71 KiB
71 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_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TA_TA_BUSY_sum | TA_SH_FIFO_BUSY_sum | TA_BUFFER_COALESCED_READ_CYCLES_sum | TA_BUFFER_COALESCED_WRITE_CYCLES_sum | TA_ADDR_STALLED_BY_TC_CYCLES_sum | TA_TOTAL_WAVEFRONTS_sum | TA_ADDR_STALLED_BY_TD_CYCLES_sum | TA_DATA_STALLED_BY_TC_CYCLES_sum | TA_FLAT_WAVEFRONTS_sum | TA_FLAT_READ_WAVEFRONTS_sum | TA_FLAT_WRITE_WAVEFRONTS_sum | TA_FLAT_ATOMIC_WAVEFRONTS_sum | TA_FLAT_COALESCEABLE_WAVEFRONTS_sum | TA_SH_FIFO_CMD_BUSY_sum | TA_SH_FIFO_ADDR_BUSY_sum | TA_SH_FIFO_DATA_BUSY_sum | TA_SH_FIFO_DATA_SFIFO_BUSY_sum | TA_SH_FIFO_DATA_TFIFO_BUSY_sum | TA_SQ_TA_CMD_CYCLES_sum | TA_SP_TA_ADDR_CYCLES_sum | TA_SP_TA_DATA_CYCLES_sum | TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum | TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum | TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum | TA_TA_SH_FIFO_STARVED_sum | TA_BUFFER_WAVEFRONTS_sum | TA_BUFFER_READ_WAVEFRONTS_sum | TA_BUFFER_WRITE_WAVEFRONTS_sum | TA_BUFFER_ATOMIC_WAVEFRONTS_sum | TA_BUFFER_TOTAL_CYCLES_sum | TA_BUFFER_COALESCABLE_WAVEFRONTS_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 859003 | 859008 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fe216404180 | 4050960 | 3839309 | 57277865 | 524288 | 367224834 | 506369 | 506369 | 54608419 | 54503566 | 0 | 0 | 17483596 | 1048576 | 0 | 37640446 | 1048576 | 0 | 1048576 | 0 | 1048576 | 52690157 | 52476635 | 54330552 | 53979516 | 54506700 | 4194304 | 4194304 | 4194304 | 0 | 0 | 0 | 302809 | 0 | 0 | 0 | 0 | 0 | 1048576 | 12075036785139935 | 12075053930670524 | 12075053930994841 | 12075037032390637 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 859003 | 859008 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fe216435100 | 222080 | 78011 | 1064244 | 512 | 1134453 | 27759 | 27759 | 187422 | 169938 | 0 | 0 | 55306 | 4096 | 0 | 0 | 4096 | 4096 | 0 | 0 | 4096 | 112930 | 110169 | 0 | 0 | 0 | 16384 | 16384 | 0 | 0 | 0 | 0 | 3101 | 0 | 0 | 0 | 0 | 0 | 4096 | 12075037046900972 | 12075053946463595 | 12075053946470315 | 12075037047355808 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fe321fc1900 | 0x7fe216435140 | 1740672 | 1586248 | 23494145 | 65536 | 141654714 | 217583 | 217583 | 22565080 | 22489456 | 0 | 0 | 20081327 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21462978 | 21450493 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 9506 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037047525954 | 12075053946537675 | 12075053946667114 | 12075037048021645 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fe321fc1800 | 0x7fe216435180 | 3138856 | 2968291 | 44148750 | 65536 | 186278954 | 392356 | 392356 | 41780844 | 41340676 | 0 | 0 | 35341859 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43117985 | 43109631 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 1578 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037048267682 | 12075053946727593 | 12075053946972551 | 12075037048873618 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fe321fc1700 | 0x7fe2164351c0 | 3112232 | 2954320 | 44104394 | 65536 | 342449027 | 389028 | 389028 | 43517882 | 43485473 | 0 | 0 | 35454457 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43964251 | 43951004 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3391 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037049039056 | 12075053947109990 | 12075053947359268 | 12075037049641716 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fe321fc1600 | 0x7fe216435200 | 1727000 | 1569671 | 23262409 | 65536 | 148045960 | 215874 | 215874 | 22458167 | 22407554 | 0 | 0 | 21517028 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21381515 | 21365678 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 6999 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037049799389 | 12075053947492867 | 12075053947618466 | 12075037050222425 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fe321fc1500 | 0x7fe216435240 | 1726232 | 1572220 | 23239383 | 65536 | 133691904 | 215778 | 215778 | 22097146 | 21980395 | 0 | 0 | 20285891 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22225534 | 22214562 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4239 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037050456971 | 12075053947660225 | 12075053947785344 | 12075037050871521 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fe321fc1400 | 0x7fe216435280 | 1686440 | 1531341 | 22657097 | 65536 | 155635566 | 210804 | 210804 | 21710287 | 21617584 | 0 | 0 | 20279164 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21843840 | 21830222 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 5027 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037051122147 | 12075053947852704 | 12075053947976703 | 12075037051538280 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fe321fc1300 | 0x7fe2164352c0 | 3163240 | 3005603 | 44790596 | 65536 | 345647398 | 395404 | 395404 | 43880811 | 43849421 | 0 | 0 | 34079981 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44137949 | 44133654 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4252 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037051769320 | 12075053948025183 | 12075053948269661 | 12075037052373242 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fe321fc1a00 | 0x7fe216435300 | 3173488 | 3017735 | 44884523 | 65536 | 283830254 | 396685 | 396685 | 43814302 | 43689916 | 0 | 0 | 33272645 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43703603 | 43695763 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 85869 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037052529442 | 12075053948404859 | 12075053948648057 | 12075037053137041 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fe321fc1900 | 0x7fe216435340 | 1720304 | 1561426 | 23150477 | 65536 | 155348481 | 215037 | 215037 | 22364069 | 22292764 | 0 | 0 | 19528700 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21665234 | 21646858 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 15553 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037053296127 | 12075053948780216 | 12075053948905335 | 12075037053707351 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fe321fc1800 | 0x7fe216435380 | 1735464 | 1574206 | 23298319 | 65536 | 154996811 | 216932 | 216932 | 22592807 | 22551617 | 0 | 0 | 20488748 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21176920 | 21161065 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 12529 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037053935345 | 12075053948946935 | 12075053949071734 | 12075037054361457 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fe321fc1700 | 0x7fe2164353c0 | 1662208 | 1503960 | 22363976 | 65536 | 167154623 | 207775 | 207775 | 21604193 | 21558517 | 0 | 0 | 20984850 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21880980 | 21860752 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 13977 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037054605691 | 12075053949127414 | 12075053949251733 | 12075037055011094 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fe321fc1600 | 0x7fe216435400 | 3232704 | 3078049 | 45925473 | 65536 | 294759859 | 404087 | 404087 | 42911129 | 42608459 | 0 | 0 | 31925129 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 45067706 | 45057791 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4034 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037055229320 | 12075053949293652 | 12075053949544530 | 12075037055835646 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fe321fc1500 | 0x7fe216435440 | 3143808 | 2964995 | 44285816 | 65536 | 278380746 | 392975 | 392975 | 43033578 | 42832722 | 0 | 0 | 35405715 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44636344 | 44630361 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3802 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037056007155 | 12075053949656049 | 12075053949938127 | 12075037056602321 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fe321fc1400 | 0x7fe216435480 | 1646504 | 1497749 | 22236054 | 65536 | 160416009 | 205812 | 205812 | 21511861 | 21447529 | 0 | 0 | 20138955 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21605436 | 21590789 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 14299 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037056758341 | 12075053950052206 | 12075053950177165 | 12075037057166239 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fe321fc1300 | 0x7fe2164354c0 | 1686064 | 1528546 | 22635704 | 65536 | 151169263 | 210757 | 210757 | 21659046 | 21555066 | 0 | 0 | 20125904 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21896750 | 21873537 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4626 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037057395756 | 12075053950220205 | 12075053950345644 | 12075037057805567 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fe321fc1a00 | 0x7fe216435500 | 1701288 | 1548560 | 22927480 | 65536 | 163721465 | 212660 | 212660 | 22160318 | 22098775 | 0 | 0 | 20219936 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21573173 | 21544171 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 21411 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037058046174 | 12075053950402123 | 12075053950526282 | 12075037058453010 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fe321fc1900 | 0x7fe216435540 | 3129960 | 2961281 | 44098216 | 65536 | 300046955 | 391244 | 391244 | 43352241 | 43322991 | 0 | 0 | 35309053 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43564120 | 