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 | 805626 | 805631 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fb185e04180 | 12074086852499837 | 12074086852546520 | 12074086852868916 | 12074086852973757 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 805626 | 805631 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fb185e35100 | 12074086867987925 | 12074086868085971 | 12074086868093171 | 12074086868099052 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fb291b5d900 | 0x7fb185e35140 | 12074086868143194 | 12074086868158130 | 12074086868289009 | 12074086868292682 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fb291b5d800 | 0x7fb185e35180 | 12074086868336994 | 12074086868350448 | 12074086868593966 | 12074086868690561 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fb291b5d700 | 0x7fb185e351c0 | 12074086868714816 | 12074086868726445 | 12074086868969643 | 12074086869067020 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fb291b5d600 | 0x7fb185e35200 | 12074086869091676 | 12074086869103241 | 12074086869228840 | 12074086869232368 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fb291b5d500 | 0x7fb185e35240 | 12074086869258837 | 12074086869270600 | 12074086869395718 | 12074086869399128 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fb291b5d400 | 0x7fb185e35280 | 12074086869449241 | 12074086869462278 | 12074086869586437 | 12074086869589692 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fb291b5d300 | 0x7fb185e352c0 | 12074086869615590 | 12074086869628836 | 12074086869880994 | 12074086869977091 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fb291b5da00 | 0x7fb185e35300 | 12074086869996578 | 12074086870014593 | 12074086870258430 | 12074086870357949 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fb291b5d900 | 0x7fb185e35340 | 12074086870378217 | 12074086870389469 | 12074086870514268 | 12074086870517956 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fb291b5d800 | 0x7fb185e35380 | 12074086870543684 | 12074086870555387 | 12074086870680186 | 12074086870683414 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fb291b5d700 | 0x7fb185e353c0 | 12074086870720232 | 12074086870736826 | 12074086870861145 | 12074086870864430 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fb291b5d600 | 0x7fb185e35400 | 12074086870889918 | 12074086870901304 | 12074086871149942 | 12074086871248123 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fb291b5d500 | 0x7fb185e35440 | 12074086871268351 | 12074086871279861 | 12074086871527058 | 12074086871594998 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fb291b5d400 | 0x7fb185e35480 | 12074086871616187 | 12074086871627697 | 12074086871752016 | 12074086871755275 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fb291b5d300 | 0x7fb185e354c0 | 12074086871780072 | 12074086871792816 | 12074086871918095 | 12074086871921414 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fb291b5da00 | 0x7fb185e35500 | 12074086871957301 | 12074086871971534 | 12074086872096013 | 12074086872099385 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fb291b5d900 | 0x7fb185e35540 | 12074086872125824 | 12074086872138732 | 12074086872386410 | 12074086872453333 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fb291b5d800 | 0x7fb185e35580 | 12074086872473370 | 12074086872486729 | 12074086872733127 | 12074086872799005 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fb291b5d700 | 0x7fb185e355c0 | 12074086872818832 | 12074086872832326 | 12074086872956645 | 12074086872959794 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fb291b5d600 | 0x7fb185e35600 | 12074086872985211 | 12074086872997604 | 12074086873123043 | 12074086873126223 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fb291b5d500 | 0x7fb185e35640 | 12074086873162180 | 12074086873175043 | 12074086873299681 | 12074086873302951 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fb291b5d400 | 0x7fb185e35680 | 12074086873328679 | 12074086873341281 | 12074086873590559 | 12074086873657630 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fb291b5d300 | 0x7fb185e356c0 | 12074086873677257 | 12074086873690878 | 12074086873935515 | 12074086874006939 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fb291b5da00 | 0x7fb185e35700 | 12074086874029461 | 12074086874042714 | 12074086874166873 | 12074086874170072 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fb291b5d900 | 0x7fb185e35740 | 12074086874196612 | 12074086874211833 | 12074086874336952 | 12074086874340369 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fb291b5d800 | 