38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 138652 | 138652 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f5f48204280 | 0 | 0 | 0 | 15906151326125 | 15905443557786 | 15906300453989 | 15906300545499 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 138652 | 138652 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f5f48223f80 | 0 | 0 | 0 | 15906305702753 | 15906300453989 | 15906305829843 | 15906305834530 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f5f56a38380 | 0x7f5f48223fc0 | 0 | 0 | 0 | 15906305869720 | 15906305829843 | 15906306214644 | 15906306217152 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f5f56a38200 | 0x7f5f48224000 | 0 | 0 | 0 | 15906306253681 | 15906306214644 | 15906306625045 | 15906306627383 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f5f56a38080 | 0x7f5f48224040 | 0 | 0 | 0 | 15906306657842 | 15906306625045 | 15906307023126 | 15906307025554 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f5f54409f00 | 0x7f5f48224080 | 0 | 0 | 0 | 15906307058463 | 15906307023126 | 15906307332247 | 15906307334467 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f5f54409d80 | 0x7f5f482240c0 | 0 | 0 | 0 | 15906307366016 | 15906307332247 | 15906307636567 | 15906307638840 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f5f54409c00 | 0x7f5f48224100 | 0 | 0 | 0 | 15906307682489 | 15906307636567 | 15906307935128 | 15906307937434 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f5f54409a80 | 0x7f5f48224140 | 0 | 0 | 0 | 15906307968693 | 15906307935128 | 15906308322809 | 15906308325105 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f5f54409900 | 0x7f5f48224180 | 0 | 0 | 0 | 15906308355984 | 15906308322809 | 15906308712570 | 15906308714806 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f5f54409780 | 0x7f5f482241c0 | 0 | 0 | 0 | 15906308745026 | 15906308712570 | 15906309027131 | 15906309029319 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f5f54409600 | 0x7f5f48224200 | 0 | 0 | 0 | 15906309060759 | 15906309027131 | 15906309326492 | 15906309328513 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f5f56a38480 | 0x7f5f48224240 | 0 | 0 | 0 | 15906309368142 | 15906309326492 | 15906309626653 | 15906309628836 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f5f56a38300 | 0x7f5f48224280 | 0 | 0 | 0 | 15906309660296 | 15906309626653 | 15906310017374 | 15906310019598 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f5f56a38180 | 0x7f5f482242c0 | 0 | 0 | 0 | 15906310051017 | 15906310017374 | 15906310436255 | 15906310438778 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f5f56a38000 | 0x7f5f48224300 | 0 | 0 | 0 | 15906310469537 | 15906310436255 | 15906310734176 | 15906310735802 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f5f54409e80 | 0x7f5f48224340 | 0 | 0 | 0 | 15906310766681 | 15906310734176 | 15906311008096 | 15906311009895 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f5f54409d00 | 0x7f5f48224380 | 0 | 0 | 0 | 15906311047785 | 15906311008096 | 15906311285057 | 15906311286649 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f5f54409b80 | 0x7f5f482243c0 | 0 | 0 | 0 | 15906311318669 | 15906311285057 | 15906311649378 | 15906311651001 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f5f54409a00 | 0x7f5f48224400 | 0 | 0 | 0 | 15906311681630 | 15906311649378 | 15906312012259 | 15906312013893 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f5f54409880 | 0x7f5f48224440 | 0 | 0 | 0 | 15906312044142 | 15906312012259 | 15906312293220 | 15906312294907 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f5f54409700 | 0x7f5f48224480 | 0 | 0 | 0 | 15906312325976 | 15906312293220 | 15906312568261 | 15906312569991 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f5f56a38580 | 0x7f5f482244c0 | 0 | 0 | 0 | 15906312607530 | 15906312568261 | 15906312843301 | 15906312845134 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f5f56a38400 | 0x7f5f48224500 | 0 | 0 | 0 | 15906312877004 | 15906312843301 | 15906313203622 | 15906313205336 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f5f56a38280 | 0x7f5f48224540 | 0 | 0 | 0 | 15906313236006 | 15906313203622 | 15906313568263 | 15906313569968 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f5f56a38100 | 0x7f5f48224580 | 0 | 0 | 0 | 15906313600768 | 15906313568263 | 15906313845544 | 15906313847332 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f5f54409f80 | 0x7f5f482245c0 | 0 | 0 | 0 | 15906313878771 | 15906313845544 | 15906314121705 | 15906314123296 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f5f54409e00 | 0x7f5f48224600 | 0 | 0 | 0 | 15906314161585 | 15906314121705 | 15906314404425 | 15906314406220 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f5f54409c80 | 0x7f5f48224640 | 0 | 0 | 0 | 15906314437119 | 15906314404425 | 15906314770186 | 15906314771951 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f5f54409b00 | 0x7f5f48224680 | 0 | 0 | 0 | 15906314802581 | 15906314770186 | 15906315134507 | 15906315136303 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f5f54409980 | 0x7f5f482246c0 | 0 | 0 | 0 | 15906315167223 | 15906315134507 | 15906315415788 | 15906315417587 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f5f54409800 | 0x7f5f48224700 | 0 | 0 | 0 | 15906315447556 | 15906315415788 | 15906315694509 | 15906315696401 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f5f54409680 | 0x7f5f48224740 | 0 | 0 | 0 | 15906315734610 | 15906315694509 | 15906315977390 | 15906315979034 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f5f56a38500 | 0x7f5f48224780 | 0 | 0 | 0 | 15906316009694 | 15906315977390 | 15906316342351 | 15906316344126 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f5f56a38380 | 0x7f5f482247c0 | 0 | 0 | 0 | 15906316375076 | 15906316342351 | 15906316706672 | 15906316708278 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f5f56a38200 | 0x7f5f48224800 | 0 | 0 | 0 | 15906316739107 | 15906316706672 | 15906316982032 | 15906316983692 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f5f56a38080 | 0x7f5f48224840 | 0 | 0 | 0 | 15906317014511 | 15906316982032 | 15906317258193 | 15906317260046 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f5f54409f00 | 0x7f5f48224880 | 0 | 0 | 0 | 15906317298135 | 15906317258193 | 15906317536594 | 15906317538310 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f5f54409d80 | 0x7f5f482248c0 | 0 | 0 | 0 | 15906317568389 | 15906317536594 | 15906317897395 | 15906317899212 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f5f54409c00 | 0x7f5f48224900 | 0 | 0 | 0 | 15906317930321 | 15906317897395 | 15906318263476 | 15906318265533 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f5f54409a80 | 0x7f5f48224940 | 0 | 0 | 0 | 15906318297413 | 15906318263476 | 15906318544756 | 15906318546517 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f5f54409900 | 0x7f5f48224980 | 0 | 0 | 0 | 15906318577576 | 15906318544756 | 15906318822837 | 15906318824651 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f5f54409780 | 0x7f5f482249c0 | 0 | 0 | 0 | 15906318862850 | 15906318822837 | 15906319105558 | 15906319107185 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f5f54409600 | 0x7f5f48224a00 | 0 | 0 | 0 | 15906319137534 | 15906319105558 | 15906319468119 | 15906319469767 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f5f56a38480 | 0x7f5f48224a40 | 0 | 0 | 0 | 15906319500676 | 15906319468119 | 15906319836760 | 15906319838438 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f5f56a38300 | 0x7f5f48224a80 | 0 | 0 | 0 | 15906319869828 | 15906319836760 | 15906320112761 | 15906320114442 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f5f56a38180 | 0x7f5f48224ac0 | 0 | 0 | 0 | 15906320145272 | 15906320112761 | 15906320390841 | 15906320392506 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f5f56a38000 | 0x7f5f48224b00 | 0 | 0 | 0 | 15906320430665 | 15906320390841 | 15906320665882 | 15906320667760 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f5f54409e80 | 0x7f5f48224b40 | 0 | 0 | 0 | 15906320699609 | 15906320665882 | 15906321027643 | 15906321029312 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f5f54409d00 | 0x7f5f48224b80 | 0 | 0 | 0 | 15906321060721 | 15906321027643 | 15906321390684 | 15906321392374 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f5f54409b80 | 0x7f5f48224bc0 | 0 | 0 | 0 | 15906321422863 | 15906321390684 | 15906321665885 | 15906321667558 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f5f54409a00 | 0x7f5f48224c00 | 0 | 0 | 0 | 15906321698527 | 15906321665885 | 15906321943166 | 15906321945082 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f5f54409880 | 0x7f5f48224c40 | 0 | 0 | 0 | 15906321982701 | 15906321943166 | 15906322235166 | 15906322236965 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f5f54409700 | 0x7f5f48224c80 | 0 | 0 | 0 | 15906322267985 | 15906322235166 | 15906322601567 | 15906322603227 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f5f56a38580 | 0x7f5f48224cc0 | 0 | 0 | 0 | 15906322633926 | 15906322601567 | 15906322964288 | 15906322966059 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f5f56a38400 | 0x7f5f48224d00 | 0 | 0 | 0 | 15906322996588 | 15906322964288 | 15906323241889 | 15906323243643 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f5f56a38280 | 0x7f5f48224d40 | 0 | 0 | 0 | 15906323274482 | 15906323241889 | 15906323524450 | 15906323526246 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f5f56a38100 | 0x7f5f48224d80 | 0 | 0 | 0 | 15906323564756 | 15906323524450 | 15906323802850 | 15906323804630 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f5f54409f80 | 0x7f5f48224dc0 | 0 | 0 | 0 | 15906323836080 | 15906323802850 | 15906324170691 | 15906324172512 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f5f54409e00 | 0x7f5f48224e00 | 0 | 0 | 0 | 15906324203321 | 15906324170691 | 15906324531812 | 15906324533614 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f5f54409c80 | 0x7f5f48224e40 | 0 | 0 | 0 | 15906324563823 | 15906324531812 | 15906324809413 | 15906324811068 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f5f54409b00 | 0x7f5f48224e80 | 0 | 0 | 0 | 15906324841247 | 15906324809413 | 15906325095334 | 15906325097161 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f5f54409980 | 0x7f5f48224ec0 | 0 | 0 | 0 | 15906325134741 | 15906325095334 | 15906325371975 | 15906325373695 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f5f54409800 | 0x7f5f48224f00 | 0 | 0 | 0 | 15906325405924 | 15906325371975 | 15906325731976 | 15906325733817 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f5f54409680 | 0x7f5f48224f40 | 0 | 0 | 0 | 15906325764246 | 15906325731976 | 15906326094537 | 15906326096419 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f5f56a38500 | 0x7f5f48224f80 | 0 | 0 | 0 | 15906326127848 | 15906326094537 | 15906326374857 | 15906326376443 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f5f56a38380 | 0x7f5f48224fc0 | 0 | 0 | 0 | 15906326407462 | 15906326374857 | 15906326664458 | 15906326666036 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f5f56a38200 | 0x7f5f48225000 | 0 | 0 | 0 | 15906326704605 | 15906326664458 | 15906326938539 | 15906326940240 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f5f56a38080 | 0x7f5f48225040 | 0 | 0 | 0 | 15906326971020 | 15906326938539 | 15906327306860 | 15906327308802 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f5f54409f00 | 0x7f5f48225080 | 0 | 0 | 0 | 15906327340341 | 15906327306860 | 15906327669421 | 15906327671164 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f5f54409d80 | 0x7f5f482250c0 | 0 | 0 | 0 | 15906327702013 | 15906327669421 | 15906327945582 | 15906327947478 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f5f54409c00 | 0x7f5f48225100 | 0 | 0 | 0 | 15906327978917 | 15906327945582 | 15906328239982 | 15906328241721 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f5f54409a80 | 0x7f5f48225140 | 0 | 0 | 0 | 15906328291050 | 15906328239982 | 15906328514863 | 15906328516735 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f5f54409900 | 0x7f5f48225180 | 0 | 0 | 0 | 15906328547314 | 15906328514863 | 15906328883344 | 15906328885027 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f5f54409780 | 0x7f5f482251c0 | 0 | 0 | 0 | 15906328916126 | 15906328883344 | 15906329244305 | 15906329246039 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f5f54409600 | 0x7f5f48225200 | 0 | 0 | 0 | 15906329276708 | 15906329244305 | 15906329520306 | 15906329522113 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f5f56a38480 | 0x7f5f48225240 | 0 | 0 | 0 | 15906329552732 | 15906329520306 | 15906329823667 | 15906329825276 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f5f56a38300 | 0x7f5f48225280 | 0 | 0 | 0 | 15906329863385 | 15906329823667 | 15906330112147 | 15906330114069 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f5f56a38180 | 0x7f5f482252c0 | 0 | 0 | 0 | 15906330146939 | 15906330112147 | 15906330481108 | 15906330482871 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f5f56a38000 | 0x7f5f48225300 | 0 | 0 | 0 | 15906330514460 | 15906330481108 | 15906330845749 | 15906330847443 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f5f54409e80 | 0x7f5f48225340 | 0 | 0 | 0 | 15906330877972 | 15906330845749 | 15906331124470 | 15906331126147 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f5f54409d00 | 0x7f5f48225380 | 0 | 0 | 0 | 15906331156496 | 15906331124470 | 15906331430711 | 15906331432480 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f5f54409b80 | 0x7f5f482253c0 | 0 | 0 | 0 | 15906331470049 | 15906331430711 | 15906331705592 | 15906331707294 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f5f54409a00 | 0x7f5f48225400 | 0 | 0 | 0 | 15906331738143 | 15906331705592 | 15906332066392 | 15906332068056 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f5f54409880 | 0x7f5f48225440 | 0 | 0 | 0 | 15906332099315 | 15906332066392 | 15906332427673 | 15906332429458 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f5f54409700 | 0x7f5f48225480 | 0 | 0 | 0 | 15906332459707 | 15906332427673 | 15906332703194 | 15906332704891 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f5f56a38580 | 0x7f5f482254c0 | 0 | 0 | 0 | 15906332735481 | 15906332703194 | 15906333022555 | 15906333024234 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f5f56a38400 | 0x7f5f48225500 | 0 | 0 | 0 | 15906333063133 | 15906333022555 | 15906333307836 | 15906333309478 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f5f56a38280 | 0x7f5f48225540 | 0 | 0 | 0 | 15906333339717 | 15906333307836 | 15906333671837 | 15906333673500 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f5f56a38100 | 0x7f5f48225580 | 0 | 0 | 0 | 15906333705019 | 15906333671837 | 15906334035038 | 15906334036622 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f5f54409f80 | 0x7f5f482255c0 | 0 | 0 | 0 | 15906334067301 | 15906334035038 | 15906334324478 | 15906334326375 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f5f54409e00 | 0x7f5f48225600 | 0 | 0 | 0 | 15906334357355 | 15906334324478 | 15906334645279 | 15906334646998 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f5f54409c80 | 0x7f5f48225640 | 0 | 0 | 0 | 15906334685177 | 15906334645279 | 15906334930240 | 15906334932152 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f5f54409b00 | 0x7f5f48225680 | 0 | 0 | 0 | 15906334961751 | 15906334930240 | 15906335292801 | 15906335294434 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f5f54409980 | 0x7f5f482256c0 | 0 | 0 | 0 | 15906335325393 | 15906335292801 | 15906335656322 | 15906335657906 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f5f54409800 | 0x7f5f48225700 | 0 | 0 | 0 | 