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 | 762995 | 763000 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7ff6fb004180 | 12073420227749665 | 12073420227791147 | 12073420228118984 | 12073420228229266 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 762995 | 763000 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7ff6fb035100 | 12073420243914836 | 12073420244026605 | 12073420244033805 | 12073420244039838 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7ff82b006900 | 0x7ff6fb035140 | 12073420244098277 | 12073420244113324 | 12073420244247403 | 12073420244250861 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7ff82b006800 | 0x7ff6fb035180 | 12073420244304540 | 12073420244316843 | 12073420244560361 | 12073420244658799 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7ff82b006700 | 0x7ff6fb0351c0 | 12073420244691209 | 12073420244702599 | 12073420244947077 | 12073420245051458 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7ff82b006600 | 0x7ff6fb035200 | 12073420245089118 | 12073420245101156 | 12073420245226435 | 12073420245229309 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7ff82b006500 | 0x7ff6fb035240 | 12073420245264855 | 12073420245276674 | 12073420245401313 | 12073420245404234 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7ff82b006400 | 0x7ff6fb035280 | 12073420245464386 | 12073420245476993 | 12073420245601152 | 12073420245603995 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7ff82b006300 | 0x7ff6fb0352c0 | 12073420245637938 | 12073420245649791 | 12073420245897469 | 12073420245982368 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7ff82b006a00 | 0x7ff6fb035300 | 12073420246016612 | 12073420246029148 | 12073420246274266 | 12073420246374397 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7ff82b006900 | 0x7ff6fb035340 | 12073420246405785 | 12073420246418744 | 12073420246543383 | 12073420246546306 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7ff82b006800 | 0x7ff6fb035380 | 12073420246581582 | 12073420246592983 | 12073420246718262 | 12073420246721171 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7ff82b006700 | 0x7ff6fb0353c0 | 12073420246767247 | 12073420246780501 | 12073420246905300 | 12073420246908099 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7ff82b006600 | 0x7ff6fb035400 | 12073420246941380 | 12073420246953940 | 12073420247204978 | 12073420247304926 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7ff82b006500 | 0x7ff6fb035440 | 12073420247339540 | 12073420247350896 | 12073420247595054 | 12073420247694159 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7ff82b006400 | 0x7ff6fb035480 | 12073420247722793 | 12073420247735693 | 12073420247860332 | 12073420247863624 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7ff82b006300 | 0x7ff6fb0354c0 | 12073420247897097 | 12073420247908651 | 12073420248033770 | 12073420248036956 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7ff82b006a00 | 0x7ff6fb035500 | 12073420248083894 | 12073420248096170 | 12073420248220969 | 12073420248223794 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7ff82b006900 | 0x7ff6fb035540 | 12073420248257216 | 12073420248270568 | 12073420248518886 | 12073420248592479 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7ff82b006800 | 0x7ff6fb035580 | 12073420248618167 | 12073420248630085 | 12073420248876643 | 12073420248946246 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7ff82b006700 | 0x7ff6fb0355c0 | 12073420248975350 | 12073420248987842 | 12073420249112321 | 12073420249115401 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7ff82b006600 | 0x7ff6fb035600 | 12073420249148692 | 12073420249160641 | 12073420249285760 | 12073420249288612 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7ff82b006500 | 0x7ff6fb035640 | 12073420249333336 | 12073420249346399 | 12073420249470238 | 12073420249473185 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7ff82b006400 | 0x7ff6fb035680 | 12073420249505686 | 12073420249518557 | 12073420249770875 | 12073420249814780 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7ff82b006300 | 0x7ff6fb0356c0 | 12073420249843303 | 12073420249855515 | 12073420250101272 | 12073420250170161 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7ff82b006a00 | 0x7ff6fb035700 | 12073420250198313 | 12073420250212951 | 12073420250337270 | 12073420250339966 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7ff82b006900 | 0x7ff6fb035740 | 12073420250374611 | 12073420250387030 | 12073420250511989 | 12073420250514921 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7ff82b006800 | 