37 KiB
37 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_fillBufferAligned.kd | 0 | 0 | 0 | 192599 | 192599 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fe0d0a04280 | 17087794552242 | 17087794577422 | 17087794817742 | 17087794929171 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 192599 | 192599 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fe0d0a23f80 | 17087799611640 | 17087799627169 | 17087799640289 | 17087799658048 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fe0d3a33380 | 0x7fe0d0a23fc0 | 17087799662538 | 17087799711169 | 17087799803489 | 17087799805664 |
| 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 | 8 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fe0d3a33200 | 0x7fe0d0a24000 | 17087799826674 | 17087799837089 | 17087800015489 | 17087800017528 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fe0d3a33080 | 0x7fe0d0a24040 | 17087800032998 | 17087800041569 | 17087800220608 | 17087800222763 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fe0d1403f00 | 0x7fe0d0a24080 | 17087800236762 | 17087800245088 | 17087800337888 | 17087800340029 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fe0d1403d80 | 0x7fe0d0a240c0 | 17087800356379 | 17087800364608 | 17087800456448 | 17087800458346 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fe0d1403c00 | 0x7fe0d0a24100 | 17087800485805 | 17087800496447 | 17087800588767 | 17087800590682 |
| 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 | 23 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fe0d1403a80 | 0x7fe0d0a24140 | 17087800610172 | 17087800625087 | 17087800804287 | 17087800806106 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fe0d1403900 | 0x7fe0d0a24180 | 17087800830185 | 17087800839807 | 17087801018846 | 17087801020890 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fe0d1403780 | 0x7fe0d0a241c0 | 17087801034880 | 17087801043806 | 17087801137406 | 17087801139227 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fe0d1403600 | 0x7fe0d0a24200 | 17087801158336 | 17087801167166 | 17087801260126 | 17087801262043 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fe0d3a33480 | 0x7fe0d0a24240 | 17087801284773 | 17087801294046 | 17087801387165 | 17087801389090 |
| 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 | 38 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fe0d3a33300 | 0x7fe0d0a24280 | 17087801411099 | 17087801421405 | 17087801601085 | 17087801602884 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fe0d3a33180 | 0x7fe0d0a242c0 | 17087801623963 | 17087801634685 | 17087801814524 | 17087801816348 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fe0d3a33000 | 0x7fe0d0a24300 | 17087801837787 | 17087801854044 | 17087801946844 | 17087801948764 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fe0d1403e80 | 0x7fe0d0a24340 | 17087801970823 | 17087801980284 | 17087802073404 | 17087802075220 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fe0d1403d00 | 0x7fe0d0a24380 | 17087802107539 | 17087802117724 | 17087802211003 | 17087802212916 |
| 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 | 53 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fe0d1403b80 | 0x7fe0d0a243c0 | 17087802238346 | 17087802247483 | 17087802428603 | 17087802430430 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fe0d1403a00 | 0x7fe0d0a24400 | 17087802445710 | 17087802454843 | 17087802636442 | 17087802638345 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fe0d1403880 | 0x7fe0d0a24440 | 17087802654324 | 17087802663322 | 17087802756922 | 17087802758811 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fe0d1403700 | 0x7fe0d0a24480 | 17087802777971 | 17087802786842 | 17087802879802 | 17087802881668 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fe0d3a33580 | 0x7fe0d0a244c0 | 17087802902887 | 17087802913562 | 17087803006362 | 17087803008254 |
| 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 | 68 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fe0d3a33400 | 0x7fe0d0a24500 | 17087803026364 | 17087803035482 | 17087803214681 | 17087803216598 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fe0d3a33280 | 0x7fe0d0a24540 | 17087803231378 | 17087803239801 | 17087803421241 | 17087803423113 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fe0d3a33100 | 0x7fe0d0a24580 | 17087803439482 | 17087803448761 | 17087803540760 | 17087803542649 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fe0d1403f80 | 0x7fe0d0a245c0 | 17087803561609 | 17087803584440 | 17087803676600 | 17087803678515 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fe0d1403e00 | 0x7fe0d0a24600 | 17087803700105 | 17087803710680 | 17087803803320 | 17087803805542 |
