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 | 934549 | 934554 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f43d3a04180 | 12076585535757218 | 12076585535799471 | 12076585536125708 | 12076585536237040 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 934549 | 934554 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f43d3a35100 | 12076585551962501 | 12076585552066419 | 12076585552073299 | 12076585552079840 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f4503d10900 | 0x7f43d3a35140 | 12076585552136776 | 12076585552150098 | 12076585552288977 | 12076585552292365 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f4503d10800 | 0x7f43d3a35180 | 12076585552347618 | 12076585552365937 | 12076585552611695 | 12076585552708800 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f4503d10700 | 0x7f43d3a351c0 | 12076585552744055 | 12076585552755693 | 12076585553001291 | 12076585553098685 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f4503d10600 | 0x7f43d3a35200 | 12076585553137717 | 12076585553148970 | 12076585553274249 | 12076585553277407 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f4503d10500 | 0x7f43d3a35240 | 12076585553313434 | 12076585553326729 | 12076585553452168 | 12076585553455328 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f4503d10400 | 0x7f43d3a35280 | 12076585553516462 | 12076585553528647 | 12076585553652806 | 12076585553655941 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f4503d10300 | 0x7f43d3a352c0 | 12076585553691618 | 12076585553704166 | 12076585553951044 | 12076585554050836 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f4503d10a00 | 0x7f43d3a35300 | 12076585554081693 | 12076585554093283 | 12076585554341121 | 12076585554438737 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f4503d10900 | 0x7f43d3a35340 | 12076585554469976 | 12076585554481280 | 12076585554605759 | 12076585554608954 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f4503d10800 | 0x7f43d3a35380 | 12076585554644300 | 12076585554657758 | 12076585554782877 | 12076585554786184 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f4503d10700 | 0x7f43d3a353c0 | 12076585554835706 | 12076585554846877 | 12076585554971676 | 12076585554974875 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f4503d10600 | 0x7f43d3a35400 | 12076585555014338 | 12076585555026235 | 12076585555275033 | 12076585555348650 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f4503d10500 | 0x7f43d3a35440 | 12076585555379447 | 12076585555390712 | 12076585555672470 | 12076585555741290 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f4503d10400 | 0x7f43d3a35480 | 12076585555773210 | 12076585555787829 | 12076585555913108 | 12076585555916126 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f4503d10300 | 0x7f43d3a354c0 | 12076585555950019 | 12076585555962068 | 12076585556087347 | 12076585556090560 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f4503d10a00 | 0x7f43d3a35500 | 12076585556137858 | 12076585556149266 | 12076585556273265 | 12076585556276506 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f4503d10900 | 0x7f43d3a35540 | 12076585556310990 | 12076585556323665 | 12076585556608462 | 12076585556651564 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f4503d10800 | 0x7f43d3a35580 | 12076585556680347 | 12076585556692142 | 12076585556971819 | 12076585557049183 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f4503d10700 | 0x7f43d3a355c0 | 12076585557075803 | 12076585557088139 | 12076585557212777 | 12076585557215993 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f4503d10600 | 0x7f43d3a35600 | 12076585557250488 | 12076585557261897 | 12076585557387176 | 12076585557389997 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f4503d10500 | 0x7f43d3a35640 | 12076585557435472 | 12076585557447496 | 12076585557571655 | 12076585557574430 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f4503d10400 | 0x7f43d3a35680 | 12076585557607953 | 12076585557625734 | 12076585557872132 | 12076585557916547 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f4503d10300 | 0x7f43d3a356c0 | 12076585557945931 | 12076585557957571 | 12076585558202210 | 12076585558270715 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f4503d10a00 | 0x7f43d3a35700 | 12076585558301342 | 12076585558313569 | 12076585558436928 | 12076585558439840 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f4503d10900 | 0x7f43d3a35740 | 12076585558475176 | 12076585558486687 | 12076585558612446 | 12076585558615707 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f4503d10800 | 