43550684 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4689 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037058676305 | 12075053950569162 | 12075053950819080 | 12075037059283043 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fe321fc1800 | 0x7fe216435580 | 3124120 | 2964078 | 44281170 | 65536 | 338890385 | 390514 | 390514 | 43660815 | 43637549 | 0 | 0 | 34263582 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42692151 | 42640220 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 5972 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037059443311 | 12075053950901319 | 12075053951147397 | 12075037060040360 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fe321fc1700 | 0x7fe2164355c0 | 1713688 | 1554637 | 23017125 | 65536 | 161448719 | 214210 | 214210 | 22393910 | 22335978 | 0 | 0 | 19854901 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21432898 | 21405231 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 8825 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037060201680 | 12075053951281316 | 12075053951406595 | 12075037060608696 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fe321fc1600 | 0x7fe216435600 | 1688752 | 1526169 | 22606601 | 65536 | 156260740 | 211093 | 211093 | 21536525 | 21448966 | 0 | 0 | 19983772 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21451969 | 21426302 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 15979 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037060836029 | 12075053951448035 | 12075053951573314 | 12075037061263744 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fe321fc1500 | 0x7fe216435640 | 1704104 | 1546927 | 22930534 | 65536 | 160603622 | 213012 | 213012 | 22185956 | 22112309 | 0 | 0 | 19997879 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21944607 | 21924224 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 16871 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037061501746 | 12075053951625953 | 12075053951749952 | 12075037061917489 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fe321fc1400 | 0x7fe216435680 | 3107456 | 2941968 | 43814739 | 65536 | 301603393 | 388431 | 388431 | 43026116 | 42992240 | 0 | 0 | 34455750 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43922140 | 43910746 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4893 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037062140984 | 12075053951793152 | 12075053952040670 | 12075037062734617 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fe321fc1300 | 0x7fe2164356c0 | 3150760 | 2982119 | 44445673 | 65536 | 300372465 | 393844 | 393844 | 43830464 | 43803694 | 0 | 0 | 34457353 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44065417 | 44061293 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 12212 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037062884335 | 12075053952171869 | 12075053952416187 | 12075037063496213 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fe321fc1a00 | 0x7fe216435700 | 1714648 | 1562933 | 23161534 | 65536 | 157078118 | 214330 | 214330 | 22100935 | 21997450 | 0 | 0 | 20041620 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22257719 | 22244952 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 11931 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037063646492 | 12075053952545786 | 12075053952669785 | 12075037064052526 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fe321fc1900 | 0x7fe216435740 | 1709784 | 1552099 | 22901387 | 65536 | 163688710 | 213722 | 213722 | 22001377 | 21916187 | 0 | 0 | 19761384 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22334386 | 22321951 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 21229 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037064276162 | 12075053952710425 | 12075053952835544 | 12075037064696653 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fe321fc1800 | 0x7fe216435780 | 1675176 | 1522082 | 22523722 | 65536 | 163315201 | 209396 | 209396 | 21726336 | 21661159 | 0 | 0 | 19606292 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21684083 | 21670494 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 13165 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037064905842 | 12075053952886743 | 12075053953011062 | 12075037065317377 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fe321fc1700 | 0x7fe2164357c0 | 3169968 | 3007712 | 44808232 | 65536 | 318024430 | 396245 | 396245 | 43953571 | 43923528 | 0 | 0 | 34470918 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42298117 | 42269028 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 8014 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037065534430 | 12075053953053462 | 12075053953297940 | 12075037066137912 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fe321fc1600 | 0x7fe216435800 | 3105008 | 2942044 | 43801707 | 65536 | 316731796 | 388125 | 388125 | 43060098 | 43014205 | 0 | 0 | 33141439 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43966468 | 43957972 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 22882 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037066288061 | 12075053953431219 | 12075053953679217 | 12075037066886052 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fe321fc1500 | 0x7fe216435840 | 1720984 | 1565687 | 23183497 | 65536 | 154001256 | 215122 | 215122 | 22301636 | 22203092 | 0 | 0 | 19810488 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21537175 | 21515916 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 14637 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037067049867 | 12075053953809616 | 12075053953933935 | 12075037067461782 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fe321fc1400 | 0x7fe216435880 | 1821936 | 1662582 | 24557418 | 65536 | 165321548 | 227741 | 227741 | 23357442 | 23156854 | 0 | 0 | 20141859 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21496155 | 21465598 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 28476 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037067690347 | 12075053953975054 | 12075053954100173 | 12075037068107702 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fe321fc1300 | 0x7fe2164358c0 | 1665776 | 1505835 | 22356230 | 65536 | 165811288 | 208221 | 208221 | 21544192 | 21490531 | 0 | 0 | 19462481 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22412978 | 22380460 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 8090 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037068348259 | 12075053954155533 | 12075053954280172 | 12075037068762409 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fe321fc1a00 | 0x7fe216435900 | 3194368 | 3031977 | 45093422 | 65536 | 287449993 | 399295 | 399295 | 43600182 | 43441148 | 0 | 0 | 35693110 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42428899 | 42362543 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 5203 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037068979042 | 12075053954322892 | 12075053954567690 | 12075037069590508 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fe321fc1900 | 0x7fe216435940 | 3124864 | 2941787 | 43931382 | 65536 | 288503059 | 390607 | 390607 | 43226689 | 43189298 | 0 | 0 | 34612766 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44898988 | 44892962 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 22893 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037069750275 | 12075053954661289 | 12075053954906727 | 12075037070347304 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fe321fc1800 | 0x7fe216435980 | 1713384 | 1558556 | 23042466 | 65536 | 162754366 | 214172 | 214172 | 22188020 | 22090453 | 0 | 0 | 19603454 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22342534 | 22309269 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 9016 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037070478478 | 12075053955022246 | 12075053955147365 | 12075037070891876 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fe321fc1700 | 0x7fe2164359c0 | 1725928 | 1568823 | 23106759 | 65536 | 166419487 | 215740 | 215740 | 22018012 | 21864139 | 0 | 0 | 20368740 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20739666 | 20703802 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 28125 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037071122645 | 12075053955191205 | 12075053955316803 | 12075037071533328 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fe321fc1600 | 0x7fe216435a00 | 1701488 | 1542791 | 22810825 | 65536 | 166240189 | 212685 | 212685 | 22015816 | 21942606 | 0 | 0 | 19967451 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21535462 | 21524492 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 15017 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037071772723 | 12075053955370083 | 12075053955495042 | 12075037072195118 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fe321fc1500 | 0x7fe216435a40 | 3111216 | 2943192 | 43729121 | 65536 | 290906354 | 388901 | 388901 | 42814166 | 42750043 | 0 | 0 | 35175859 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44308095 | 44302650 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4890 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037072422922 | 12075053955537442 | 12075053955784160 | 12075037073025672 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fe321fc1400 | 0x7fe216435a80 | 3071936 | 2897331 | 43244775 | 65536 | 316655401 | 383991 | 383991 | 42248654 | 42178163 | 0 | 0 | 35147920 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43004267 | 42999764 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 37636 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037073188044 | 12075053955846559 | 12075053956092637 | 12075037073779483 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fe321fc1300 | 0x7fe216435ac0 | 1646696 | 1484104 | 22035779 | 65536 | 167518418 | 205836 | 205836 | 21342400 | 21294431 | 0 | 0 | 19632898 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22163471 | 22141149 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 11856 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037073942846 | 12075053956177597 | 12075053956302876 | 12075037074360572 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fe321fc1a00 | 0x7fe216435b00 | 1764672 | 1610861 | 23703398 | 65536 | 164626502 | 220583 | 220583 | 22333313 | 22030398 | 0 | 0 | 18902643 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20007897 | 19927139 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 24748 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037074590269 | 12075053956344475 | 12075053956470234 | 12075037075007204 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fe321fc1900 | 0x7fe216435b40 | 1703464 | 1542925 | 22816963 | 65536 | 166324628 | 212932 | 212932 | 21892982 | 21811785 | 0 | 0 | 19861634 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21759003 | 21730585 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 11386 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037075240588 | 12075053956527034 | 12075053956651993 | 12075037075657583 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fe321fc1800 | 0x7fe216435b80 | 3267352 | 3103653 | 46058033 | 65536 | 275475149 | 408418 | 408418 | 41442800 | 40403281 | 0 | 0 | 34986201 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44901556 | 44861434 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 81074 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037075875939 | 12075053956693752 | 12075053956947990 | 12075037076494538 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fe321fc1700 | 0x7fe216435bc0 | 3141040 | 2982075 | 44546308 | 65536 | 316402349 | 392629 | 392629 | 43847404 | 43816178 | 0 | 0 | 34872073 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44350276 | 44341487 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 5735 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037076651490 | 12075053957006230 | 12075053957293747 | 12075037077246966 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fe321fc1600 | 0x7fe216435c00 | 1715496 | 1533432 | 22691176 | 65536 | 161222753 | 214436 | 214436 | 21849461 | 21766871 | 0 | 0 | 19482435 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21257997 | 21223622 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 19960 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037077399800 | 12075053957380307 | 12075053957505106 | 12075037077805214 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fe321fc1500 | 0x7fe216435c40 | 1770536 | 1612605 | 23703226 | 65536 | 165824289 | 221316 | 221316 | 21959694 | 21460316 | 0 | 0 | 18713490 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 19998930 | 19882438 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 64085 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037078038007 | 12075053957549265 | 12075053957675984 | 12075037078459560 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fe321fc1400 | 0x7fe216435c80 | 1658560 | 1497963 | 22211455 | 65536 | 162246618 | 207319 | 207319 | 21387484 | 21300991 | 0 | 0 | 20392495 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21931673 | 21905179 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 15910 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037078693945 | 12075053957728784 | 12075053957854063 | 12075037079097776 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fe321fc1300 | 0x7fe216435cc0 | 3233920 | 3047994 | 45336180 | 65536 | 301777328 | 404239 | 404239 | 43099584 | 42599054 | 0 | 0 | 35277413 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 45754685 | 45717777 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 51374 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037079315250 | 12075053957897903 | 12075053958159180 | 12075037079925374 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fe321fc1a00 | 0x7fe216435d00 | 3133424 | 2968716 | 44254512 | 65536 | 308513334 | 391677 | 391677 | 43542762 | 43508712 | 0 | 0 | 31867563 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43049468 | 43015886 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3703 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037080091032 | 12075053958224620 | 12075053958471338 | 12075037080688722 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fe321fc1900 | 0x7fe216435d40 | 1668120 | 1505996 | 22338628 | 65536 | 170389774 | 208514 | 208514 | 21547947 | 21482895 | 0 | 0 | 19802864 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21518095 | 21498125 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 18195 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037080849040 | 12075053958529737 | 12075053958654856 | 12075037081259133 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fe321fc1800 | 0x7fe216435d80 | 1767616 | 1611147 | 23524598 | 65536 | 174137884 | 220951 | 220951 | 20418231 | 19596392 | 0 | 0 | 18284267 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 18660801 | 18482414 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 102715 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037081466889 | 12075053958699176 | 12075053958827815 | 12075037081879525 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fe321fc1700 | 0x7fe216435dc0 | 1714944 | 1558628 | 22988389 | 65536 | 169021268 | 214367 | 214367 | 22306815 | 22235156 | 0 | 0 | 19726949 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21581579 | 21544206 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 14904 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037082094625 | 12075053958880935 | 12075053959006214 | 12075037082511340 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fe321fc1600 | 0x7fe216435e00 | 3197680 | 3018219 | 44882912 | 65536 | 299408713 | 399709 | 399709 | 41028320 | 40234495 | 0 | 0 | 34275742 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 41602582 | 41473514 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 121625 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037082732260 | 12075053959050053 | 12075053959312611 | 12075037083339048 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fe321fc1500 | 0x7fe216435e40 | 3080936 | 2898199 | 43237641 | 65536 | 314813851 | 385116 | 385116 | 42454071 | 42398939 | 0 | 0 | 31676398 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43558205 | 43532002 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4331 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037083501720 | 12075053959371011 | 12075053959619649 | 12075037084098619 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fe321fc1400 | 0x7fe216435e80 | 1673584 | 1515283 | 22429618 | 65536 | 160365792 | 209197 | 209197 | 21478082 | 21371323 | 0 | 0 | 20172012 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21579914 | 21550754 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 11078 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037084261923 | 12075053959682688 | 12075053959807967 | 12075037084667867 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fe321fc1300 | 0x7fe216435ec0 | 1770648 | 1603756 | 23517404 | 65536 | 182515100 | 221330 | 221330 | 17572662 | 16113202 | 0 | 0 | 15678766 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 16452217 | 16167010 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 247328 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037084890391 | 12075053959851487 | 12075053959981406 | 12075037085317825 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fe321fc1a00 | 0x7fe216435f00 | 1720768 | 1561470 | 23034210 | 65536 | 169816105 | 215095 | 215095 | 22221564 | 22127914 | 0 | 0 | 19332613 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21119230 | 21082786 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 12017 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037085551559 | 12075053960038045 | 12075053960163164 | 12075037085966120 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fe321fc1900 | 0x7fe216435f40 | 3248432 | 3080286 | 45600212 | 65536 | 290948600 | 406053 | 406053 | 40075104 | 38925744 | 0 | 0 | 33680941 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43537939 | 43452390 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 154414 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037086191899 | 12075053960204604 | 12075053960472602 | 12075037086797214 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fe321fc1800 | 0x7fe216435f80 | 3153392 | 2990424 | 44628293 | 65536 | 271737530 | 394173 | 394173 | 41506800 | 41055896 | 0 | 0 | 35342791 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42871291 | 42823852 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4301 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037086952152 | 12075053960535321 | 12075053960779319 | 12075037087561124 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fe321fc1700 | 0x7fe216435fc0 | 1721176 | 1564857 | 23151680 | 65536 | 158478544 | 215146 | 215146 | 22236406 | 22080350 | 0 | 0 | 20054681 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20746669 | 20706070 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 14850 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037087711333 | 12075053960834039 | 12075053960959478 | 12075037088118840 