0x7fb185e35780 | 12074086874375664 | 12074086874391351 | 12074086874515670 | 12074086874519001 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fb291b5d700 | 0x7fb185e357c0 | 12074086874543556 | 12074086874557269 | 12074086874811507 | 12074086874863050 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fb291b5d600 | 0x7fb185e35800 | 12074086874882156 | 12074086874898386 | 12074086875145104 | 12074086875224462 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fb291b5d500 | 0x7fb185e35840 | 12074086875245140 | 12074086875256463 | 12074086875381102 | 12074086875384679 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fb291b5d400 | 0x7fb185e35880 | 12074086875409445 | 12074086875420781 | 12074086875546540 | 12074086875550047 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fb291b5d300 | 0x7fb185e358c0 | 12074086875585082 | 12074086875598860 | 12074086875723338 | 12074086875726685 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fb291b5da00 | 0x7fb185e35900 | 12074086875751551 | 12074086875764458 | 12074086876013576 | 12074086876070584 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fb291b5d900 | 0x7fb185e35940 | 12074086876091142 | 12074086876110535 | 12074086876354692 | 12074086876409213 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fb291b5d800 | 0x7fb185e35980 | 12074086876429561 | 12074086876440292 | 12074086876564610 | 12074086876568158 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fb291b5d700 | 0x7fb185e359c0 | 12074086876593485 | 12074086876605410 | 12074086876731489 | 12074086876734868 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fb291b5d600 | 0x7fb185e35a00 | 12074086876769312 | 12074086876783488 | 12074086876907647 | 12074086876911076 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fb291b5d500 | 0x7fb185e35a40 | 12074086876936653 | 12074086876949567 | 12074086877200764 | 12074086877232352 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fb291b5d400 | 0x7fb185e35a80 | 12074086877252340 | 12074086877265404 | 12074086877509241 | 12074086877534314 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fb291b5d300 | 0x7fb185e35ac0 | 12074086877556996 | 12074086877569881 | 12074086877695000 | 12074086877698459 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fb291b5da00 | 0x7fb185e35b00 | 12074086877724928 | 12074086877738999 | 12074086877864598 | 12074086877868034 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fb291b5d900 | 0x7fb185e35b40 | 12074086877903209 | 12074086877915638 | 12074086878040116 | 12074086878043500 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fb291b5d800 | 0x7fb185e35b80 | 12074086878070299 | 12074086878083156 | 12074086878346353 | 12074086878367422 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fb291b5d700 | 0x7fb185e35bc0 | 12074086878388170 | 12074086878400913 | 12074086878647791 | 12074086878671887 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fb291b5d600 | 0x7fb185e35c00 | 12074086878690161 | 12074086878703310 | 12074086878827949 | 12074086878831153 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fb291b5d500 | 0x7fb185e35c40 | 12074086878856560 | 12074086878869068 | 12074086878995947 | 12074086878999125 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fb291b5d400 | 0x7fb185e35c80 | 12074086879037917 | 12074086879050347 | 12074086879174666 | 12074086879177998 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fb291b5d300 | 0x7fb185e35cc0 | 12074086879204938 | 12074086879218025 | 12074086879476263 | 12074086879503332 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fb291b5da00 | 0x7fb185e35d00 | 12074086879523480 | 12074086879536102 | 12074086879780420 | 12074086879803750 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fb291b5d900 | 0x7fb185e35d40 | 12074086879823908 | 12074086879837059 | 12074086879962338 | 12074086879965761 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fb291b5d800 | 0x7fb185e35d80 | 12074086879990107 | 12074086880002658 | 12074086880131616 | 12074086880135186 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fb291b5d700 | 0x7fb185e35dc0 | 12074086880171073 | 12074086880183296 | 12074086880307775 | 12074086880311113 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fb291b5d600 | 0x7fb185e35e00 | 12074086880336240 | 12074086880349214 | 12074086880604892 | 12074086880628783 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fb291b5d500 | 0x7fb185e35e40 | 12074086880648300 | 12074086880660891 | 12074086880908089 | 12074086880931676 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fb291b5d400 | 0x7fb185e35e80 | 12074086880955029 | 12074086880967929 | 12074086881092567 | 12074086881096011 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fb291b5d300 | 0x7fb185e35ec0 | 12074086881121629 | 12074086881134327 | 12074086881264726 | 12074086881268001 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fb291b5da00 | 0x7fb185e35f00 | 12074086881304158 | 12074086881316885 | 12074086881442324 | 12074086881445571 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fb291b5d900 | 0x7fb185e35f40 | 12074086881471740 | 12074086881485044 | 12074086881741201 | 12074086881768731 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fb291b5d800 | 0x7fb185e35f80 | 12074086881788418 | 12074086881801201 | 12074086882044558 | 12074086882072947 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fb291b5d700 | 0x7fb185e35fc0 | 12074086882093355 | 12074086882106318 | 12074086882231277 | 12074086882234647 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fb291b5d600 | 0x7fb185e36000 | 12074086882260064 | 12074086882272716 | 12074086882411275 | 12074086882414652 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fb291b5d500 | 0x7fb185e36040 | 12074086882451821 | 12074086882464714 | 12074086882589993 | 12074086882593354 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fb291b5d400 | 0x7fb185e36080 | 12074086882618631 | 12074086882631273 | 12074086882890150 | 12074086882909772 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fb291b5d300 | 0x7fb185e360c0 | 12074086882929839 | 12074086882942630 | 12074086883189347 | 12074086883218004 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fb291b5da00 | 0x7fb185e36100 | 12074086883237330 | 12074086883250307 | 12074086883375106 | 12074086883378663 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fb291b5d900 | 0x7fb185e36140 | 12074086883403439 | 12074086883415905 | 12074086883558944 | 12074086883562424 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fb291b5d800 | 0x7fb185e36180 | 12074086883597099 | 12074086883610463 | 12074086883735742 | 12074086883739143 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fb291b5d700 | 0x7fb185e361c0 | 12074086883764319 | 12074086883776702 | 12074086884034939 | 12074086884063055 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fb291b5d600 | 0x7fb185e36200 | 12074086884083663 | 12074086884096859 | 12074086884341657 | 12074086884368983 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fb291b5d500 | 0x7fb185e36240 | 12074086884391114 | 12074086884403736 | 12074086884529335 | 12074086884532547 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fb291b5d400 | 0x7fb185e36280 | 12074086884557173 | 12074086884569974 | 12074086884719253 | 12074086884722670 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fb291b5d300 | 0x7fb185e362c0 | 12074086884773825 | 12074086884786132 | 12074086884911411 | 12074086884915058 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fb291b5da00 | 0x7fb185e36300 | 12074086884939513 | 12074086884952691 | 12074086885206288 | 12074086885237006 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fb291b5d900 | 0x7fb185e36340 | 12074086885256552 | 12074086885269328 | 12074086885514925 | 12074086885538025 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fb291b5d800 | 0x7fb185e36380 | 12074086885558423 | 12074086885570925 | 12074086885695884 | 12074086885699265 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fb291b5d700 | 0x7fb185e363c0 | 12074086885725133 | 12074086885737963 | 12074086885895242 | 12074086885898535 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fb291b5d600 | 0x7fb185e36400 | 12074086885935384 | 12074086885948041 | 12074086886073160 | 12074086886076736 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fb291b5d500 | 0x7fb185e36440 | 12074086886098386 | 12074086886114120 | 12074086886370117 | 12074086886394517 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fb291b5d400 | 0x7fb185e36480 | 12074086886415436 | 12074086886427717 | 12074086886673954 | 12074086886697099 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fb291b5d300 | 0x7fb185e364c0 | 12074086886716415 | 12074086886728994 | 12074086886854753 | 12074086886858038 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fb291b5da00 | 0x7fb185e36500 | 12074086886882573 | 12074086886895552 | 12074086887060191 | 12074086887063570 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fb291b5d900 | 0x7fb185e36540 | 12074086887100619 | 12074086887119710 | 12074086887245949 | 12074086887249555 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fb291b5d800 | 0x7fb185e36580 | 