39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 863012 | 863017 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7ff876004180 | 12075147439705970 | 12075147439751938 | 12075147440072415 | 12075147440177957 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 863012 | 863017 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7ff876035100 | 12075147454372485 | 12075147454470885 | 12075147454477285 | 12075147454482670 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7ff981bfa900 | 0x7ff876035140 | 12075147454526472 | 12075147454541604 | 12075147454675843 | 12075147454679055 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7ff981bfa800 | 0x7ff876035180 | 12075147454720642 | 12075147454733442 | 12075147454975840 | 12075147455073368 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7ff981bfa700 | 0x7ff8760351c0 | 12075147455099136 | 12075147455111999 | 12075147455360957 | 12075147455457372 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7ff981bfa600 | 0x7ff876035200 | 12075147455483220 | 12075147455495676 | 12075147455621114 | 12075147455624452 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7ff981bfa500 | 0x7ff876035240 | 12075147455651773 | 12075147455663354 | 12075147455788953 | 12075147455792134 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7ff981bfa400 | 0x7ff876035280 | 12075147455844130 | 12075147455856152 | 12075147455979831 | 12075147455982948 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7ff981bfa300 | 0x7ff8760352c0 | 12075147456014547 | 12075147456026871 | 12075147456277269 | 12075147456375548 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7ff981bfaa00 | 0x7ff876035300 | 12075147456396286 | 12075147456411667 | 12075147456654705 | 12075147456751577 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7ff981bfa900 | 0x7ff876035340 | 12075147456775972 | 12075147456788304 | 12075147456912623 | 12075147456915882 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7ff981bfa800 | 0x7ff876035380 | 12075147456946449 | 12075147456957582 | 12075147457082701 | 12075147457085818 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7ff981bfa700 | 0x7ff8760353c0 | 12075147457131623 | 12075147457143501 | 12075147457267500 | 12075147457270401 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7ff981bfa600 | 0x7ff876035400 | 12075147457297331 | 12075147457309259 | 12075147457560137 | 12075147457631812 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7ff981bfa500 | 0x7ff876035440 | 12075147457656118 | 12075147457668296 | 12075147457952293 | 12075147458020635 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7ff981bfa400 | 0x7ff876035480 | 12075147458041053 | 12075147458055013 | 12075147458179971 | 12075147458183528 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7ff981bfa300 | 0x7ff8760354c0 | 12075147458208374 | 12075147458220131 | 12075147458346050 | 12075147458349005 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7ff981bfaa00 | 0x7ff876035500 | 12075147458383790 | 12075147458395650 | 12075147458520128 | 12075147458523069 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7ff981bfa900 | 0x7ff876035540 | 12075147458548556 | 12075147458560288 | 12075147458814366 | 12075147458886264 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7ff981bfa800 | 0x7ff876035580 | 12075147458906972 | 12075147458919005 | 12075147459161403 | 12075147459230473 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7ff981bfa700 | 0x7ff8760355c0 | 12075147459251362 | 12075147459262842 | 12075147459387321 | 12075147459390591 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7ff981bfa600 | 0x7ff876035600 | 12075147459415828 | 12075147459427320 | 12075147459552439 | 12075147459555367 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7ff981bfa500 | 0x7ff876035640 | 12075147459591925 | 12075147459603799 | 12075147459728278 | 12075147459731294 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7ff981bfa400 | 0x7ff876035680 | 12075147459756250 | 12075147459768277 | 12075147460018035 | 12075147460097465 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7ff981bfa300 | 0x7ff8760356c0 | 12075147460117632 | 12075147460128594 | 12075147460373392 | 12075147460440332 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7ff981bfaa00 | 0x7ff876035700 | 12075147460459547 | 12075147460471951 | 12075147460596430 | 12075147460599558 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7ff981bfa900 | 0x7ff876035740 | 12075147460625386 | 12075147460636909 | 12075147460761708 | 12075147460764674 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7ff981bfa800 | 0x7ff876035780 | 12075147460798708 | 12075147460809868 | 12075147460934827 | 12075147460937876 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7ff981bfa700 | 0x7ff8760357c0 | 12075147460962642 | 12075147460974026 | 12075147461226664 | 12075147461328402 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7ff981bfa600 | 0x7ff876035800 | 12075147461347828 | 12075147461359623 | 12075147461602661 | 12075147461680316 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7ff981bfa500 | 0x7ff876035840 | 12075147461700003 | 12075147461711300 | 12075147461835459 | 12075147461838600 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7ff981bfa400 | 0x7ff876035880 | 12075147461863416 | 12075147461875138 | 12075147462000737 | 12075147462011361 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7ff981bfa300 | 0x7ff8760358c0 | 12075147462040816 | 12075147462054337 | 12075147462178975 | 12075147462182109 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7ff981bfaa00 | 0x7ff876035900 | 12075147462206253 | 12075147462219455 | 12075147462470493 | 12075147462523403 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7ff981bfa900 | 0x7ff876035940 | 12075147462542649 | 12075147462563932 | 12075147462807130 | 12075147462884143 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7ff981bfa800 | 0x7ff876035980 | 12075147462904120 | 12075147462916409 | 12075147463041368 | 12075147463044792 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7ff981bfa700 | 0x7ff8760359c0 | 12075147463069608 | 12075147463081207 | 12075147463207606 | 12075147463210660 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7ff981bfa600 | 0x7ff876035a00 | 12075147463245124 | 12075147463261526 | 12075147463386005 | 12075147463389122 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7ff981bfa500 | 0x7ff876035a40 | 12075147463414188 | 12075147463427444 | 12075147463680562 | 12075147463702594 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7ff981bfa400 | 0x7ff876035a80 | 12075147463722000 | 12075147463734801 | 12075147463977679 | 12075147464025584 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7ff981bfa300 | 0x7ff876035ac0 | 12075147464045882 | 12075147464058959 | 12075147464183597 | 12075147464187085 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7ff981bfaa00 | 0x7ff876035b00 | 12075147464214115 | 12075147464227437 | 12075147464353836 | 12075147464356890 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7ff981bfa900 | 0x7ff876035b40 | 12075147464391003 | 12075147464403755 | 12075147464528874 | 12075147464531955 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7ff981bfa800 | 0x7ff876035b80 | 12075147464556932 | 12075147464568714 | 12075147464828232 | 12075147464852331 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7ff981bfa700 | 0x7ff876035bc0 | 12075147464872639 | 12075147464884071 | 12075147465128389 | 12075147465156185 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7ff981bfa600 | 0x7ff876035c00 | 12075147465174900 | 12075147465186468 | 12075147465310467 | 12075147465313548 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7ff981bfa500 | 0x7ff876035c40 | 12075147465339035 | 12075147465350467 | 12075147465476706 | 12075147465479897 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7ff981bfa400 | 0x7ff876035c80 | 12075147465516465 | 12075147465527585 | 12075147465652064 | 12075147465654912 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7ff981bfa300 | 0x7ff876035cc0 | 12075147465680520 | 12075147465692544 | 12075147465951421 | 12075147465979886 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7ff981bfaa00 | 0x7ff876035d00 | 12075147465999172 | 12075147466013501 | 12075147466258299 | 12075147466289772 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7ff981bfa900 | 0x7ff876035d40 | 12075147466309869 | 12075147466322618 | 12075147466448217 | 12075147466451152 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7ff981bfa800 | 0x7ff876035d80 | 12075147466476469 | 12075147466488537 | 12075147466616856 | 12075147466619715 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7ff981bfa700 | 0x7ff876035dc0 | 12075147466654931 | 12075147466666775 | 12075147466791574 | 12075147466794390 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7ff981bfa600 | 0x7ff876035e00 | 12075147466819627 | 12075147466830934 | 12075147467085971 | 12075147467110547 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7ff981bfa500 | 0x7ff876035e40 | 12075147467130074 | 12075147467141331 | 12075147467389169 | 12075147467412168 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7ff981bfa400 | 0x7ff876035e80 | 12075147467434329 | 12075147467445808 | 12075147467570767 | 12075147467573528 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7ff981bfa300 | 0x7ff876035ec0 | 12075147467598274 | 12075147467611567 | 12075147467739085 | 12075147467742021 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7ff981bfaa00 | 0x7ff876035f00 | 12075147467777006 | 12075147467789325 | 12075147467914124 | 12075147467916916 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7ff981bfa900 | 0x7ff876035f40 | 12075147467942313 | 12075147467955243 | 12075147468212361 | 12075147468240668 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7ff981bfa800 | 0x7ff876035f80 | 12075147468260124 | 12075147468272201 | 12075147468516198 | 12075147468539543 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7ff981bfa700 | 0x7ff876035fc0 | 12075147468559450 | 12075147468570918 | 12075147468696037 | 12075147468698839 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7ff981bfa600 | 0x7ff876036000 | 12075147468724527 | 12075147468737636 | 12075147468874115 | 12075147468877060 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7ff981bfa500 | 0x7ff876036040 | 12075147468912656 | 12075147468924995 | 12075147469049634 | 12075147469052767 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7ff981bfa400 | 0x7ff876036080 | 12075147469078164 | 12075147469090753 | 12075147469351551 | 12075147469377530 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7ff981bfa300 | 0x7ff8760360c0 | 12075147469397547 | 12075147469410910 | 12075147469655548 | 12075147469683679 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7ff981bfaa00 | 0x7ff876036100 | 12075147469702915 | 12075147469715868 | 12075147469841146 | 12075147469844197 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7ff981bfa900 | 0x7ff876036140 | 12075147469867932 | 12075147469880186 | 12075147470022265 | 12075147470025214 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7ff981bfa800 | 0x7ff876036180 | 12075147470060970 | 12075147470073144 | 12075147470198583 | 12075147470201361 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7ff981bfa700 | 0x7ff8760361c0 | 12075147470226107 | 12075147470239063 | 12075147470489941 | 12075147470513511 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7ff981bfa600 | 0x7ff876036200 | 12075147470534550 | 12075147470547540 | 12075147470794738 | 12075147470817757 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7ff981bfa500 | 0x7ff876036240 | 12075147470838666 | 12075147470851537 | 12075147470976976 | 12075147470979898 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7ff981bfa400 | 0x7ff876036280 | 12075147471009062 | 12075147471021616 | 12075147471170255 | 12075147471173217 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7ff981bfa300 | 0x7ff8760362c0 | 12075147471224493 | 12075147471236974 | 12075147471361933 | 12075147471365114 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7ff981bfaa00 | 0x7ff876036300 | 12075147471389559 | 12075147471401932 | 12075147471655850 | 12075147471675300 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7ff981bfa900 | 0x7ff876036340 | 12075147471694646 | 12075147471707370 | 12075147471955527 | 12075147471978834 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7ff981bfa800 | 0x7ff876036380 | 12075147471997780 | 12075147472016167 | 12075147472142086 | 12075147472145234 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7ff981bfa700 | 0x7ff8760363c0 | 12075147472170210 | 12075147472181285 | 12075147472339524 | 12075147472342350 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7ff981bfa600 | 0x7ff876036400 | 12075147472377435 | 12075147472389924 | 12075147472515362 | 12075147472518287 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7ff981bfa500 | 0x7ff876036440 | 12075147472542362 | 12075147472554402 | 12075147472812320 | 12075147472831669 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7ff981bfa400 | 0x7ff876036480 | 12075147472851606 | 12075147472863999 | 12075147473108157 | 12075147473137818 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7ff981bfa300 | 0x7ff8760364c0 | 12075147473156904 | 12075147473168477 | 12075147473293755 | 12075147473296844 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7ff981bfaa00 | 0x7ff876036500 | 12075147473321730 | 12075147473333435 | 12075147473498874 | 12075147473501805 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7ff981bfa900 | 0x7ff876036540 | 12075147473536159 | 12075147473547033 | 12075147473672472 | 12075147473675327 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7ff981bfa800 | 0x7ff876036580 | 12075147473699662 | 12075147473713432 | 12075147473971189 | 12075147473993589 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7ff981bfa700 | 0x7ff8760365c0 | 12075147474019587 | 12075147474032149 | 12075147474316466 | 12075147474342577 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7ff981bfa600 | 0x7ff876036600 | 12075147474364498 | 12075147474377906 | 12075147474503825 | 12075147474507173 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7ff981bfa500 | 0x7ff876036640 | 12075147474531638 | 12075147474544624 | 12075147474717743 | 12075147474720590 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7ff981bfa400 | 0x7ff876036680 | 12075147474754513 | 12075147474767502 | 12075147474892941 | 12075147474895925 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7ff981bfa300 | 0x7ff8760366c0 | 12075147474920251 | 12075147474933741 | 12075147475184938 | 12075147475209178 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7ff981bfaa00 | 0x7ff876036700 | 12075147475229225 | 12075147475242538 | 12075147475487016 | 12075147475509395 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7ff981bfa900 | 0x7ff876036740 | 12075147475530134 | 12075147475543015 | 12075147475668294 | 12075147475671136 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7ff981bfa800 | 0x7ff876036780 | 12075147475696704 | 12075147475709094 | 12075147475891172 | 12075147475894100 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7ff981bfa700 | 0x7ff8760367c0 | 12075147475930037 | 12075147475943332 | 12075147476069090 | 12075147476072272 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7ff981bfa600 | 0x7ff876036800 | 12075147476097619 | 12075147476110210 | 12075147476372928 | 12075147476399530 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7ff981bfa500 | 0x7ff876036840 | 12075147476419627 | 12075147476432287 | 12075147476677085 | 12075147476699748 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7ff981bfa400 | 0x7ff876036880 | 12075147476719544 | 12075147476732764 | 12075147476858043 | 12075147476861037 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7ff981bfa300 | 0x7ff8760368c0 | 12075147476886334 | 12075147476898843 | 12075147477089881 | 12075147477093109 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7ff981bfaa00 | 0x7ff876036900 | 12075147477127913 | 12075147477139001 | 12075147477265080 | 12075147477268004 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7ff981bfa900 | 0x7ff876036940 | 12075147477292169 | 12075147477304119 | 12075147477586037 | 12075147477608476 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7ff981bfa800 | 0x7ff876036980 | 12075147477628093 | 12075147477639316 | 12075147477887154 | 12075147477909646 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7ff981bfa700 | 0x7ff8760369c0 | 12075147477930695 | 12075147477943314 | 12075147478068912 | 12075147478072038 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7ff981bfa600 | 0x7ff876036a00 | 12075147478098146 | 12075147478109392 | 12075147478319470 | 12075147478347670 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7ff981bfa500 | 0x7ff876036a40 | 12075147478376744 | 12075147478388910 | 12075147478516908 | 12075147478519830 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7ff981bfa400 | 0x7ff876036a80 | 12075147478544666 | 12075147478557068 | 12075147478893385 | 12075147478919553 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7ff981bfa300 | 0x7ff876036ac0 | 12075147478939299 | 12075147478952104 | 12075147479205382 | 12075147479233997 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7ff981bfaa00 | 0x7ff876036b00 | 12075147479253934 | 12075147479267622 | 12075147479394820 | 12075147479397761 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7ff981bfa900 | 0x7ff876036b40 | 12075147479421846 | 12075147479434020 | 12075147479660898 | 12075147479687219 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7ff981bfa800 | 0x7ff876036b80 | 12075147479717025 | 12075147479730177 | 12075147479857696 | 12075147479860912 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7ff981bfa700 | 0x7ff876036bc0 | 12075147479885117 | 12075147479897856 | 12075147480226333 | 12075147480253251 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7ff981bfa600 | 0x7ff876036c00 | 12075147480273539 | 12075147480286172 | 12075147480539610 | 12075147480566113 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7ff981bfa500 | 0x7ff876036c40 | 12075147480586631 | 12075147480599610 | 12075147480727608 | 12075147480730679 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7ff981bfa400 | 0x7ff876036c80 | 12075147480754863 | 12075147480767608 | 12075147481011446 | 12075147481035204 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7ff981bfa300 | 0x7ff876036cc0 | 12075147481065411 | 12075147481078325 | 12075147481208564 | 12075147481211763 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7ff981bfaa00 | 0x7ff876036d00 | 12075147481235717 | 12075147481248564 | 12075147481622800 | 12075147481645018 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7ff981bfa900 | 0x7ff876036d40 | 12075147481666578 | 12075147481679280 | 12075147481934798 | 12075147481957338 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7ff981bfa800 | 0x7ff876036d80 | 12075147481979159 | 12075147481991757 | 12075147482119916 | 12075147482123136 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7ff981bfa700 | 0x7ff876036dc0 | 12075147482149676 | 12075147482161036 | 12075147482439913 | 12075147482468127 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7ff981bfa600 | 0x7ff876036e00 | 12075147482497572 | 12075147482509192 | 12075147482644871 | 12075147482647821 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7ff981bfa500 | 0x7ff876036e40 | 12075147482672066 | 12075147482685511 | 12075147483108547 | 12075147483136249 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7ff981bfa400 | 0x7ff876036e80 | 12075147483156386 | 12075147483168867 | 12075147483428064 | 12075147483454300 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7ff981bfa300 | 0x7ff876036ec0 | 12075147483475770 | 12075147483487424 | 12075147483624062 | 12075147483627071 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7ff981bfaa00 | 0x7ff876036f00 | 12075147483652258 | 12075147483663262 | 12075147484006939 | 12075147484033747 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7ff981bfa900 | 0x7ff876036f40 | 12075147484065336 | 12075147484077018 | 12075147484228377 | 12075147484231965 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7ff981bfa800 | 0x7ff876036f80 | 12075147484255569 | 12075147484268697 | 12075147484784052 | 12075147484810180 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7ff981bfa700 | 0x7ff876036fc0 | 12075147484830087 | 12075147484843251 | 12075147485140369 | 12075147485167925 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7ff981bfa600 | 0x7ff876037000 | 12075147485187731 | 12075147485200848 | 12075147485353807 | 12075147485356916 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7ff981bfa500 | 0x7ff876037040 | 12075147485381762 | 12075147485394446 | 12075147485778763 | 12075147485805760 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7ff981bfa400 | 0x7ff876037080 | 12075147485834734 | 12075147485847722 | 12075147486022921 | 12075147486026340 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7ff981bfa300 | 0x7ff8760370c0 | 12075147486050595 | 12075147486063240 | 12075147486671875 | 12075147486699431 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7ff981bfaa00 | 0x7ff876037100 | 12075147486719348 | 12075147486731714 | 12075147487060031 | 12075147487088464 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7ff981bfa900 | 0x7ff876037140 | 12075147487111056 | 12075147487124511 | 12075147487300989 | 12075147487304495 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7ff981bfa800 | 0x7ff876037180 | 12075147487327718 | 12075147487339869 | 12075147487794105 | 12075147487818180 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7ff981bfa700 | 0x7ff8760371c0 | 12075147487847304 | 12075147487858264 | 12075147488057783 | 12075147488085997 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7ff981bfa600 | 0x7ff876037200 | 12075147488104091 | 12075147488115702 | 12075147488817776 | 12075147488847603 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7ff981bfa500 | 0x7ff876037240 | 12075147488868001 | 12075147488879215 | 12075147489252332 | 12075147489285086 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7ff981bfa400 | 0x7ff876037280 | 12075147489306035 | 12075147489317451 | 12075147489519689 | 12075147489545610 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7ff981bfa300 | 0x7ff8760372c0 | 12075147489563964 | 12075147489574729 | 12075147490100004 | 12075147490127702 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7ff981bfaa00 | 0x7ff876037300 | 12075147490159360 | 12075147490170563 | 12075147490394401 | 12075147490416508 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7ff981bfa900 | 0x7ff876037340 | 12075147490438690 | 12075147490450401 | 12075147491247834 | 12075147491275435 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7ff981bfa800 | 