9d52ca00 | 0x7f5a91836900 | 12073277977490425 | 12073277977505174 | 12073277977632853 | 12073277977636547 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f5b9d52c900 | 0x7f5a91836940 | 12073277977663096 | 12073277977677493 | 12073277977992050 | 12073277978022985 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f5b9d52c800 | 0x7f5a91836980 | 12073277978045797 | 12073277978062289 | 12073277978314127 | 12073277978342669 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f5b9d52c700 | 0x7f5a918369c0 | 12073277978366914 | 12073277978384686 | 12073277978510765 | 12073277978514608 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f5b9d52c600 | 0x7f5a91836a00 | 12073277978540887 | 12073277978555405 | 12073277978800682 | 12073277978825756 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f5b9d52c500 | 0x7f5a91836a40 | 12073277978859409 | 12073277978874922 | 12073277979002760 | 12073277979006973 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f5b9d52c400 | 0x7f5a91836a80 | 12073277979034805 | 12073277979049320 | 12073277979355397 | 12073277979377001 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f5b9d52c300 | 0x7f5a91836ac0 | 12073277979398711 | 12073277979414277 | 12073277979661474 | 12073277979686355 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f5b9d52ca00 | 0x7f5a91836b00 | 12073277979709769 | 12073277979726274 | 12073277979854912 | 12073277979858656 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f5b9d52c900 | 0x7f5a91836b40 | 12073277979885916 | 12073277979900512 | 12073277980128030 | 12073277980154185 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f5b9d52c800 | 0x7f5a91836b80 | 12073277980188268 | 12073277980205789 | 12073277980333308 | 12073277980336984 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f5b9d52c700 | 0x7f5a91836bc0 | 12073277980363734 | 12073277980378108 | 12073277980707384 | 12073277980732239 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f5b9d52c600 | 0x7f5a91836c00 | 12073277980753108 | 12073277980768824 | 12073277981020822 | 12073277981047224 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f5b9d52c500 | 0x7f5a91836c40 | 12073277981069956 | 12073277981087221 | 12073277981216180 | 12073277981219975 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f5b9d52c400 | 0x7f5a91836c80 | 12073277981246715 | 12073277981262099 | 12073277981505617 | 12073277981526925 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f5b9d52c300 | 0x7f5a91836cc0 | 12073277981559536 | 12073277981573616 | 12073277981702255 | 12073277981705888 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f5b9d52ca00 | 0x7f5a91836d00 | 12073277981732127 | 12073277981746575 | 12073277982122091 | 12073277982148280 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f5b9d52c900 | 0x7f5a91836d40 | 12073277982171904 | 12073277982188331 | 12073277982446248 | 12073277982471230 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f5b9d52c800 | 0x7f5a91836d80 | 12073277982493632 | 12073277982510248 | 12073277982640166 | 12073277982643911 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f5b9d52c700 | 0x7f5a91836dc0 | 12073277982670851 | 12073277982685446 | 12073277982963683 | 12073277982988521 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f5b9d52c600 | 0x7f5a91836e00 | 12073277983034006 | 12073277983048963 | 12073277983184641 | 12073277983188833 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f5b9d52c500 | 0x7f5a91836e40 | 12073277983214902 | 12073277983230081 | 12073277983652797 | 12073277983682451 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f5b9d52c400 | 0x7f5a91836e80 | 12073277983708940 | 12073277983724316 | 12073277983979994 | 12073277984009679 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f5b9d52c300 | 0x7f5a91836ec0 | 12073277984039244 | 12073277984054873 | 12073277984190552 | 12073277984194252 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f5b9d52ca00 | 0x7f5a91836f00 | 12073277984221091 | 12073277984235992 | 12073277984550709 | 12073277984579107 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f5b9d52c900 | 0x7f5a91836f40 | 12073277984615003 | 12073277984629428 | 12073277984780946 | 12073277984784859 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f5b9d52c800 | 0x7f5a91836f80 | 12073277984812220 | 12073277984827666 | 12073277985343981 | 12073277985370046 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f5b9d52c700 | 0x7f5a91836fc0 | 12073277985394051 | 12073277985409741 | 12073277985708138 | 12073277985736617 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f5b9d52c600 | 0x7f5a91837000 | 12073277985758819 | 12073277985776297 | 12073277985931816 | 12073277985935647 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f5b9d52c500 | 0x7f5a91837040 | 12073277985961996 | 12073277985976935 | 12073277986361412 | 12073277986391454 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f5b9d52c400 | 0x7f5a91837080 | 12073277986424806 | 12073277986441251 | 12073277986617569 | 12073277986621452 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f5b9d52c300 | 0x7f5a918370c0 | 12073277986647911 | 12073277986662209 | 12073277987272283 | 12073277987302577 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f5b9d52ca00 | 0x7f5a91837100 | 12073277987328235 | 12073277987343802 | 12073277987671799 | 12073277987696449 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f5b9d52c900 | 0x7f5a91837140 | 12073277987721656 | 12073277987737879 | 12073277987915637 | 12073277987919524 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f5b9d52c800 | 0x7f5a91837180 | 12073277987945943 | 12073277987960117 | 12073277988415792 | 12073277988445230 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f5b9d52c700 | 0x7f5a918371c0 | 