| 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 | 83 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fe0d1403c80 | 0x7fe0d0a24640 | 17087803830101 | 17087803840920 | 17087804021879 | 17087804023706 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fe0d1403b00 | 0x7fe0d0a24680 | 17087804046125 | 17087804056439 | 17087804238999 | 17087804240860 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fe0d1403980 | 0x7fe0d0a246c0 | 17087804265289 | 17087804275959 | 17087804370678 | 17087804372496 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fe0d1403800 | 0x7fe0d0a24700 | 17087804393995 | 17087804404438 | 17087804499478 | 17087804501442 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fe0d1403680 | 0x7fe0d0a24740 | 17087804523842 | 17087804532918 | 17087804626838 | 17087804628749 |
| 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 | 98 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fe0d3a33500 | 0x7fe0d0a24780 | 17087804644868 | 17087804653238 | 17087804833237 | 17087804835363 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fe0d3a33380 | 0x7fe0d0a247c0 | 17087804851943 | 17087804862837 | 17087805044757 | 17087805046577 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fe0d3a33200 | 0x7fe0d0a24800 | 17087805059747 | 17087805068117 | 17087805160917 | 17087805162744 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fe0d3a33080 | 0x7fe0d0a24840 | 17087805181623 | 17087805190836 | 17087805284436 | 17087805286270 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fe0d1403f00 | 0x7fe0d0a24880 | 17087805306110 | 17087805316916 | 17087805410676 | 17087805412567 |
| 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 | 113 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fe0d1403d80 | 0x7fe0d0a248c0 | 17087805429296 | 17087805438516 | 17087805617395 | 17087805619291 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fe0d1403c00 | 0x7fe0d0a24900 | 17087805641100 | 17087805657395 | 17087805836595 | 17087805838645 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fe0d1403a80 | 0x7fe0d0a24940 | 17087805860164 | 17087805869715 | 17087805963955 | 17087805965871 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fe0d1403900 | 0x7fe0d0a24980 | 17087805981141 | 17087805990035 | 17087806085554 | 17087806096968 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fe0d1403780 | 0x7fe0d0a249c0 | 17087806112517 | 17087806122194 | 17087806216594 | 17087806218544 |
| 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 | 128 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fe0d1403600 | 0x7fe0d0a24a00 | 17087806236194 | 17087806244914 | 17087806425074 | 17087806426868 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fe0d3a33480 | 0x7fe0d0a24a40 | 17087806451078 | 17087806461554 | 17087806640273 | 17087806642122 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fe0d3a33300 | 0x7fe0d0a24a80 | 17087806659592 | 17087806674993 | 17087806767953 | 17087806770079 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fe0d3a33180 | 0x7fe0d0a24ac0 | 17087806783778 | 17087806795153 | 17087806888433 | 17087806890335 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fe0d3a33000 | 0x7fe0d0a24b00 | 17087806913025 | 17087806923312 | 17087807014992 | 17087807016852 |
| 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 | 143 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fe0d1403e80 | 0x7fe0d0a24b40 | 17087807034821 | 17087807043312 | 17087807222032 | 17087807223876 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fe0d1403d00 | 0x7fe0d0a24b80 | 17087807236916 | 17087807246832 | 17087807426671 | 17087807428080 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fe0d1403b80 | 0x7fe0d0a24bc0 | 17087807441970 | 17087807450031 | 17087807544431 | 17087807545787 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fe0d1403a00 | 0x7fe0d0a24c00 | 17087807559756 | 17087807568751 | 17087807663471 | 17087807664883 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fe0d1403880 | 0x7fe0d0a24c40 | 17087807685773 | 17087807696591 | 17087807790670 | 17087807791990 |
