80 KiB
80 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_WAVES | SQ_BUSY_CU_CYCLES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TA_TA_BUSY_sum | TA_SH_FIFO_BUSY_sum | CPC_CPC_STAT_BUSY | CPC_CPC_STAT_IDLE | 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 | CPC_CPC_TCIU_BUSY | CPC_CPC_TCIU_IDLE | TA_SH_FIFO_DATA_BUSY_sum | TA_SH_FIFO_DATA_SFIFO_BUSY_sum | CPC_CPC_STAT_STALL | CPC_UTCL1_STALL_ON_TRANSLATION | TA_SH_FIFO_DATA_TFIFO_BUSY_sum | TA_SQ_TA_CMD_CYCLES_sum | CPC_CPC_UTCL2IU_BUSY | CPC_CPC_UTCL2IU_IDLE | TA_SP_TA_ADDR_CYCLES_sum | TA_SP_TA_DATA_CYCLES_sum | CPC_CPC_UTCL2IU_STALL | CPC_ME1_BUSY_FOR_PACKET_DECODE | TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum | TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum | CPC_ME1_DC0_SPI_BUSY | 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 | 871499 | 871504 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f4be5a04180 | 4059152 | 3844127 | 524288 | 57377893 | 367960703 | 507393 | 507393 | 54491517 | 54385312 | 507393 | 0 | 0 | 0 | 17573208 | 1048576 | 0 | 37445754 | 1048576 | 0 | 1048576 | 0 | 1048576 | 52652181 | 52428399 | 724 | 502077 | 54350164 | 54039227 | 11893 | 2015 | 54077405 | 4194304 | 2904 | 498642 | 4194304 | 4194304 | 0 | 16455 | 0 | 0 | 477793 | 0 | 329999 | 0 | 0 | 0 | 0 | 0 | 1048576 | 12075355475932331 | 12075372569005997 | 12075372569330474 | 12075355721433734 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 871499 | 871504 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f4be5a35100 | 225320 | 77757 | 512 | 1082107 | 1153771 | 28164 | 28164 | 88545 | 63266 | 28164 | 0 | 0 | 0 | 104775 | 4096 | 0 | 0 | 4096 | 4096 | 0 | 0 | 4096 | 69572 | 66590 | 606 | 26910 | 0 | 0 | 11530 | 2023 | 0 | 16384 | 2798 | 24972 | 16384 | 0 | 0 | 19972 | 0 | 0 | 696 | 0 | 3198 | 0 | 0 | 0 | 0 | 0 | 4096 | 12075355735989601 | 12075372584412327 | 12075372584418887 | 12075355736459775 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f4cf1757900 | 0x7f4be5a35140 | 1721336 | 1554366 | 65536 | 23051560 | 137677073 | 215166 | 215166 | 21611925 | 21435597 | 215166 | 0 | 0 | 0 | 19421739 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22593525 | 22582088 | 747 | 224718 | 0 | 0 | 11116 | 2060 | 0 | 2097152 | 2915 | 210511 | 2097152 | 0 | 0 | 21453 | 0 | 0 | 194283 | 0 | 4852 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355736631033 | 12075372584470887 | 12075372584608486 | 12075355737130741 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f4cf1757800 | 0x7f4be5a35180 | 3173192 | 3017963 | 65536 | 44950787 | 224053676 | 396648 | 396648 | 43819754 | 43693788 | 396648 | 0 | 0 | 0 | 35002446 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43800801 | 43798020 | 717 | 394812 | 0 | 0 | 11551 | 1988 | 0 | 2097152 | 2757 | 396389 | 2097152 | 0 | 0 | 29529 | 0 | 0 | 368539 | 0 | 5644 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355737374765 | 12075372584655845 | 12075372584902563 | 12075355738013652 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f4cf1757700 | 0x7f4be5a351c0 | 3237136 | 3068541 | 65536 | 45759827 | 344813897 | 404641 | 404641 | 45129282 | 45112227 | 404641 | 0 | 0 | 0 | 35627964 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42419247 | 42355473 | 747 | 405654 | 0 | 0 | 11622 | 2438 | 0 | 2097152 | 3178 | 398816 | 2097152 | 0 | 0 | 25838 | 0 | 0 | 369204 | 0 | 3430 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355738166666 | 12075372585044321 | 12075372585324479 | 12075355738786748 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f4cf1757600 | 0x7f4be5a35200 | 1803912 | 1648439 | 65536 | 24417442 | 118253571 | 225488 | 225488 | 22157488 | 21967971 | 225488 | 0 | 0 | 0 | 19290628 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22628731 | 22617995 | 717 | 223644 | 0 | 0 | 11312 | 2057 | 0 | 2097152 | 3013 | 217092 | 2097152 | 0 | 0 | 21871 | 0 | 0 | 198867 | 0 | 5217 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355738951064 | 12075372585462397 | 12075372585588316 | 12075355739384529 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f4cf1757500 | 0x7f4be5a35240 | 1806648 | 1638748 | 65536 | 24328764 | 118135575 | 225830 | 225830 | 22884669 | 22735747 | 225830 | 0 | 0 | 0 | 19815970 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22756724 | 22744309 | 747 | 225254 | 0 | 0 | 11248 | 2052 | 0 | 2097152 | 2899 | 216926 | 2097152 | 0 | 0 | 21837 | 0 | 0 | 193059 | 0 | 6393 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355739616009 | 12075372585617596 | 12075372585742715 | 12075355740051859 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f4cf1757400 | 0x7f4be5a35280 | 1729144 | 1574794 | 65536 | 23314876 | 148010014 | 216142 | 216142 | 22369577 | 22291421 | 216142 | 0 | 0 | 0 | 19850734 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21883371 | 21869584 | 717 | 212004 | 0 | 0 | 11344 | 2387 | 0 | 2097152 | 3935 | 215490 | 2097152 | 0 | 0 | 22702 | 0 | 0 | 186551 | 0 | 13334 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355740294300 | 12075372585802394 | 12075372585926393 | 12075355740712166 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f4cf1757300 | 0x7f4be5a352c0 | 3201504 | 3034676 | 65536 | 45248950 | 286049723 | 400187 | 400187 | 44106302 | 44006997 | 400187 | 0 | 0 | 0 | 35765778 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43031051 | 42978457 | 763 | 