989e29cf81
Signed-off-by: Jose Santos <josantos@login1.hpcfund>
39 KiB
39 KiB
| 1 | Dispatch_ID | Kernel_Name | GPU_ID | queue-id | queue-index | pid | tid | grd | Workgroup_Size | LDS_Per_Workgroup | scr | vgpr | SGPR | fbar | sig | obj | DispatchNs | Start_Timestamp | End_Timestamp | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 904000 | 904005 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fca35a04180 | 12075990193071892 | 12075990193119383 | 12075990193445140 | 12075990193551032 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 904000 | 904005 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fca35a35100 | 12075990208121941 | 12075990208226449 | 12075990208233329 | 12075990208238829 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fcb41588900 | 0x7fca35a35140 | 12075990208283181 | 12075990208297008 | 12075990208434447 | 12075990208437748 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fcb41588800 | 0x7fca35a35180 | 12075990208481289 | 12075990208494767 | 12075990208743884 | 12075990208840567 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fcb41588700 | 0x7fca35a351c0 | 12075990208865634 | 12075990208877643 | 12075990209123401 | 12075990209223178 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fcb41588600 | 0x7fca35a35200 | 12075990209249798 | 12075990209261960 | 12075990209387239 | 12075990209390689 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fcb41588500 | 0x7fca35a35240 | 12075990209418481 | 12075990209429958 | 12075990209554757 | 12075990209557830 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fcb41588400 | 0x7fca35a35280 | 12075990209612401 | 12075990209626597 | 12075990209750275 | 12075990209753213 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fcb41588300 | 0x7fca35a352c0 | 12075990209779732 | 12075990209793635 | 12075990210040033 | 12075990210122670 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fcb41588a00 | 0x7fca35a35300 | 12075990210143689 | 12075990210154912 | 12075990210399390 | 12075990210495703 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fcb41588900 | 0x7fca35a35340 | 12075990210516401 | 12075990210527869 | 12075990210652347 | 12075990210655700 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fcb41588800 | 0x7fca35a35380 | 12075990210681829 | 12075990210693147 | 12075990210818106 | 12075990210821268 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fcb41588700 | 0x7fca35a353c0 | 12075990210857886 | 12075990210869466 | 12075990210992984 | 12075990210996113 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fcb41588600 | 0x7fca35a35400 | 12075990211029074 | 12075990211040504 | 12075990211288502 | 12075990211360390 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fcb41588500 | 0x7fca35a35440 | 12075990211382000 | 12075990211393621 | 12075990211637619 | 12075990211705692 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fcb41588400 | 0x7fca35a35480 | 12075990211727142 | 12075990211739058 | 12075990211864017 | 12075990211867062 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fcb41588300 | 0x7fca35a354c0 | 12075990211893952 | 12075990211905936 | 12075990212030895 | 12075990212034022 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fcb41588a00 | 0x7fca35a35500 | 12075990212072073 | 12075990212083375 | 12075990212207854 | 12075990212210931 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fcb41588900 | 0x7fca35a35540 | 12075990212235867 | 12075990212247693 | 12075990212491371 | 12075990212533139 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fcb41588800 | 0x7fca35a35580 | 12075990212553557 | 12075990212565291 | 12075990212808488 | 12075990212873793 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fcb41588700 | 0x7fca35a355c0 | 12075990212894281 | 12075990212906088 | 12075990213030886 | 12075990213033940 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fcb41588600 | 0x7fca35a35600 | 12075990213059898 | 12075990213072326 | 12075990213197445 | 12075990213200580 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fcb41588500 | 0x7fca35a35640 | 12075990213235695 | 12075990213246885 | 12075990213371043 | 12075990213374102 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fcb41588400 | 0x7fca35a35680 | 12075990213399880 | 12075990213412003 | 12075990213701921 | 12075990213742607 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fcb41588300 | 0x7fca35a356c0 | 12075990213763316 | 12075990213776000 | 12075990214020318 | 12075990214120149 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fcb41588a00 | 0x7fca35a35700 | 12075990214141388 | 12075990214153597 | 12075990214277435 | 12075990214280667 