| 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 | 158 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fe0d1403700 | 0x7fe0d0a24c80 | 17087807806619 | 17087807815150 | 17087807994190 | 17087807995584 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fe0d3a33580 | 0x7fe0d0a24cc0 | 17087808011224 | 17087808018990 | 17087808198829 | 17087808200258 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fe0d3a33400 | 0x7fe0d0a24d00 | 17087808216088 | 17087808225389 | 17087808318989 | 17087808320315 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fe0d3a33280 | 0x7fe0d0a24d40 | 17087808335665 | 17087808344269 | 17087808442989 | 17087808444351 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fe0d3a33100 | 0x7fe0d0a24d80 | 17087808464681 | 17087808475469 | 17087808569069 | 17087808570508 |
| 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 | 173 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fe0d1403f80 | 0x7fe0d0a24dc0 | 17087808586457 | 17087808595149 | 17087808774508 | 17087808775992 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fe0d1403e00 | 0x7fe0d0a24e00 | 17087808791442 | 17087808802028 | 17087808981388 | 17087808982866 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fe0d1403c80 | 0x7fe0d0a24e40 | 17087808998846 | 17087809007628 | 17087809102187 | 17087809103623 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fe0d1403b00 | 0x7fe0d0a24e80 | 17087809117543 | 17087809128107 | 17087809232427 | 17087809233849 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fe0d1403980 | 0x7fe0d0a24ec0 | 17087809255909 | 17087809266507 | 17087809359467 | 17087809360796 |
| 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 | 188 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fe0d1403800 | 0x7fe0d0a24f00 | 17087809375215 | 17087809385387 | 17087809564746 | 17087809566160 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fe0d1403680 | 0x7fe0d0a24f40 | 17087809583069 | 17087809592266 | 17087809772746 | 17087809774104 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fe0d3a33500 | 0x7fe0d0a24f80 | 17087809788224 | 17087809797226 | 17087809890665 | 17087809892101 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fe0d3a33380 | 0x7fe0d0a24fc0 | 17087809906360 | 17087809914985 | 17087810021385 | 17087810022797 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fe0d3a33200 | 0x7fe0d0a25000 | 17087810042356 | 17087810053705 | 17087810148425 | 17087810149863 |
| 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 | 203 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fe0d3a33080 | 0x7fe0d0a25040 | 17087810165163 | 17087810174025 | 17087810354184 | 17087810355558 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fe0d1403f00 | 0x7fe0d0a25080 | 17087810369177 | 17087810378344 | 17087810557704 | 17087810559162 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fe0d1403d80 | 0x7fe0d0a250c0 | 17087810572732 | 17087810582184 | 17087810677384 | 17087810678799 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fe0d1403c00 | 0x7fe0d0a25100 | 17087810693368 | 17087810702024 | 17087810818183 | 17087810819505 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fe0d1403a80 | 0x7fe0d0a25140 | 17087810853944 | 17087810863623 | 17087810957703 | 17087810959071 |
| 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 | 218 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fe0d1403900 | 0x7fe0d0a25180 | 17087810977930 | 17087810986503 | 17087811166022 | 17087811167515 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fe0d1403780 | 0x7fe0d0a251c0 | 17087811182464 | 17087811190182 | 17087811368902 | 17087811370349 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fe0d1403600 | 0x7fe0d0a25200 | 17087811385729 | 17087811394022 | 17087811489382 | 17087811490826 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fe0d3a33480 | 0x7fe0d0a25240 | 17087811505175 | 17087811514182 | 17087811636101 | 17087811637492 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fe0d3a33300 | 0x7fe0d0a25280 | 17087811657291 | 17087811668261 | 17087811762021 | 17087811763498 |
| 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 | 233 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fe0d3a33180 | 0x7fe0d0a252c0 | 17087811779018 | 17087811786981 | 17087811966661 | 17087811968092 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fe0d3a33000 | 0x7fe0d0a25300 | 17087811983262 | 17087811992101 | 17087812171460 | 17087812172937 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fe0d1403e80 | 0x7fe0d0a25340 | 17087812188006 | 17087812196580 | 17087812292100 | 17087812293583 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fe0d1403d00 | 0x7fe0d0a25380 | 17087812307373 | 17087812316260 | 17087812442820 | 17087812444179 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fe0d1403b80 | 0x7fe0d0a253c0 | 17087812464149 | 17087812474819 | 17087812568579 | 17087812570016 |
