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 | 790597 | 790602 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f60ee004180 | 12073880436501963 | 12073880436547597 | 12073880436871114 | 12073880436977586 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 790597 | 790602 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f60ee035100 | 12073880451590914 | 12073880451692626 | 12073880451699186 | 12073880451704575 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f61f9bc9900 | 0x7f60ee035140 | 12073880451745270 | 12073880451758225 | 12073880451892304 | 12073880451895439 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f61f9bc9800 | 0x7f60ee035180 | 12073880451936876 | 12073880451950863 | 12073880452197741 | 12073880452297477 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f61f9bc9700 | 0x7f60ee0351c0 | 12073880452323695 | 12073880452335340 | 12073880452578538 | 12073880452675319 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f61f9bc9600 | 0x7f60ee035200 | 12073880452700646 | 12073880452712137 | 12073880452838056 | 12073880452841097 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f61f9bc9500 | 0x7f60ee035240 | 12073880452867295 | 12073880452878695 | 12073880453003654 | 12073880453011023 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f61f9bc9400 | 0x7f60ee035280 | 12073880453060905 | 12073880453076774 | 12073880453200773 | 12073880453203911 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f61f9bc9300 | 0x7f60ee0352c0 | 12073880453230440 | 12073880453245732 | 12073880453494850 | 12073880453591932 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f61f9bc9a00 | 0x7f60ee035300 | 12073880453612140 | 12073880453628609 | 12073880453871327 | 12073880453968262 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f61f9bc9900 | 0x7f60ee035340 | 12073880453989100 | 12073880454000606 | 12073880454125565 | 12073880454129301 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f61f9bc9800 | 0x7f60ee035380 | 12073880454155890 | 12073880454167644 | 12073880454292763 | 12073880454295981 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f61f9bc9700 | 0x7f60ee0353c0 | 12073880454333150 | 12073880454344283 | 12073880454469242 | 12073880454472278 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f61f9bc9600 | 0x7f60ee035400 | 12073880454497235 | 12073880454509081 | 12073880454758679 | 12073880454830754 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f61f9bc9500 | 0x7f60ee035440 | 12073880454851373 | 12073880454861718 | 12073880455111476 | 12073880455181777 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f61f9bc9400 | 0x7f60ee035480 | 12073880455200932 | 12073880455212435 | 12073880455337234 | 12073880455340201 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f61f9bc9300 | 0x7f60ee0354c0 | 12073880455365348 | 12073880455376914 | 12073880455502353 | 12073880455505248 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f61f9bc9a00 | 0x7f60ee035500 | 12073880455541085 | 12073880455552752 | 12073880455677711 | 12073880455680704 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f61f9bc9900 | 0x7f60ee035540 | 12073880455706352 | 12073880455718671 | 12073880455968109 | 12073880456017600 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f61f9bc9800 | 0x7f60ee035580 | 12073880456041915 | 12073880456055148 | 12073880456299306 | 12073880456396544 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f61f9bc9700 | 0x7f60ee0355c0 | 12073880456415630 | 12073880456426505 | 12073880456551624 | 12073880456554758 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f61f9bc9600 | 0x7f60ee035600 | 12073880456580416 | 12073880456592103 | 12073880456717222 | 12073880456720697 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f61f9bc9500 | 0x7f60ee035640 | 12073880456755752 | 12073880456767462 | 12073880456891621 | 12073880456894820 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f61f9bc9400 | 0x7f60ee035680 | 12073880456920197 | 12073880456931781 | 12073880457180418 | 12073880457280477 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f61f9bc9300 | 0x7f60ee0356c0 | 12073880457300484 | 12073880457311777 | 12073880457557695 | 12073880457653961 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f61f9bc9a00 | 0x7f60ee035700 | 12073880457675561 | 12073880457687134 | 12073880457811293 | 12073880457814539 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f61f9bc9900 | 0x7f60ee035740 | 12073880457840257 | 12073880457851453 | 12073880457976412 | 12073880457979616 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f61f9bc9800 | 