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fcb41588900 | 0x7fca35a35740 | 12075990214307737 | 12075990214319035 | 12075990214443674 | 12075990214447056 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fcb41588800 | 0x7fca35a35780 | 12075990214480949 | 12075990214493754 | 12075990214618232 | 12075990214621260 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fcb41588700 | 0x7fca35a357c0 | 12075990214646457 | 12075990214658872 | 12075990214910710 | 12075990214963165 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fcb41588600 | 0x7fca35a35800 | 12075990214983624 | 12075990214998869 | 12075990215284787 | 12075990215362217 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fcb41588500 | 0x7fca35a35840 | 12075990215383587 | 12075990215395826 | 12075990215520784 | 12075990215524479 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fcb41588400 | 0x7fca35a35880 | 12075990215549505 | 12075990215560944 | 12075990215686223 | 12075990215689545 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fcb41588300 | 0x7fca35a358c0 | 12075990215725382 | 12075990215738863 | 12075990215863821 | 12075990215866885 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fcb41588a00 | 0x7fca35a35900 | 12075990215893625 | 12075990215905101 | 12075990216151659 | 12075990216229770 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fcb41588900 | 0x7fca35a35940 | 12075990216251009 | 12075990216269578 | 12075990216513736 | 12075990216591692 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fcb41588800 | 0x7fca35a35980 | 12075990216611870 | 12075990216623015 | 12075990216747334 | 12075990216750628 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fcb41588700 | 0x7fca35a359c0 | 12075990216778319 | 12075990216790213 | 12075990216915812 | 12075990216919271 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fcb41588600 | 0x7fca35a35a00 | 12075990216954717 | 12075990216966532 | 12075990217090851 | 12075990217094076 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fcb41588500 | 0x7fca35a35a40 | 12075990217121968 | 12075990217133730 | 12075990217385088 | 12075990217415203 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fcb41588400 | 0x7fca35a35a80 | 12075990217435460 | 12075990217446847 | 12075990217690365 | 12075990217740126 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fcb41588300 | 0x7fca35a35ac0 | 12075990217762598 | 12075990217775165 | 12075990217900123 | 12075990217903340 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fcb41588a00 | 0x7fca35a35b00 | 12075990217931642 | 12075990217943803 | 12075990218069562 | 12075990218072684 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fcb41588900 | 0x7fca35a35b40 | 12075990218107750 | 12075990218118842 | 12075990218244120 | 12075990218247039 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fcb41588800 | 0x7fca35a35b80 | 12075990218272977 | 12075990218284280 | 12075990218534198 | 12075990218554500 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fcb41588700 | 0x7fca35a35bc0 | 12075990218576391 | 12075990218587797 | 12075990218832115 | 12075990218851452 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fcb41588600 | 0x7fca35a35c00 | 12075990218871469 | 12075990218882835 | 12075990219006994 | 12075990219010187 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fcb41588500 | 0x7fca35a35c40 | 12075990219036105 | 12075990219047793 | 12075990219174192 | 12075990219177087 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fcb41588400 | 0x7fca35a35c80 | 12075990219213094 | 12075990219225232 | 12075990219350351 | 12075990219353294 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fcb41588300 | 0x7fca35a35cc0 | 12075990219379393 | 12075990219390510 | 12075990219650348 | 12075990219674231 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fcb41588a00 | 0x7fca35a35d00 | 12075990219694028 | 12075990219705388 | 12075990219984905 | 12075990220014323 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fcb41588900 | 0x7fca35a35d40 | 12075990220034330 | 12075990220046185 | 12075990220171303 | 12075990220174901 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fcb41588800 | 0x7fca35a35d80 | 12075990220201922 | 12075990220215143 | 12075990220343142 | 12075990220346230 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fcb41588700 | 0x7fca35a35dc0 | 12075990220381906 | 12075990220393701 | 12075990220519140 | 12075990220522097 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fcb41588600 | 0x7fca35a35e00 | 12075990220548145 | 12075990220559300 | 12075990220812258 | 12075990220836080 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fcb41588500 | 0x7fca35a35e40 | 12075990220856739 | 12075990220869537 | 12075990221114175 | 12075990221142700 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fcb41588400 | 0x7fca35a35e80 | 12075990221164310 | 12075990221176895 | 12075990221301693 | 12075990221305082 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fcb41588300 | 0x7fca35a35ec0 | 12075990221331240 | 12075990221343453 | 12075990221472412 | 12075990221475478 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fcb41588a00 | 0x7fca35a35f00 | 12075990221511906 | 12075990221524891 | 12075990221649850 | 12075990221652808 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fcb41588900 | 0x7fca35a35f40 | 12075990221678706 | 12075990221690810 | 12075990221950968 | 12075990221970198 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fcb41588800 | 0x7fca35a35f80 | 12075990221999452 | 12075990222016407 | 12075990222264565 | 12075990222291956 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fcb41588700 | 0x7fca35a35fc0 | 12075990222313846 | 12075990222326804 | 12075990222452403 | 12075990222455420 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fcb41588600 | 0x7fca35a36000 | 12075990222481688 | 12075990222493523 | 12075990222630002 | 12075990222633220 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fcb41588500 | 0x7fca35a36040 | 12075990222669698 | 12075990222680881 | 12075990222805040 | 12075990222808005 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fcb41588400 | 0x7fca35a36080 | 12075990222834344 | 12075990222846320 | 12075990223106477 | 12075990223130033 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fcb41588300 | 0x7fca35a360c0 | 12075990223151323 | 12075990223162637 | 12075990223407435 | 12075990223429961 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fcb41588a00 | 0x7fca35a36100 | 12075990223449667 | 12075990223460874 | 12075990223585513 | 12075990223588465 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fcb41588900 | 0x7fca35a36140 | 12075990223615506 | 12075990223626953 | 12075990223769192 | 12075990223772277 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fcb41588800 | 0x7fca35a36180 | 12075990223808113 | 12075990223819751 | 12075990223944230 | 12075990223947352 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fcb41588700 | 0x7fca35a361c0 | 12075990223973741 | 12075990223984710 | 12075990224242467 | 12075990224266125 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fcb41588600 | 0x7fca35a36200 | 12075990224285551 | 12075990224297027 | 12075990224541505 | 12075990224564249 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fcb41588500 | 0x7fca35a36240 | 12075990224584336 | 12075990224595744 | 12075990224720863 | 12075990224723966 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fcb41588400 | 0x7fca35a36280 | 12075990224749583 | 12075990224760863 | 12075990224910462 | 12075990224913528 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fcb41588300 | 0x7fca35a362c0 | 12075990224966146 | 12075990224977981 | 12075990225103420 | 12075990225106717 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fcb41588a00 | 0x7fca35a36300 | 12075990225131834 | 12075990225143259 | 12075990225394617 | 12075990225418787 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fcb41588900 | 0x7fca35a36340 | 12075990225441810 | 12075990225453817 | 12075990225700375 | 12075990225719506 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fcb41588800 | 0x7fca35a36380 | 12075990225742428 | 12075990225753974 | 12075990225879253 | 12075990225882438 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fcb41588700 | 0x7fca35a363c0 | 12075990225910020 | 12075990225921013 | 12075990226078611 | 12075990226081889 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fcb41588600 | 0x7fca35a36400 | 12075990226117786 | 12075990226129171 | 12075990226253970 | 12075990226256995 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fcb41588500 | 0x7fca35a36440 | 12075990226283564 | 12075990226296049 | 12075990226549487 | 12075990226572892 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fcb41588400 | 0x7fca35a36480 | 12075990226593209 | 12075990226604207 | 12075990226849164 | 12075990226871577 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fcb41588300 | 0x7fca35a364c0 | 12075990226891213 | 12075990226902764 | 12075990227029003 | 12075990227032045 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fcb41588a00 | 0x7fca35a36500 | 12075990227059726 | 12075990227071242 | 12075990227236681 | 12075990227239851 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fcb41588900 | 0x7fca35a36540 | 12075990227275638 | 