| 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 | 248 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fe0d1403a00 | 0x7fe0d0a25400 | 17087812586825 | 17087812595459 | 17087812775779 | 17087812777120 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fe0d1403880 | 0x7fe0d0a25440 | 17087812791189 | 17087812799939 | 17087812978818 | 17087812980194 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fe0d1403700 | 0x7fe0d0a25480 | 17087812993274 | 17087813001218 | 17087813094658 | 17087813096171 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fe0d3a33580 | 0x7fe0d0a254c0 | 17087813109751 | 17087813118018 | 17087813248098 | 17087813249527 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fe0d3a33400 | 0x7fe0d0a25500 | 17087813271416 | 17087813282978 | 17087813376097 | 17087813377443 |
| 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 | 263 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fe0d3a33280 | 0x7fe0d0a25540 | 17087813395273 | 17087813403137 | 17087813581697 | 17087813583377 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fe0d3a33100 | 0x7fe0d0a25580 | 17087813598087 | 17087813606177 | 17087813785056 | 17087813786532 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fe0d1403f80 | 0x7fe0d0a255c0 | 17087813802331 | 17087813811136 | 17087813906656 | 17087813908008 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fe0d1403e00 | 0x7fe0d0a25600 | 17087813923008 | 17087813931296 | 17087814070176 | 17087814071504 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fe0d1403c80 | 0x7fe0d0a25640 | 17087814104113 | 17087814114816 | 17087814209535 | 17087814210960 |
| 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 | 278 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fe0d1403b00 | 0x7fe0d0a25680 | 17087814225439 | 17087814233535 | 17087814413695 | 17087814415224 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fe0d1403980 | 0x7fe0d0a256c0 | 17087814429833 | 17087814438175 | 17087814617854 | 17087814619338 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fe0d1403800 | 0x7fe0d0a25700 | 17087814635108 | 17087814642974 | 17087814741214 | 17087814742915 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fe0d1403680 | 0x7fe0d0a25740 | 17087814758744 | 17087814767294 | 17087814912094 | 17087814913780 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fe0d3a33500 | 0x7fe0d0a25780 | 17087814932489 | 17087814940414 | 17087815036093 | 17087815037656 |
| 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 | 293 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fe0d3a33380 | 0x7fe0d0a257c0 | 17087815052506 | 17087815060733 | 17087815241853 | 17087815243361 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fe0d3a33200 | 0x7fe0d0a25800 | 17087815257380 | 17087815265693 | 17087815446652 | 17087815448255 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fe0d3a33080 | 0x7fe0d0a25840 | 17087815462554 | 17087815471132 | 17087815571772 | 17087815573291 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fe0d1403f00 | 0x7fe0d0a25880 | 17087815588191 | 17087815596252 | 17087815751612 | 17087815753416 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fe0d1403d80 | 0x7fe0d0a258c0 | 17087815774406 | 17087815785212 | 17087815880571 | 17087815882173 |
| 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 | 308 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fe0d1403c00 | 0x7fe0d0a25900 | 17087815897982 | 17087815906651 | 17087816084891 | 17087816086367 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fe0d1403a80 | 0x7fe0d0a25940 | 17087816102916 | 17087816110971 | 17087816291130 | 17087816292791 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fe0d1403900 | 0x7fe0d0a25980 | 17087816306211 | 17087816314330 | 17087816422010 | 17087816423597 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fe0d1403780 | 0x7fe0d0a259c0 | 17087816438217 | 17087816446330 | 17087816616890 | 17087816618572 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fe0d1403600 | 0x7fe0d0a25a00 | 17087816639581 | 17087816650170 | 17087816745849 | 17087816747468 |
| 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 | 323 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fe0d3a33480 | 0x7fe0d0a25a40 | 17087816761778 | 17087816769849 | 17087816950169 | 17087816951752 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fe0d3a33300 | 0x7fe0d0a25a80 | 17087816966842 | 17087816974809 | 17087817157048 | 17087817158607 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fe0d3a33180 | 0x7fe0d0a25ac0 | 17087817173056 | 17087817181048 | 17087817291448 | 17087817293093 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fe0d3a33000 | 0x7fe0d0a25b00 | 17087817308452 | 17087817316568 | 17087817497688 | 17087817499247 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fe0d1403e80 | 0x7fe0d0a25b40 | 17087817520726 | 17087817530488 | 17087817632407 | 17087817633743 |
