50 KiB
50 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_WAVES | GRBM_COUNT | GRBM_GUI_ACTIVE | CPF_CPF_STAT_BUSY | CPF_CPF_STAT_STALL | CPF_CPF_TCIU_BUSY | CPF_CPF_TCIU_STALL | CPF_CPF_STAT_IDLE | CPF_CPF_TCIU_IDLE | CPF_CMP_UTCL1_STALL_ON_TRANSLATION | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 870326 | 870331 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7faa94c04180 | 4036816 | 3832483 | 524288 | 504601 | 504601 | 504601 | 0 | 4193 | 0 | 0 | 503524 | 0 | 12075333171398844 | 12075337326712913 | 12075337327035950 | 12075333417182692 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 870326 | 870331 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7faa94c35100 | 222952 | 77688 | 512 | 27868 | 27868 | 27868 | 0 | 2274 | 0 | 0 | 24307 | 0 | 12075333431726747 | 12075337341910373 | 12075337341917253 | 12075333432073060 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7faba08f5900 | 0x7faa94c35140 | 1734176 | 1571525 | 65536 | 216771 | 216771 | 216771 | 0 | 2258 | 0 | 0 | 222232 | 0 | 12075333432135907 | 12075337341978052 | 12075337342114851 | 12075333432497238 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7faba08f5800 | 0x7faa94c35180 | 3177808 | 3012740 | 65536 | 397225 | 397225 | 397225 | 0 | 2384 | 0 | 0 | 390819 | 0 | 12075333432564523 | 12075337342175970 | 12075337342423008 | 12075333433065594 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7faba08f5700 | 0x7faa94c351c0 | 3193896 | 3024352 | 65536 | 399236 | 399236 | 399236 | 0 | 2459 | 0 | 0 | 392324 | 0 | 12075333433097293 | 12075337342558527 | 12075337342806524 | 12075333433618712 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7faba08f5600 | 0x7faa94c35200 | 1777552 | 1622780 | 65536 | 222193 | 222193 | 222193 | 0 | 2276 | 0 | 0 | 221856 | 0 | 12075333433642927 | 12075337342939963 | 12075337343064922 | 12075333433975656 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7faba08f5500 | 0x7faa94c35240 | 1732904 | 1570212 | 65536 | 216612 | 216612 | 216612 | 0 | 2285 | 0 | 0 | 220248 | 0 | 12075333434032191 | 12075337343108922 | 12075337343233560 | 12075333434358467 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7faba08f5400 | 0x7faa94c35280 | 1661840 | 1503968 | 65536 | 207729 | 207729 | 207729 | 0 | 2317 | 0 | 0 | 212241 | 0 | 12075333434441361 | 12075337343305400 | 12075337343429879 | 12075333434749333 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7faba08f5300 | 0x7faa94c352c0 | 3152992 | 2977801 | 65536 | 394123 | 394123 | 394123 | 0 | 2452 | 0 | 0 | 403193 | 0 | 12075333434798434 | 12075337343474358 | 12075337343717876 | 12075333435273477 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7faba08f5a00 | 0x7faa94c35300 | 3172176 | 3015801 | 65536 | 396521 | 396521 | 396521 | 0 | 2428 | 0 | 0 | 449307 | 0 | 12075333435291330 | 12075337343847155 | 12075337344090673 | 12075333435790127 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7faba08f5900 | 0x7faa94c35340 | 1712232 | 1548926 | 65536 | 214028 | 214028 | 214028 | 0 | 2284 | 0 | 0 | 212503 | 0 | 12075333435813781 | 12075337344225391 | 12075337344350350 | 12075333436139366 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7faba08f5800 | 0x7faa94c35380 | 1744464 | 1587554 | 65536 | 218057 | 218057 | 218057 | 0 | 2336 | 0 | 0 | 213206 | 0 | 12075333436187846 | 12075337344391150 | 12075337344515949 | 12075333436507811 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7faba08f5700 | 0x7faa94c353c0 | 1682720 | 1522805 | 65536 | 210339 | 210339 | 210339 | 0 | 2299 | 0 | 0 | 211947 | 0 | 12075333436571108 | 12075337344567308 | 12075337344691627 | 12075333436872869 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7faba08f5600 | 0x7faa94c35400 | 3182096 | 3012279 | 65536 | 397761 | 397761 | 397761 | 0 | 2486 | 0 | 0 | 404354 | 0 | 12075333436922020 | 12075337344732267 | 12075337344984424 | 12075333437438300 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7faba08f5500 | 0x7faa94c35440 | 3160872 | 2987912 | 65536 | 395108 | 395108 | 395108 | 0 | 2401 | 0 | 0 | 398298 | 0 | 12075333437463006 | 12075337345095143 | 12075337345344261 | 12075333437970989 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7faba08f5400 | 0x7faa94c35480 | 1711760 | 1559597 | 65536 | 213969 | 213969 | 213969 | 0 | 2278 | 0 | 0 | 214842 | 0 | 12075333437994583 | 12075337345443620 | 12075337345568579 | 12075333438325588 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7faba08f5300 | 0x7faa94c354c0 | 1727456 | 1561000 | 65536 | 215931 | 215931 | 215931 | 0 | 2308 | 0 | 0 | 214008 | 0 | 12075333438368268 | 12075337345610499 | 12075337345736417 | 12075333438692700 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7faba08f5a00 | 0x7faa94c35500 | 1703440 | 1538779 | 65536 | 212929 | 212929 | 212929 | 0 | 2303 | 0 | 0 | 215508 | 0 | 12075333438754064 | 12075337345787937 | 12075337345912576 | 12075333439056657 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7faba08f5900 | 0x7faa94c35540 | 3101024 | 2932205 | 65536 | 387627 | 387627 | 387627 | 0 | 2407 | 0 | 0 | 398619 | 0 | 12075333439101821 | 12075337345953375 | 12075337346200253 | 12075333439604785 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7faba08f5800 | 0x7faa94c35580 | 3200144 | 3038776 | 65536 | 400017 | 400017 | 400017 | 0 | 2397 | 0 | 0 | 400529 | 0 | 12075333439624181 | 12075337346303132 | 12075337346546330 | 12075333440115174 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7faba08f5700 | 0x7faa94c355c0 | 1695776 | 1535084 | 65536 | 211971 | 211971 | 211971 | 0 | 2336 | 0 | 0 | 215872 | 0 | 12075333440138727 | 12075337346642809 | 12075337346767608 | 12075333440466416 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7faba08f5600 | 0x7faa94c35600 | 1648144 | 1488977 | 65536 | 206017 | 206017 | 206017 | 0 | 2309 | 0 | 0 | 282492 | 0 | 12075333440516078 | 12075337346808408 | 12075337346933366 | 12075333440823119 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7faba08f5500 | 0x7faa94c35640 | 1696288 | 1535758 | 65536 | 212035 | 212035 | 212035 | 0 | 2315 | 0 | 0 | 210176 | 0 | 12075333440885234 | 12075337346983446 | 12075337347107285 | 12075333441202434 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7faba08f5400 | 0x7faa94c35680 | 3190992 | 3035225 | 65536 | 398873 | 398873 | 398873 | 0 | 2431 | 0 | 0 | 401357 | 0 | 12075333441249902 | 12075337347148724 | 12075337347402962 | 12075333441753558 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7faba08f5300 | 0x7faa94c356c0 | 3203616 | 3015640 | 65536 | 400451 | 400451 | 400451 | 0 | 2511 | 0 | 0 | 394162 | 0 | 12075333441776370 | 12075337347476721 | 12075337347721839 | 12075333442295856 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7faba08f5a00 | 0x7faa94c35700 | 1686480 | 1531056 | 65536 | 210809 | 210809 | 210809 | 0 | 2350 | 0 | 0 | 213240 | 0 | 12075333442319229 | 12075337347817998 | 12075337347942317 | 12075333442644253 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7faba08f5900 | 0x7faa94c35740 | 1783840 | 1617793 | 65536 | 222979 | 222979 | 222979 | 0 | 2350 | 0 | 0 | 276641 | 0 | 12075333442693995 | 12075337347981677 | 12075337348106956 | 12075333443010393 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7faba08f5800 | 0x7faa94c35780 | 1723664 | 1547596 | 65536 | 215457 | 215457 | 215457 | 0 | 2308 | 0 | 0 | 211431 | 0 | 12075333443075204 | 12075337348160235 | 12075337348284554 | 12075333443379259 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7faba08f5700 | 0x7faa94c357c0 | 3606432 | 3015074 | 65536 | 450803 | 450803 | 450803 | 158 | 2429 | 0 | 0 | 392649 | 0 | 12075333443430193 | 12075337348324714 | 12075337348570631 | 12075333443943206 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7faba08f5600 | 0x7faa94c35800 | 3171088 | 2994927 | 65536 | 396385 | 396385 | 396385 | 0 | 4805 | 0 | 0 | 459950 | 0 | 12075333443969475 | 12075337348653831 | 12075337348901348 | 12075333444485995 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7faba08f5500 | 0x7faa94c35840 | 1717672 | 1562388 | 65536 | 214708 | 214708 | 214708 | 0 | 2335 | 0 | 0 | 211306 | 0 | 12075333444509689 | 12075337349013347 | 12075337349137666 | 12075333444833160 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7faba08f5400 | 0x7faa94c35880 | 1717136 | 1559196 | 65536 | 214641 | 214641 | 214641 | 0 | 2324 | 0 | 0 | 215384 | 0 | 12075333444882812 | 12075337349178786 | 12075337349304545 | 12075333445198289 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7faba08f5300 | 0x7faa94c358c0 | 1699176 | 1534205 | 65536 | 212396 | 212396 | 212396 | 0 | 2303 | 0 | 0 | 210654 | 0 | 12075333445260805 | 12075337349357344 | 12075337349482143 | 12075333445565160 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7faba08f5a00 | 0x7faa94c35900 | 3146384 | 2981959 | 65536 | 393297 | 393297 | 393297 | 0 | 2261 | 0 | 0 | 399767 | 0 | 12075333445614752 | 12075337349521663 | 12075337349769820 | 12075333446118839 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7faba08f5900 | 0x7faa94c35940 | 3126240 | 2967265 | 65536 | 390779 | 390779 | 390779 | 0 | 2436 | 0 | 0 | 387976 | 0 | 12075333446143535 | 12075337349860699 | 12075337350104537 | 12075333446659113 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7faba08f5800 | 0x7faa94c35980 | 1773712 | 1611755 | 65536 | 221713 | 221713 | 221713 | 0 | 2280 | 0 | 0 | 217162 | 0 | 12075333446684480 | 12075337350195736 | 12075337350320215 | 12075333447019122 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7faba08f5700 | 0x7faa94c359c0 | 1752416 | 1589448 | 65536 | 219051 | 219051 | 219051 | 0 | 2327 | 0 | 0 | 226138 | 0 | 12075333447067472 | 12075337350360695 | 12075337350486614 | 12075333447385703 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7faba08f5600 | 0x7faa94c35a00 | 1719056 | 1565300 | 65536 | 214881 | 214881 | 214881 | 0 | 2302 | 0 | 0 | 212163 | 0 | 12075333447446656 | 12075337350535733 | 12075337350659252 | 12075333447751483 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7faba08f5500 | 0x7faa94c35a40 | 3129896 | 2956062 | 65536 | 391236 | 391236 | 391236 | 0 | 4618 | 0 | 0 | 395884 | 0 | 12075333447800033 | 12075337350700372 | 12075337350950769 | 12075333448295494 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7faba08f5400 | 0x7faa94c35a80 | 3107920 | 2933350 | 65536 | 388489 | 388489 | 388489 | 0 | 2502 | 0 | 0 | 444773 | 0 | 12075333448319057 | 12075337351048689 | 12075337351292206 | 12075333448830498 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7faba08f5300 | 0x7faa94c35ac0 | 1715240 | 1557087 | 65536 | 214404 | 214404 | 214404 | 0 | 2310 | 0 | 0 | 215538 | 0 | 12075333448852699 | 12075337351370126 | 12075337351495084 | 