15906335688705 | 15906335656322 | 15906335934723 | 15906335936420 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f5f54409680 | 0x7f5f48225740 | 0 | 0 | 0 | 15906335966699 | 15906335934723 | 15906336263684 | 15906336265352 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f5f56a38500 | 0x7f5f48225780 | 0 | 0 | 0 | 15906336303531 | 15906336263684 | 15906336545444 | 15906336547146 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f5f56a38380 | 0x7f5f482257c0 | 0 | 0 | 0 | 15906336578515 | 15906336545444 | 15906336906565 | 15906336908278 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f5f56a38200 | 0x7f5f48225800 | 0 | 0 | 0 | 15906336939537 | 15906336906565 | 15906337268486 | 15906337270090 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f5f56a38080 | 0x7f5f48225840 | 0 | 0 | 0 | 15906337300379 | 15906337268486 | 15906337552007 | 15906337553844 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f5f54409f00 | 0x7f5f48225880 | 0 | 0 | 0 | 15906337585293 | 15906337552007 | 15906337890248 | 15906337891916 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f5f54409d80 | 0x7f5f482258c0 | 0 | 0 | 0 | 15906337930365 | 15906337890248 | 15906338168969 | 15906338170970 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f5f54409c00 | 0x7f5f48225900 | 0 | 0 | 0 | 15906338202229 | 15906338168969 | 15906338536010 | 15906338537872 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f5f54409a80 | 0x7f5f48225940 | 0 | 0 | 0 | 15906338569441 | 15906338536010 | 15906338898891 | 15906338900544 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f5f54409900 | 0x7f5f48225980 | 0 | 0 | 0 | 15906338930863 | 15906338898891 | 15906339186891 | 15906339188607 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f5f54409780 | 0x7f5f482259c0 | 0 | 0 | 0 | 15906339219307 | 15906339186891 | 15906339539852 | 15906339541569 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f5f54409600 | 0x7f5f48225a00 | 0 | 0 | 0 | 15906339580448 | 15906339539852 | 15906339817133 | 15906339818883 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f5f56a38480 | 0x7f5f48225a40 | 0 | 0 | 0 | 15906339849632 | 15906339817133 | 15906340178894 | 15906340180535 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f5f56a38300 | 0x7f5f48225a80 | 0 | 0 | 0 | 15906340211454 | 15906340178894 | 15906340540655 | 15906340542277 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f5f56a38180 | 0x7f5f48225ac0 | 0 | 0 | 0 | 15906340572626 | 15906340540655 | 15906340832016 | 15906340833790 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f5f56a38000 | 0x7f5f48225b00 | 0 | 0 | 0 | 15906340864870 | 15906340832016 | 15906341194097 | 15906341195862 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f5f54409e80 | 0x7f5f48225b40 | 0 | 0 | 0 | 15906341233912 | 15906341194097 | 15906341478098 | 15906341479786 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f5f54409d00 | 0x7f5f48225b80 | 0 | 0 | 0 | 15906341510745 | 15906341478098 | 15906341843539 | 15906341845238 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f5f54409b80 | 0x7f5f48225bc0 | 0 | 0 | 0 | 15906341876107 | 15906341843539 | 15906342210260 | 15906342212140 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f5f54409a00 | 0x7f5f48225c00 | 0 | 0 | 0 | 15906342243579 | 15906342210260 | 15906342525780 | 15906342527633 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f5f54409880 | 0x7f5f48225c40 | 0 | 0 | 0 | 15906342558622 | 15906342525780 | 15906342916981 | 15906342962803 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f5f54409700 | 0x7f5f48225c80 | 0 | 0 | 0 | 15906342982432 | 15906342916981 | 15906343246102 | 15906343247967 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f5f56a38580 | 0x7f5f48225cc0 | 0 | 0 | 0 | 15906343278066 | 15906343246102 | 15906343610743 | 15906343612338 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f5f56a38400 | 0x7f5f48225d00 | 0 | 0 | 0 | 15906343643758 | 15906343610743 | 15906343975064 | 15906343976720 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f5f56a38280 | 0x7f5f48225d40 | 0 | 0 | 0 | 15906344007120 | 15906343975064 | 15906344292185 | 15906344293833 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f5f56a38100 | 0x7f5f48225d80 | 0 | 0 | 0 | 15906344325882 | 15906344292185 | 15906344707866 | 15906344753523 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f5f54409f80 | 0x7f5f48225dc0 | 0 | 0 | 0 | 15906344772242 | 15906344707866 | 15906345050747 | 15906345052426 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f5f54409e00 | 0x7f5f48225e00 | 0 | 0 | 0 | 15906345083076 | 15906345050747 | 15906345424828 | 15906345444217 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f5f54409c80 | 0x7f5f48225e40 | 0 | 0 | 0 | 15906345457287 | 15906345424828 | 15906345807549 | 15906345826929 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f5f54409b00 | 0x7f5f48225e80 | 0 | 0 | 0 | 15906345839609 | 15906345807549 | 15906346163390 | 15906346165511 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f5f54409980 | 0x7f5f48225ec0 | 0 | 0 | 0 | 15906346196821 | 15906346163390 | 15906346633631 | 15906346656221 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f5f54409800 | 0x7f5f48225f00 | 0 | 0 | 0 | 15906346674840 | 15906346633631 | 15906346974752 | 15906346976453 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f5f54409680 | 0x7f5f48225f40 | 0 | 0 | 0 | 15906347006763 | 15906346974752 | 15906347371073 | 15906347413614 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f5f56a38500 | 0x7f5f48225f80 | 0 | 0 | 0 | 15906347424343 | 15906347371073 | 15906347790914 | 15906347832854 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f5f56a38380 | 0x7f5f48225fc0 | 0 | 0 | 0 | 15906347843374 | 15906347790914 | 15906348189955 | 15906348191586 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f5f56a38200 | 0x7f5f48226000 | 0 | 0 | 0 | 15906348222546 | 15906348189955 | 15906348707877 | 15906348749684 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f5f56a38080 | 0x7f5f48226040 | 0 | 0 | 0 | 15906348768124 | 15906348707877 | 15906349086118 | 15906349087837 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f5f54409f00 | 0x7f5f48226080 | 0 | 0 | 0 | 15906349119236 | 15906349086118 | 15906349497799 | 15906349539237 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f5f54409d80 | 0x7f5f482260c0 | 0 | 0 | 0 | 15906349549786 | 15906349497799 | 15906349942600 | 15906349960877 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f5f54409c00 | 0x7f5f48226100 | 0 | 0 | 0 | 15906349974827 | 15906349942600 | 15906350350441 | 15906350394478 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f5f54409a80 | 0x7f5f48226140 | 0 | 0 | 0 | 15906350405427 | 15906350350441 | 15906350954763 | 15906350999094 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f5f54409900 | 0x7f5f48226180 | 0 | 0 | 0 | 15906351017594 | 15906350954763 | 15906351355884 | 15906351357586 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f5f54409780 | 0x7f5f482261c0 | 0 | 0 | 0 | 15906351388295 | 15906351355884 | 15906351796525 | 15906351838435 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f5f54409600 | 0x7f5f48226200 | 0 | 0 | 0 | 15906351848985 | 15906351796525 | 15906352255566 | 15906352297715 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f5f56a38480 | 0x7f5f48226240 | 0 | 0 | 0 | 15906352308925 | 15906352255566 | 15906352706127 | 15906352747625 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f5f56a38300 | 0x7f5f48226280 | 0 | 0 | 0 | 15906352759365 | 15906352706127 | 15906353369809 | 15906353412070 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f5f56a38180 | 0x7f5f482262c0 | 0 | 0 | 0 | 15906353431060 | 15906353369809 | 15906353807890 | 15906353826151 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f5f56a38000 | 0x7f5f48226300 | 0 | 0 | 0 | 15906353840911 | 