| 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 | 338 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fe0d1403d00 | 0x7fe0d0a25b80 | 17087817650163 | 17087817658007 | 17087817845207 | 17087817846607 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fe0d1403b80 | 0x7fe0d0a25bc0 | 17087817861267 | 17087817869687 | 17087818055766 | 17087818057241 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fe0d1403a00 | 0x7fe0d0a25c00 | 17087818072891 | 17087818086966 | 17087818209526 | 17087818211177 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fe0d1403880 | 0x7fe0d0a25c40 | 17087818225486 | 17087818233686 | 17087818439925 | 17087818486139 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fe0d1403700 | 0x7fe0d0a25c80 | 17087818500989 | 17087818511765 | 17087818621845 | 17087818623295 |
| 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 | 353 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fe0d3a33580 | 0x7fe0d0a25cc0 | 17087818638305 | 17087818646805 | 17087818829525 | 17087818831089 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fe0d3a33400 | 0x7fe0d0a25d00 | 17087818845369 | 17087818853364 | 17087819041684 | 17087819043183 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fe0d3a33280 | 0x7fe0d0a25d40 | 17087819059503 | 17087819066964 | 17087819201524 | 17087819203249 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fe0d3a33100 | 0x7fe0d0a25d80 | 17087819217999 | 17087819226004 | 17087819458643 | 17087819502571 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fe0d1403f80 | 0x7fe0d0a25dc0 | 17087819517540 | 17087819528403 | 17087819655123 | 17087819656496 |
| 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 | 368 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fe0d1403e00 | 0x7fe0d0a25e00 | 17087819671506 | 17087819679923 | 17087819873202 | 17087819874690 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fe0d1403c80 | 0x7fe0d0a25e40 | 17087819888890 | 17087819897362 | 17087820089522 | 17087820091154 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fe0d1403b00 | 0x7fe0d0a25e80 | 17087820105664 | 17087820114002 | 17087820274001 | 17087820275619 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fe0d1403980 | 0x7fe0d0a25ec0 | 17087820290888 | 17087820298961 | 17087820582640 | 17087820626199 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fe0d1403800 | 0x7fe0d0a25f00 | 17087820640718 | 17087820651600 | 17087820801200 | 17087820802554 |
| 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 | 383 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fe0d1403680 | 0x7fe0d0a25f40 | 17087820818273 | 17087820825840 | 17087821034159 | 17087821055327 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fe0d3a33500 | 0x7fe0d0a25f80 | 17087821063397 | 17087821073679 | 17087821283919 | 17087821300570 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fe0d3a33380 | 0x7fe0d0a25fc0 | 17087821309410 | 17087821319599 | 17087821505198 | 17087821506564 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fe0d3a33200 | 0x7fe0d0a26000 | 17087821523364 | 17087821531278 | 17087821865997 | 17087821881593 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fe0d3a33080 | 0x7fe0d0a26040 | 17087821897343 | 17087821908077 | 17087822074957 | 17087822080518 |
| 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 | 398 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fe0d1403f00 | 0x7fe0d0a26080 | 17087822116827 | 17087822127597 | 17087822355436 | 17087822397529 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fe0d1403d80 | 0x7fe0d0a260c0 | 17087822407449 | 17087822417836 | 17087822647436 | 17087822687341 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fe0d1403c00 | 0x7fe0d0a26100 | 17087822696131 | 17087822706475 | 17087822917675 | 17087822960793 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fe0d1403a80 | 0x7fe0d0a26140 | 17087822971403 | 17087822980715 | 17087823365834 | 17087823409581 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fe0d1403900 | 0x7fe0d0a26180 | 17087823424920 | 17087823435754 | 17087823623593 | 17087823625025 |