12075990227288041 | 12075990227414119 | 12075990227417151 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fcb41588800 | 0x7fca35a36580 | 12075990227442778 | 12075990227453959 | 12075990227708037 | 12075990227727147 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fcb41588700 | 0x7fca35a365c0 | 12075990227751161 | 12075990227762436 | 12075990228009954 | 12075990228034328 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fcb41588600 | 0x7fca35a36600 | 12075990228054104 | 12075990228065154 | 12075990228189793 | 12075990228193143 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fcb41588500 | 0x7fca35a36640 | 12075990228218500 | 12075990228229472 | 12075990228401151 | 12075990228404175 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fcb41588400 | 0x7fca35a36680 | 12075990228439340 | 12075990228450750 | 12075990228576669 | 12075990228579791 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fcb41588300 | 0x7fca35a366c0 | 12075990228605870 | 12075990228617149 | 12075990228870427 | 12075990228893134 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fcb41588a00 | 0x7fca35a36700 | 12075990228916277 | 12075990228928986 | 12075990229174104 | 12075990229201657 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fcb41588900 | 0x7fca35a36740 | 12075990229221604 | 12075990229233463 | 12075990229359062 | 12075990229362376 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fcb41588800 | 0x7fca35a36780 | 12075990229388324 | 12075990229400982 | 12075990229582900 | 12075990229586242 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fcb41588700 | 0x7fca35a367c0 | 12075990229622579 | 12075990229633460 | 12075990229761139 | 12075990229764333 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fcb41588600 | 0x7fca35a36800 | 12075990229790131 | 12075990229802418 | 12075990230065456 | 12075990230089247 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fcb41588500 | 0x7fca35a36840 | 12075990230110035 | 12075990230122416 | 12075990230368013 | 12075990230391048 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fcb41588400 | 0x7fca35a36880 | 12075990230411335 | 12075990230423853 | 12075990230549292 | 12075990230552478 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fcb41588300 | 0x7fca35a368c0 | 12075990230579538 | 12075990230590891 | 12075990230781450 | 12075990230785411 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fcb41588a00 | 0x7fca35a36900 | 12075990230821317 | 12075990230832649 | 12075990230959528 | 12075990230962780 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fcb41588900 | 0x7fca35a36940 | 12075990230989450 | 12075990231001128 | 12075990231283205 | 12075990231310326 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fcb41588800 | 0x7fca35a36980 | 12075990231331465 | 12075990231343845 | 12075990231591363 | 12075990231617717 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fcb41588700 | 0x7fca35a369c0 | 12075990231636061 | 12075990231648802 | 12075990231774881 | 12075990231778005 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fcb41588600 | 0x7fca35a36a00 | 12075990231804815 | 12075990231816641 | 12075990232025439 | 12075990232048979 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fcb41588500 | 0x7fca35a36a40 | 12075990232079596 | 12075990232091038 | 12075990232218557 | 12075990232221770 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fcb41588400 | 0x7fca35a36a80 | 12075990232248109 | 12075990232259677 | 12075990232565754 | 12075990232588562 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fcb41588300 | 0x7fca35a36ac0 | 12075990232611665 | 12075990232624953 | 12075990232872471 | 12075990232898898 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fcb41588a00 | 0x7fca35a36b00 | 12075990232919046 | 12075990232930551 | 12075990233058710 | 12075990233061911 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fcb41588900 | 0x7fca35a36b40 | 12075990233089142 | 12075990233100469 | 12075990233327347 | 12075990233355878 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fcb41588800 | 0x7fca35a36b80 | 12075990233386094 | 12075990233397427 | 12075990233523345 | 12075990233526575 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fcb41588700 | 0x7fca35a36bc0 | 12075990233552874 | 12075990233563985 | 12075990233891502 | 12075990233910719 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fcb41588600 | 0x7fca35a36c00 | 12075990233933732 | 12075990233944942 | 12075990234196140 | 12075990234223350 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fcb41588500 | 0x7fca35a36c40 | 12075990234243958 | 12075990234255179 | 12075990234383658 | 12075990234386804 