15906353807890 | 15906354296692 | 15906354346039 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f5f54409e80 | 0x7f5f48226340 | 0 | 0 | 0 | 15906354357099 | 15906354296692 | 15906354824053 | 15906354868398 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f5f54409d00 | 0x7f5f48226380 | 0 | 0 | 0 | 15906354879087 | 15906354824053 | 15906355337814 | 15906355379656 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f5f54409b80 | 0x7f5f482263c0 | 0 | 0 | 0 | 15906355390156 | 15906355337814 | 15906356104697 | 15906356146599 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f5f54409a00 | 0x7f5f48226400 | 0 | 0 | 0 | 15906356166059 | 15906356104697 | 15906356581338 | 15906356622928 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f5f54409880 | 0x7f5f48226440 | 0 | 0 | 0 | 15906356633848 | 15906356581338 | 15906357142139 | 15906357183726 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f5f54409700 | 0x7f5f48226480 | 0 | 0 | 0 | 15906357194296 | 15906357142139 | 15906357701181 | 15906357742863 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f5f56a38580 | 0x7f5f482264c0 | 0 | 0 | 0 | 15906357753413 | 15906357701181 | 15906358259582 | 15906358304021 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f5f56a38400 | 0x7f5f48226500 | 0 | 0 | 0 | 15906358315651 | 15906358259582 | 15906359136225 | 15906359179931 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f5f56a38280 | 0x7f5f48226540 | 0 | 0 | 0 | 15906359198771 | 15906359136225 | 15906359799586 | 15906359841107 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f5f56a38100 | 0x7f5f48226580 | 0 | 0 | 0 | 15906359851806 | 15906359799586 | 15906360473188 | 15906360516231 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f5f54409f80 | 0x7f5f482265c0 | 0 | 0 | 0 | 15906360526871 | 15906360473188 | 15906361154310 | 15906361196206 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f5f54409e00 | 0x7f5f48226600 | 0 | 0 | 0 | 15906361206596 | 15906361154310 | 15906361817992 | 15906361859761 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f5f54409c80 | 0x7f5f48226640 | 0 | 0 | 0 | 15906361870761 | 15906361817992 | 15906362902475 | 15906362952127 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f5f54409b00 | 0x7f5f48226680 | 0 | 0 | 0 | 15906362973047 | 15906362902381 | 15906363979983 | 15906364051763 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f5f54409980 | 0x7f5f482266c0 | 0 | 0 | 0 | 15906364063233 | 15906363979983 | 15906365124465 | 15906365191348 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f5f54409800 | 0x7f5f48226700 | 0 | 0 | 0 | 15906365202247 | 15906365124465 | 15906366253588 | 15906366324642 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f5f54409680 | 0x7f5f48226740 | 0 | 0 | 0 | 15906366335942 | 15906366253588 | 15906367376311 | 15906367443637 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f5f56a38500 | 0x7f5f48226780 | 0 | 0 | 0 | 15906367455267 | 15906367376311 | 15906369327516 | 15906369395324 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f5f56a38380 | 0x7f5f482267c0 | 0 | 0 | 0 | 15906369413653 | 15906369327516 | 15906371245760 | 15906371323511 |
| 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 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f5f56a38200 | 0x7f5f48226800 | 0 | 0 | 0 | 15906371334960 | 15906371245760 | 15906373245925 | 15906373311356 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f5f56a38080 | 0x7f5f48226840 | 0 | 0 | 0 | 15906373322066 | 15906373245925 | 15906375213450 | 15906375285242 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f5f54409f00 | 0x7f5f48226880 | 0 | 0 | 0 | 15906375297482 | 15906375213450 | 15906377146415 | 15906377213140 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 138652 | 138652 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f5f54409d80 | 0x7f5f482268c0 | 0 | 0 | 0 | 15906377224349 | 15906377146415 | 15906380752504 | 15906380831479 |