0x7f60ee035780 | 12073880458023878 | 12073880458036251 | 12073880458160570 | 12073880458163658 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f61f9bc9700 | 0x7f60ee0357c0 | 12073880458194205 | 12073880458206170 | 12073880458455767 | 12073880458552190 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f61f9bc9600 | 0x7f60ee035800 | 12073880458571927 | 12073880458582966 | 12073880458825844 | 12073880458921627 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f61f9bc9500 | 0x7f60ee035840 | 12073880458942556 | 12073880458953843 | 12073880459078162 | 12073880459081634 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f61f9bc9400 | 0x7f60ee035880 | 12073880459107863 | 12073880459119282 | 12073880459245361 | 12073880459248424 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f61f9bc9300 | 0x7f60ee0358c0 | 12073880459284892 | 12073880459298000 | 12073880459422639 | 12073880459425333 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f61f9bc9a00 | 0x7f60ee035900 | 12073880459451181 | 12073880459462639 | 12073880459713197 | 12073880459791123 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f61f9bc9900 | 0x7f60ee035940 | 12073880459811030 | 12073880459830476 | 12073880460078153 | 12073880460157954 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f61f9bc9800 | 0x7f60ee035980 | 12073880460178462 | 12073880460189992 | 12073880460314791 | 12073880460318142 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f61f9bc9700 | 0x7f60ee0359c0 | 12073880460343108 | 12073880460356391 | 12073880460482950 | 12073880460486194 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f61f9bc9600 | 0x7f60ee035a00 | 12073880460521229 | 12073880460532710 | 12073880460656548 | 12073880460659296 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f61f9bc9500 | 0x7f60ee035a40 | 12073880460685104 | 12073880460696868 | 12073880460947746 | 12073880460970033 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f61f9bc9400 | 0x7f60ee035a80 | 12073880460990451 | 12073880461002465 | 12073880461245983 | 12073880461274329 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f61f9bc9300 | 0x7f60ee035ac0 | 12073880461297692 | 12073880461311423 | 12073880461436862 | 12073880461439927 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f61f9bc9a00 | 0x7f60ee035b00 | 12073880461465344 | 12073880461479261 | 12073880461605340 | 12073880461608420 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f61f9bc9900 | 0x7f60ee035b40 | 12073880461643265 | 12073880461654140 | 12073880461779099 | 12073880461781892 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f61f9bc9800 | 0x7f60ee035b80 | 12073880461807239 | 12073880461818778 | 12073880462071896 | 12073880462101957 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f61f9bc9700 | 0x7f60ee035bc0 | 12073880462121784 | 12073880462134456 | 12073880462378774 | 12073880462406082 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f61f9bc9600 | 0x7f60ee035c00 | 12073880462425178 | 12073880462437813 | 12073880462562452 | 12073880462565298 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f61f9bc9500 | 0x7f60ee035c40 | 12073880462591016 | 12073880462603732 | 12073880462730931 | 12073880462734072 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f61f9bc9400 | 0x7f60ee035c80 | 12073880462771051 | 12073880462784530 | 12073880462909649 | 12073880462912614 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f61f9bc9300 | 0x7f60ee035cc0 | 12073880462937480 | 12073880462950289 | 12073880463211246 | 12073880463239872 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f61f9bc9a00 | 0x7f60ee035d00 | 12073880463260009 | 12073880463273326 | 12073880463516844 | 12073880463540811 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f61f9bc9900 | 0x7f60ee035d40 | 12073880463560548 | 12073880463573163 | 12073880463698122 | 12073880463700969 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f61f9bc9800 | 0x7f60ee035d80 | 12073880463726226 | 12073880463737642 | 12073880463867241 | 12073880463869953 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f61f9bc9700 | 0x7f60ee035dc0 | 12073880463905429 | 12073880463916840 | 12073880464041639 | 12073880464044798 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f61f9bc9600 | 0x7f60ee035e00 | 12073880464070846 | 12073880464082279 | 12073880464332677 | 12073880464352800 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f61f9bc9500 | 0x7f60ee035e40 | 12073880464372647 | 12073880464384196 | 12073880464629154 | 12073880464656384 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f61f9bc9400 | 0x7f60ee035e80 | 12073880464680108 | 12073880464692674 | 12073880464818113 | 12073880464820790 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f61f9bc9300 | 0x7f60ee035ec0 | 12073880464845656 | 12073880464857152 | 12073880464984831 | 12073880464987610 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f61f9bc9a00 | 0x7f60ee035f00 | 12073880465031341 | 12073880465042751 | 12073880465168030 | 12073880465170900 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f61f9bc9900 | 0x7f60ee035f40 | 12073880465196859 | 12073880465208669 | 12073880465463867 | 12073880465487519 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f61f9bc9800 | 0x7f60ee035f80 | 12073880465507225 | 12073880465518587 | 12073880465765304 | 12073880465788909 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f61f9bc9700 | 0x7f60ee035fc0 | 12073880465808676 | 12073880465819864 | 12073880465944823 | 12073880465947524 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f61f9bc9600 | 0x7f60ee036000 | 12073880465973292 | 12073880465984663 | 12073880466121621 | 12073880466124673 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f61f9bc9500 | 0x7f60ee036040 | 12073880466164587 | 12073880466175861 | 12073880466300180 | 12073880466303215 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f61f9bc9400 | 0x7f60ee036080 | 12073880466328852 | 12073880466340019 | 12073880466602897 | 12073880466631354 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f61f9bc9300 | 0x7f60ee0360c0 | 12073880466651281 | 12073880466662737 | 12073880466912175 | 12073880466935470 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f61f9bc9a00 | 0x7f60ee036100 | 12073880466954665 | 12073880466966094 | 12073880467091533 | 12073880467094896 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f61f9bc9900 | 0x7f60ee036140 | 12073880467121846 | 12073880467132813 | 12073880467274411 | 12073880467277235 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f61f9bc9800 | 0x7f60ee036180 | 12073880467313743 | 12073880467324971 | 12073880467450090 | 12073880467453061 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f61f9bc9700 | 0x7f60ee0361c0 | 12073880467478619 | 12073880467489930 | 12073880467745447 | 12073880467769039 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f61f9bc9600 | 0x7f60ee036200 | 12073880467789116 | 12073880467800327 | 12073880468044165 | 12073880468071932 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f61f9bc9500 | 0x7f60ee036240 | 12073880468096297 | 12073880468108324 | 12073880468234243 | 12073880468237289 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f61f9bc9400 | 0x7f60ee036280 | 12073880468262456 | 12073880468273443 | 12073880468424322 | 12073880468427422 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f61f9bc9300 | 0x7f60ee0362c0 | 12073880468481122 | 12073880468492481 | 12073880468617600 | 12073880468620792 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f61f9bc9a00 | 0x7f60ee036300 | 12073880468645588 | 12073880468656960 | 12073880468910077 | 12073880468933873 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f61f9bc9900 | 0x7f60ee036340 | 12073880468954091 | 12073880468967197 | 12073880469214715 | 12073880469243940 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f61f9bc9800 | 0x7f60ee036380 | 12073880469263286 | 12073880469275514 | 12073880469401273 | 12073880469404298 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f61f9bc9700 | 0x7f60ee0363c0 | 12073880469429575 | 12073880469441273 | 12073880469597911 | 12073880469600853 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f61f9bc9600 | 0x7f60ee036400 | 12073880469638994 | 12073880469649911 | 12073880469775030 | 12073880469778062 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f61f9bc9500 | 0x7f60ee036440 | 12073880469804371 | 12073880469815830 | 12073880470078707 | 12073880470107094 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f61f9bc9400 | 0x7f60ee036480 | 12073880470127451 | 12073880470139987 | 12073880470385905 | 12073880470410307 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f61f9bc9300 | 0x7f60ee0364c0 | 12073880470430465 | 12073880470442544 | 12073880470567983 | 12073880470570906 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f61f9bc9a00 | 0x7f60ee036500 | 12073880470595752 | 12073880470607023 | 12073880470772141 | 12073880470775045 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f61f9bc9900 | 0x7f60ee036540 | 12073880470811753 | 12073880470823501 | 12073880470948780 | 12073880470951653 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f61f9bc9800 | 0x7f60ee036580 | 