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fcb41588400 | 0x7fca35a36c80 | 12075990234414255 | 12075990234425578 | 12075990234668935 | 12075990234695106 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fcb41588300 | 0x7fca35a36cc0 | 12075990234725413 | 12075990234738375 | 12075990234867814 | 12075990234871043 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fcb41588a00 | 0x7fca35a36d00 | 12075990234897072 | 12075990234907973 | 12075990235283010 | 12075990235306783 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fcb41588900 | 0x7fca35a36d40 | 12075990235327622 | 12075990235338849 | 12075990235593727 | 12075990235620226 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fcb41588800 | 0x7fca35a36d80 | 12075990235640123 | 12075990235651327 | 12075990235779966 | 12075990235783189 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fcb41588700 | 0x7fca35a36dc0 | 12075990235808826 | 12075990235819965 | 12075990236098043 | 12075990236132177 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fcb41588600 | 0x7fca35a36e00 | 12075990236163536 | 12075990236175322 | 12075990236311641 | 12075990236314897 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fcb41588500 | 0x7fca35a36e40 | 12075990236341426 | 12075990236352440 | 12075990236798837 | 12075990236821178 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fcb41588400 | 0x7fca35a36e80 | 12075990236843419 | 12075990236855156 | 12075990237109074 | 12075990237140110 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fcb41588300 | 0x7fca35a36ec0 | 12075990237161019 | 12075990237172753 | 12075990237309232 | 12075990237312551 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fcb41588a00 | 0x7fca35a36f00 | 12075990237338158 | 12075990237349552 | 12075990237663789 | 12075990237690243 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fcb41588900 | 0x7fca35a36f40 | 12075990237719948 | 12075990237731148 | 12075990237881547 | 12075990237884824 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fcb41588800 | 0x7fca35a36f80 | 12075990237910953 | 12075990237922187 | 12075990238438342 | 12075990238461747 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fcb41588700 | 0x7fca35a36fc0 | 12075990238483287 | 12075990238494502 | 12075990238791619 | 12075990238810485 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fcb41588600 | 0x7fca35a37000 | 12075990238833417 | 12075990238844578 | 12075990238999137 | 12075990239003884 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fcb41588500 | 0x7fca35a37040 | 12075990239030243 | 12075990239041377 | 12075990239426173 | 12075990239449302 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fcb41588400 | 0x7fca35a37080 | 12075990239483556 | 12075990239494493 | 12075990239670331 | 12075990239673569 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fcb41588300 | 0x7fca35a370c0 | 12075990239698615 | 12075990239710331 | 12075990240318645 | 12075990240346359 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fcb41588a00 | 0x7fca35a37100 | 12075990240365895 | 12075990240378645 | 12075990240705682 | 12075990240731785 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fcb41588900 | 0x7fca35a37140 | 12075990240753987 | 12075990240764882 | 12075990240942800 | 12075990240946054 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fcb41588800 | 0x7fca35a37180 | 12075990240971271 | 12075990240982320 | 12075990241437196 | 12075990241470819 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fcb41588700 | 0x7fca35a371c0 | 12075990241502237 | 12075990241512875 | 12075990241711433 | 12075990241737645 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fcb41588600 | 0x7fca35a37200 | 12075990241756600 | 12075990241770313 | 12075990242471586 | 12075990242499741 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fcb41588500 | 0x7fca35a37240 | 12075990242523615 | 12075990242534786 | 12075990242907263 | 12075990242933427 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fcb41588400 | 0x7fca35a37280 | 12075990242953805 | 12075990242965022 | 12075990243167580 | 12075990243198670 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fcb41588300 | 0x7fca35a372c0 | 12075990243219479 | 12075990243232540 | 12075990243757495 | 12075990243783637 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fcb41588a00 | 0x7fca35a37300 | 12075990243814184 | 12075990243826454 | 12075990244049973 | 12075990244076842 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fcb41588900 | 0x7fca35a37340 | 12075990244097811 | 12075990244109012 | 12075990244906125 | 12075990244932061 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fcb41588800 | 