12073277988480776 | 12073277988495472 | 12073277988731310 | 12073277988759805 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f5b9d52c600 | 0x7f5a91837200 | 12073277988782717 | 12073277988797709 | 12073277989500742 | 12073277989531058 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f5b9d52c500 | 0x7f5a91837240 | 12073277989554862 | 12073277989571942 | 12073277989944578 | 12073277989972799 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f5b9d52c400 | 0x7f5a91837280 | 12073277989996032 | 12073277990016738 | 12073277990219456 | 12073277990249012 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f5b9d52c300 | 0x7f5a918372c0 | 12073277990273818 | 12073277990288895 | 12073277990815130 | 12073277990843496 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f5b9d52ca00 | 0x7f5a91837300 | 12073277990877930 | 12073277990893689 | 12073277991118167 | 12073277991150597 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f5b9d52c900 | 0x7f5a91837340 | 12073277991174782 | 12073277991190167 | 12073277991988239 | 12073277992021976 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f5b9d52c800 | 0x7f5a91837380 | 12073277992046582 | 12073277992061998 | 12073277992480714 | 12073277992508951 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f5b9d52c700 | 0x7f5a918373c0 | 12073277992530611 | 12073277992547114 | 12073277992773512 | 12073277992801404 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f5b9d52c600 | 0x7f5a91837400 | 12073277992824568 | 12073277992838951 | 12073277993436386 | 12073277993466380 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f5b9d52c500 | 0x7f5a91837440 | 12073277993499532 | 12073277993515105 | 12073277993784542 | 12073277993813144 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f5b9d52c400 | 0x7f5a91837480 | 12073277993834734 | 12073277993849182 | 12073277994834132 | 12073277994864177 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f5b9d52c300 | 0x7f5a918374c0 | 12073277994888923 | 12073277994904532 | 12073277995438127 | 12073277995467909 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f5b9d52ca00 | 0x7f5a91837500 | 12073277995493867 | 12073277995509646 | 12073277995781644 | 12073277995810065 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f5b9d52c900 | 0x7f5a91837540 | 12073277995834400 | 12073277995849483 | 12073277996586756 | 12073277996616393 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f5b9d52c800 | 0x7f5a91837580 | 12073277996651268 | 12073277996665635 | 12073277996980352 | 12073277997011447 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f5b9d52c700 | 0x7f5a918375c0 | 12073277997035271 | 12073277997050752 | 12073277998224661 | 12073277998255829 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f5b9d52c600 | 0x7f5a91837600 | 12073277998279724 | 12073277998295220 | 12073277998903854 | 12073277998932977 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f5b9d52c500 | 0x7f5a91837640 | 12073277998956902 | 12073277998972814 | 12073277999291531 | 12073277999322712 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f5b9d52c400 | 0x7f5a91837680 | 12073277999346947 | 12073277999361930 | 12073278000239842 | 12073278000271394 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f5b9d52c300 | 0x7f5a918376c0 | 12073278000308153 | 12073278000323361 | 12073278000733437 | 12073278000762477 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f5b9d52ca00 | 0x7f5a91837700 | 12073278000785369 | 12073278000800477 | 12073278002351662 | 12073278002401923 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f5b9d52c900 | 0x7f5a91837740 | 12073278002427100 | 12073278002443702 | 12073278003240816 | 12073278003319017 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f5b9d52c800 | 0x7f5a91837780 | 12073278003340417 | 12073278003357774 | 12073278003772171 | 12073278003846097 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f5b9d52c700 | 0x7f5a918377c0 | 12073278003871233 | 12073278003886410 | 12073278005045761 | 12073278005119493 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f5b9d52c600 | 0x7f5a91837800 | 12073278005155680 | 12073278005171361 | 12073278005956635 | 12073278006030475 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f5b9d52c500 | 0x7f5a91837840 | 12073278006056023 | 12073278006072314 | 12073278009125251 | 12073278009198903 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f5b9d52c400 | 0x7f5a91837880 | 12073278009223558 | 12073278009239490 | 12073278010781558 | 12073278010855180 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f5b9d52c300 | 0x7f5a918378c0 | 12073278010882771 | 12073278010899317 | 12073278011688111 | 12073278011761444 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f5b9d52ca00 | 0x7f5a91837900 | 12073278011786300 | 12073278011801870 | 12073278014084253 | 12073278014158207 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f5b9d52c900 | 0x7f5a91837940 | 12073278014193884 | 12073278014209372 | 12073278015744561 | 12073278015817110 |
| 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 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f5b9d52c800 | 0x7f5a91837980 | 12073278015843058 | 12073278015859280 | 12073278021917794 | 12073278021992314 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f5b9d52c700 | 0x7f5a918379c0 | 12073278022024664 | 12073278022040673 | 12073278025084970 | 12073278025160721 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f5b9d52c600 | 0x7f5a91837a00 | 12073278025186138 | 12073278025202249 | 12073278026741598 | 12073278026815045 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 755525 | 755530 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f5b9d52c500 | 0x7f5a91837a40 | 12073278026839891 | 12073278026854877 | 12073278031382363 | 12073278031455988 |