0x7f43d3a35780 | 12076585558661673 | 12076585558673886 | 12076585558798685 | 12076585558801914 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f4503d10700 | 0x7f43d3a357c0 | 12076585558837390 | 12076585558848924 | 12076585559096282 | 12076585559163837 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f4503d10600 | 0x7f43d3a35800 | 12076585559195155 | 12076585559207001 | 12076585559453239 | 12076585559550336 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f4503d10500 | 0x7f43d3a35840 | 12076585559578488 | 12076585559590198 | 12076585559714997 | 12076585559718118 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f4503d10400 | 0x7f43d3a35880 | 12076585559752311 | 12076585559763477 | 12076585559888756 | 12076585559892121 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f4503d10300 | 0x7f43d3a358c0 | 12076585559934691 | 12076585559946995 | 12076585560071954 | 12076585560074891 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f4503d10a00 | 0x7f43d3a35900 | 12076585560108825 | 12076585560120754 | 12076585560370992 | 12076585560450781 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f4503d10900 | 0x7f43d3a35940 | 12076585560479504 | 12076585560490991 | 12076585560734829 | 12076585560813746 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f4503d10800 | 0x7f43d3a35980 | 12076585560841187 | 12076585560852748 | 12076585560978027 | 12076585560980987 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f4503d10700 | 0x7f43d3a359c0 | 12076585561024017 | 12076585561035307 | 12076585561161226 | 12076585561164188 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f4503d10600 | 0x7f43d3a35a00 | 12076585561211826 | 12076585561226025 | 12076585561350184 | 12076585561352849 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f4503d10500 | 0x7f43d3a35a40 | 12076585561390859 | 12076585561405224 | 12076585561656582 | 12076585561705675 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f4503d10400 | 0x7f43d3a35a80 | 12076585561737504 | 12076585561748581 | 12076585561992099 | 12076585562046849 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f4503d10300 | 0x7f43d3a35ac0 | 12076585562078278 | 12076585562092258 | 12076585562217057 | 12076585562220272 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f4503d10a00 | 0x7f43d3a35b00 | 12076585562253063 | 12076585562264737 | 12076585562390816 | 12076585562393414 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f4503d10900 | 0x7f43d3a35b40 | 12076585562439319 | 12076585562450975 | 12076585562576254 | 12076585562578959 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f4503d10800 | 0x7f43d3a35b80 | 12076585562612071 | 12076585562625214 | 12076585562882812 | 12076585562907741 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f4503d10700 | 0x7f43d3a35bc0 | 12076585562936594 | 12076585562947771 | 12076585563195609 | 12076585563228397 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f4503d10600 | 0x7f43d3a35c00 | 12076585563256439 | 12076585563267929 | 12076585563392088 | 12076585563394797 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f4503d10500 | 0x7f43d3a35c40 | 12076585563430333 | 12076585563441687 | 12076585563568406 | 12076585563571135 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f4503d10400 | 0x7f43d3a35c80 | 12076585563615197 | 12076585563626966 | 12076585563751605 | 12076585563754276 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f4503d10300 | 0x7f43d3a35cc0 | 12076585563786576 | 12076585563799444 | 12076585564052402 | 12076585564082326 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f4503d10a00 | 0x7f43d3a35d00 | 12076585564113594 | 12076585564124722 | 12076585564369200 | 12076585564396971 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f4503d10900 | 0x7f43d3a35d40 | 12076585564425194 | 12076585564437359 | 12076585564562318 | 12076585564564994 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f4503d10800 | 0x7f43d3a35d80 | 12076585564598586 | 12076585564610158 | 12076585564737517 | 12076585564740230 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f4503d10700 | 0x7f43d3a35dc0 | 12076585564784472 | 12076585564796076 | 12076585564921195 | 12076585564923821 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f4503d10600 | 0x7f43d3a35e00 | 12076585564956291 | 12076585564969355 | 12076585565220073 | 12076585565248214 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f4503d10500 | 0x7f43d3a35e40 | 12076585565277569 | 12076585565290472 | 12076585565573190 | 12076585565596172 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f4503d10400 | 0x7f43d3a35e80 | 12076585565628983 | 12076585565642150 | 12076585565767429 | 12076585565770426 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f4503d10300 | 0x7f43d3a35ec0 | 12076585565802706 | 12076585565814308 | 12076585565942467 | 12076585565945121 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f4503d10a00 | 0x7f43d3a35f00 | 12076585565987429 | 12076585565999907 | 12076585566125666 | 12076585566128732 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f4503d10900 | 0x7f43d3a35f40 | 12076585566162806 | 12076585566175105 | 12076585566427743 | 12076585566451653 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f4503d10800 | 0x7f43d3a35f80 | 12076585566480677 | 12076585566492543 | 12076585566737981 | 12076585566760678 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f4503d10700 | 0x7f43d3a35fc0 | 12076585566790313 | 12076585566801180 | 12076585566926299 | 12076585566929031 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f4503d10600 | 0x7f43d3a36000 | 12076585566961381 | 12076585566972699 | 12076585567109818 | 12076585567112953 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f4503d10500 | 0x7f43d3a36040 | 12076585567159349 | 12076585567173177 | 12076585567297496 | 12076585567300221 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f4503d10400 | 0x7f43d3a36080 | 12076585567332582 | 12076585567345016 | 12076585567597174 | 12076585567617642 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f4503d10300 | 0x7f43d3a360c0 | 12076585567647988 | 12076585567661813 | 12076585567905491 | 12076585567929612 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f4503d10a00 | 0x7f43d3a36100 | 12076585567957614 | 12076585567968851 | 12076585568093490 | 12076585568096472 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f4503d10900 | 0x7f43d3a36140 | 12076585568130576 | 12076585568142289 | 12076585568284688 | 12076585568287738 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f4503d10800 | 0x7f43d3a36180 | 12076585568331189 | 12076585568342768 | 12076585568467567 | 12076585568470228 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f4503d10700 | 0x7f43d3a361c0 | 12076585568502638 | 12076585568515566 | 12076585568773164 | 12076585568800542 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f4503d10600 | 0x7f43d3a36200 | 12076585568829466 | 12076585568842124 | 12076585569093002 | 12076585569121399 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f4503d10500 | 0x7f43d3a36240 | 12076585569154010 | 12076585569165801 | 12076585569290920 | 12076585569293629 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f4503d10400 | 0x7f43d3a36280 | 12076585569328454 | 12076585569342280 | 12076585569491559 | 12076585569494393 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f4503d10300 | 0x7f43d3a362c0 | 12076585569556378 | 12076585569567878 | 12076585569694277 | 12076585569697380 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f4503d10a00 | 0x7f43d3a36300 | 12076585569729911 | 12076585569743237 | 12076585570006594 | 12076585570035339 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f4503d10900 | 0x7f43d3a36340 | 12076585570064914 | 12076585570075874 | 12076585570321312 | 12076585570345045 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f4503d10800 | 0x7f43d3a36380 | 12076585570373728 | 12076585570385151 | 12076585570510910 | 12076585570513609 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f4503d10700 | 0x7f43d3a363c0 | 12076585570547702 | 12076585570559550 | 12076585570718269 | 12076585570721024 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f4503d10600 | 0x7f43d3a36400 | 12076585570766229 | 12076585570778428 | 12076585570904027 | 12076585570906700 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f4503d10500 | 0x7f43d3a36440 | 12076585570939391 | 12076585570951547 | 12076585571207385 | 12076585571235742 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f4503d10400 | 0x7f43d3a36480 | 12076585571264475 | 12076585571276184 | 12076585571528822 | 12076585571556238 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f4503d10300 | 0x7f43d3a364c0 | 12076585571584751 | 12076585571595862 | 12076585571721621 | 12076585571724411 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f4503d10a00 | 0x7f43d3a36500 | 12076585571756230 | 12076585571769620 | 12076585571935699 | 12076585571938379 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f4503d10900 | 0x7f43d3a36540 | 12076585571982271 | 12076585571995378 | 12076585572121297 | 12076585572124796 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f4503d10800 | 0x7f43d3a36580 | 