| 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 | 413 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fe0d1403780 | 0x7fe0d0a261c0 | 17087823639884 | 17087823647753 | 17087823897993 | 17087823922226 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fe0d1403600 | 0x7fe0d0a26200 | 17087823932756 | 17087823942953 | 17087824191112 | 17087824213728 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fe0d3a33480 | 0x7fe0d0a26240 | 17087824223808 | 17087824234952 | 17087824471431 | 17087824493500 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fe0d3a33300 | 0x7fe0d0a26280 | 17087824502330 | 17087824512391 | 17087824965670 | 17087824983697 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fe0d3a33180 | 0x7fe0d0a262c0 | 17087824999156 | 17087825009670 | 17087825233990 | 17087825250449 |
| 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 | 428 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fe0d3a33000 | 0x7fe0d0a26300 | 17087825258909 | 17087825269189 | 17087825567269 | 17087825582780 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fe0d1403e80 | 0x7fe0d0a26340 | 17087825592939 | 17087825602469 | 17087825900388 | 17087825918620 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fe0d1403d00 | 0x7fe0d0a26380 | 17087825928170 | 17087825938468 | 17087826235267 | 17087826254741 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fe0d1403b80 | 0x7fe0d0a263c0 | 17087826265831 | 17087826276067 | 17087826832706 | 17087826872923 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fe0d1403a00 | 0x7fe0d0a26400 | 17087826888443 | 17087826898946 | 17087827162945 | 17087827206204 |
| 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 | 443 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fe0d1403880 | 0x7fe0d0a26440 | 17087827214204 | 17087827225185 | 17087827575264 | 17087827619032 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fe0d1403700 | 0x7fe0d0a26480 | 17087827627012 | 17087827637344 | 17087827988063 | 17087828010061 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fe0d3a33580 | 0x7fe0d0a264c0 | 17087828021941 | 17087828032383 | 17087828380062 | 17087828402770 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fe0d3a33400 | 0x7fe0d0a26500 | 17087828413230 | 17087828423582 | 17087829083741 | 17087829124060 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fe0d3a33280 | 0x7fe0d0a26540 | 17087829140060 | 17087829149980 | 17087829597019 | 17087829613716 |
| 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 | 458 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fe0d3a33100 | 0x7fe0d0a26580 | 17087829622616 | 17087829633019 | 17087830096698 | 17087830121732 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fe0d1403f80 | 0x7fe0d0a265c0 | 17087830132322 | 17087830142618 | 17087830605817 | 17087830649837 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fe0d1403e00 | 0x7fe0d0a26600 | 17087830657847 | 17087830668217 | 17087831119736 | 17087831162883 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fe0d1403c80 | 0x7fe0d0a26640 | 17087831170533 | 17087831181016 | 17087832050934 | 17087832094547 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fe0d1403b00 | 0x7fe0d0a26680 | 17087832111356 | 17087832122133 | 17087832976531 | 17087833024641 |
| 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 | 473 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fe0d1403980 | 0x7fe0d0a266c0 | 17087833033250 | 17087833043731 | 17087833928849 | 17087833972294 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fe0d1403800 | 0x7fe0d0a26700 | 17087833984154 | 17087833994609 | 17087834873807 | 17087834920927 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fe0d1403680 | 0x7fe0d0a26740 | 17087834930377 | 17087834947407 | 17087835806765 | 17087835852231 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fe0d3a33500 | 0x7fe0d0a26780 | 17087835862011 | 17087835871405 | 17087837569481 | 17087837636281 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fe0d3a33380 | 0x7fe0d0a267c0 | 17087837653510 | 17087837664200 | 17087839329637 | 17087839399871 |
| 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 | 488 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fe0d3a33200 | 0x7fe0d0a26800 | 17087839412421 | 17087839430276 | 17087841155232 | 17087841228130 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fe0d3a33080 | 0x7fe0d0a26840 | 17087841239310 | 17087841248192 | 17087842963388 | 17087843036049 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fe0d1403f00 | 0x7fe0d0a26880 | 17087843045619 | 17087843060508 | 17087844734104 | 17087844803139 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 192599 | 192599 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fe0d1403d80 | 0x7fe0d0a268c0 | 17087844811899 | 17087844833624 | 17087848191376 | 17087848263002 |