0x7ff6fb035780 | 12073420250558583 | 12073420250570228 | 12073420250694867 | 12073420250697701 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7ff82b006700 | 0x7ff6fb0357c0 | 12073420250730763 | 12073420250743507 | 12073420250990225 | 12073420251022064 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7ff82b006600 | 0x7ff6fb035800 | 12073420251055396 | 12073420251066864 | 12073420251312462 | 12073420251391571 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7ff82b006500 | 0x7ff6fb035840 | 12073420251419743 | 12073420251431341 | 12073420251556300 | 12073420251559162 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7ff82b006400 | 0x7ff6fb035880 | 12073420251592204 | 12073420251604139 | 12073420251729258 | 12073420251732274 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7ff82b006300 | 0x7ff6fb0358c0 | 12073420251776927 | 12073420251789578 | 12073420251914377 | 12073420251916977 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7ff82b006a00 | 0x7ff6fb035900 | 12073420251948937 | 12073420251961096 | 12073420252207654 | 12073420252289820 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7ff82b006900 | 0x7ff6fb035940 | 12073420252319515 | 12073420252331013 | 12073420252575491 | 12073420252655890 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7ff82b006800 | 0x7ff6fb035980 | 12073420252683141 | 12073420252695810 | 12073420252821089 | 12073420252824113 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7ff82b006700 | 0x7ff6fb0359c0 | 12073420252858066 | 12073420252871488 | 12073420252997407 | 12073420253005961 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7ff82b006600 | 0x7ff6fb035a00 | 12073420253043891 | 12073420253056127 | 12073420253180446 | 12073420253183050 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7ff82b006500 | 0x7ff6fb035a40 | 12073420253216602 | 12073420253229565 | 12073420253479803 | 12073420253532409 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7ff82b006400 | 0x7ff6fb035a80 | 12073420253558117 | 12073420253569722 | 12073420253812760 | 12073420253867081 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7ff82b006300 | 0x7ff6fb035ac0 | 12073420253900213 | 12073420253912439 | 12073420254037878 | 12073420254041155 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7ff82b006a00 | 0x7ff6fb035b00 | 12073420254075599 | 12073420254092278 | 12073420254217717 | 12073420254220738 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7ff82b006900 | 0x7ff6fb035b40 | 12073420254263107 | 12073420254276596 | 12073420254401715 | 12073420254404620 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7ff82b006800 | 0x7ff6fb035b80 | 12073420254437952 | 12073420254450195 | 12073420254707952 | 12073420254737479 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7ff82b006700 | 0x7ff6fb035bc0 | 12073420254766483 | 12073420254778032 | 12073420255022190 | 12073420255049539 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7ff82b006600 | 0x7ff6fb035c00 | 12073420255075727 | 12073420255087629 | 12073420255212268 | 12073420255215066 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7ff82b006500 | 0x7ff6fb035c40 | 12073420255248538 | 12073420255259628 | 12073420255385867 | 12073420255388508 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7ff82b006400 | 0x7ff6fb035c80 | 12073420255433292 | 12073420255448586 | 12073420255573545 | 12073420255576207 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7ff82b006300 | 0x7ff6fb035cc0 | 12073420255609389 | 12073420255623464 | 12073420255879942 | 12073420255902504 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7ff82b006a00 | 0x7ff6fb035d00 | 12073420255932970 | 12073420255946182 | 12073420256189220 | 12073420256217219 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7ff82b006900 | 0x7ff6fb035d40 | 12073420256246423 | 12073420256259779 | 12073420256384898 | 12073420256387565 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7ff82b006800 | 0x7ff6fb035d80 | 12073420256419865 | 12073420256431457 | 12073420256560896 | 12073420256563562 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7ff82b006700 | 0x7ff6fb035dc0 | 12073420256606552 | 12073420256621536 | 12073420256746975 | 12073420256749588 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7ff82b006600 | 0x7ff6fb035e00 | 12073420256784242 | 12073420256798174 | 12073420257050652 | 12073420257080954 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7ff82b006500 | 0x7ff6fb035e40 | 12073420257109887 | 12073420257122971 | 12073420257366969 | 12073420257394366 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7ff82b006400 | 0x7ff6fb035e80 | 12073420257423620 | 12073420257437049 | 12073420257562808 | 12073420257565444 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7ff82b006300 | 0x7ff6fb035ec0 | 12073420257597854 | 12073420257609687 | 12073420257737686 | 12073420257740419 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7ff82b006a00 | 0x7ff6fb035f00 | 12073420257784992 | 12073420257797686 | 12073420257922324 | 12073420257924992 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7ff82b006900 | 0x7ff6fb035f40 | 12073420257957092 | 12073420257971604 | 12073420258225202 | 12073420258253773 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7ff82b006800 | 0x7ff6fb035f80 | 12073420258283358 | 12073420258296721 | 12073420258543759 | 12073420258571343 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7ff82b006700 | 0x7ff6fb035fc0 | 12073420258599335 | 12073420258612718 | 12073420258737677 | 12073420258740398 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7ff82b006600 | 0x7ff6fb036000 | 12073420258771936 | 12073420258784557 | 12073420258921196 | 12073420258923808 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7ff82b006500 | 0x7ff6fb036040 | 12073420258968491 | 12073420258981675 | 12073420259106954 | 12073420259110215 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7ff82b006400 | 0x7ff6fb036080 | 12073420259144218 | 12073420259156874 | 12073420259414951 | 12073420259434988 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7ff82b006300 | 0x7ff6fb0360c0 | 12073420259464754 | 12073420259477031 | 12073420259723749 | 12073420259747279 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7ff82b006a00 | 0x7ff6fb036100 | 12073420259777194 | 12073420259788868 | 12073420259913347 | 12073420259916143 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7ff82b006900 | 0x7ff6fb036140 | 12073420259948793 | 12073420259961187 | 12073420260103266 | 12073420260106316 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7ff82b006800 | 0x7ff6fb036180 | 12073420260149096 | 12073420260161505 | 12073420260286784 | 12073420260289847 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7ff82b006700 | 0x7ff6fb0361c0 | 12073420260322969 | 12073420260335423 | 12073420260591901 | 12073420260615963 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7ff82b006600 | 0x7ff6fb036200 | 12073420260644767 | 12073420260657341 | 12073420260903739 | 12073420260932411 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7ff82b006500 | 0x7ff6fb036240 | 12073420260961525 | 12073420260974618 | 12073420261100537 | 12073420261104000 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7ff82b006400 | 0x7ff6fb036280 | 12073420261137522 | 12073420261149656 | 12073420261300215 | 12073420261303010 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7ff82b006300 | 0x7ff6fb0362c0 | 12073420261365987 | 12073420261378134 | 12073420261503573 | 12073420261506698 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7ff82b006a00 | 0x7ff6fb036300 | 12073420261537927 | 12073420261552053 | 12073420261815891 | 12073420261835810 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7ff82b006900 | 0x7ff6fb036340 | 12073420261865275 | 12073420261876690 | 12073420262127088 | 12073420262159291 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7ff82b006800 | 0x7ff6fb036380 | 12073420262187694 | 12073420262201487 | 12073420262327406 | 12073420262330219 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7ff82b006700 | 0x7ff6fb0363c0 | 12073420262363831 | 12073420262377326 | 12073420262535404 | 12073420262538265 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7ff82b006600 | 0x7ff6fb036400 | 12073420262581315 | 12073420262593324 | 12073420262718283 | 12073420262721105 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7ff82b006500 | 0x7ff6fb036440 | 12073420262753495 | 12073420262766282 | 12073420263034120 | 12073420263059745 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7ff82b006400 | 0x7ff6fb036480 | 12073420263088548 | 12073420263101799 | 12073420263348997 | 12073420263372195 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7ff82b006300 | 0x7ff6fb0364c0 | 12073420263400658 | 12073420263413477 | 12073420263540196 | 12073420263542953 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7ff82b006a00 | 0x7ff6fb036500 | 12073420263575323 | 12073420263587395 | 12073420263752354 | 12073420263755197 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7ff82b006900 | 0x7ff6fb036540 | 12073420263798377 | 12073420263811233 | 12073420263937792 | 12073420263940872 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7ff82b006800 | 0x7ff6fb036580 | 