12076585572159320 | 12076585572172657 | 12076585572430895 | 12076585572455110 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f4503d10700 | 0x7f43d3a365c0 | 12076585572482912 | 12076585572494254 | 12076585572740172 | 12076585572767391 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f4503d10600 | 0x7f43d3a36600 | 12076585572797497 | 12076585572809292 | 12076585572935211 | 12076585572938149 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f4503d10500 | 0x7f43d3a36640 | 12076585572970278 | 12076585572981770 | 12076585573154409 | 12076585573157887 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f4503d10400 | 0x7f43d3a36680 | 12076585573201609 | 12076585573213769 | 12076585573339688 | 12076585573342411 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f4503d10300 | 0x7f43d3a366c0 | 12076585573375502 | 12076585573388007 | 12076585573643205 | 12076585573667465 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f4503d10a00 | 0x7f43d3a36700 | 12076585573695688 | 12076585573706565 | 12076585573952163 | 12076585573971982 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f4503d10900 | 0x7f43d3a36740 | 12076585574010523 | 12076585574022082 | 12076585574148001 | 12076585574150854 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f4503d10800 | 0x7f43d3a36780 | 12076585574184216 | 12076585574196001 | 12076585574378719 | 12076585574381463 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f4503d10700 | 0x7f43d3a367c0 | 12076585574427850 | 12076585574440159 | 12076585574566238 | 12076585574568962 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f4503d10600 | 0x7f43d3a36800 | 12076585574601923 | 12076585574613597 | 12076585574877275 | 12076585574900459 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f4503d10500 | 0x7f43d3a36840 | 12076585574926928 | 12076585574939515 | 12076585575183833 | 12076585575208532 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f4503d10400 | 0x7f43d3a36880 | 12076585575235803 | 12076585575247992 | 12076585575374071 | 12076585575376925 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f4503d10300 | 0x7f43d3a368c0 | 12076585575408584 | 12076585575421591 | 12076585575613429 | 12076585575617382 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f4503d10a00 | 0x7f43d3a36900 | 12076585575659591 | 12076585575672949 | 12076585575800148 | 12076585575802988 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f4503d10900 | 0x7f43d3a36940 | 12076585575836049 | 12076585575849747 | 12076585576131825 | 12076585576159931 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f4503d10800 | 0x7f43d3a36980 | 12076585576189346 | 12076585576200945 | 12076585576446863 | 12076585576478865 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f4503d10700 | 0x7f43d3a369c0 | 12076585576510133 | 12076585576521262 | 12076585576647021 | 12076585576649813 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f4503d10600 | 0x7f43d3a36a00 | 12076585576683836 | 12076585576695341 | 12076585576904139 | 12076585576931316 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f4503d10500 | 0x7f43d3a36a40 | 12076585576968686 | 12076585576980458 | 12076585577107817 | 12076585577110920 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f4503d10400 | 0x7f43d3a36a80 | 12076585577143952 | 12076585577156617 | 12076585577462534 | 12076585577490156 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f4503d10300 | 0x7f43d3a36ac0 | 12076585577518609 | 12076585577531334 | 12076585577783652 | 12076585577810953 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f4503d10a00 | 0x7f43d3a36b00 | 12076585577840668 | 12076585577852451 | 12076585577979330 | 12076585577982211 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f4503d10900 | 0x7f43d3a36b40 | 12076585578020723 | 12076585578034850 | 12076585578262208 | 12076585578290555 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f4503d10800 | 0x7f43d3a36b80 | 12076585578329377 | 12076585578343807 | 12076585578471006 | 12076585578473806 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f4503d10700 | 0x7f43d3a36bc0 | 12076585578506697 | 12076585578518846 | 12076585578876923 | 12076585578899768 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f4503d10600 | 0x7f43d3a36c00 | 12076585578929093 | 12076585578942362 | 12076585579196760 | 12076585579221727 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f4503d10500 | 0x7f43d3a36c40 | 12076585579252053 | 12076585579265400 | 12076585579393719 | 12076585579396562 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f4503d10400 | 0x7f43d3a36c80 | 12076585579428051 | 