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fe321fc1600 | 0x7fe216436000 | 1777576 | 1619832 | 24025712 | 65536 | 189173486 | 222196 | 222196 | 13673380 | 11983057 | 0 | 0 | 9995067 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 11306822 | 10806877 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 535538 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037088344800 | 12075053961001877 | 12075053961138036 | 12075037088759431 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fe321fc1500 | 0x7fe216436040 | 1708712 | 1550079 | 22867505 | 65536 | 164424639 | 213588 | 213588 | 21992678 | 21891976 | 0 | 0 | 20218093 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21920988 | 21895605 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 17199 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037088992324 | 12075053961190676 | 12075053961315475 | 12075037089407766 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fe321fc1400 | 0x7fe216436080 | 3270808 | 3067362 | 45599443 | 65536 | 332629664 | 408850 | 408850 | 43447921 | 43088834 | 0 | 0 | 36180108 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44812381 | 44742621 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 248788 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037089630900 | 12075053961356275 | 12075053961608433 | 12075037090250231 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fe321fc1300 | 0x7fe2164360c0 | 3146088 | 2986510 | 44504037 | 65536 | 317197341 | 393260 | 393260 | 43829050 | 43800221 | 0 | 0 | 34772068 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44101724 | 44093200 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3818 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037090413715 | 12075053961665072 | 12075053961911310 | 12075037091021464 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fe321fc1a00 | 0x7fe216436100 | 1677424 | 1526699 | 22602225 | 65536 | 165619033 | 209677 | 209677 | 21764972 | 21692648 | 0 | 0 | 19907881 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21535820 | 21504158 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 20596 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037091176593 | 12075053961971630 | 12075053962096589 | 12075037091588729 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fe321fc1900 | 0x7fe216436140 | 1843752 | 1682428 | 24926704 | 65536 | 194449371 | 230468 | 230468 | 11447077 | 9572316 | 0 | 0 | 7122452 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 9093012 | 8463799 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 656835 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037091816592 | 12075053962140748 | 12075053962283467 | 12075037092251340 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fe321fc1800 | 0x7fe216436180 | 1647600 | 1496147 | 22191455 | 65536 | 165390314 | 205949 | 205949 | 21235077 | 21123111 | 0 | 0 | 19078288 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21398600 | 21374469 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 18239 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037092468353 | 12075053962335147 | 12075053962460746 | 12075037092870731 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fe321fc1700 | 0x7fe2164361c0 | 3196736 | 3027840 | 45002774 | 65536 | 330592349 | 399591 | 399591 | 42721877 | 42303182 | 0 | 0 | 31568343 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43581541 | 43499800 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 226003 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037093079719 | 12075053962501545 | 12075053962755303 | 12075037093688651 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fe321fc1600 | 0x7fe216436200 | 3071592 | 2911643 | 43441253 | 65536 | 323112331 | 383948 | 383948 | 42734871 | 42707441 | 0 | 0 | 34238753 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44460490 | 44455661 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4077 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037093849290 | 12075053962817543 | 12075053963099940 | 12075037094447912 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fe321fc1500 | 0x7fe216436240 | 1732840 | 1568841 | 23140164 | 65536 | 162337588 | 216604 | 216604 | 22028529 | 21826043 | 0 | 0 | 20920464 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21322187 | 21291211 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 13485 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037094605084 | 12075053963162020 | 12075053963287619 | 12075037095017040 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fe321fc1400 | 0x7fe216436280 | 1906496 | 1755747 | 26063780 | 65536 | 209625377 | 238311 | 238311 | 8538968 | 6835127 | 0 | 0 | 5502762 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7166819 | 6446296 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 693080 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037095230887 | 12075053963330179 | 12075053963478657 | 12075037095653833 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fe321fc1300 | 0x7fe2164362c0 | 1727744 | 1571522 | 23202286 | 65536 | 166775761 | 215967 | 215967 | 22137263 | 21985374 | 0 | 0 | 20436085 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20744079 | 20712381 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 29498 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037095901193 | 12075053963543937 | 12075053963669536 | 12075037096324279 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fe321fc1a00 | 0x7fe216436300 | 3193712 | 2996189 | 44481615 | 65536 | 284910140 | 399213 | 399213 | 36551806 | 34852250 | 0 | 0 | 26683679 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 40070627 | 39866154 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 154207 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037096540100 | 12075053963712096 | 12075053963968893 | 12075037097140265 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fe321fc1900 | 0x7fe216436340 | 3123160 | 2948774 | 43867655 | 65536 | 276331261 | 390394 | 390394 | 42749373 | 42618581 | 0 | 0 | 34190291 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43144523 | 43121230 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 27489 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037097295183 | 12075053964034173 | 12075053964279291 | 12075037097890700 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fe321fc1800 | 0x7fe216436380 | 1708904 | 1518471 | 22485302 | 65536 | 164264117 | 213612 | 213612 | 21491927 | 21349700 | 0 | 0 | 20479658 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21973829 | 21939397 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 21687 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037098054184 | 12075053964341850 | 12075053964467289 | 12075037098459547 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fe321fc1700 | 0x7fe2164363c0 | 2003456 | 1849594 | 27442307 | 65536 | 222095619 | 250431 | 250431 | 7803419 | 6160662 | 0 | 0 | 3048610 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5724965 | 4950613 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 758724 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037098661933 | 12075053964509689 | 12075053964666968 | 12075037099089818 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fe321fc1600 | 0x7fe216436400 | 1721728 | 1563061 | 23065907 | 65536 | 159047232 | 215215 | 215215 | 21748520 | 21524889 | 0 | 0 | 18902720 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21523930 | 21486948 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 27250 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037099324244 | 12075053964717847 | 12075053964842646 | 12075037099730820 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fe321fc1500 | 0x7fe216436440 | 3202072 | 2999763 | 44624169 | 65536 | 307324210 | 400258 | 400258 | 37143690 | 35577849 | 0 | 0 | 26155945 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 39577086 | 39355420 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 281065 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037099946160 | 12075053964884406 | 12075053965143764 | 12075037100551575 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fe321fc1400 | 0x7fe216436480 | 3113128 | 2938914 | 43727469 | 65536 | 265350929 | 389140 | 389140 | 42162024 | 41912270 | 0 | 0 | 35244841 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43812359 | 43807897 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3747 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037100702285 | 12075053965205683 | 12075053965451761 | 12075037101290919 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fe321fc1300 | 0x7fe2164364c0 | 1779520 | 1621234 | 23880953 | 65536 | 171241821 | 222439 | 222439 | 22531445 | 22231985 | 0 | 0 | 19286928 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21332641 | 21305750 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 28374 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037101451988 | 12075053965511441 | 12075053965637360 | 12075037101875525 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fe321fc1a00 | 0x7fe216436500 | 2098496 | 1948388 | 28941954 | 65536 | 234575108 | 262311 | 262311 | 7252545 | 5662400 | 0 | 0 | 2917207 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5339088 | 4578470 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 791481 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037102105082 | 12075053965682800 | 12075053965847598 | 12075037102552583 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fe321fc1900 | 0x7fe216436540 | 2199808 | 1542762 | 22788851 | 65536 | 164378447 | 274975 | 274975 | 21638128 | 21463416 | 0 | 0 | 20086932 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21769764 | 21739730 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 15105 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037102791287 | 12075053965899278 | 12075053966024237 | 12075037103255339 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fe321fc1800 | 0x7fe216436580 | 3303320 | 3128704 | 46466322 | 65536 | 335107382 | 412914 | 412914 | 37269293 | 35591617 | 0 | 0 | 25143728 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 28130426 | 27530281 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 355834 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037103473244 | 12075053966066476 | 12075053966326954 | 12075037104082587 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fe321fc1700 | 0x7fe2164365c0 | 3127080 | 2952059 | 43962058 | 65536 | 314506172 | 390884 | 390884 | 43194112 | 43170792 | 0 | 0 | 31663460 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43314696 | 43279898 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 43083 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037104244598 | 12075053966387594 | 12075053966636072 | 12075037104813285 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fe321fc1600 | 0x7fe216436600 | 1696088 | 1536872 | 22711133 | 65536 | 168176578 | 212010 | 212010 | 21719699 | 21572163 | 0 | 0 | 19316286 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21197904 | 21126965 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 27172 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037104976658 | 12075053966698631 | 12075053966824230 | 12075037105400105 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fe321fc1500 | 0x7fe216436640 | 2208728 | 2049130 | 30421651 | 65536 | 246029388 | 276090 | 276090 | 6876111 | 5344497 | 0 | 0 | 2421045 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5090650 | 4329832 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 795768 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037105630864 | 12075053966867750 | 12075053967040069 | 12075037106082203 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fe321fc1400 | 0x7fe216436680 | 1724528 | 1562633 | 23016887 | 65536 | 166889262 | 215565 | 215565 | 21826863 | 21616482 | 0 | 0 | 20059965 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21590014 | 21521197 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 18029 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037106314695 | 12075053967094308 | 12075053967220387 | 12075037106722793 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fe321fc1300 | 0x7fe2164366c0 | 3164632 | 2984550 | 44371603 | 65536 | 330090878 | 395578 | 395578 | 25178785 | 22253512 | 0 | 0 | 13987424 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 23028872 | 22258354 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 850452 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037106939155 | 12075053967261827 | 12075053967514465 | 12075037107549089 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fe321fc1a00 | 0x7fe216436700 | 3112472 | 2940921 | 43773446 | 65536 | 302973268 | 389058 | 389058 | 42712901 | 42630218 | 0 | 0 | 34353889 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44241487 | 44235508 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 80355 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037107710379 | 12075053967573184 | 12075053967822142 | 12075037108310834 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fe321fc1900 | 0x7fe216436740 | 1724656 | 1561735 | 23020837 | 65536 | 161429246 | 215581 | 215581 | 21600551 | 21300573 | 0 | 0 | 20738427 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22068015 | 22021666 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 14103 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037108473978 | 12075053967878782 | 12075053968004701 | 12075037108883378 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fe321fc1800 | 0x7fe216436780 | 2305600 | 2147119 | 31908495 | 65536 | 255355467 | 288199 | 288199 | 6711299 | 5194479 | 0 | 0 | 2179113 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5053620 | 4323652 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 823782 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037109112835 | 12075053968046300 | 12075053968227579 | 12075037109636738 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fe321fc1700 | 0x7fe2164367c0 | 1764800 | 1608459 | 23754030 | 65536 | 169427669 | 220599 | 220599 | 22589012 | 22261564 | 0 | 0 | 19682014 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21324566 | 21276420 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 27744 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037109803208 | 12075053968279739 | 12075053968406138 | 12075037110226605 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fe321fc1600 | 0x7fe216436800 | 3283840 | 3119628 | 46483545 | 65536 | 380286554 | 410479 | 410479 | 22430713 | 15099370 | 0 | 0 | 2837466 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9818425 | 6372699 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3585199 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037110426977 | 12075053968446937 | 12075053968708535 | 12075037111023355 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fe321fc1500 | 0x7fe216436840 | 3122984 | 2951433 | 43999030 | 65536 | 286423612 | 390372 | 390372 | 42313948 | 42149165 | 0 | 0 | 33173086 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44777569 | 44761180 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 47285 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037111202558 | 12075053968765335 | 12075053969012053 | 12075037111797855 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fe321fc1400 | 0x7fe216436880 | 1728432 | 1576429 | 23214606 | 65536 | 164605758 | 216053 | 216053 | 21819283 | 21534695 | 0 | 0 | 20003484 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21908184 | 21876688 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 24318 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037111959215 | 12075053969070292 | 12075053969196371 | 12075037112377963 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fe321fc1300 | 0x7fe2164368c0 | 2405808 | 2248272 | 33397683 | 65536 | 269685219 | 300725 | 300725 | 6758699 | 5235619 | 0 | 0 | 2398443 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4962864 | 4200443 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 795594 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037112606197 | 12075053969241171 | 12075053969431889 | 12075037113139027 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fe321fc1a00 | 0x7fe216436900 | 1795968 | 1639234 | 24095310 | 65536 | 178436271 | 224495 | 224495 | 22249898 | 21785025 | 0 | 0 | 19786353 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20552235 | 20453927 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 43176 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037113305567 | 12075053969485169 | 12075053969611088 | 12075037113729504 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fe321fc1900 | 0x7fe216436940 | 3872936 | 3340011 | 49704136 | 65536 | 405703561 | 484116 | 484116 | 22938857 | 15021399 | 0 | 0 | 1869800 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9058933 | 5468983 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3715451 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037113946397 | 12075053969653327 | 12075053969935565 | 12075037114611203 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fe321fc1800 | 0x7fe216436980 | 3170856 | 2989003 | 44397412 | 65536 | 295757832 | 396356 | 396356 | 43258529 | 43147356 | 0 | 0 | 34417278 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44187751 | 44166382 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 27332 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037114773825 | 12075053969992685 | 12075053970238603 | 12075037115384550 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fe321fc1700 | 0x7fe2164369c0 | 1735016 | 1568687 | 23068549 | 65536 | 167821512 | 216876 | 216876 | 21627885 | 21280742 | 0 | 0 | 19242969 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20200000 | 20113384 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 43942 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037115546441 | 12075053970302762 | 12075053970429961 | 12075037115963286 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fe321fc1600 | 0x7fe216436a00 | 2643440 | 2489235 | 36974758 | 65536 | 300615900 | 330429 | 330429 | 7043569 | 5465556 | 0 | 0 | 2570741 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5238377 | 4465482 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 795377 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037116192271 | 12075053970472521 | 12075053970680999 | 12075037116746421 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fe321fc1500 | 0x7fe216436a40 | 1814424 | 1649772 | 24293716 | 65536 | 176925806 | 226802 | 226802 | 22296454 | 21775309 | 0 | 0 | 19603001 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20111183 | 20004683 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 63571 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037116912860 | 12075053970751719 | 12075053970878758 | 12075037117346656 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fe321fc1400 | 0x7fe216436a80 | 3776176 | 3610786 | 53766913 | 65536 | 440712255 | 472021 | 472021 | 23380071 | 14956365 | 0 | 0 | 1374098 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9133981 | 5454559 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3798372 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037117568338 | 12075053970922437 | 12075053971228355 | 12075037118222604 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fe321fc1300 | 0x7fe216436ac0 | 3126568 | 2942142 | 43795029 | 65536 | 322269212 | 390820 | 390820 | 42942450 | 42920925 | 0 | 0 | 34012401 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43908148 | 43899565 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 5526 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037118383193 | 12075053971296034 | 12075053971545792 | 12075037118986875 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fe321fc1a00 | 0x7fe216436b00 | 1798824 | 1641079 | 24121743 | 65536 | 177916105 | 224852 | 224852 | 22233473 | 21666265 | 0 | 0 | 19102564 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 19730440 | 19597716 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 82235 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037119148074 | 12075053971603392 | 12075053971730271 | 12075037119572874 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fe321fc1900 | 0x7fe216436b40 | 2854080 | 2693105 | 39998876 | 65536 | 326566259 | 356759 | 356759 | 7018820 | 5426218 | 0 | 0 | 2370440 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5119909 | 4343271 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 827879 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037119801298 | 12075053971771870 | 12075053971999228 | 12075037120378310 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fe321fc1800 | 0x7fe216436b80 | 1792472 | 1631791 | 24026156 | 65536 | 177802528 | 224058 | 224058 | 21873060 | 21251959 | 0 | 0 | 18924334 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 19330583 | 19196860 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 108497 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037120550080 | 12075053972072668 | 12075053972200827 | 12075037120974438 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fe321fc1700 | 0x7fe216436bc0 | 4032488 | 3873994 | 57674796 | 65536 | 473462731 | 504060 | 504060 | 23306084 | 14787588 | 0 | 0 | 1277488 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8681161 | 4973816 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3797810 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037121200428 | 12075053972241787 | 12075053972569944 | 12075037121878979 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fe321fc1600 | 0x7fe216436c00 | 3186392 | 3007555 | 44633301 | 65536 | 293800108 | 398298 | 398298 | 43016435 | 42808236 | 0 | 0 | 33369935 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43730158 | 43724815 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 102017 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037122048164 | 12075053972628663 | 12075053972881301 | 12075037122645714 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fe321fc1500 | 0x7fe216436c40 | 1818736 | 1647940 | 24210799 | 65536 | 175091803 | 227341 | 227341 | 21641387 | 20867911 | 0 | 0 | 19021806 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 18596066 | 18404766 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 109748 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037122805331 | 12075053972943861 | 12075053973071540 | 12075037123229309 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fe321fc1400 | 0x7fe216436c80 | 3060608 | 2904509 | 43208715 | 65536 | 353128175 | 382575 | 382575 | 6884502 | 5332937 | 0 | 0 | 2292144 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5016480 | 4219958 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 845809 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037123455940 | 12075053973115539 | 12075053973358897 | 12075037124051877 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fe321fc1300 | 0x7fe216436cc0 | 1822888 | 1659147 | 24365536 | 65536 | 182683222 | 227860 | 227860 | 20694219 | 19754698 | 0 | 0 | 18265349 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 17786871 | 17569799 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 185056 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037124220701 | 12075053973426577 | 12075053973556496 | 12075037124637956 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fe321fc1a00 | 0x7fe216436d00 | 4893936 | 4445810 | 66172365 | 65536 | 541160909 | 611741 | 611741 | 24170862 | 15184370 | 0 | 0 | 1668741 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8935768 | 5171377 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3862785 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037124840633 | 12075053973596976 | 12075053973971373 | 12075037125591629 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fe321fc1900 | 0x7fe216436d40 | 3167768 | 2991414 | 44436074 | 65536 | 344733495 | 395970 | 395970 | 42666535 | 42519791 | 0 | 0 | 28770110 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43178649 | 43118084 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 74943 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037125750323 | 12075053974038092 | 12075053974298250 | 12075037126359015 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fe321fc1800 | 0x7fe216436d80 | 1758680 | 1602234 | 23568125 | 65536 | 176854185 | 219834 | 219834 | 18875348 | 17532593 | 0 | 0 | 16337137 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 17035734 | 16778103 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 205623 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037126514834 | 12075053974363849 | 12075053974492168 | 12075037126927802 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fe321fc1700 | 0x7fe216436dc0 | 3471616 | 3314359 | 49294580 | 65536 | 404043246 | 433951 | 433951 | 6797153 | 5259809 | 0 | 0 | 2217018 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4982049 | 4203964 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 817663 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037127151788 | 12075053974533128 | 12075053974811206 | 12075037127774525 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fe321fc1600 | 0x7fe216436e00 | 1783528 | 1625542 | 23946980 | 65536 | 187431218 | 222940 | 222940 | 15864037 | 14136279 | 0 | 0 | 13257601 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 11199204 | 10661360 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 457877 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037127943690 | 12075053974877925 | 12075053975012484 | 12075037128372146 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fe321fc1500 | 0x7fe216436e40 | 5169856 | 4996247 | 74474905 | 65536 | 611106378 | 646231 | 646231 | 24358908 | 15072339 | 0 | 0 | 1352223 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8542337 | 4746800 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3874401 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037128600200 | 12075053975056164 | 12075053975477440 | 12075037129368317 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fe321fc1400 | 0x7fe216436e80 | 3194840 | 3012432 | 44625807 | 65536 | 326995692 | 399354 | 399354 | 34414812 | 33281550 | 0 | 0 | 24160409 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 27753241 | 27389566 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 316958 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037129521672 | 12075053975536000 | 12075053975801598 | 12075037130121948 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fe321fc1300 | 0x7fe216436ec0 | 1818048 | 1652348 | 24461268 | 65536 | 191324564 | 227255 | 227255 | 15486411 | 13643577 | 0 | 0 | 10912168 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 9406066 | 8779793 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 550705 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037130271385 | 12075053975858237 | 12075053975992796 | 12075037130696646 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fe321fc1a00 | 0x7fe216436f00 | 3908352 | 3752940 | 55858304 | 65536 | 456501275 | 488543 | 488543 | 6931650 | 5328419 | 0 | 0 | 2186053 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5175206 | 4381164 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 798243 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037130895144 | 12075053976037596 | 12075053976350873 | 12075037131571692 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fe321fc1900 | 0x7fe216436f40 | 1934464 | 1777009 | 26415170 | 65536 | 213679332 | 241807 | 241807 | 7882424 | 5453968 | 0 | 0 | 1973155 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5512907 | 4679707 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 853501 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037131743972 | 12075053976423673 | 12075053976574871 | 12075037132177427 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fe321fc1800 | 0x7fe216436f80 | 6261056 | 6110812 | 91159751 | 65536 | 751007295 | 782631 | 782631 | 24808742 | 15000334 | 0 | 0 | 1372845 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8785790 | 4913828 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3943124 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037132397927 | 12075053976617591 | 12075053977133267 | 12075037133262484 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fe321fc1700 | 0x7fe216436fc0 | 3630120 | 3470562 | 51402003 | 65536 | 392259303 | 453764 | 453764 | 26521503 | 25087022 | 0 | 0 | 16544671 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 23527999 | 23081315 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 438754 