0x7fca35a37380 | 12075990244951317 | 12075990244962124 | 12075990245381481 | 12075990245415660 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fcb41588700 | 0x7fca35a373c0 | 12075990245435627 | 12075990245446920 | 12075990245671398 | 12075990245695260 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fcb41588600 | 0x7fca35a37400 | 12075990245720407 | 12075990245731398 | 12075990246327712 | 12075990246354816 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fcb41588500 | 0x7fca35a37440 | 12075990246386464 | 12075990246397632 | 12075990246666429 | 12075990246692744 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fcb41588400 | 0x7fca35a37480 | 12075990246714143 | 12075990246725469 | 12075990247709300 | 12075990247736543 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fcb41588300 | 0x7fca35a374c0 | 12075990247757803 | 12075990247768660 | 12075990248283055 | 12075990248310560 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fcb41588a00 | 0x7fca35a37500 | 12075990248330487 | 12075990248341455 | 12075990248612492 | 12075990248638910 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fcb41588900 | 0x7fca35a37540 | 12075990248659529 | 12075990248670572 | 12075990249407525 | 12075990249434759 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fcb41588800 | 0x7fca35a37580 | 12075990249465056 | 12075990249476485 | 12075990249790722 | 12075990249816509 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fcb41588700 | 0x7fca35a375c0 | 12075990249838370 | 12075990249849281 | 12075990251019991 | 12075990251053758 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fcb41588600 | 0x7fca35a37600 | 12075990251077593 | 12075990251089110 | 12075990251698065 | 12075990251724495 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fcb41588500 | 0x7fca35a37640 | 12075990251744171 | 12075990251754864 | 12075990252072622 | 12075990252100544 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fcb41588400 | 0x7fca35a37680 | 12075990252122504 | 12075990252133901 | 12075990253011493 | 12075990253039328 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fcb41588300 | 0x7fca35a376c0 | 12075990253071518 | 12075990253082853 | 12075990253493409 | 12075990253520433 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fcb41588a00 | 0x7fca35a37700 | 12075990253541141 | 12075990253553409 | 12075990255101555 | 12075990255172463 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fcb41588900 | 0x7fca35a37740 | 12075990255194283 | 12075990255206674 | 12075990255999947 | 12075990256072305 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fcb41588800 | 0x7fca35a37780 | 12075990256091411 | 12075990256103651 | 12075990256517248 | 12075990256590879 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fcb41588700 | 0x7fca35a377c0 | 12075990256615214 | 12075990256626366 | 12075990257784597 | 12075990257855239 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fcb41588600 | 0x7fca35a37800 | 12075990257887038 | 12075990257900117 | 12075990258685391 | 12075990258759559 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fcb41588500 | 0x7fca35a37840 | 12075990258781660 | 12075990258794510 | 12075990261844886 | 12075990261915054 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fcb41588400 | 0x7fca35a37880 | 12075990261935441 | 12075990261946966 | 12075990263487434 | 12075990263562024 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fcb41588300 | 0x7fca35a378c0 | 12075990263580970 | 12075990263593033 | 12075990264381827 | 12075990264452379 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fcb41588a00 | 0x7fca35a37900 | 12075990264474781 | 12075990264486466 | 12075990266767409 | 12075990266837923 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fcb41588900 | 0x7fca35a37940 | 12075990266869481 | 12075990266881328 | 12075990268416996 | 12075990268490804 |
| 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 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fcb41588800 | 0x7fca35a37980 | 12075990268513987 | 12075990268525316 | 12075990274580629 | 12075990274650352 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fcb41588700 | 0x7fca35a379c0 | 12075990274673745 | 12075990274685109 | 12075990277726685 | 12075990277797731 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fcb41588600 | 0x7fca35a37a00 | 12075990277818199 | 12075990277830205 | 12075990279369073 | 12075990279444311 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 904000 | 904005 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fcb41588500 | 0x7fca35a37a40 | 12075990279464158 | 12075990279475632 | 12075990284001998 | 12075990284072632 |