12076585579439478 | 12076585579683636 | 12076585579710526 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f4503d10300 | 0x7f43d3a36cc0 | 12076585579746373 | 12076585579758836 | 12076585579888115 | 12076585579891282 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f4503d10a00 | 0x7f43d3a36d00 | 12076585579924113 | 12076585579935474 | 12076585580311311 | 12076585580339456 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f4503d10900 | 0x7f43d3a36d40 | 12076585580367739 | 12076585580378511 | 12076585580634509 | 12076585580661796 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f4503d10800 | 0x7f43d3a36d80 | 12076585580691661 | 12076585580703948 | 12076585580833867 | 12076585580836681 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f4503d10700 | 0x7f43d3a36dc0 | 12076585580869271 | 12076585580880747 | 12076585581159465 | 12076585581191882 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f4503d10600 | 0x7f43d3a36e00 | 12076585581229261 | 12076585581241864 | 12076585581376743 | 12076585581379601 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f4503d10500 | 0x7f43d3a36e40 | 12076585581411250 | 12076585581423142 | 12076585581846499 | 12076585581873930 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f4503d10400 | 0x7f43d3a36e80 | 12076585581903135 | 12076585581914018 | 12076585582174176 | 12076585582206228 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f4503d10300 | 0x7f43d3a36ec0 | 12076585582236044 | 12076585582248256 | 12076585582384415 | 12076585582387305 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f4503d10a00 | 0x7f43d3a36f00 | 12076585582420267 | 12076585582431774 | 12076585582746492 | 12076585582773524 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f4503d10900 | 0x7f43d3a36f40 | 12076585582814340 | 12076585582827611 | 12076585582979450 | 12076585582982412 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f4503d10800 | 0x7f43d3a36f80 | 12076585583023278 | 12076585583037209 | 12076585583554005 | 12076585583582208 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f4503d10700 | 0x7f43d3a36fc0 | 12076585583616071 | 12076585583628885 | 12076585583926962 | 12076585583954140 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f4503d10600 | 0x7f43d3a37000 | 12076585583988083 | 12076585584002162 | 12076585584157360 | 12076585584160624 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f4503d10500 | 0x7f43d3a37040 | 12076585584198564 | 12076585584211760 | 12076585584596077 | 12076585584623845 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f4503d10400 | 0x7f43d3a37080 | 12076585584661966 | 12076585584673676 | 12076585584849995 | 12076585584852811 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f4503d10300 | 0x7f43d3a370c0 | 12076585584885672 | 12076585584898314 | 12076585585507590 | 12076585585540270 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f4503d10a00 | 0x7f43d3a37100 | 12076585585569795 | 12076585585582149 | 12076585585909826 | 12076585585936868 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f4503d10900 | 0x7f43d3a37140 | 12076585585968286 | 12076585585979426 | 12076585586157504 | 12076585586161375 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f4503d10800 | 0x7f43d3a37180 | 12076585586195439 | 12076585586206624 | 12076585586661820 | 12076585586688756 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f4503d10700 | 0x7f43d3a371c0 | 12076585586727629 | 12076585586741020 | 12076585586940858 | 12076585586968567 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f4503d10600 | 0x7f43d3a37200 | 12076585586993133 | 12076585587004537 | 12076585587707892 | 12076585587735383 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f4503d10500 | 0x7f43d3a37240 | 12076585587767353 | 12076585587778611 | 12076585588151568 | 12076585588180291 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f4503d10400 | 0x7f43d3a37280 | 12076585588210176 | 12076585588221328 | 12076585588423726 | 12076585588450373 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f4503d10300 | 0x7f43d3a372c0 | 12076585588480179 | 12076585588491566 | 12076585589017001 | 12076585589046322 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f4503d10a00 | 0x7f43d3a37300 | 12076585589087899 | 12076585589099881 | 12076585589323239 | 12076585589350167 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f4503d10900 | 0x7f43d3a37340 | 12076585589381605 | 12076585589393798 | 12076585590192192 | 12076585590220867 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f4503d10800 | 0x7f43d3a37380 | 12076585590250802 | 12076585590263871 | 12076585590707228 | 12076585590733730 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f4503d10700 | 0x7f43d3a373c0 | 12076585590762674 | 12076585590775227 | 12076585591035225 | 12076585591064396 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f4503d10600 | 0x7f43d3a37400 | 12076585591094652 | 12076585591108344 | 12076585591704340 | 12076585591731296 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f4503d10500 | 0x7f43d3a37440 | 12076585591771150 | 12076585591784339 | 12076585592052337 | 12076585592080516 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f4503d10400 | 0x7f43d3a37480 | 12076585592109710 | 12076585592122896 | 12076585593107368 | 12076585593136350 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f4503d10300 | 0x7f43d3a374c0 | 12076585593165163 | 12076585593176008 | 12076585593709603 | 12076585593736346 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f4503d10a00 | 0x7f43d3a37500 | 12076585593769357 | 12076585593780963 | 12076585594052641 | 12076585594081017 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f4503d10900 | 0x7f43d3a37540 | 12076585594109881 | 12076585594121920 | 12076585594864794 | 12076585594891625 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f4503d10800 | 0x7f43d3a37580 | 12076585594929325 | 12076585594940634 | 12076585595255831 | 12076585595287802 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f4503d10700 | 0x7f43d3a375c0 | 12076585595317818 | 12076585595329910 | 12076585596502061 | 12076585596533018 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f4503d10600 | 0x7f43d3a37600 | 12076585596561631 | 12076585596572460 | 12076585597183815 | 12076585597214806 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f4503d10500 | 0x7f43d3a37640 | 12076585597245533 | 12076585597257895 | 12076585597578372 | 12076585597608408 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f4503d10400 | 0x7f43d3a37680 | 12076585597637583 | 12076585597650692 | 12076585598528605 | 12076585598558596 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f4503d10300 | 0x7f43d3a376c0 | 12076585598599532 | 12076585598613267 | 12076585599023985 | 12076585599058636 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f4503d10a00 | 0x7f43d3a37700 | 12076585599090185 | 12076585599102063 | 12076585600651653 | 12076585600726709 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f4503d10900 | 0x7f43d3a37740 | 12076585600761083 | 12076585600773732 | 12076585601569887 | 12076585601641380 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f4503d10800 | 0x7f43d3a37780 | 12076585601676445 | 12076585601687806 | 12076585602102043 | 12076585602174422 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f4503d10700 | 0x7f43d3a377c0 | 12076585602217832 | 12076585602229563 | 12076585603388595 | 12076585603459993 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f4503d10600 | 0x7f43d3a37800 | 12076585603502793 | 12076585603514034 | 12076585604299469 | 12076585604372170 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f4503d10500 | 0x7f43d3a37840 | 12076585604403318 | 12076585604417708 | 12076585607471608 | 12076585607543469 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f4503d10400 | 0x7f43d3a37880 | 12076585607576711 | 12076585607588407 | 12076585609132077 | 12076585609203116 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f4503d10300 | 0x7f43d3a378c0 | 12076585609238131 | 12076585609251277 | 12076585610040391 | 12076585610112047 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f4503d10a00 | 0x7f43d3a37900 | 12076585610143004 | 12076585610155431 | 12076585612437816 | 12076585612509666 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f4503d10900 | 0x7f43d3a37940 | 12076585612556864 | 12076585612568375 | 12076585614104045 | 12076585614175565 |
| 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 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f4503d10800 | 0x7f43d3a37980 | 12076585614207364 | 12076585614220044 | 12076585620275844 | 12076585620347336 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f4503d10700 | 0x7f43d3a379c0 | 12076585620381619 | 12076585620393283 | 12076585623435503 | 12076585623507293 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f4503d10600 | 0x7f43d3a37a00 | 12076585623538572 | 12076585623551983 | 12076585625090692 | 12076585625162943 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 934549 | 934554 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f4503d10500 | 0x7f43d3a37a40 | 12076585625195524 | 12076585625209092 | 12076585629735142 | 12076585629806891 |