12073880470977271 | 12073880470988459 | 12073880471243977 | 12073880471272069 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f61f9bc9700 | 0x7f60ee0365c0 | 12073880471292076 | 12073880471303497 | 12073880471551175 | 12073880471574491 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f61f9bc9600 | 0x7f60ee036600 | 12073880471595951 | 12073880471606854 | 12073880471732293 | 12073880471735250 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f61f9bc9500 | 0x7f60ee036640 | 12073880471759895 | 12073880471771173 | 12073880471943011 | 12073880471945961 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f61f9bc9400 | 0x7f60ee036680 | 12073880471982870 | 12073880471994211 | 12073880472120130 | 12073880472123421 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f61f9bc9300 | 0x7f60ee0366c0 | 12073880472149169 | 12073880472160609 | 12073880472412767 | 12073880472432836 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f61f9bc9a00 | 0x7f60ee036700 | 12073880472452042 | 12073880472463007 | 12073880472709405 | 12073880472732663 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f61f9bc9900 | 0x7f60ee036740 | 12073880472753241 | 12073880472765404 | 12073880472890683 | 12073880472893762 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f61f9bc9800 | 0x7f60ee036780 | 12073880472918749 | 12073880472929883 | 12073880473112601 | 12073880473116025 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f61f9bc9700 | 0x7f60ee0367c0 | 12073880473154858 | 12073880473166361 | 12073880473292280 | 12073880473295188 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f61f9bc9600 | 0x7f60ee036800 | 12073880473321137 | 12073880473331959 | 12073880473595317 | 12073880473616375 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f61f9bc9500 | 0x7f60ee036840 | 12073880473636172 | 12073880473648597 | 12073880473901714 | 12073880473921653 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f61f9bc9400 | 0x7f60ee036880 | 12073880473940989 | 12073880473953234 | 12073880474079313 | 12073880474082441 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f61f9bc9300 | 0x7f60ee0368c0 | 12073880474108289 | 12073880474119632 | 12073880474310031 | 12073880474314362 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f61f9bc9a00 | 0x7f60ee036900 | 12073880474350480 | 12073880474365070 | 12073880474492429 | 12073880474495639 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f61f9bc9900 | 0x7f60ee036940 | 12073880474521367 | 12073880474534669 | 12073880474817546 | 12073880474845149 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f61f9bc9800 | 0x7f60ee036980 | 12073880474865406 | 12073880474877866 | 12073880475130344 | 12073880475161477 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f61f9bc9700 | 0x7f60ee0369c0 | 12073880475182796 | 12073880475194663 | 12073880475319782 | 12073880475322766 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f61f9bc9600 | 0x7f60ee036a00 | 12073880475348354 | 12073880475359462 | 12073880475569060 | 12073880475595884 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f61f9bc9500 | 0x7f60ee036a40 | 12073880475628124 | 12073880475639139 | 12073880475766658 | 12073880475769697 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f61f9bc9400 | 0x7f60ee036a80 | 12073880475795104 | 12073880475806498 | 12073880476112735 | 12073880476141989 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f61f9bc9300 | 0x7f60ee036ac0 | 12073880476162427 | 12073880476173535 | 12073880476421373 | 12073880476448468 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f61f9bc9a00 | 0x7f60ee036b00 | 12073880476469197 | 12073880476480092 | 12073880476607611 | 12073880476610570 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f61f9bc9900 | 0x7f60ee036b40 | 12073880476636678 | 12073880476647771 | 12073880476875289 | 12073880476898585 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f61f9bc9800 | 0x7f60ee036b80 | 12073880476931496 | 12073880476942808 | 12073880477069847 | 12073880477073069 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f61f9bc9700 | 0x7f60ee036bc0 | 12073880477099168 | 12073880477110487 | 12073880477439444 | 12073880477459768 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f61f9bc9600 | 0x7f60ee036c00 | 12073880477480166 | 12073880477492883 | 12073880477749361 | 12073880477772769 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f61f9bc9500 | 0x7f60ee036c40 | 12073880477792276 | 12073880477804561 | 12073880477932400 | 12073880477935452 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f61f9bc9400 | 0x7f60ee036c80 | 12073880477960669 | 