12073420263974695 | 12073420263986752 | 12073420264241790 | 12073420264269783 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7ff82b006700 | 0x7ff6fb0365c0 | 12073420264297575 | 12073420264310109 | 12073420264557627 | 12073420264581182 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7ff82b006600 | 0x7ff6fb036600 | 12073420264611017 | 12073420264622906 | 12073420264748345 | 12073420264751128 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7ff82b006500 | 0x7ff6fb036640 | 12073420264783408 | 12073420264795545 | 12073420264967543 | 12073420264970335 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7ff82b006400 | 0x7ff6fb036680 | 12073420265021570 | 12073420265035223 | 12073420265160502 | 12073420265163705 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7ff82b006300 | 0x7ff6fb0366c0 | 12073420265197006 | 12073420265209301 | 12073420265465779 | 12073420265485643 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7ff82b006a00 | 0x7ff6fb036700 | 12073420265513835 | 12073420265527058 | 12073420265776336 | 12073420265799686 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7ff82b006900 | 0x7ff6fb036740 | 12073420265829822 | 12073420265842896 | 12073420265968175 | 12073420265971075 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7ff82b006800 | 0x7ff6fb036780 | 12073420266009276 | 12073420266021134 | 12073420266203373 | 12073420266206212 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7ff82b006700 | 0x7ff6fb0367c0 | 12073420266253169 | 12073420266265132 | 12073420266391691 | 12073420266394482 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7ff82b006600 | 0x7ff6fb036800 | 12073420266426401 | 12073420266439050 | 12073420266701608 | 12073420266725246 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7ff82b006500 | 0x7ff6fb036840 | 12073420266754371 | 12073420266765608 | 12073420267012805 | 12073420267038859 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7ff82b006400 | 0x7ff6fb036880 | 12073420267066420 | 12073420267080805 | 12073420267207044 | 12073420267209977 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7ff82b006300 | 0x7ff6fb0368c0 | 12073420267243800 | 12073420267257443 | 12073420267449122 | 12073420267451927 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7ff82b006a00 | 0x7ff6fb036900 | 12073420267493855 | 12073420267507681 | 12073420267634880 | 12073420267637822 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7ff82b006900 | 0x7ff6fb036940 | 12073420267670864 | 12073420267684960 | 12073420267968157 | 12073420267995377 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7ff82b006800 | 0x7ff6fb036980 | 12073420268029570 | 12073420268042077 | 12073420268289274 | 12073420268321132 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7ff82b006700 | 0x7ff6fb0369c0 | 12073420268354114 | 12073420268368794 | 12073420268494393 | 12073420268497360 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7ff82b006600 | 0x7ff6fb036a00 | 12073420268529229 | 12073420268541112 | 12073420268750710 | 12073420268774324 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7ff82b006500 | 0x7ff6fb036a40 | 12073420268810862 | 12073420268823350 | 12073420268951029 | 12073420268953898 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7ff82b006400 | 0x7ff6fb036a80 | 12073420268987400 | 12073420268999668 | 12073420269305906 | 12073420269331069 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7ff82b006300 | 0x7ff6fb036ac0 | 12073420269362538 | 12073420269374225 | 12073420269623343 | 12073420269646596 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7ff82b006a00 | 0x7ff6fb036b00 | 12073420269675700 | 12073420269687502 | 12073420269814221 | 12073420269817092 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7ff82b006900 | 0x7ff6fb036b40 | 12073420269849122 | 12073420269861421 | 12073420270089259 | 12073420270115016 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7ff82b006800 | 0x7ff6fb036b80 | 12073420270155872 | 12073420270169578 | 12073420270297097 | 12073420270299950 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7ff82b006700 | 0x7ff6fb036bc0 | 12073420270332811 | 12073420270344937 | 12073420270673574 | 12073420270700835 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7ff82b006600 | 0x7ff6fb036c00 | 12073420270729478 | 12073420270742533 | 12073420270997411 | 12073420271027031 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7ff82b006500 | 0x7ff6fb036c40 | 12073420271057317 | 12073420271070530 | 12073420271199809 | 12073420271202737 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7ff82b006400 | 0x7ff6fb036c80 | 12073420271235088 | 