406438 | 0 | 0 | 11665 | 2059 | 0 | 2097152 | 3341 | 466340 | 2097152 | 0 | 0 | 23307 | 0 | 0 | 359104 | 0 | 67602 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355740934158 | 12075372585957433 | 12075372586207990 | 12075355741549562 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f4cf1757a00 | 0x7f4be5a35300 | 3165896 | 3008985 | 65536 | 44865506 | 310870379 | 395736 | 395736 | 44182387 | 44155239 | 395736 | 0 | 0 | 0 | 36081285 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44346465 | 44331441 | 717 | 401668 | 0 | 0 | 12126 | 2051 | 0 | 2097152 | 3007 | 401627 | 2097152 | 0 | 0 | 16352 | 0 | 0 | 363804 | 0 | 3533 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355741710291 | 12075372586341909 | 12075372586585427 | 12075355742332928 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f4cf1757900 | 0x7f4be5a35340 | 1730872 | 1556348 | 65536 | 23044299 | 147953089 | 216358 | 216358 | 21750936 | 21627345 | 216358 | 0 | 0 | 0 | 19005642 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22708230 | 22687660 | 747 | 224422 | 0 | 0 | 11286 | 2056 | 0 | 2097152 | 2902 | 211284 | 2097152 | 0 | 0 | 19308 | 0 | 0 | 189323 | 0 | 13329 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355742495440 | 12075372586720305 | 12075372586845424 | 12075355742912374 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f4cf1757800 | 0x7f4be5a35380 | 1692816 | 1538207 | 65536 | 22806460 | 152174760 | 211601 | 211601 | 22008657 | 21949597 | 211601 | 0 | 0 | 0 | 20170890 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22327528 | 22303709 | 717 | 224412 | 0 | 0 | 11299 | 2056 | 0 | 2097152 | 2914 | 213600 | 2097152 | 0 | 0 | 22369 | 0 | 0 | 193875 | 0 | 6774 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355743140829 | 12075372586874224 | 12075372586999503 | 12075355743554467 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f4cf1757700 | 0x7f4be5a353c0 | 1724472 | 1561730 | 65536 | 23087460 | 150549840 | 215558 | 215558 | 21917146 | 21809618 | 215558 | 0 | 0 | 0 | 20084875 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21191096 | 21176231 | 747 | 208118 | 0 | 0 | 11396 | 2042 | 0 | 2097152 | 2909 | 212381 | 2097152 | 0 | 0 | 24848 | 0 | 0 | 185939 | 0 | 10478 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355743793311 | 12075372587042702 | 12075372587168141 | 12075355744214744 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f4cf1757600 | 0x7f4be5a35400 | 3222456 | 3062519 | 65536 | 45680866 | 330681066 | 402806 | 402806 | 44601226 | 44536760 | 402806 | 0 | 0 | 0 | 35854325 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44927513 | 44921658 | 717 | 404132 | 0 | 0 | 11543 | 2057 | 0 | 2097152 | 3443 | 409638 | 2097152 | 0 | 0 | 15862 | 0 | 0 | 370238 | 0 | 70835 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355744436526 | 12075372587196301 | 12075372587484298 | 12075355745046860 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f4cf1757500 | 0x7f4be5a35440 | 3145144 | 2975335 | 65536 | 44349744 | 346592294 | 393142 | 393142 | 43719296 | 43693762 | 393142 | 0 | 0 | 0 | 36058106 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42522847 | 42461195 | 747 | 405382 | 0 | 0 | 12176 | 2491 | 0 | 2097152 | 2902 | 399108 | 2097152 | 0 | 0 | 33725 | 0 | 0 | 363688 | 0 | 70172 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355745213971 | 12075372587619817 | 12075372587864134 | 12075355745808676 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f4cf1757400 | 0x7f4be5a35480 | 1681464 | 1522277 | 65536 | 22560716 | 156199924 | 210182 | 210182 | 21382508 | 21264297 | 210182 | 0 | 0 | 0 | 19711967 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21702696 | 21674940 | 717 | 219972 | 0 | 0 | 11143 | 2059 | 0 | 2097152 | 2792 | 213737 | 2097152 | 0 | 0 | 23593 | 0 | 0 | 185619 | 0 | 16091 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355745968573 | 12075372587954373 | 12075372588078852 | 12075355746394765 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f4cf1757300 | 0x7f4be5a354c0 | 1744696 | 1573889 | 65536 | 23333621 | 143236678 | 218086 | 218086 | 21746377 | 21621717 | 218086 | 0 | 0 | 0 | 20012792 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22052002 | 22024052 | 764 | 223277 | 0 | 0 | 11387 | 2024 | 0 | 2097152 | 2893 | 217037 | 2097152 | 0 | 0 | 20638 | 0 | 0 | 188222 | 0 | 11075 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355746626456 | 12075372588107012 | 12075372588232131 | 12075355747038641 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f4cf1757a00 | 0x7f4be5a35500 | 1737160 | 1575877 | 65536 | 23405004 | 152045887 | 217144 | 217144 | 22549692 | 22482648 | 217144 | 0 | 0 | 0 | 20063213 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21367469 | 21354670 | 717 | 208364 | 0 | 0 | 11564 | 2048 | 0 | 2097152 | 3451 | 223374 | 2097152 | 0 | 0 | 22128 | 0 | 0 | 188106 | 0 | 12716 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355747271524 | 12075372588278690 | 12075372588403329 | 12075355747695312 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f4cf1757900 | 0x7f4be5a35540 | 3123576 | 2959795 | 65536 | 44193384 | 341473233 | 390446 | 390446 | 43337114 | 43313157 | 390446 | 0 | 0 | 0 | 35740601 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 41956077 | 41878942 | 747 | 406550 | 0 | 0 | 11487 | 2052 | 0 | 2097152 | 2788 | 399749 | 2097152 | 0 | 0 | 30789 | 0 | 0 | 361660 | 0 | 4777 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355747914178 | 12075372588431649 | 12075372588680126 | 12075355748514203 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f4cf1757800 | 0x7f4be5a35580 | 3172304 | 3016229 | 65536 | 45028030 | 343165613 | 396537 | 396537 | 44252564 | 44222542 | 396537 | 0 | 0 | 0 | 35999431 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43472746 | 43418038 | 717 | 411892 | 0 | 0 | 12044 | 2050 | 0 | 2097152 | 3032 | 405377 | 2097152 | 0 | 0 | 32805 | 0 | 0 | 364090 | 0 | 78933 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355748676846 | 12075372588742846 | 12075372588988763 | 12075355749285877 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f4cf1757700 | 0x7f4be5a355c0 | 1732424 | 1568855 | 65536 | 23222522 | 152554102 | 216552 | 216552 | 21884183 | 21755926 | 216552 | 0 | 0 | 0 | 19742816 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21443947 | 21429028 | 747 | 209182 | 0 | 0 | 11507 | 2050 | 0 | 2097152 | 3295 | 215795 | 2097152 | 0 | 0 | 23727 | 0 | 0 | 184976 | 0 | 13477 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355749447888 | 12075372589080603 | 12075372589205721 | 12075355749873599 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f4cf1757600 | 0x7f4be5a35600 | 1752336 | 1597240 | 65536 | 23657986 | 137499734 | 219041 | 219041 | 22164418 | 21997824 | 219041 | 0 | 0 | 0 | 19953811 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21333596 | 21320523 | 717 | 210852 | 0 | 0 | 11447 | 2048 | 0 | 2097152 | 3169 | 224512 | 2097152 | 0 | 0 | 22134 | 0 | 0 | 196003 | 0 | 7332 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355750101943 | 12075372589232921 | 12075372589357880 | 12075355750519429 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f4cf1757500 | 0x7f4be5a35640 | 1700472 | 1537215 | 65536 | 22786601 | 160131690 | 212558 | 212558 | 21820777 | 21727939 | 212558 | 0 | 0 | 0 | 20197621 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21363162 | 21356544 | 761 | 207312 | 0 | 0 | 11188 | 2052 | 0 | 2097152 | 2917 | 220749 | 2097152 | 0 | 0 | 22393 | 0 | 0 | 184604 | 0 | 21722 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355750750058 | 12075372589399320 | 12075372589523798 | 12075355751169046 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f4cf1757400 | 0x7f4be5a35680 | 3269136 | 3092790 | 65536 | 46044274 | 285955147 | 408641 | 408641 | 44286934 | 44118124 | 408641 | 0 | 0 | 0 | 35340806 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44396213 | 44390024 | 717 | 400628 | 0 | 0 | 12273 | 2050 | 0 | 2097152 | 3074 | 403960 | 2097152 | 0 | 0 | 15911 | 0 | 0 | 370804 | 0 | 9747 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355751390808 | 12075372589552118 | 12075372589806356 | 12075355751999459 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f4cf1757300 | 0x7f4be5a356c0 | 3202576 | 3025282 | 65536 | 45105240 | 236647236 | 400321 | 400321 | 43498675 | 43227567 | 400321 | 0 | 0 | 0 | 36207792 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 45008087 | 44993260 | 747 | 409910 | 0 | 0 | 12532 | 2056 | 0 | 2097152 | 2903 | 395267 | 2097152 | 0 | 0 | 34213 | 0 | 0 | 358058 | 0 | 56598 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355752164767 | 12075372589867795 | 12075372590112113 | 12075355752764140 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f4cf1757a00 | 0x7f4be5a35700 | 1711544 | 1553161 | 65536 | 22983690 | 148633022 | 213942 | 213942 | 21824894 | 21708298 | 213942 | 0 | 0 | 0 | 19832013 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21878185 | 21860510 | 717 | 214396 | 0 | 0 | 11400 | 2050 | 0 | 2097152 | 2899 | 210150 | 2097152 | 0 | 0 | 22373 | 0 | 0 | 183258 | 0 | 9252 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355752923877 | 12075372590208112 | 12075372590332911 | 12075355753344889 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f4cf1757900 | 0x7f4be5a35740 | 1714552 | 1550282 | 65536 | 22881544 | 154374342 | 214318 | 214318 | 21381492 | 21241775 | 214318 | 0 | 0 | 0 | 19671142 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 23080153 | 23052324 | 747 | 230038 | 0 | 0 | 11353 | 2051 | 0 | 2097152 | 3092 | 216774 | 2097152 | 0 | 0 | 19480 | 0 | 0 | 189616 | 0 | 8169 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355753572272 | 12075372590364430 | 12075372590489069 | 12075355753984999 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f4cf1757800 | 0x7f4be5a35780 | 1683168 | 1529587 | 65536 | 22665932 | 158236301 | 210395 | 210395 | 21400952 | 21302252 | 210395 | 0 | 0 | 0 | 19504139 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21300457 | 21269727 | 717 | 212404 | 0 | 0 | 11273 | 2057 | 0 | 2097152 | 2904 | 213193 | 2097152 | 0 | 0 | 23108 | 0 | 0 | 190924 | 0 | 10762 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355754217681 | 12075372590529549 | 12075372590654187 | 12075355754622273 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f4cf1757700 | 0x7f4be5a357c0 | 3155616 | 2987104 | 65536 | 44504505 | 334650992 | 394451 | 394451 | 43660122 | 43631767 | 394451 | 0 | 0 | 0 | 35281113 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43633242 | 43620857 | 747 | 396406 | 0 | 0 | 11536 | 2061 | 0 | 2097152 | 3588 | 399806 | 2097152 | 0 | 0 | 27405 | 0 | 0 | 358022 | 0 | 19924 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355754849064 | 12075372590685547 | 12075372590936265 | 12075355755452045 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f4cf1757600 | 0x7f4be5a35800 | 3186952 | 3032485 | 65536 | 45247453 | 258045868 | 398368 | 398368 | 43827346 | 43617040 | 398368 | 0 | 0 | 0 | 35230081 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42372898 | 42317997 | 717 | 400972 | 0 | 0 | 12403 | 2050 | 0 | 2097152 | 3497 | 397033 | 2097152 | 0 | 0 | 28190 | 0 | 0 | 368858 | 0 | 3440 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355755611842 | 12075372591032424 | 12075372591275781 | 12075355756210063 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f4cf1757500 | 0x7f4be5a35840 | 1696760 | 1529863 | 65536 | 22685746 | 155447852 | 212094 | 212094 | 21749177 | 21652596 | 212094 | 0 | 0 | 0 | 20024604 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22036363 | 22020459 | 747 | 214894 | 0 | 0 | 10942 | 2057 | 0 | 2097152 | 3436 | 210038 | 2097152 | 0 | 0 | 22802 | 0 | 0 | 184632 | 0 | 13233 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355756341838 | 12075372591390340 | 12075372591514499 | 12075355756747562 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f4cf1757400 | 0x7f4be5a35880 | 1771792 | 1599130 | 65536 | 23706191 | 144404598 | 221473 | 221473 | 21791612 | 21529448 | 221473 | 0 | 0 | 0 | 19537954 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21601915 | 21575587 | 717 | 216500 | 0 | 0 | 11464 | 2059 | 0 | 2097152 | 2897 | 216025 | 2097152 | 0 | 0 | 23751 | 0 | 0 | 189276 | 0 | 20910 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355756949367 | 12075372591545699 | 12075372591671138 | 12075355757383403 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f4cf1757300 | 0x7f4be5a358c0 | 1734928 | 1576521 | 65536 | 23348160 | 154260653 | 216865 | 216865 | 22230415 | 22133687 | 216865 | 0 | 0 | 0 | 19681809 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21301470 | 21292022 | 747 | 206918 | 0 | 0 | 11199 | 2066 | 0 | 2097152 | 3276 | 208078 | 2097152 | 0 | 0 | 20696 | 0 | 0 | 184818 | 0 | 23277 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355757614643 | 12075372591711617 | 12075372591836736 | 12075355758035685 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f4cf1757a00 | 0x7f4be5a35900 | 3155472 | 2996819 | 65536 | 44602994 | 325949938 | 394433 | 394433 | 43710356 | 43682452 | 394433 | 0 | 0 | 0 | 36479174 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44704892 | 44699791 | 717 | 402052 | 0 | 0 | 12595 | 2042 | 0 | 2097152 | 2786 | 388016 | 2097152 | 0 | 0 | 33789 | 0 | 0 | 367748 | 0 | 53128 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355758251777 | 12075372591863456 | 12075372592108893 | 12075355758851231 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f4cf1757900 | 0x7f4be5a35940 | 3205792 | 3042427 | 65536 | 45335414 | 313817623 | 400723 | 400723 | 44452204 | 44400786 | 400723 | 0 | 0 | 0 | 35166366 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43609326 | 43604599 | 747 | 391230 | 0 | 0 | 12427 | 2059 | 0 | 2097152 | 2893 | 399773 | 2097152 | 0 | 0 | 33779 | 0 | 0 | 364820 | 0 | 3583 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355759013132 | 12075372592226812 | 12075372592470650 | 12075355759626582 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f4cf1757800 | 0x7f4be5a35980 | 1800864 | 1639924 | 65536 | 24286703 | 137336612 | 225107 | 225107 | 22767621 | 22609790 | 225107 | 0 | 0 | 0 | 19472544 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21475646 | 21450292 | 717 | 214324 | 0 | 0 | 11512 | 2003 | 0 | 2097152 | 2908 | 215173 | 2097152 | 0 | 0 | 22389 | 0 | 0 | 189300 | 0 | 32311 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355759780688 | 12075372592582009 | 12075372592706808 | 12075355760204125 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f4cf1757700 | 0x7f4be5a359c0 | 1752760 | 1588949 | 65536 | 23422649 | 156565738 | 219094 | 219094 | 22095922 | 21885463 | 219094 | 0 | 0 | 0 | 19167398 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21253414 | 21199937 | 747 | 223438 | 0 | 0 | 11617 | 2067 | 0 | 2097152 | 2787 | 218702 | 2097152 | 0 | 0 | 24840 | 0 | 0 | 184246 | 0 | 28113 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355760426037 | 12075372592734007 | 12075372592859926 | 12075355760849053 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f4cf1757600 | 0x7f4be5a35a00 | 1734840 | 1578512 | 65536 | 23290277 | 143683661 | 216854 | 216854 | 22145921 | 22035469 | 216854 | 0 | 0 | 0 | 19378587 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21372384 | 21358049 | 717 | 208988 | 0 | 0 | 11439 | 2050 | 0 | 2097152 | 2897 | 213664 | 2097152 | 0 | 0 | 18962 | 0 | 0 | 183170 | 0 | 12065 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355761088197 | 12075372592899286 | 12075372593023285 | 12075355761512285 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f4cf1757500 | 0x7f4be5a35a40 | 3200096 | 3036529 | 65536 | 45203295 | 250338168 | 400011 | 400011 | 42368127 | 41921652 | 400011 | 0 | 0 | 0 | 34294758 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44013151 | 43999788 | 747 | 400446 | 0 | 0 | 12270 | 1978 | 0 | 2097152 | 3060 | 406877 | 2097152 | 0 | 0 | 28655 | 0 | 0 | 362883 | 0 | 5294 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355761737424 | 12075372593054484 | 12075372593303602 | 12075355762344201 