12074086887274963 | 12074086887289468 | 12074086887542906 | 12074086887570933 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fb291b5d700 | 0x7fb185e365c0 | 12074086887590970 | 12074086887603546 | 12074086887849623 | 12074086887876711 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fb291b5d600 | 0x7fb185e36600 | 12074086887898211 | 12074086887910903 | 12074086888037941 | 12074086888041597 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fb291b5d500 | 0x7fb185e36640 | 12074086888067445 | 12074086888080821 | 12074086888253619 | 12074086888256997 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fb291b5d400 | 0x7fb185e36680 | 12074086888292363 | 12074086888305459 | 12074086888431378 | 12074086888434838 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fb291b5d300 | 0x7fb185e366c0 | 12074086888460556 | 12074086888472977 | 12074086888725295 | 12074086888751296 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fb291b5da00 | 0x7fb185e36700 | 12074086888771894 | 12074086888783694 | 12074086889028332 | 12074086889053247 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fb291b5d900 | 0x7fb185e36740 | 12074086889072753 | 12074086889085291 | 12074086889210890 | 12074086889214296 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fb291b5d800 | 0x7fb185e36780 | 12074086889239513 | 12074086889252490 | 12074086889436008 | 12074086889439424 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fb291b5d700 | 0x7fb185e367c0 | 12074086889476724 | 12074086889488968 | 12074086889615686 | 12074086889618988 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fb291b5d600 | 0x7fb185e36800 | 12074086889644365 | 12074086889657126 | 12074086889919524 | 12074086889939343 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fb291b5d500 | 0x7fb185e36840 | 12074086889957898 | 12074086889970243 | 12074086890219201 | 12074086890247195 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fb291b5d400 | 0x7fb185e36880 | 12074086890266631 | 12074086890279200 | 12074086890405119 | 12074086890408605 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fb291b5d300 | 0x7fb185e368c0 | 12074086890433421 | 12074086890446079 | 12074086890637117 | 12074086890640616 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fb291b5da00 | 0x7fb185e36900 | 12074086890675551 | 12074086890688156 | 12074086890815515 | 12074086890819098 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fb291b5d900 | 0x7fb185e36940 | 12074086890844726 | 12074086890856955 | 12074086891139512 | 12074086891168006 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fb291b5d800 | 0x7fb185e36980 | 12074086891187993 | 12074086891200631 | 12074086891454229 | 12074086891481258 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fb291b5d700 | 0x7fb185e369c0 | 12074086891502037 | 12074086891514868 | 12074086891640147 | 12074086891643510 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fb291b5d600 | 0x7fb185e36a00 | 12074086891668136 | 12074086891680467 | 12074086891889425 | 12074086891915886 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fb291b5d500 | 0x7fb185e36a40 | 12074086891945852 | 12074086891959184 | 12074086892087183 | 12074086892090691 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fb291b5d400 | 0x7fb185e36a80 | 12074086892115767 | 12074086892127983 | 12074086892433900 | 12074086892457763 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fb291b5d300 | 0x7fb185e36ac0 | 12074086892477630 | 12074086892490219 | 12074086892737417 | 12074086892760395 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fb291b5da00 | 0x7fb185e36b00 | 12074086892779551 | 12074086892791816 | 12074086892919015 | 12074086892922426 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fb291b5d900 | 0x7fb185e36b40 | 12074086892947292 | 12074086892959975 | 12074086893186532 | 12074086893214759 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fb291b5d800 | 0x7fb185e36b80 | 12074086893246188 | 12074086893258372 | 12074086893385891 | 12074086893389284 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fb291b5d700 | 0x7fb185e36bc0 | 12074086893415162 | 12074086893427810 | 12074086893756447 | 12074086893779719 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fb291b5d600 | 0x7fb185e36c00 | 12074086893800488 | 12074086893812767 | 12074086894064764 | 12074086894099022 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fb291b5d500 | 0x7fb185e36c40 | 12074086894118719 | 12074086894131484 | 12074086894259802 | 12074086894263468 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fb291b5d400 | 0x7fb185e36c80 | 12074086894288945 | 