12073420271246689 | 12073420271526366 | 12073420271549832 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7ff82b006300 | 0x7ff6fb036cc0 | 12073420271586821 | 12073420271600766 | 12073420271729884 | 12073420271733153 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7ff82b006a00 | 0x7ff6fb036d00 | 12073420271764511 | 12073420271777244 | 12073420272153081 | 12073420272182518 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7ff82b006900 | 0x7ff6fb036d40 | 12073420272212284 | 12073420272226040 | 12073420272483318 | 12073420272510458 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7ff82b006800 | 0x7ff6fb036d80 | 12073420272540554 | 12073420272553877 | 12073420272684276 | 12073420272687196 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7ff82b006700 | 0x7ff6fb036dc0 | 12073420272720678 | 12073420272732596 | 12073420273011313 | 12073420273040953 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7ff82b006600 | 0x7ff6fb036e00 | 12073420273078954 | 12073420273090833 | 12073420273226191 | 12073420273229033 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7ff82b006500 | 0x7ff6fb036e40 | 12073420273260902 | 12073420273273071 | 12073420273697067 | 12073420273724083 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7ff82b006400 | 0x7ff6fb036e80 | 12073420273751764 | 12073420273764587 | 12073420274024585 | 12073420274053726 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7ff82b006300 | 0x7ff6fb036ec0 | 12073420274083371 | 12073420274097704 | 12073420274233383 | 12073420274236345 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7ff82b006a00 | 0x7ff6fb036f00 | 12073420274269126 | 12073420274280742 | 12073420274624579 | 12073420274651176 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7ff82b006900 | 0x7ff6fb036f40 | 12073420274690669 | 12073420274704259 | 12073420274854977 | 12073420274858601 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7ff82b006800 | 0x7ff6fb036f80 | 12073420274892324 | 12073420274905057 | 12073420275421052 | 12073420275454569 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7ff82b006700 | 0x7ff6fb036fc0 | 12073420275483843 | 12073420275495452 | 12073420275793849 | 12073420275822763 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7ff82b006600 | 0x7ff6fb037000 | 12073420275852168 | 12073420275865369 | 12073420276019127 | 12073420276022735 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7ff82b006500 | 0x7ff6fb037040 | 12073420276055305 | 12073420276066967 | 12073420276452403 | 12073420276479954 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7ff82b006400 | 0x7ff6fb037080 | 12073420276519768 | 12073420276532723 | 12073420276708241 | 12073420276711154 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7ff82b006300 | 0x7ff6fb0370c0 | 12073420276743434 | 12073420276754481 | 12073420277365356 | 12073420277394664 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7ff82b006a00 | 0x7ff6fb037100 | 12073420277425862 | 12073420277439595 | 12073420277765672 | 12073420277792935 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7ff82b006900 | 0x7ff6fb037140 | 12073420277823932 | 12073420277836871 | 12073420278014790 | 12073420278018083 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7ff82b006800 | 0x7ff6fb037180 | 12073420278051325 | 12073420278064709 | 12073420278520385 | 12073420278551735 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7ff82b006700 | 0x7ff6fb0371c0 | 12073420278591969 | 12073420278605345 | 12073420278805983 | 12073420278832847 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7ff82b006600 | 0x7ff6fb037200 | 12073420278859487 | 12073420278872542 | 12073420279576376 | 12073420279604752 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7ff82b006500 | 0x7ff6fb037240 | 12073420279636671 | 12073420279650136 | 12073420280023092 | 12073420280053125 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7ff82b006400 | 0x7ff6fb037280 | 12073420280083531 | 12073420280096532 | 12073420280298610 | 12073420280325401 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7ff82b006300 | 0x7ff6fb0372c0 | 12073420280355236 | 12073420280368849 | 12073420280894925 | 12073420280923142 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7ff82b006a00 | 0x7ff6fb037300 | 12073420280964328 | 12073420280979724 | 12073420281203242 | 12073420281235863 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7ff82b006900 | 0x7ff6fb037340 | 12073420281267061 | 12073420281281001 | 12073420282080355 | 12073420282108444 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7ff82b006800 | 0x7ff6fb037380 | 12073420282138741 | 12073420282151714 | 12073420282573310 | 12073420282600489 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7ff82b006700 | 0x7ff6fb0373c0 | 12073420282628361 | 12073420282639870 | 12073420282864988 | 12073420282893553 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7ff82b006600 | 0x7ff6fb037400 | 12073420282923259 | 12073420282936507 | 12073420283534102 | 12073420283563939 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7ff82b006500 | 0x7ff6fb037440 | 12073420283602942 | 12073420283617141 | 12073420283887059 | 12073420283915893 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7ff82b006400 | 0x7ff6fb037480 | 12073420283944406 | 12073420283958098 | 12073420284943530 | 12073420284975122 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7ff82b006300 | 0x7ff6fb0374c0 | 12073420285010858 | 12073420285023529 | 12073420285558884 | 12073420285587670 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7ff82b006a00 | 0x7ff6fb037500 | 12073420285625300 | 12073420285638404 | 12073420285909921 | 12073420285939013 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7ff82b006900 | 0x7ff6fb037540 | 12073420285981422 | 12073420285992801 | 12073420286731514 | 12073420286764016 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7ff82b006800 | 0x7ff6fb037580 | 12073420286802608 | 12073420286815193 | 12073420287159830 | 12073420287188375 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7ff82b006700 | 0x7ff6fb0375c0 | 12073420287237737 | 12073420287251350 | 12073420288424619 | 12073420288454778 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7ff82b006600 | 0x7ff6fb037600 | 12073420288498540 | 12073420288511979 | 12073420289123813 | 12073420289153547 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7ff82b006500 | 0x7ff6fb037640 | 12073420289183503 | 12073420289197573 | 12073420289517410 | 12073420289545996 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7ff82b006400 | 0x7ff6fb037680 | 12073420289577915 | 12073420289591169 | 12073420290469082 | 12073420290499468 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7ff82b006300 | 0x7ff6fb0376c0 | 12073420290543330 | 12073420290563512 | 12073420290975192 | 12073420291008434 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7ff82b006a00 | 0x7ff6fb037700 | 12073420291041105 | 12073420291059672 | 12073420292611033 | 12073420292680752 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7ff82b006900 | 0x7ff6fb037740 | 12073420292710848 | 12073420292727833 | 12073420293523994 | 12073420293592546 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7ff82b006800 | 0x7ff6fb037780 | 12073420293624065 | 12073420293640474 | 12073420294055674 | 12073420294124735 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7ff82b006700 | 0x7ff6fb0377c0 | 12073420294155312 | 12073420294171514 | 12073420295330715 | 12073420295398773 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7ff82b006600 | 0x7ff6fb037800 | 12073420295437565 | 12073420295456475 | 12073420296242236 | 12073420296311319 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7ff82b006500 | 0x7ff6fb037840 | 12073420296341014 | 12073420296359356 | 12073420299415839 | 12073420299484045 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7ff82b006400 | 0x7ff6fb037880 | 12073420299516756 | 12073420299535039 | 12073420301079520 | 12073420301149219 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7ff82b006300 | 0x7ff6fb0378c0 | 12073420301182521 | 12073420301200961 | 12073420301991361 | 12073420302060393 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7ff82b006a00 | 0x7ff6fb037900 | 12073420302092021 | 12073420302110401 | 12073420304392963 | 12073420304461204 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7ff82b006900 | 0x7ff6fb037940 | 12073420304502160 | 12073420304520483 | 12073420306056005 | 12073420306125377 |
| 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 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7ff82b006800 | 0x7ff6fb037980 | 12073420306157617 | 12073420306176485 | 12073420312237130 | 12073420312306123 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7ff82b006700 | 0x7ff6fb0379c0 | 12073420312335979 | 12073420312353930 | 12073420315399853 | 12073420315468741 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7ff82b006600 | 0x7ff6fb037a00 | 12073420315499678 | 12073420315519533 | 12073420317060335 | 12073420317128866 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 762995 | 763000 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7ff82b006500 | 0x7ff6fb037a40 | 12073420317168690 | 12073420317186415 | 12073420321714739 | 12073420321783816 |