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f4cf1757400 | 0x7f4be5a35a80 | 3247712 | 3095189 | 65536 | 46136687 | 318139526 | 405963 | 405963 | 44516396 | 44386760 | 405963 | 0 | 0 | 0 | 36308316 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43897666 | 43886223 | 717 | 395940 | 0 | 0 | 11686 | 2056 | 0 | 2097152 | 2936 | 393369 | 2097152 | 0 | 0 | 34631 | 0 | 0 | 368384 | 0 | 7419 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355762475445 | 12075372593350162 | 12075372593596559 | 12075355763093233 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f4cf1757300 | 0x7f4be5a35ac0 | 1706104 | 1542223 | 65536 | 22777842 | 153786869 | 213262 | 213262 | 21491326 | 21359005 | 213262 | 0 | 0 | 0 | 19736816 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21386904 | 21359508 | 747 | 214230 | 0 | 0 | 11542 | 2057 | 0 | 2097152 | 2900 | 214469 | 2097152 | 0 | 0 | 24172 | 0 | 0 | 184046 | 0 | 14052 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355763248411 | 12075372593642479 | 12075372593767918 | 12075355763658543 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f4cf1757a00 | 0x7f4be5a35b00 | 1718544 | 1557001 | 65536 | 22931360 | 159052476 | 214817 | 214817 | 21526991 | 21322956 | 214817 | 0 | 0 | 0 | 19043646 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22164465 | 22118410 | 715 | 227598 | 0 | 0 | 11680 | 2389 | 0 | 2097152 | 2913 | 216369 | 2097152 | 0 | 0 | 25924 | 0 | 0 | 183174 | 0 | 19691 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355763885004 | 12075372593798957 | 12075372593925196 | 12075355764315514 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f4cf1757900 | 0x7f4be5a35b40 | 1702600 | 1535739 | 65536 | 22767473 | 158650228 | 212824 | 212824 | 21891435 | 21817341 | 212824 | 0 | 0 | 0 | 19476863 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21287788 | 21231406 | 747 | 219054 | 0 | 0 | 11382 | 2042 | 0 | 2097152 | 3019 | 206775 | 2097152 | 0 | 0 | 21879 | 0 | 0 | 188108 | 0 | 19678 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355764551563 | 12075372593965196 | 12075372594089834 | 12075355764970010 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f4cf1757800 | 0x7f4be5a35b80 | 3249464 | 3081893 | 65536 | 45895930 | 325867016 | 406182 | 406182 | 44096242 | 43803160 | 406182 | 0 | 0 | 0 | 35351275 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44926625 | 44872944 | 717 | 417252 | 0 | 0 | 12467 | 2040 | 0 | 2097152 | 2898 | 411040 | 2097152 | 0 | 0 | 31273 | 0 | 0 | 384283 | 0 | 48337 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355765193315 | 12075372594117354 | 12075372594369192 | 12075355765809270 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f4cf1757700 | 0x7f4be5a35bc0 | 3201544 | 3032500 | 65536 | 45217791 | 319018621 | 400192 | 400192 | 44237132 | 44183746 | 400192 | 0 | 0 | 0 | 35741437 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44481312 | 44471817 | 747 | 400350 | 0 | 0 | 11735 | 2408 | 0 | 2097152 | 2894 | 392508 | 2097152 | 0 | 0 | 31826 | 0 | 0 | 367231 | 0 | 27683 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355765963136 | 12075372594414951 | 12075372594661349 | 12075355766573710 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f4cf1757600 | 0x7f4be5a35c00 | 1726328 | 1563881 | 65536 | 23171029 | 151158208 | 215790 | 215790 | 22251703 | 22148559 | 215790 | 0 | 0 | 0 | 19355035 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21680443 | 21658895 | 717 | 212908 | 0 | 0 | 11610 | 2386 | 0 | 2097152 | 2795 | 215743 | 2097152 | 0 | 0 | 21453 | 0 | 0 | 180738 | 0 | 23586 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355766730692 | 12075372594706628 | 12075372594831747 | 12075355767149851 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f4cf1757500 | 0x7f4be5a35c40 | 1827832 | 1654380 | 65536 | 24368869 | 152016130 | 228478 | 228478 | 21324209 | 20642204 | 228478 | 0 | 0 | 0 | 17600956 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20633154 | 20547477 | 747 | 224934 | 0 | 0 | 12215 | 2082 | 0 | 2097152 | 3180 | 217165 | 2097152 | 0 | 0 | 25767 | 0 | 0 | 188264 | 0 | 71005 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355767378566 | 12075372594860547 | 12075372594987586 | 12075355767800981 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f4cf1757400 | 0x7f4be5a35c80 | 1708128 | 1551500 | 65536 | 22995336 | 157174132 | 213515 | 213515 | 21730460 | 21643109 | 213515 | 0 | 0 | 0 | 19772076 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21235691 | 21188150 | 717 | 216940 | 0 | 0 | 11393 | 2050 | 0 | 2097152 | 2794 | 211679 | 2097152 | 0 | 0 | 21642 | 0 | 0 | 189852 | 0 | 20730 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355768015980 | 12075372595033345 | 12075372595158784 | 12075355768436381 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f4cf1757300 | 0x7f4be5a35cc0 | 3305528 | 3133623 | 65536 | 46636693 | 306353270 | 413190 | 413190 | 43882048 | 43338417 | 413190 | 0 | 0 | 0 | 37240382 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 45239934 | 45179557 | 747 | 421382 | 0 | 0 | 12089 | 2049 | 0 | 2097152 | 3486 | 418619 | 2097152 | 0 | 0 | 28937 | 0 | 0 | 382407 | 0 | 73888 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355768663573 | 12075372595186144 | 12075372595444541 | 12075355769286160 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f4cf1757a00 | 0x7f4be5a35d00 | 3224760 | 3067327 | 65536 | 45803512 | 350285635 | 403094 | 403094 | 45088694 | 45069104 | 403094 | 0 | 0 | 0 | 35593225 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44892376 | 44887987 | 717 | 402620 | 0 | 0 | 12293 | 2050 | 0 | 2097152 | 2899 | 404623 | 2097152 | 0 | 0 | 32829 | 0 | 0 | 346136 | 0 | 27035 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355769436890 | 12075372595485821 | 12075372595736059 | 12075355770045591 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f4cf1757900 | 0x7f4be5a35d40 | 1740944 | 1576305 | 65536 | 23351145 | 149343497 | 217617 | 217617 | 21839795 | 21634202 | 217617 | 0 | 0 | 0 | 19502749 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22075851 | 22057521 | 747 | 215718 | 0 | 0 | 11540 | 2396 | 0 | 2097152 | 2909 | 208653 | 2097152 | 0 | 0 | 22037 | 0 | 0 | 184770 | 0 | 14750 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355770205859 | 12075372595777978 | 12075372595902937 | 12075355770621501 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f4cf1757800 | 0x7f4be5a35d80 | 1835664 | 1676861 | 65536 | 24634142 | 153847796 | 229457 | 229457 | 20847968 | 19837463 | 229457 | 0 | 0 | 0 | 17389847 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 18805490 | 18626692 | 717 | 229532 | 0 | 0 | 11995 | 2051 | 0 | 2097152 | 3290 | 223639 | 2097152 | 0 | 0 | 26733 | 0 | 0 | 194059 | 0 | 120841 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355770849144 | 12075372595931417 | 12075372596060215 | 12075355771284133 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f4cf1757700 | 0x7f4be5a35dc0 | 1743056 | 1580881 | 65536 | 23363765 | 150222244 | 217881 | 217881 | 21820674 | 21643785 | 217881 | 0 | 0 | 0 | 19948749 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21847716 | 21834747 | 747 | 212766 | 0 | 0 | 11445 | 2067 | 0 | 2097152 | 2895 | 214779 | 2097152 | 0 | 0 | 23952 | 0 | 0 | 188714 | 0 | 32986 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355771520221 | 12075372596101655 | 12075372596226454 | 12075355771933720 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f4cf1757600 | 0x7f4be5a35e00 | 3280824 | 3118739 | 65536 | 46396559 | 344212549 | 410102 | 410102 | 44751050 | 44532103 | 410102 | 0 | 0 | 0 | 35201886 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 41891068 | 41760919 | 717 | 409892 | 0 | 0 | 12041 | 2234 | 0 | 2097152 | 2908 | 408694 | 2097152 | 0 | 0 | 33254 | 0 | 0 | 365519 | 0 | 139785 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355772151324 | 12075372596254614 | 12075372596513331 | 12075355772771627 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f4cf1757500 | 0x7f4be5a35e40 | 3173216 | 2999544 | 65536 | 44733730 | 308967997 | 396651 | 396651 | 43939874 | 43898424 | 396651 | 0 | 0 | 0 | 36749371 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43819512 | 43795565 | 747 | 403966 | 0 | 0 | 12499 | 2057 | 0 | 2097152 | 3368 | 458361 | 2097152 | 0 | 0 | 31566 | 0 | 0 | 363528 | 0 | 3895 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355772926855 | 12075372596552531 | 12075372596798608 | 12075355773540586 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f4cf1757400 | 0x7f4be5a35e80 | 1735112 | 1574947 | 65536 | 23335459 | 154339855 | 216888 | 216888 | 21867158 | 21702783 | 216888 | 0 | 0 | 0 | 20203825 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21720057 | 21684162 | 720 | 218705 | 0 | 0 | 11482 | 2092 | 0 | 2097152 | 2907 | 216718 | 2097152 | 0 | 0 | 25095 | 0 | 0 | 188166 | 0 | 23046 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355773672911 | 12075372596843408 | 12075372596968047 | 12075355774090898 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f4cf1757300 | 0x7f4be5a35ec0 | 1827656 | 1631269 | 65536 | 23925580 | 176425135 | 228456 | 228456 | 18106932 | 16703223 | 228456 | 0 | 0 | 0 | 15749792 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 15976084 | 15668808 | 747 | 227758 | 0 | 0 | 12099 | 1987 | 0 | 2097152 | 2782 | 219972 | 2097152 | 0 | 0 | 28134 | 0 | 0 | 190379 | 0 | 302395 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355774317740 | 12075372596995726 | 12075372597122925 | 12075355774745314 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f4cf1757a00 | 0x7f4be5a35f00 | 1738528 | 1584904 | 65536 | 23483784 | 151558197 | 217315 | 217315 | 22131207 | 21928313 | 217315 | 0 | 0 | 0 | 19263030 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21590613 | 21564748 | 717 | 214252 | 0 | 0 | 11543 | 2042 | 0 | 2097152 | 2792 | 214250 | 2097152 | 0 | 0 | 21875 | 0 | 0 | 188583 | 0 | 21590 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355774983627 | 12075372597163245 | 12075372597288044 | 12075355775405391 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f4cf1757900 | 0x7f4be5a35f40 | 3281016 | 3108103 | 65536 | 46157736 | 309831087 | 410126 | 410126 | 43508614 | 42935983 | 410126 | 0 | 0 | 0 | 32355288 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 37902040 | 37671888 | 747 | 401374 | 0 | 0 | 12580 | 2057 | 0 | 2097152 | 2789 | 404156 | 2097152 | 0 | 0 | 32622 | 0 | 0 | 364331 | 0 | 15961 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355775626131 | 12075372597316843 | 12075372597579881 | 12075355776243197 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f4cf1757800 | 0x7f4be5a35f80 | 3177440 | 3020655 | 65536 | 44979766 | 334800860 | 397179 | 397179 | 44255381 | 44224091 | 397179 | 0 | 0 | 