0x7ff876037380 | 12075147491297365 | 12075147491308473 | 12075147491728629 | 12075147491755076 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7ff981bfa700 | 0x7ff8760373c0 | 12075147491775303 | 12075147491786869 | 12075147492012627 | 12075147492039364 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7ff981bfa600 | 0x7ff876037400 | 12075147492059982 | 12075147492071346 | 12075147492667021 | 12075147492693079 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7ff981bfa500 | 0x7ff876037440 | 12075147492723145 | 12075147492734380 | 12075147493002058 | 12075147493029344 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7ff981bfa400 | 0x7ff876037480 | 12075147493048830 | 12075147493059977 | 12075147494043969 | 12075147494071390 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7ff981bfa300 | 0x7ff8760374c0 | 12075147494090907 | 12075147494102208 | 12075147494615483 | 12075147494641380 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7ff981bfaa00 | 0x7ff876037500 | 12075147494663891 | 12075147494675483 | 12075147494945721 | 12075147494971673 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7ff981bfa900 | 0x7ff876037540 | 12075147494992051 | 12075147495004600 | 12075147495741073 | 12075147495771570 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7ff981bfa800 | 0x7ff876037580 | 12075147495801165 | 12075147495812273 | 12075147496125870 | 12075147496153550 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7ff981bfa700 | 0x7ff8760375c0 | 12075147496173667 | 12075147496185069 | 12075147497354979 | 12075147497382203 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7ff981bfa600 | 0x7ff876037600 | 12075147497401469 | 12075147497412738 | 12075147498022173 | 12075147498050325 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7ff981bfa500 | 0x7ff876037640 | 12075147498070803 | 12075147498083932 | 12075147498402649 | 12075147498429519 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7ff981bfa400 | 0x7ff876037680 | 12075147498449537 | 12075147498461849 | 12075147499338801 | 12075147499367843 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7ff981bfa300 | 0x7ff8760376c0 | 12075147499397839 | 12075147499410160 | 12075147499844076 | 12075147499867161 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7ff981bfaa00 | 0x7ff876037700 | 12075147499889372 | 12075147499901836 | 12075147501449662 | 12075147501501198 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7ff981bfa900 | 0x7ff876037740 | 12075147501522538 | 12075147501535901 | 12075147502330774 | 12075147502401551 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7ff981bfa800 | 0x7ff876037780 | 12075147502420626 | 12075147502432527 | 12075147502845804 | 12075147502919744 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7ff981bfa700 | 0x7ff8760377c0 | 12075147502939851 | 12075147502952522 | 12075147504109794 | 12075147504181228 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7ff981bfa600 | 0x7ff876037800 | 12075147504211515 | 12075147504224673 | 12075147505008827 | 12075147505079688 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7ff981bfa500 | 0x7ff876037840 | 12075147505099324 | 12075147505113146 | 12075147508162723 | 12075147508233008 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7ff981bfa400 | 0x7ff876037880 | 12075147508253316 | 12075147508266402 | 12075147509806871 | 12075147509877344 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7ff981bfa300 | 0x7ff8760378c0 | 12075147509899024 | 12075147509911030 | 12075147510699024 | 12075147510773629 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7ff981bfaa00 | 0x7ff876037900 | 12075147510795500 | 12075147510807983 | 12075147513088926 | 12075147513163210 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7ff981bfa900 | 0x7ff876037940 | 12075147513194388 | 12075147513205885 | 12075147514740593 | 12075147514811403 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7ff981bfa800 | 0x7ff876037980 | 12075147514832081 | 12075147514843953 | 12075147520895587 | 12075147520970379 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7ff981bfa700 | 0x7ff8760379c0 | 12075147520991047 | 12075147521002786 | 12075147524042763 | 12075147524116044 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7ff981bfa600 | 0x7ff876037a00 | 12075147524134799 | 12075147524147883 | 12075147525685951 | 12075147525756854 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 863012 | 863017 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7ff981bfa500 | 0x7ff876037a40 | 12075147525779125 | 12075147525792830 | 12075147530319036 | 12075147530390034 |