12073880477971919 | 12073880478215917 | 12073880478244125 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f61f9bc9300 | 0x7f60ee036cc0 | 12073880478275784 | 12073880478288237 | 12073880478417675 | 12073880478420683 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f61f9bc9a00 | 0x7f60ee036d00 | 12073880478446041 | 12073880478457035 | 12073880478832392 | 12073880478855812 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f61f9bc9900 | 0x7f60ee036d40 | 12073880478875950 | 12073880478888391 | 12073880479141989 | 12073880479173282 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f61f9bc9800 | 0x7f60ee036d80 | 12073880479195403 | 12073880479206629 | 12073880479335748 | 12073880479338820 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f61f9bc9700 | 0x7f60ee036dc0 | 12073880479364187 | 12073880479374947 | 12073880479654145 | 12073880479677740 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f61f9bc9600 | 0x7f60ee036e00 | 12073880479709148 | 12073880479720064 | 12073880479855263 | 12073880479858315 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f61f9bc9500 | 0x7f60ee036e40 | 12073880479883242 | 12073880479894783 | 12073880480317979 | 12073880480347154 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f61f9bc9400 | 0x7f60ee036e80 | 12073880480368203 | 12073880480379259 | 12073880480643736 | 12073880480670965 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f61f9bc9300 | 0x7f60ee036ec0 | 12073880480691213 | 12073880480702296 | 12073880480837335 | 12073880480840400 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f61f9bc9a00 | 0x7f60ee036f00 | 12073880480866068 | 12073880480877174 | 12073880481191572 | 12073880481224865 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f61f9bc9900 | 0x7f60ee036f40 | 12073880481258567 | 12073880481269491 | 12073880481421970 | 12073880481425047 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f61f9bc9800 | 0x7f60ee036f80 | 12073880481450344 | 12073880481462129 | 12073880481979565 | 12073880482009533 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f61f9bc9700 | 0x7f60ee036fc0 | 12073880482030923 | 12073880482041964 | 12073880482344202 | 12073880482372718 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f61f9bc9600 | 0x7f60ee037000 | 12073880482392214 | 12073880482402921 | 12073880482556040 | 12073880482559044 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f61f9bc9500 | 0x7f60ee037040 | 12073880482584391 | 12073880482595559 | 12073880482980516 | 12073880483005654 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f61f9bc9400 | 0x7f60ee037080 | 12073880483056118 | 12073880483068995 | 12073880483245314 | 12073880483248325 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f61f9bc9300 | 0x7f60ee0370c0 | 12073880483273792 | 12073880483285633 | 12073880483896188 | 12073880483924472 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f61f9bc9a00 | 0x7f60ee037100 | 12073880483944459 | 12073880483955388 | 12073880484284345 | 12073880484316921 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f61f9bc9900 | 0x7f60ee037140 | 12073880484339543 | 12073880484351064 | 12073880484528823 | 12073880484532201 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f61f9bc9800 | 0x7f60ee037180 | 12073880484557238 | 12073880484568022 | 12073880485024018 | 12073880485052869 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f61f9bc9700 | 0x7f60ee0371c0 | 12073880485084888 | 12073880485097298 | 12073880485296336 | 12073880485323061 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f61f9bc9600 | 0x7f60ee037200 | 12073880485342527 | 12073880485354896 | 12073880486066730 | 12073880486096368 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f61f9bc9500 | 0x7f60ee037240 | 12073880486117066 | 12073880486129769 | 12073880486502726 | 12073880486529914 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f61f9bc9400 | 0x7f60ee037280 | 12073880486550081 | 12073880486561285 | 12073880486764004 | 12073880486790858 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f61f9bc9300 | 0x7f60ee0372c0 | 12073880486810846 | 12073880486821603 | 12073880487347998 | 12073880487381877 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f61f9bc9a00 | 0x7f60ee037300 | 12073880487416261 | 12073880487428158 | 12073880487651196 | 12073880487678047 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f61f9bc9900 | 0x7f60ee037340 | 12073880487698996 | 12073880487709915 | 12073880488509108 | 12073880488537284 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f61f9bc9800 | 0x7f60ee037380 | 12073880488558664 | 12073880488569748 | 12073880488989584 | 12073880489017767 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f61f9bc9700 | 0x7f60ee0373c0 | 12073880489037714 | 12073880489048784 | 12073880489274062 | 12073880489300983 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f61f9bc9600 | 0x7f60ee037400 | 12073880489321932 | 12073880489332941 | 12073880489929096 | 12073880489956201 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f61f9bc9500 | 0x7f60ee037440 | 12073880489988090 | 12073880490000936 | 12073880490268933 | 12073880490300731 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f61f9bc9400 | 0x7f60ee037480 | 12073880490322862 | 12073880490334053 | 12073880491319484 | 12073880491347617 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f61f9bc9300 | 0x7f60ee0374c0 | 12073880491366672 | 12073880491377564 | 12073880491910839 | 12073880491937743 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f61f9bc9a00 | 0x7f60ee037500 | 12073880491959654 | 12073880491971319 | 12073880492242036 | 12073880492273497 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f61f9bc9900 | 0x7f60ee037540 | 12073880492294777 | 12073880492306356 | 12073880493045069 | 12073880493073594 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f61f9bc9800 | 0x7f60ee037580 | 12073880493106726 | 12073880493117869 | 12073880493434986 | 12073880493462347 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f61f9bc9700 | 0x7f60ee0375c0 | 12073880493482384 | 12073880493493546 | 12073880494668095 | 12073880494697191 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f61f9bc9600 | 0x7f60ee037600 | 12073880494717339 | 12073880494729695 | 12073880495342970 | 12073880495371845 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f61f9bc9500 | 0x7f60ee037640 | 12073880495391502 | 12073880495403929 | 12073880495723606 | 12073880495750789 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f61f9bc9400 | 0x7f60ee037680 | 12073880495771588 | 12073880495783926 | 12073880496661998 | 12073880496690816 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f61f9bc9300 | 0x7f60ee0376c0 | 12073880496724930 | 12073880496737518 | 12073880497147594 | 12073880497177050 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f61f9bc9a00 | 0x7f60ee037700 | 12073880497198370 | 12073880497211113 | 12073880498762300 | 12073880498812439 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f61f9bc9900 | 0x7f60ee037740 | 12073880498832807 | 12073880498845237 | 12073880499642831 | 12073880499723192 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f61f9bc9800 | 0x7f60ee037780 | 12073880499740414 | 12073880499751629 | 12073880500165866 | 12073880500238409 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f61f9bc9700 | 0x7f60ee0377c0 | 12073880500260540 | 12073880500272105 | 12073880501431136 | 12073880501504131 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f61f9bc9600 | 0x7f60ee037800 | 12073880501534949 | 12073880501546176 | 12073880502331290 | 12073880502403663 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f61f9bc9500 | 0x7f60ee037840 | 12073880502425113 | 12073880502438169 | 12073880505493665 | 12073880505566581 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f61f9bc9400 | 0x7f60ee037880 | 12073880505588301 | 12073880505600865 | 12073880507145013 | 12073880507218250 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f61f9bc9300 | 0x7f60ee0378c0 | 12073880507240612 | 12073880507253972 | 12073880508043406 | 12073880508115919 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f61f9bc9a00 | 0x7f60ee037900 | 12073880508136878 | 12073880508147885 | 12073880510430908 | 12073880510503776 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f61f9bc9900 | 0x7f60ee037940 | 12073880510535956 | 12073880510547547 | 12073880512083695 | 12073880512156518 |
| 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 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f61f9bc9800 | 0x7f60ee037980 | 12073880512178408 | 12073880512189614 | 12073880518250368 | 12073880518323628 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f61f9bc9700 | 0x7f60ee0379c0 | 12073880518343566 | 12073880518354687 | 12073880521400744 | 12073880521474173 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f61f9bc9600 | 0x7f60ee037a00 | 12073880521495493 | 12073880521509223 | 12073880523048731 | 12073880523121204 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 790597 | 790602 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f61f9bc9500 | 0x7f60ee037a40 | 12073880523142053 | 12073880523154810 | 12073880527682136 | 12073880527754725 |