12075333449184395 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7faba08f5a00 | 0x7faa94c35b00 | 1718224 | 1554236 | 65536 | 214777 | 214777 | 214777 | 0 | 2333 | 0 | 0 | 218704 | 0 | 12075333449233226 | 12075337351537644 | 12075337351663563 | 12075333449550846 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7faba08f5900 | 0x7faa94c35b40 | 1728936 | 1575429 | 65536 | 216116 | 216116 | 216116 | 0 | 2324 | 0 | 0 | 212795 | 0 | 12075333449612831 | 12075337351713002 | 12075337351837481 | 12075333449920623 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7faba08f5800 | 0x7faa94c35b80 | 3232912 | 3065038 | 65536 | 404113 | 404113 | 404113 | 0 | 2493 | 0 | 0 | 412948 | 0 | 12075333449973562 | 12075337351878921 | 12075337352130759 | 12075333450479822 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7faba08f5700 | 0x7faa94c35bc0 | 3170664 | 3012849 | 65536 | 396332 | 396332 | 396332 | 0 | 2511 | 0 | 0 | 395531 | 0 | 12075333450503587 | 12075337352213478 | 12075337352460036 | 12075333451017261 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7faba08f5600 | 0x7faa94c35c00 | 1728080 | 1565874 | 65536 | 216009 | 216009 | 216009 | 0 | 2289 | 0 | 0 | 219526 | 0 | 12075333451040905 | 12075337352515395 | 12075337352639874 | 12075333451365097 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7faba08f5500 | 0x7faa94c35c40 | 1749416 | 1581674 | 65536 | 218676 | 218676 | 218676 | 0 | 2326 | 0 | 0 | 223835 | 0 | 12075333451414940 | 12075337352680674 | 12075337352807392 | 12075333451733292 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7faba08f5400 | 0x7faa94c35c80 | 1710096 | 1556074 | 65536 | 213761 | 213761 | 213761 | 0 | 2287 | 0 | 0 | 207584 | 0 | 12075333451794766 | 12075337352858272 | 12075337352983551 | 12075333452095605 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7faba08f5300 | 0x7faa94c35cc0 | 3250272 | 3065507 | 65536 | 406283 | 406283 | 406283 | 0 | 2648 | 0 | 0 | 418638 | 0 | 12075333452146459 | 12075337353031390 | 12075337353283868 | 12075333452655665 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7faba08f5a00 | 0x7faa94c35d00 | 3105616 | 2924046 | 65536 | 388201 | 388201 | 388201 | 0 | 2439 | 0 | 0 | 400778 | 0 | 12075333452679309 | 12075337353341947 | 12075337353590585 | 12075333453180140 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7faba08f5900 | 0x7faa94c35d40 | 1690856 | 1531360 | 65536 | 211356 | 211356 | 211356 | 0 | 2293 | 0 | 0 | 215761 | 0 | 12075333453205717 | 12075337353640505 | 12075337353765304 | 12075333453525101 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7faba08f5800 | 0x7faa94c35d80 | 1753936 | 1591290 | 65536 | 219241 | 219241 | 219241 | 0 | 2294 | 0 | 0 | 218008 | 0 | 12075333453575334 | 12075337353806583 | 12075337353936342 | 12075333453887985 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7faba08f5700 | 0x7faa94c35dc0 | 1723424 | 1561085 | 65536 | 215427 | 215427 | 215427 | 0 | 2294 | 0 | 0 | 212733 | 0 | 12075333453949810 | 12075337353985462 | 12075337354110420 | 12075333454259165 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7faba08f5600 | 0x7faa94c35e00 | 3255696 | 3067431 | 65536 | 406961 | 406961 | 406961 | 0 | 2393 | 0 | 0 | 397868 | 0 | 12075333454303337 | 12075337354152020 | 12075337354410738 | 12075333454813355 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7faba08f5500 | 0x7faa94c35e40 | 3078952 | 2916805 | 65536 | 384868 | 384868 | 384868 | 0 | 2371 | 0 | 0 | 382844 | 0 | 12075333454837089 | 12075337354467217 | 12075337354714895 | 12075333455347828 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7faba08f5400 | 0x7faa94c35e80 | 1698640 | 1541271 | 65536 | 212329 | 212329 | 212329 | 0 | 2316 | 0 | 0 | 218695 | 0 | 12075333455372353 | 12075337354768814 | 12075337354893613 | 12075333455695935 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7faba08f5300 | 0x7faa94c35ec0 | 1787944 | 1622863 | 65536 | 223492 | 223492 | 223492 | 0 | 2376 | 0 | 0 | 222634 | 0 | 12075333455744405 | 12075337354934253 | 12075337355062572 | 12075333456063407 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7faba08f5a00 | 0x7faa94c35f00 | 1690256 | 1533136 | 65536 | 211281 | 211281 | 211281 | 0 | 2315 | 0 | 0 | 212443 | 0 | 12075333456130021 | 12075337355113451 | 12075337355238410 | 12075333456430429 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7faba08f5900 | 0x7faa94c35f40 | 3259432 | 3078572 | 65536 | 407428 | 407428 | 407428 | 0 | 2512 | 0 | 0 | 397353 | 0 | 12075333456479751 | 12075337355277610 | 12075337355535207 | 12075333456984409 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7faba08f5800 | 0x7faa94c35f80 | 3140048 | 2977647 | 65536 | 392505 | 392505 | 392505 | 0 | 2483 | 0 | 0 | 398673 | 0 | 12075333457014024 | 12075337355593287 | 12075337355840644 | 12075333457525334 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7faba08f5700 | 0x7faa94c35fc0 | 1699944 | 1531453 | 65536 | 212492 | 212492 | 212492 | 0 | 2317 | 0 | 0 | 217529 | 0 | 12075333457549108 | 12075337355894564 | 12075337356019363 | 12075333457874212 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7faba08f5600 | 0x7faa94c36000 | 1812304 | 1652102 | 65536 | 226537 | 226537 | 226537 | 0 | 2316 | 0 | 0 | 217721 | 0 | 12075333457925107 | 12075337356061122 | 12075337356197281 | 12075333458261732 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7faba08f5500 | 0x7faa94c36040 | 1732200 | 1568790 | 65536 | 216524 | 216524 | 216524 | 0 | 2332 | 0 | 0 | 209912 | 0 | 12075333458325000 | 12075337356246721 | 12075337356371840 | 12075333458629946 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7faba08f5400 | 0x7faa94c36080 | 3256976 | 3082297 | 65536 | 407121 | 407121 | 407121 | 0 | 2526 | 0 | 0 | 414263 | 0 | 12075333458679408 | 12075337356412639 | 12075337356670717 | 12075333459185158 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7faba08f5300 | 0x7faa94c360c0 | 3067872 | 2889680 | 65536 | 383483 | 383483 | 383483 | 0 | 2406 | 0 | 0 | 393604 | 0 | 12075333459209924 | 12075337356722716 | 12075337356968154 | 12075333459711576 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7faba08f5a00 | 0x7faa94c36100 | 1712208 | 1550526 | 65536 | 214025 | 214025 | 214025 | 0 | 2324 | 0 | 0 | 205223 | 0 | 12075333459740660 | 12075337357025594 | 12075337357150552 | 12075333460064332 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7faba08f5900 | 0x7faa94c36140 | 1829928 | 1667347 | 65536 | 228740 | 228740 | 228740 | 0 | 2334 | 0 | 0 | 231337 | 0 | 12075333460113503 | 12075337357193112 | 12075337357335191 | 12075333460437786 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7faba08f5800 | 0x7faa94c36180 | 1702864 | 1539630 | 65536 | 212857 | 212857 | 212857 | 0 | 2293 | 0 | 0 | 213489 | 0 | 12075333460500232 | 12075337357385270 | 12075337357509909 | 12075333460800069 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7faba08f5700 | 0x7faa94c361c0 | 3242720 | 3059645 | 65536 | 405339 | 405339 | 405339 | 0 | 2429 | 0 | 0 | 411768 | 0 | 12075333460850102 | 12075337357549269 | 12075337357807986 | 12075333461340763 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7faba08f5600 | 0x7faa94c36200 | 3184592 | 3006462 | 65536 | 398073 | 398073 | 398073 | 0 | 2750 | 0 | 0 | 395222 | 0 | 12075333461363946 | 12075337357861106 | 12075337358108464 | 12075333461861872 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7faba08f5500 | 0x7faa94c36240 | 1705128 | 1542701 | 65536 | 213140 | 213140 | 213140 | 0 | 2332 | 0 | 0 | 214976 | 0 | 12075333461885065 | 12075337358169263 | 12075337358294222 | 12075333462216310 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7faba08f5400 | 0x7faa94c36280 | 1937616 | 1769423 | 65536 | 242201 | 242201 | 242201 | 0 | 2325 | 0 | 0 | 239265 | 0 | 12075333462258419 | 12075337358334222 | 12075337358483340 | 12075333462597879 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7faba08f5300 | 0x7faa94c362c0 | 1708256 | 1546953 | 65536 | 213531 | 213531 | 213531 | 0 | 2368 | 0 | 0 | 211783 | 0 | 12075333462680062 | 12075337358552939 | 12075337358678058 | 12075333462979999 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7faba08f5a00 | 0x7faa94c36300 | 3231952 | 3032603 | 65536 | 403993 | 403993 | 403993 | 0 | 2447 | 0 | 0 | 418010 | 0 | 12075333463030874 | 12075337358717258 | 12075337358974056 | 12075333463525743 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7faba08f5900 | 0x7faa94c36340 | 3166048 | 2999510 | 65536 | 395755 | 395755 | 395755 | 0 | 2454 | 0 | 0 | 396056 | 0 | 12075333463550259 | 12075337359039335 | 12075337359284933 | 12075333464016746 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7faba08f5800 | 0x7faa94c36380 | 1705680 | 1538578 | 65536 | 213209 | 213209 | 213209 | 0 | 2310 | 0 | 0 | 223266 | 0 | 12075333464057481 | 12075337359341412 | 12075337359467491 | 12075333464360775 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7faba08f5700 | 0x7faa94c363c0 | 2010152 | 1854020 | 65536 | 251268 | 251268 | 251268 | 0 | 2317 | 0 | 0 | 248913 | 0 | 12075333464411840 | 12075337359507971 | 12075337359665249 | 12075333464745239 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7faba08f5600 | 0x7faa94c36400 | 1758160 | 1574089 | 65536 | 219769 | 219769 | 219769 | 0 | 2284 | 0 | 0 | 210806 | 158 | 12075333464805632 | 12075337359715169 | 12075337359839808 | 12075333465111179 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7faba08f5500 | 0x7faa94c36440 | 3351456 | 3169686 | 65536 | 418931 | 418931 | 418931 | 0 | 2372 | 0 | 0 | 414945 | 0 | 12075333465163026 | 12075337359879647 | 12075337360136125 | 12075333465638890 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7faba08f5400 | 0x7faa94c36480 | 3149392 | 2969327 | 65536 | 393673 | 393673 | 393673 | 0 | 2516 | 0 | 0 | 392798 | 0 | 12075333465678794 | 12075337360194364 | 12075337360438362 | 12075333466126807 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7faba08f5300 | 0x7faa94c364c0 | 1788704 | 1629149 | 65536 | 223587 | 223587 | 223587 | 0 | 2299 | 0 | 0 | 214390 | 0 | 12075333466169997 | 12075337360494042 | 12075337360620280 | 12075333466479943 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7faba08f5a00 | 0x7faa94c36500 | 2114064 | 1958664 | 65536 | 264257 | 264257 | 264257 | 0 | 2320 | 0 | 0 | 261304 | 0 | 12075333466524425 | 12075337360662040 | 12075337360827159 | 12075333466873434 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7faba08f5900 | 0x7faa94c36540 | 1762920 | 1603173 | 65536 | 220364 | 220364 | 220364 | 0 | 2279 | 0 | 0 | 217046 | 0 | 12075333466937272 | 12075337360876118 | 12075337361001237 | 12075333467243992 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7faba08f5800 | 0x7faa94c36580 | 3234896 | 3038070 | 65536 | 404361 | 404361 | 404361 | 0 | 2429 | 0 | 0 | 413025 | 0 | 12075333467293003 | 12075337361042037 | 12075337361298194 | 12075333467768607 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7faba08f5700 | 0x7faa94c365c0 | 3203040 | 3023913 | 65536 | 400379 | 400379 | 400379 | 0 | 2423 | 0 | 0 | 400762 | 0 | 12075333467817879 | 12075337361352914 | 12075337361637871 | 12075333468275148 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7faba08f5600 | 0x7faa94c36600 | 1757776 | 1583843 | 65536 | 219721 | 219721 | 219721 | 0 | 2282 | 0 | 0 | 218999 | 0 | 12075333468321254 | 12075337361687311 | 12075337361813069 | 12075333468628074 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7faba08f5500 | 0x7faa94c36640 | 2202208 | 2043802 | 65536 | 275275 | 275275 | 275275 | 0 | 2302 | 0 | 0 | 272264 | 0 | 12075333468672196 | 12075337361853229 | 12075337362025708 | 12075333469029580 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7faba08f5400 | 0x7faa94c36680 | 1772944 | 1610741 | 65536 | 221617 | 221617 | 221617 | 0 | 2336 | 0 | 0 | 219538 | 0 | 12075333469093740 | 12075337362076747 | 12075337362202986 | 12075333469402744 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7faba08f5300 | 0x7faa94c366c0 | 3188648 | 2999076 | 65536 | 398580 | 398580 | 398580 | 0 | 2504 | 0 | 0 | 404303 | 0 | 12075333469451344 | 12075337362242506 | 12075337362495943 | 12075333469904536 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7faba08f5a00 | 0x7faa94c36700 | 3145168 | 2968212 | 65536 | 393145 | 393145 | 393145 | 0 | 2446 | 0 | 0 | 384976 | 0 | 12075333469949670 | 12075337362550023 | 12075337362794500 | 12075333470405928 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7faba08f5900 | 0x7faa94c36740 | 1754336 | 1589542 | 65536 | 219291 | 219291 | 219291 | 0 | 2270 | 0 | 0 | 222587 | 0 | 12075333470447775 | 12075337362848420 | 12075337362973699 | 12075333470751329 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7faba08f5800 | 0x7faa94c36780 | 2309904 | 2155063 | 65536 | 288737 | 288737 | 288737 | 0 | 2286 | 0 | 0 | 286481 | 0 | 12075333470799228 | 12075337363017858 | 12075337363200577 | 12075333471162393 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7faba08f5700 | 0x7faa94c367c0 | 1774440 | 1618527 | 65536 | 221804 | 221804 | 221804 | 0 | 2287 | 0 | 0 | 224360 | 0 | 12075333471222735 | 12075337363251296 | 12075337363377055 | 12075333471529566 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7faba08f5600 | 0x7faa94c36800 | 3261520 | 3101513 | 65536 | 407689 | 407689 | 407689 | 0 | 2471 | 0 | 0 | 407516 | 0 | 12075333471578446 | 12075337363417535 | 12075337363682012 | 12075333472056024 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7faba08f5500 | 0x7faa94c36840 | 3144224 | 2947035 | 65536 | 393027 | 393027 | 393027 | 0 | 4850 | 0 | 0 | 387947 | 158 | 12075333472097481 | 12075337363734812 | 12075337363981050 | 12075333472539983 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7faba08f5400 | 0x7faa94c36880 | 1706320 | 1537975 | 65536 | 213289 | 213289 | 213289 | 0 | 2295 | 0 | 0 | 218736 | 0 | 12075333472588313 | 12075337364039929 | 12075337364166648 | 12075333472892288 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7faba08f5300 | 0x7faa94c368c0 | 2414112 | 2253785 | 65536 | 301763 | 301763 | 301763 | 0 | 2284 | 0 | 0 | 298368 | 0 | 12075333472940607 | 12075337364207767 | 12075337364399126 | 12075333473349427 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7faba08f5a00 | 0x7faa94c36900 | 1818768 | 1629649 | 65536 | 227345 | 227345 | 227345 | 0 | 2385 | 0 | 0 | 215281 | 0 | 12075333473406092 | 12075337364462005 | 12075337364588564 | 12075333473717040 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7faba08f5900 | 0x7faa94c36940 | 3506408 | 3337374 | 65536 | 438300 | 438300 | 438300 | 0 | 2403 | 0 | 0 | 432097 | 0 | 12075333473767053 | 12075337364628724 | 12075337364910801 | 12075333474258126 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7faba08f5800 | 0x7faa94c36980 | 3166416 | 2997442 | 65536 | 395801 | 395801 | 395801 | 0 | 2403 | 0 | 0 | 397314 | 0 | 12075333474301536 | 12075337364966800 | 12075337365214478 | 12075333474751402 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7faba08f5700 | 0x7faa94c369c0 | 1737640 | 1567463 | 65536 | 217204 | 217204 | 217204 | 0 | 2280 | 0 | 0 | 225753 | 0 | 12075333474793470 | 12075337365268078 | 12075337365393517 | 12075333475097786 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7faba08f5600 | 0x7faa94c36a00 | 2632464 | 2471310 | 65536 | 329057 | 329057 | 329057 | 0 | 2280 | 0 | 0 | 326705 | 0 | 12075333475148219 | 12075337365434796 | 12075337365645354 | 12075333475558502 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7faba08f5500 | 0x7faa94c36a40 | 1751904 | 1585130 | 65536 | 218987 | 218987 | 218987 | 0 | 2270 | 0 | 0 | 213169 | 0 | 12075333475625827 | 12075337365709834 | 12075337365837992 | 12075333475941083 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7faba08f5400 | 0x7faa94c36a80 | 3763472 | 3598171 | 65536 | 470433 | 470433 | 470433 | 0 | 2420 | 0 | 0 | 509695 | 0 | 12075333475990394 | 12075337365880552 | 12075337366186789 | 12075333476505732 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7faba08f5300 | 0x7faa94c36ac0 | 3143328 | 2965555 | 65536 | 392915 | 392915 | 392915 | 0 | 2460 | 0 | 0 | 400257 | 0 | 12075333476547910 | 12075337366252069 | 12075337366502466 | 12075333476988539 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7faba08f5a00 | 0x7faa94c36b00 | 1782032 | 1616309 | 65536 | 222753 | 222753 | 222753 | 0 | 2295 | 0 | 0 | 225745 | 0 | 12075333477038352 | 12075337366560706 | 12075337366687265 | 12075333477348658 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7faba08f5900 | 0x7faa94c36b40 | 2856808 | 2693964 | 65536 | 357100 | 357100 | 357100 | 0 | 2413 | 0 | 0 | 352559 | 0 | 12075333477397890 | 12075337366727104 | 12075337366954942 | 12075333477822428 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7faba08f5800 | 0x7faa94c36b80 | 1772368 | 1609769 | 65536 | 221545 | 221545 | 221545 | 0 | 2316 | 0 | 0 | 222497 | 0 | 12075333477881258 | 12075337367023422 | 12075337367150140 | 12075333478195221 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7faba08f5700 | 0x7faa94c36bc0 | 4038568 | 3871816 | 65536 | 504820 | 504820 | 504820 | 0 | 2452 | 0 | 0 | 541082 | 158 | 12075333478244603 | 12075337367190780 | 12075337367519417 | 12075333478777072 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7faba08f5600 | 0x7faa94c36c00 | 3196176 | 3014279 | 65536 | 399521 | 399521 | 399521 | 0 | 2495 | 0 | 0 | 396344 | 0 | 12075333478820182 | 12075337367573656 | 12075337367821334 | 12075333479270078 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7faba08f5500 | 0x7faa94c36c40 | 1787744 | 1623759 | 65536 | 223467 | 223467 | 223467 | 0 | 2307 | 0 | 0 | 227919 | 0 | 12075333479311866 | 12075337367874294 | 12075337368002453 | 12075333479621782 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7faba08f5400 | 0x7faa94c36c80 | 3051344 | 2890372 | 65536 | 381417 | 381417 | 381417 | 0 | 2504 | 0 | 0 | 378989 | 0 | 12075333479669661 | 12075337368044052 | 12075337368321490 | 12075333480120348 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7faba08f5300 | 0x7faa94c36cc0 | 1813600 | 1644123 | 65536 | 226699 | 226699 | 226699 | 0 | 2318 | 0 | 0 | 223121 | 0 | 12075333480176042 | 12075337368385489 | 12075337368514928 | 12075333480491478 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7faba08f5a00 | 0x7faa94c36d00 | 4595024 | 4424426 | 65536 | 574377 | 574377 | 574377 | 0 | 2512 | 0 | 0 | 570059 | 0 | 12075333480539387 | 12075337368556687 | 12075337368932524 | 12075333481116629 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7faba08f5900 | 0x7faa94c36d40 | 3173536 | 2972334 | 65536 | 396691 | 396691 | 396691 | 0 | 2452 | 0 | 0 | 400401 | 0 | 12075333481161453 | 12075337368985964 | 12075337369243081 | 12075333481611840 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7faba08f5800 | 0x7faa94c36d80 | 1815952 | 1656977 | 65536 | 226993 | 226993 | 226993 | 0 | 2292 | 0 | 0 | 226179 | 0 | 12075333481651864 | 12075337369297481 | 12075337369426599 | 12075333481961409 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7faba08f5700 | 0x7faa94c36dc0 | 3472288 | 3311147 | 65536 | 434035 | 434035 | 434035 | 0 | 2421 | 0 | 0 | 430473 | 0 | 12075333482014999 | 12075337369467399 | 12075337369745477 | 12075333482512113 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7faba08f5600 | 0x7faa94c36e00 | 1820560 | 1639632 | 65536 | 227569 | 227569 | 227569 | 0 | 2304 | 0 | 0 | 224939 | 0 | 12075333482569900 | 12075337369810116 | 12075337369945955 | 12075333482885096 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7faba08f5500 | 0x7faa94c36e40 | 5154592 | 4995260 | 65536 | 644323 | 644323 | 644323 | 0 | 2455 | 0 | 0 | 643597 | 0 | 12075333482934507 | 12075337369986274 | 12075337370408990 | 12075333483561653 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7faba08f5400 | 0x7faa94c36e80 | 3201744 | 2998195 | 65536 | 400217 | 400217 | 400217 | 0 | 2445 | 0 | 0 | 412162 | 0 | 12075333483607358 | 12075337370472990 | 12075337370740187 | 12075333484057734 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7faba08f5300 | 0x7faa94c36ec0 | 1767008 | 1601154 | 65536 | 220875 | 220875 | 220875 | 0 | 2309 | 0 | 0 | 221546 | 0 | 12075333484100444 | 12075337370793627 | 12075337370929466 | 12075333484405240 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7faba08f5a00 | 0x7faa94c36f00 | 3912272 | 3750314 | 65536 | 489033 | 489033 | 489033 | 0 | 2476 | 0 | 0 | 485559 | 158 | 12075333484454181 | 12075337370968505 | 12075337371282742 | 12075333484970631 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7faba08f5900 | 0x7faa94c36f40 | 1935080 | 1779046 | 65536 | 241884 | 241884 | 241884 | 0 | 2326 | 0 | 0 | 238242 | 0 | 12075333485036223 | 12075337371353782 | 12075337371505300 | 12075333485361187 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7faba08f5800 | 0x7faa94c36f80 | 6277968 | 6114231 | 65536 | 784745 | 784745 | 784745 | 0 | 2430 | 0 | 0 | 781032 | 0 | 12075333485410097 | 12075337371545780 | 12075337372062255 | 12075333486139423 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7faba08f5700 | 0x7faa94c36fc0 | 3700384 | 3479029 | 65536 | 462547 | 462547 | 462547 | 0 | 2479 | 0 | 0 | 453223 | 0 | 12075333486186871 | 12075337372121775 | 12075337372417292 | 12075333486679967 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7faba08f5600 | 0x7faa94c37000 | 2005712 | 1825134 | 65536 | 250713 | 250713 | 250713 | 0 | 2326 | 0 | 0 | 242386 | 0 | 12075333486728537 | 12075337372475371 | 12075337372628810 | 12075333487056757 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7faba08f5500 | 0x7faa94c37040 | 4749160 | 4584834 | 65536 | 593644 | 593644 | 593644 | 0 | 2356 | 0 | 0 | 589240 | 0 | 12075333487106850 | 12075337372669610 | 12075337373053606 | 12075333487707266 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7faba08f5400 | 0x7faa94c37080 | 2210256 | 2052756 | 65536 | 276281 | 276281 | 276281 | 0 | 2273 | 0 | 0 | 273824 | 0 | 12075333487767267 | 12075337373123205 | 12075337373299364 | 12075333488114563 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7faba08f5300 | 0x7faa94c370c0 | 7540008 | 7230534 | 65536 | 942500 | 942500 | 942500 | 158 | 2440 | 0 | 0 | 923089 | 0 | 12075333488161159 | 12075337373339043 | 12075337373948958 | 12075333488985621 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7faba08f5a00 | 0x7faa94c37100 | 4003792 | 3826272 | 65536 | 500473 | 500473 | 500473 | 0 | 2541 | 0 | 0 | 499560 | 0 | 12075333489033730 | 12075337374006557 | 12075337374333114 | 12075333489555861 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7faba08f5900 | 0x7faa94c37140 | 2265320 | 2107157 | 65536 | 283164 | 283164 | 283164 | 0 | 2318 | 0 | 0 | 279179 | 0 | 12075333489599341 | 12075337374395834 | 12075337374573432 | 12075333489945455 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7faba08f5800 | 0x7faa94c37180 | 5576208 | 5419435 | 65536 | 697025 | 697025 | 697025 | 0 | 2365 | 0 | 0 | 695104 | 158 | 12075333489997491 | 12075337374615032 | 12075337375091347 | 12075333490660263 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7faba08f5700 | 0x7faa94c371c0 | 2510688 | 2348133 | 65536 | 313835 | 313835 | 313835 | 0 | 2291 | 0 | 0 | 310038 | 0 | 12075333490720685 | 12075337375162067 | 12075337375360305 | 12075333491117242 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7faba08f5600 | 0x7faa94c37200 | 8521488 | 8362026 | 65536 | 1065185 | 1065185 | 1065185 | 0 | 2432 | 0 | 0 | 1061977 | 0 | 12075333491163588 | 12075337375416624 | 12075337376118378 | 12075333492061106 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7faba08f5500 | 0x7faa94c37240 | 4850720 | 4379099 | 65536 | 606339 | 606339 | 606339 | 158 | 2430 | 0 | 0 | 562903 | 0 | 12075333492108043 | 12075337376180137 | 12075337376552614 | 12075333492698340 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7faba08f5400 | 0x7faa94c37280 | 2986576 | 2382745 | 65536 | 373321 | 373321 | 373321 | 158 | 2328 | 0 | 0 | 315168 | 0 | 12075333492742422 | 12075337376610213 | 12075337376811332 | 12075333493169235 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7faba08f5300 | 0x7faa94c372c0 | 6423912 | 6258329 | 65536 | 802988 | 802988 | 802988 | 0 | 2478 | 0 | 0 | 800785 | 0 | 12075333493213818 | 12075337376869571 | 12075337377394846 | 12075333493930069 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7faba08f5a00 | 0x7faa94c37300 | 2792656 | 2639582 | 65536 | 349081 | 349081 | 349081 | 0 | 2438 | 0 | 0 | 346945 | 0 | 12075333493990250 | 12075337377475645 | 12075337377699643 | 12075333494411233 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7faba08f5900 | 0x7faa94c37340 | 9671456 | 9494217 | 65536 | 1208931 | 1208931 | 1208931 | 158 | 2362 | 0 | 0 | 1204077 | 0 | 12075333494455695 | 12075337377757563 | 12075337378555635 | 12075333495444462 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7faba08f5800 | 0x7faa94c37380 | 5113040 | 4942735 | 65536 | 639129 | 639129 | 639129 | 0 | 2386 | 0 | 0 | 636344 | 0 | 12075333495494105 | 12075337378616115 | 12075337379038191 | 12075333496111762 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7faba08f5700 | 0x7faa94c373c0 | 2817312 | 2659717 | 65536 | 352163 | 352163 | 352163 | 0 | 2398 | 0 | 0 | 348261 | 0 | 12075333496161064 | 12075337379098670 | 12075337379324428 | 12075333496578750 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7faba08f5600 | 0x7faa94c37400 | 7431760 | 7116683 | 65536 | 928969 | 928969 | 928969 | 158 | 2445 | 0 | 0 | 906995 | 0 | 12075333496630456 | 12075337379383948 | 12075337379980582 | 12075333497438207 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7faba08f5500 | 0x7faa94c37440 | 3345320 | 3175325 | 65536 | 418164 | 418164 | 418164 | 0 | 2471 | 0 | 0 | 412766 | 158 | 12075333497499441 | 12075337380051142 | 12075337380319939 | 12075333497964725 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7faba08f5400 | 0x7faa94c37480 | 11895952 | 11736932 | 65536 | 1486993 | 1486993 | 1486993 | 0 | 4268 | 0 | 0 | 1485033 | 158 | 12075333498013917 | 12075337380378819 | 12075337381363130 | 12075333499241618 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7faba08f5300 | 0x7faa94c374c0 | 6227744 | 6059869 | 65536 | 778467 | 778467 | 778467 | 0 | 2478 | 0 | 0 | 775232 | 0 | 12075333499271604 | 12075337381420089 | 12075337381950484 | 12075333500050962 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7faba08f5a00 | 0x7faa94c37500 | 3377808 | 3222045 | 65536 | 422225 | 422225 | 422225 | 0 | 2362 | 0 | 0 | 420493 | 0 | 12075333500082280 | 12075337382012724 | 12075337382284241 | 12075333500607907 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7faba08f5900 | 0x7faa94c37540 | 9006568 | 8843372 | 65536 | 1125820 | 1125820 | 1125820 | 0 | 2445 | 0 | 0 | 1123937 | 0 | 12075333500631330 | 12075337382347121 | 12075337383084074 | 12075333501625287 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7faba08f5800 | 0x7faa94c37580 | 4271952 | 3740102 | 65536 | 533993 | 533993 | 533993 | 158 | 2412 | 0 | 0 | 487763 | 0 | 12075333501667896 | 12075337383155273 | 12075337383469670 | 12075333502250800 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7faba08f5700 | 0x7faa94c375c0 | 14150176 | 13979710 | 65536 | 1768771 | 1768771 | 1768771 | 158 | 2412 | 0 | 0 | 1764445 | 158 | 12075333502274494 | 12075337383527270 | 12075337384697979 | 12075333503701505 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7faba08f5600 | 0x7faa94c37600 | 7350096 | 7173407 | 65536 | 918761 | 918761 | 918761 | 0 | 2467 | 0 | 0 | 920328 | 0 | 12075333503731531 | 12075337384760538 | 12075337385370613 | 12075333504598302 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7faba08f5500 | 0x7faa94c37640 | 3938784 | 3777180 | 65536 | 492347 | 492347 | 492347 | 0 | 2437 | 0 | 0 | 489849 | 0 | 12075333504623068 | 12075337385432692 | 12075337385751249 | 12075333505204969 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7faba08f5400 | 0x7faa94c37680 | 10690320 | 10527685 | 65536 | 1336289 | 1336289 | 1336289 | 0 | 2426 | 0 | 0 | 1331774 | 0 | 12075333505229935 | 12075337385810449 | 12075337386687721 | 12075333506362590 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7faba08f5300 | 0x7faa94c376c0 | 5034144 | 4866775 | 65536 | 629267 | 629267 | 629267 | 0 | 2458 | 0 | 0 | 631616 | 0 | 12075333506398877 | 12075337386765160 | 12075337387175716 | 12075333507064554 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7faba08f5a00 | 0x7faa94c37700 | 18652112 | 18492948 | 65536 | 2331513 | 2331513 | 2331513 | 0 | 4315 | 0 | 0 | 2329207 | 0 | 12075333507094219 | 12075337387236996 | 12075337388785941 | 12075333508901527 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7faba08f5900 | 0x7faa94c37740 | 9599016 | 9436847 | 65536 | 1199876 | 1199876 | 1199876 | 0 | 2519 | 0 | 0 | 1197109 | 0 | 12075333508928237 | 12075337388889251 | 12075337389683164 | 12075333510025907 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7faba08f5800 | 0x7faa94c37780 | 5121680 | 4957887 | 65536 | 640209 | 640209 | 640209 | 0 | 2997 | 0 | 0 | 636943 | 0 | 12075333510061323 | 12075337389787642 | 12075337390200919 | 12075333510723363 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7faba08f5700 | 0x7faa94c377c0 | 14055080 | 13897304 | 65536 | 1756884 | 1756884 | 1756884 | 0 | 2664 | 0 | 0 | 1754671 | 158 | 12075333510749732 | 12075337390310998 | 12075337391469229 | 12075333512162747 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7faba08f5600 | 0x7faa94c37800 | 9605712 | 9423905 | 65536 | 1200713 | 1200713 | 1200713 | 158 | 2435 | 0 | 0 | 1194384 | 0 | 12075333512211007 | 12075337391584108 | 12075337392369221 | 12075333513239829 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7faba08f5500 | 0x7faa94c37840 | 36677480 | 36504826 | 65536 | 4584684 | 4584684 | 4584684 | 158 | 2451 | 0 | 0 | 4579607 | 158 | 12075333513271047 | 12075337392474340 | 12075337395525356 | 12075333516576449 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7faba08f5400 | 0x7faa94c37880 | 18584464 | 18426379 | 65536 | 2323057 | 2323057 | 2323057 | 158 | 4289 | 0 | 0 | 2322363 | 0 | 12075333516605032 | 12075337395630475 | 12075337397171742 | 12075333518407180 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7faba08f5300 | 0x7faa94c378c0 | 9633248 | 9459598 | 65536 | 1204155 | 1204155 | 1204155 | 0 | 2445 | 0 | 0 | 1199105 | 0 | 12075333518433489 | 12075337397276541 | 12075337398065495 | 12075333519487127 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7faba08f5a00 | 0x7faa94c37900 | 27538960 | 27379153 | 65536 | 3442369 | 3442369 | 3442369 | 0 | 3016 | 0 | 0 | 3437778 | 158 | 12075333519518175 | 12075337398170774 | 12075337400451876 | 12075333522053225 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7faba08f5900 | 0x7faa94c37940 | 18580064 | 18418933 | 65536 | 2322507 | 2322507 | 2322507 | 0 | 2405 | 0 | 0 | 2320600 | 0 | 12075333522100353 | 12075337400566275 | 12075337402101782 | 12075333523872505 |
| 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 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7faba08f5800 | 0x7faa94c37980 | 72689296 | 72527179 | 65536 | 9086161 | 9086161 | 9086161 | 0 | 2316 | 0 | 0 | 9083384 | 0 | 12075333523904295 | 12075337402208341 | 12075337408263012 | 12075333530221753 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7faba08f5700 | 0x7faa94c379c0 | 36583592 | 36419575 | 65536 | 4572948 | 4572948 | 4572948 | 158 | 2462 | 0 | 0 | 4567712 | 0 | 12075333530253763 | 12075337408369251 | 12075337411410667 | 12075333533564154 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7faba08f5600 | 0x7faa94c37a00 | 18625360 | 18458469 | 65536 | 2328169 | 2328169 | 2328169 | 0 | 2517 | 0 | 0 | 2323842 | 0 | 12075333533589671 | 12075337411516106 | 12075337413054813 | 12075333535391770 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 870326 | 870331 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7faba08f5500 | 0x7faa94c37a40 | 54491744 | 54333153 | 65536 | 6811467 | 6811467 | 6811467 | 0 | 2779 | 0 | 0 | 6807296 | 0 | 12075333535424030 | 12075337413159772 | 12075337417685176 | 12075333540205033 |