12074086894301722 | 12074086894545720 | 12074086894572372 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fb291b5d300 | 0x7fb185e36cc0 | 12074086894602217 | 12074086894615159 | 12074086894744758 | 12074086894748209 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fb291b5da00 | 0x7fb185e36d00 | 12074086894773395 | 12074086894785397 | 12074086895161074 | 12074086895185962 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fb291b5d900 | 0x7fb185e36d40 | 12074086895205438 | 12074086895218193 | 12074086895476271 | 12074086895503101 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fb291b5d800 | 0x7fb185e36d80 | 12074086895525844 | 12074086895538350 | 12074086895667469 | 12074086895671104 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fb291b5d700 | 0x7fb185e36dc0 | 12074086895696491 | 12074086895709389 | 12074086895987626 | 12074086896017227 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fb291b5d600 | 0x7fb185e36e00 | 12074086896047383 | 12074086896059945 | 12074086896195464 | 12074086896199014 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fb291b5d500 | 0x7fb185e36e40 | 12074086896224291 | 12074086896236744 | 12074086896684419 | 12074086896708050 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fb291b5d400 | 0x7fb185e36e80 | 12074086896728919 | 12074086896742019 | 12074086897010496 | 12074086897038424 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fb291b5d300 | 0x7fb185e36ec0 | 12074086897064032 | 12074086897076896 | 12074086897211774 | 12074086897215303 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fb291b5da00 | 0x7fb185e36f00 | 12074086897240760 | 12074086897253374 | 12074086897567931 | 12074086897591021 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fb291b5d900 | 0x7fb185e36f40 | 12074086897622469 | 12074086897634810 | 12074086897786009 | 12074086897789490 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fb291b5d800 | 0x7fb185e36f80 | 12074086897814957 | 12074086897827768 | 12074086898344083 | 12074086898379235 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fb291b5d700 | 0x7fb185e36fc0 | 12074086898398471 | 12074086898410803 | 12074086898707120 | 12074086898733985 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fb291b5d600 | 0x7fb185e37000 | 12074086898754433 | 12074086898767279 | 12074086898921198 | 12074086898924679 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fb291b5d500 | 0x7fb185e37040 | 12074086898949856 | 12074086898962478 | 12074086899347114 | 12074086899375236 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fb291b5d400 | 0x7fb185e37080 | 12074086899406154 | 12074086899417993 | 12074086899594472 | 12074086899598080 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fb291b5d300 | 0x7fb185e370c0 | 12074086899623317 | 12074086899636071 | 12074086900245825 | 12074086900274447 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fb291b5da00 | 0x7fb185e37100 | 12074086900294174 | 12074086900306465 | 12074086900635262 | 12074086900662258 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fb291b5d900 | 0x7fb185e37140 | 12074086900683758 | 12074086900696221 | 12074086900874139 | 12074086900877658 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fb291b5d800 | 0x7fb185e37180 | 12074086900901983 | 12074086900914459 | 12074086901369335 | 12074086901400189 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fb291b5d700 | 0x7fb185e371c0 | 12074086901429553 | 12074086901442294 | 12074086901641812 | 12074086901668477 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fb291b5d600 | 0x7fb185e37200 | 12074086901687432 | 12074086901700212 | 12074086902402285 | 12074086902430042 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fb291b5d500 | 0x7fb185e37240 | 12074086902451783 | 12074086902463244 | 12074086902834281 | 12074086902861143 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fb291b5d400 | 0x7fb185e37280 | 12074086902881040 | 12074086902893480 | 12074086903094758 | 12074086903127468 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fb291b5d300 | 0x7fb185e372c0 | 12074086903148006 | 12074086903160358 | 12074086903686273 | 12074086903714389 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fb291b5da00 | 0x7fb185e37300 | 12074086903746939 | 12074086903760352 | 12074086904019390 | 12074086904047518 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fb291b5d900 | 0x7fb185e37340 | 12074086904069248 | 12074086904081789 | 12074086904880981 | 12074086904908397 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fb291b5d800 | 0x7fb185e37380 | 12074086904927543 | 12074086904940501 | 12074086905359857 | 12074086905388640 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fb291b5d700 | 0x7fb185e373c0 | 12074086905407805 | 12074086905420176 | 12074086905643854 | 12074086905670544 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fb291b5d600 | 0x7fb185e37400 | 12074086905692204 | 12074086905704654 | 12074086906300648 | 12074086906328646 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fb291b5d500 | 0x7fb185e37440 | 12074086906362579 | 12074086906376167 | 12074086906644005 | 12074086906670842 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fb291b5d400 | 0x7fb185e37480 | 12074086906691491 | 12074086906703844 | 12074086907688155 | 12074086907717066 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fb291b5d300 | 0x7fb185e374c0 | 12074086907740039 | 12074086907752634 | 12074086908266709 | 12074086908295100 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fb291b5da00 | 0x7fb185e37500 | 12074086908319986 | 12074086908332469 | 12074086908603186 | 12074086908629962 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fb291b5d900 | 0x7fb185e37540 | 12074086908650771 | 12074086908663505 | 12074086909399658 | 12074086909428486 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fb291b5d800 | 0x7fb185e37580 | 12074086909458141 | 12074086909470858 | 12074086909785895 | 12074086909813001 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fb291b5d700 | 0x7fb185e375c0 | 12074086909833028 | 12074086909845414 | 12074086911015483 | 12074086911049308 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fb291b5d600 | 0x7fb185e37600 | 12074086911069455 | 12074086911081722 | 12074086911692597 | 12074086911719623 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fb291b5d500 | 0x7fb185e37640 | 12074086911743297 | 12074086911755476 | 12074086912073393 | 12074086912103036 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fb291b5d400 | 0x7fb185e37680 | 12074086912127902 | 12074086912140912 | 12074086913017384 | 12074086913047190 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fb291b5d300 | 0x7fb185e376c0 | 12074086913083077 | 12074086913095783 | 12074086913505699 | 12074086913533504 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fb291b5da00 | 0x7fb185e37700 | 12074086913558430 | 12074086913571299 | 12074086915118324 | 12074086915192156 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fb291b5d900 | 0x7fb185e37740 | 12074086915212824 | 12074086915224406 | 12074086916016880 | 12074086916093380 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fb291b5d800 | 0x7fb185e37780 | 12074086916110953 | 12074086916124238 | 12074086916537515 | 12074086916608167 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fb291b5d700 | 0x7fb185e377c0 | 12074086916630488 | 12074086916643434 | 12074086917801185 | 12074086917873187 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fb291b5d600 | 0x7fb185e37800 | 12074086917903173 | 12074086917916864 | 12074086918702778 | 12074086918777237 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fb291b5d500 | 0x7fb185e37840 | 12074086918799248 | 12074086918810777 | 12074086921860992 | 12074086921936527 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fb291b5d400 | 0x7fb185e37880 | 12074086921957126 | 12074086921968831 | 12074086923510739 | 12074086923584489 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fb291b5d300 | 0x7fb185e378c0 | 12074086923606721 | 12074086923620658 | 12074086924409612 | 12074086924482408 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fb291b5da00 | 0x7fb185e37900 | 12074086924506703 | 12074086924519691 | 12074086926801272 | 12074086926873601 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fb291b5d900 | 0x7fb185e37940 | 12074086926909548 | 12074086926922712 | 12074086928457099 | 12074086928530580 |
| 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 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fb291b5d800 | 0x7fb185e37980 | 12074086928552440 | 12074086928565578 | 12074086934621690 | 12074086934692179 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fb291b5d700 | 0x7fb185e379c0 | 12074086934714109 | 12074086934727289 | 12074086937768704 | 12074086937840378 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fb291b5d600 | 0x7fb185e37a00 | 12074086937863070 | 12074086937876224 | 12074086939414131 | 12074086939490715 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 805626 | 805631 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fb291b5d500 | 0x7fb185e37a40 | 12074086939510472 | 12074086939523730 | 12074086944051054 | 12074086944121589 |