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037133421379 | 12075053977196626 | 12075053977493904 | 12075037134068522 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fe321fc1600 | 0x7fe216437000 | 1955736 | 1806246 | 26883666 | 65536 | 216588309 | 244466 | 244466 | 7439730 | 5053205 | 0 | 0 | 1507006 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4940930 | 4110642 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 841966 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037134228599 | 12075053977554863 | 12075053977708622 | 12075037134658608 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fe321fc1500 | 0x7fe216437040 | 4740480 | 4581838 | 68326227 | 65536 | 559229374 | 592559 | 592559 | 6870950 | 5428825 | 0 | 0 | 2171061 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5167124 | 4382241 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 899852 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037134884959 | 12075053977754222 | 12075053978138699 | 12075037135635904 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fe321fc1400 | 0x7fe216437080 | 2218712 | 2067657 | 30766812 | 65536 | 249564619 | 277338 | 277338 | 7814003 | 5331961 | 0 | 0 | 1811597 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4782581 | 3943711 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 835987 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037135800661 | 12075053978213898 | 12075053978389737 | 12075037136264813 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fe321fc1300 | 0x7fe2164370c0 | 7400872 | 7239084 | 108036449 | 65536 | 889015091 | 925108 | 925108 | 24939182 | 15225525 | 0 | 0 | 1684143 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8954169 | 5114435 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3911470 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037136480454 | 12075053978431016 | 12075053979039811 | 12075037137433946 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fe321fc1a00 | 0x7fe216437100 | 4005544 | 3838278 | 57107631 | 65536 | 456372238 | 500692 | 500692 | 17408130 | 15496516 | 0 | 0 | 5275557 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 14236455 | 13571731 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 676966 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037137573295 | 12075053979103331 | 12075053979432128 | 12075037138252497 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fe321fc1900 | 0x7fe216437140 | 2252208 | 2098356 | 31232435 | 65536 | 253982967 | 281525 | 281525 | 7624280 | 5262697 | 0 | 0 | 1527166 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4990240 | 4138659 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 843612 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037138414167 | 12075053979491648 | 12075053979669886 | 12075037138875525 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fe321fc1800 | 0x7fe216437180 | 5581288 | 5428876 | 80969777 | 65536 | 665815154 | 697660 | 697660 | 7143103 | 5588280 | 0 | 0 | 2169806 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5220792 | 4410301 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 929691 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037139102747 | 12075053979710526 | 12075053980165082 | 12075037139899458 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fe321fc1700 | 0x7fe2164371c0 | 2498992 | 2343463 | 34853219 | 65536 | 284811300 | 312373 | 312373 | 7508450 | 5066590 | 0 | 0 | 1503497 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4663592 | 3807359 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 845313 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037140075144 | 12075053980237082 | 12075053980435480 | 12075037140622952 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fe321fc1600 | 0x7fe216437200 | 8505920 | 8356860 | 124745653 | 65536 | 1028621635 | 1063239 | 1063239 | 25050176 | 15053707 | 0 | 0 | 1179450 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8468799 | 4583424 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3954460 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037140782308 | 12075053980494520 | 12075053981195474 | 12075037141841166 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fe321fc1500 | 0x7fe216437240 | 4528744 | 4365053 | 65036517 | 65536 | 530289734 | 566092 | 566092 | 15644418 | 13734891 | 0 | 0 | 3872430 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 12050296 | 11325869 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 693915 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037142006243 | 12075053981258674 | 12075053981632750 | 12075037142722594 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fe321fc1400 | 0x7fe216437280 | 2526448 | 2369093 | 35261569 | 65536 | 288019913 | 315805 | 315805 | 7413377 | 5014336 | 0 | 0 | 1725390 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4845024 | 4016637 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 853375 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037142883693 | 12075053981695470 | 12075053981897068 | 12075037143443033 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fe321fc1300 | 0x7fe2164372c0 | 6418160 | 6261254 | 93440266 | 65536 | 768958923 | 802269 | 802269 | 7093569 | 5595638 | 0 | 0 | 2102682 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5302505 | 4510541 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 872599 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037143604162 | 12075053981955628 | 12075053982480104 | 12075037144472897 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fe321fc1a00 | 0x7fe216437300 | 2794200 | 2640219 | 39304358 | 65536 | 321507910 | 349274 | 349274 | 7242075 | 5067334 | 0 | 0 | 1609493 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4821735 | 4018508 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 842286 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037144621703 | 12075053982561223 | 12075053982784101 | 12075037145191061 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fe321fc1900 | 0x7fe216437340 | 9656104 | 9490302 | 141702218 | 65536 | 1168889122 | 1207012 | 1207012 | 25634166 | 15495632 | 0 | 0 | 1420520 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8588384 | 4682337 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3977055 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037145350608 | 12075053982841381 | 12075053983638494 | 12075037146498551 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fe321fc1800 | 0x7fe216437380 | 5093296 | 4934995 | 73578727 | 65536 | 600878549 | 636661 | 636661 | 15903039 | 13883038 | 0 | 0 | 4139633 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 12081696 | 11339453 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 725580 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037146661714 | 12075053983700094 | 12075053984117210 | 12075037147423690 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fe321fc1700 | 0x7fe2164373c0 | 2818480 | 2659956 | 39572175 | 65536 | 323402310 | 352309 | 352309 | 7414559 | 5017579 | 0 | 0 | 1566252 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4765613 | 3919319 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 852171 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037147584589 | 12075053984180570 | 12075053984406008 | 12075037148153897 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fe321fc1600 | 0x7fe216437400 | 7268480 | 7110071 | 106164888 | 65536 | 874366636 | 908559 | 908559 | 7214887 | 5684139 | 0 | 0 | 2794061 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5544889 | 4790629 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 908679 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037148314516 | 12075053984467768 | 12075053985063443 | 12075037149264732 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fe321fc1500 | 0x7fe216437440 | 3341936 | 3183549 | 47313560 | 65536 | 387192123 | 417741 | 417741 | 7874094 | 5517637 | 0 | 0 | 2132571 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5188202 | 4316722 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 1016235 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037149434177 | 12075053985135122 | 12075053985403120 | 12075037150045362 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fe321fc1400 | 0x7fe216437480 | 11887016 | 11736037 | 175288709 | 65536 | 1446538184 | 1485876 | 1485876 | 25488346 | 15315729 | 0 | 0 | 1140436 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8970129 | 5070976 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3966789 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037150205670 | 12075053985463759 | 12075053986447112 | 12075037151530232 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fe321fc1300 | 0x7fe2164374c0 | 6220952 | 6050073 | 90230808 | 65536 | 739597601 | 777618 | 777618 | 15159706 | 13212990 | 0 | 0 | 4170883 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 12159038 | 11415018 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 719117 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037151691201 | 12075053986507271 | 12075053987020707 | 12075037152558733 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fe321fc1a00 | 0x7fe216437500 | 3375024 | 3222383 | 47926619 | 65536 | 391509846 | 421877 | 421877 | 7666163 | 5526418 | 0 | 0 | 2134820 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5155231 | 4317241 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 988991 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037152718210 | 12075053987084226 | 12075053987355584 | 12075037153334054 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fe321fc1900 | 0x7fe216437540 | 9009664 | 8847740 | 132123280 | 65536 | 1090931225 | 1126207 | 1126207 | 18646297 | 8598419 | 0 | 0 | 664282 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7832793 | 4147569 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3831876 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037153493280 | 12075053987416064 | 12075053988152538 | 12075037154573077 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fe321fc1800 | 0x7fe216437580 | 3898088 | 3735547 | 55561358 | 65536 | 455413095 | 487260 | 487260 | 7655438 | 5453669 | 0 | 0 | 1986596 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5216877 | 4314315 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 1042742 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037154744134 | 12075053988224697 | 12075053988539255 | 12075037155415522 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fe321fc1700 | 0x7fe2164375c0 | 14151064 | 13981735 | 208796767 | 65536 | 1725560928 | 1768882 | 1768882 | 26410269 | 15605332 | 0 | 0 | 1522224 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8898916 | 4928668 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4028665 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037155570620 | 12075053988600214 | 12075053989768525 | 12075037157084183 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fe321fc1600 | 0x7fe216437600 | 7347072 | 7173430 | 107099794 | 65536 | 812833977 | 918383 | 918383 | 15091492 | 13217740 | 0 | 0 | 4432074 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 11945284 | 11169558 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 756720 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037157243710 | 12075053989833004 | 12075053990438919 | 12075037158206298 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fe321fc1500 | 0x7fe216437640 | 3942144 | 3776604 | 56183991 | 65536 | 458858831 | 492767 | 492767 | 7626008 | 5437356 | 0 | 0 | 2125440 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5149768 | 4299540 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 1021012 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037158357570 | 12075053990507879 | 12075053990825796 | 12075037159024389 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fe321fc1400 | 0x7fe216437680 | 10695400 | 10536365 | 157294601 | 65536 | 1298886184 | 1336924 | 1336924 | 18504051 | 8558688 | 0 | 0 | 841922 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7441568 | 3761255 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3747455 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037159183685 | 12075053990886276 | 12075053991762268 | 12075037160408942 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fe321fc1300 | 0x7fe2164376c0 | 5037168 | 4869522 | 72568633 | 65536 | 595502297 | 629645 | 629645 | 7356046 | 5314493 | 0 | 0 | 1904611 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4984484 | 4152450 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 989020 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037160581813 | 12075053991840828 | 12075053992273944 | 12075037161337808 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fe321fc1a00 | 0x7fe216437700 | 18656216 | 18500357 | 276355341 | 65536 | 2285159797 | 2332026 | 2332026 | 26245258 | 15590936 | 0 | 0 | 830778 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8765503 | 4808122 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4008362 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037161492956 | 12075053992338986 | 12075053993885855 | 12075037163383780 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fe321fc1900 | 0x7fe216437740 | 9601640 | 9435928 | 140896025 | 65536 | 1162723795 | 1200204 | 1200204 | 25116667 | 14989491 | 0 | 0 | 1206396 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8614803 | 4717708 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3986326 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037163543798 | 12075053993996733 | 12075053994788408 | 12075037164686040 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fe321fc1800 | 0x7fe216437780 | 5105968 | 4955099 | 73926442 | 65536 | 607709839 | 638245 | 638245 | 18687874 | 8693246 | 0 | 0 | 795355 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7569297 | 3813621 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3856973 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037164847350 | 12075053994894807 | 12075053995307764 | 12075037165620116 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fe321fc1700 | 0x7fe2164377c0 | 14063896 | 13900112 | 207597027 | 65536 | 1714865179 | 1757986 | 1757986 | 18895865 | 8620744 | 0 | 0 | 804226 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7523956 | 3850869 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3716892 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037165778450 | 12075053995420083 | 12075053996577995 | 12075037167289569 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fe321fc1600 | 0x7fe216437800 | 9574808 | 9418903 | 140697513 | 65536 | 1161640076 | 1196850 | 1196850 | 18339952 | 8503598 | 0 | 0 | 787514 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7510769 | 3833249 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3826500 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037167460456 | 12075053996692074 | 12075053997476709 | 12075037168597179 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fe321fc1500 | 0x7fe216437840 | 36673128 | 36516280 | 545619319 | 65536 | 4515150867 | 4584140 | 4584140 | 26378177 | 15452823 | 0 | 0 | 1167135 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8447936 | 4465613 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4035680 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037168755443 | 12075053997581508 | 12075054000631406 | 12075037172164308 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fe321fc1400 | 0x7fe216437880 | 18628328 | 18431542 | 275305992 | 65536 | 2276060219 | 2328540 | 2328540 | 25642506 | 15259599 | 0 | 0 | 1173061 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8912776 | 4997920 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3979537 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037172322902 | 12075054000737006 | 12075054002277315 | 12075037174209969 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fe321fc1300 | 0x7fe2164378c0 | 9609704 | 9457806 | 141207503 | 65536 | 1165468521 | 1201212 | 1201212 | 19162424 | 8781974 | 0 | 0 | 714224 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7999311 | 4213314 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3829780 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037174371479 | 12075054002385154 | 12075054003173788 | 12075037175501309 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fe321fc1a00 | 0x7fe216437900 | 27528704 | 27380352 | 409131380 | 65536 | 3385924333 | 3441087 | 3441087 | 17641279 | 8111229 | 0 | 0 | 792016 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7312497 | 3962941 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3441336 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037175654363 | 12075054003279388 | 12075054005560171 | 12075037178289190 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fe321fc1900 | 0x7fe216437940 | 18588840 | 18419551 | 275137666 | 65536 | 2272780483 | 2323604 | 2323604 | 18948124 | 8548607 | 0 | 0 | 826515 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7582563 | 3961482 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3698396 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037178459657 | 12075054005676011 | 12075054007211040 | 12075037180346844 |
| 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 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fe321fc1800 | 0x7fe216437980 | 72681856 | 72527046 | 1084028330 | 65536 | 8977359771 | 9085231 | 9085231 | 26368600 | 15493764 | 0 | 0 | 983391 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8440710 | 4478653 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 4018070 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037180504948 | 12075054007316959 | 12075054013370676 | 12075037186901525 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fe321fc1700 | 0x7fe2164379c0 | 36587056 | 36429990 | 544267492 | 65536 | 4502631685 | 4573381 | 4573381 | 24198047 | 14729135 | 0 | 0 | 976667 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8682517 | 4963974 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3838151 | 0 | 0 | 0 | 0 | 0 | 0 | 12075037187060650 | 12075054013480275 | 12075054016520254 | 12075037190442345 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fe321fc1600 | 0x7fe216437a00 | 18615920 | 18460839 | 275820042 | 65536 | 2281006059 | 2326989 | 2326989 | 19211867 | 8707778 | 0 | 0 | 771919 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7851062 | 4134630 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3876840 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037190602082 | 12075054016627773 | 12075054018166322 | 12075037192492064 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 859003 | 859008 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fe321fc1500 | 0x7fe216437a40 | 54490600 | 54331628 | 812033835 | 65536 | 6724106275 | 6811324 | 6811324 | 17849592 | 8171891 | 0 | 0 | 543740 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7378626 | 4001247 | 0 | 0 | 0 | 2097152 | 2097152 | 0 | 0 | 0 | 0 | 3500000 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075037192651540 | 12075054018273041 | 12075054022797969 | 12075037197525338 |