0 | 35565504 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44515620 | 44505705 | 1084 | 460245 | 0 | 0 | 12399 | 2057 | 0 | 2097152 | 3331 | 405799 | 2097152 | 0 | 0 | 34434 | 0 | 0 | 350327 | 0 | 3733 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355776390882 | 12075372597623400 | 12075372597868518 | 12075355776998711 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f4cf1757700 | 0x7f4be5a35fc0 | 1660048 | 1502766 | 65536 | 22264330 | 161329825 | 207505 | 207505 | 20924923 | 20800209 | 207505 | 0 | 0 | 0 | 19435691 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22379974 | 22339472 | 791 | 228986 | 0 | 0 | 11690 | 2049 | 0 | 2097152 | 2892 | 213462 | 2097152 | 0 | 0 | 24952 | 0 | 0 | 197844 | 0 | 17257 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355777161544 | 12075372597910438 | 12075372598035236 | 12075355777570654 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f4cf1757600 | 0x7f4be5a36000 | 1774224 | 1616617 | 65536 | 23907888 | 188549173 | 221777 | 221777 | 12955957 | 11308578 | 221777 | 0 | 0 | 0 | 11121887 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 10544809 | 9984535 | 754 | 226607 | 0 | 0 | 12019 | 2442 | 0 | 2097152 | 2908 | 221973 | 2097152 | 0 | 0 | 27778 | 0 | 0 | 191160 | 0 | 378659 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355777797265 | 12075372598066436 | 12075372598204035 | 12075355778230570 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f4cf1757500 | 0x7f4be5a36040 | 1760080 | 1599657 | 65536 | 23641937 | 146873468 | 220009 | 220009 | 21918970 | 21625567 | 220009 | 0 | 0 | 0 | 19584333 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21356005 | 21337269 | 747 | 210550 | 0 | 0 | 11487 | 2059 | 0 | 2097152 | 2903 | 210930 | 2097152 | 0 | 0 | 24916 | 0 | 0 | 183856 | 0 | 20753 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355778463172 | 12075372598244994 | 12075372598370113 | 12075355778882271 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f4cf1757400 | 0x7f4be5a36080 | 3343160 | 3170895 | 65536 | 47181323 | 339552724 | 417894 | 417894 | 44717567 | 44361813 | 417894 | 0 | 0 | 0 | 32482651 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42293356 | 42167426 | 717 | 415852 | 0 | 0 | 12472 | 1987 | 0 | 2097152 | 2786 | 419760 | 2097152 | 0 | 0 | 37830 | 0 | 0 | 380363 | 0 | 184895 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355779089907 | 12075372598396993 | 12075372598661150 | 12075355779705260 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f4cf1757300 | 0x7f4be5a360c0 | 3184672 | 3007710 | 65536 | 44831785 | 331135933 | 398083 | 398083 | 44096904 | 44073205 | 398083 | 0 | 0 | 0 | 34590970 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43332664 | 43323783 | 747 | 392518 | 0 | 0 | 11994 | 2114 | 0 | 2097152 | 2900 | 390461 | 2097152 | 0 | 0 | 28193 | 0 | 0 | 364498 | 0 | 84243 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355779866650 | 12075372598703230 | 12075372598948668 | 12075355780484488 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f4cf1757a00 | 0x7f4be5a36100 | 1690360 | 1522980 | 65536 | 22582907 | 140616712 | 211294 | 211294 | 20947268 | 20696186 | 211294 | 0 | 0 | 0 | 19473562 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21173014 | 21140656 | 717 | 214580 | 0 | 0 | 11562 | 2056 | 0 | 2097152 | 2762 | 226200 | 2097152 | 0 | 0 | 20738 | 0 | 0 | 196554 | 0 | 17446 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355780644265 | 12075372598995067 | 12075372599120186 | 12075355781061691 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f4cf1757900 | 0x7f4be5a36140 | 1845496 | 1673483 | 65536 | 24782238 | 199050889 | 230686 | 230686 | 10565771 | 8751953 | 230686 | 0 | 0 | 0 | 6614956 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 9478211 | 8873309 | 747 | 230374 | 0 | 0 | 11961 | 2065 | 0 | 2097152 | 2901 | 228349 | 2097152 | 0 | 0 | 27127 | 0 | 0 | 198291 | 0 | 603617 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355781289404 | 12075372599148186 | 12075372599291064 | 12075355781722168 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f4cf1757800 | 0x7f4be5a36180 | 1709448 | 1550971 | 65536 | 22922246 | 151991692 | 213680 | 213680 | 21728854 | 21529871 | 213680 | 0 | 0 | 0 | 18914005 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21432064 | 21374121 | 717 | 221876 | 0 | 0 | 11452 | 2043 | 0 | 2097152 | 2906 | 216864 | 2097152 | 0 | 0 | 24036 | 0 | 0 | 181880 | 0 | 18818 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355781958938 | 12075372599331384 | 12075372599456983 | 12075355782377967 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f4cf1757700 | 0x7f4be5a361c0 | 3266336 | 3067602 | 65536 | 45601068 | 342087030 | 408291 | 408291 | 43495237 | 43180263 | 408291 | 0 | 0 | 0 | 33201840 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44205308 | 44126935 | 747 | 419654 | 0 | 0 | 12742 | 2027 | 0 | 2097152 | 2910 | 418635 | 2097152 | 0 | 0 | 30934 | 0 | 0 | 373135 | 0 | 196414 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355782599899 | 12075372599484823 | 12075372599738900 | 12075355783208329 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f4cf1757600 | 0x7f4be5a36200 | 3209848 | 3034096 | 65536 | 45110632 | 232305789 | 401230 | 401230 | 42381424 | 41905558 | 401230 | 0 | 0 | 0 | 35458288 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44530621 | 44524852 | 717 | 400596 | 0 | 0 | 12437 | 2041 | 0 | 2097152 | 2912 | 400185 | 2097152 | 0 | 0 | 33098 | 0 | 0 | 358142 | 0 | 65381 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355783366563 | 12075372599782900 | 12075372600027537 | 12075355783977569 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f4cf1757500 | 0x7f4be5a36240 | 1769592 | 1600809 | 65536 | 23702286 | 143169447 | 221198 | 221198 | 21859358 | 21568209 | 221198 | 0 | 0 | 0 | 19368195 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22363369 | 22322041 | 747 | 223694 | 0 | 0 | 11303 | 2040 | 0 | 2097152 | 2918 | 220516 | 2097152 | 0 | 0 | 24822 | 0 | 0 | 186084 | 0 | 15996 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355784140111 | 12075372600081297 | 12075372600206896 | 12075355784558118 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f4cf1757400 | 0x7f4be5a36280 | 1913552 | 1762495 | 65536 | 26119064 | 208173395 | 239193 | 239193 | 9035685 | 7262305 | 239193 | 0 | 0 | 0 | 4673630 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 6510933 | 5757639 | 717 | 238212 | 0 | 0 | 11999 | 2002 | 0 | 2097152 | 2913 | 236904 | 2097152 | 0 | 0 | 28525 | 0 | 0 | 206648 | 0 | 714341 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355784756947 | 12075372600234575 | 12075372600385454 | 12075355785191314 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f4cf1757300 | 0x7f4be5a362c0 | 1725192 | 1562404 | 65536 | 23068394 | 150847992 | 215648 | 215648 | 21550821 | 21280530 | 215648 | 0 | 0 | 0 | 20138183 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22313348 | 22296641 | 747 | 219174 | 0 | 0 | 11545 | 2050 | 0 | 2097152 | 2900 | 215373 | 2097152 | 0 | 0 | 21137 | 0 | 0 | 182306 | 0 | 19171 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355785444224 | 12075372600443533 | 12075372600568652 | 12075355785864355 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f4cf1757a00 | 0x7f4be5a36300 | 3330832 | 3158685 | 65536 | 46958497 | 327517565 | 416353 | 416353 | 41854306 | 40994262 | 416353 | 0 | 0 | 0 | 34557420 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 42134138 | 41996377 | 717 | 416932 | 0 | 0 | 12342 | 1977 | 0 | 2097152 | 2900 | 415525 | 2097152 | 0 | 0 | 36177 | 0 | 0 | 370971 | 0 | 160287 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355786089162 | 12075372600596172 | 12075372600848009 | 12075355786711268 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f4cf1757900 | 0x7f4be5a36340 | 3150712 | 2989582 | 65536 | 44607999 | 342293484 | 393838 | 393838 | 43613015 | 43568836 | 393838 | 0 | 0 | 0 | 35625649 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44418504 | 44399376 | 763 | 404454 | 0 | 0 | 12372 | 2058 | 0 | 2097152 | 2903 | 397538 | 2097152 | 0 | 0 | 33110 | 0 | 0 | 361244 | 0 | 14214 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355786870925 | 12075372600890409 | 12075372601135847 | 12075355787485918 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f4cf1757800 | 0x7f4be5a36380 | 1830480 | 1655359 | 65536 | 24522977 | 152165843 | 228809 | 228809 | 22700180 | 22362400 | 228809 | 0 | 0 | 0 | 19233550 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21051049 | 21021580 | 717 | 210252 | 0 | 0 | 11620 | 2186 | 0 | 2097152 | 3104 | 218386 | 2097152 | 0 | 0 | 25363 | 0 | 0 | 185986 | 0 | 25930 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355787644973 | 12075372601188326 | 12075372601313925 | 12075355788063491 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f4cf1757700 | 0x7f4be5a363c0 | 2009504 | 1846660 | 65536 | 27433713 | 219485496 | 251187 | 251187 | 7563016 | 5931965 | 251187 | 0 | 0 | 0 | 3288093 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 6100968 | 5349650 | 747 | 254102 | 0 | 0 | 12079 | 2049 | 0 | 2097152 | 2900 | 249861 | 2097152 | 0 | 0 | 29133 | 0 | 0 | 218882 | 0 | 777265 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355788292316 | 12075372601343045 | 12075372601500323 | 12075355788730280 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f4cf1757600 | 0x7f4be5a36400 | 1739280 | 1575673 | 65536 | 23246000 | 150179745 | 217409 | 217409 | 21460490 | 21174253 | 217409 | 0 | 0 | 0 | 19109712 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21733106 | 21711214 | 717 | 215364 | 0 | 0 | 11800 | 2059 | 0 | 2097152 | 3483 | 221951 | 2097152 | 0 | 0 | 24213 | 0 | 0 | 191480 | 0 | 28611 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355788964856 | 12075372601541443 | 12075372601667202 | 12075355789394795 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f4cf1757500 | 0x7f4be5a36440 | 3239160 | 3049345 | 65536 | 45159863 | 314402900 | 404894 | 404894 | 37438811 | 36033650 | 404894 | 0 | 0 | 0 | 26169354 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 36211322 | 35889900 | 747 | 410206 | 0 | 0 | 13096 | 2052 | 0 | 2097152 | 3291 | 399639 | 2097152 | 0 | 0 | 33954 | 0 | 0 | 371083 | 0 | 442206 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355789611046 | 12075372601696481 | 12075372601955039 | 12075355790226811 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f4cf1757400 | 0x7f4be5a36480 | 3180664 | 3016183 | 65536 | 44909473 | 274121893 | 397582 | 397582 | 43555105 | 43378175 | 397582 | 0 | 0 | 0 | 35752088 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44549627 | 44540129 | 717 | 402964 | 0 | 0 | 12416 | 2372 | 0 | 2097152 | 2721 | 393152 | 2097152 | 0 | 0 | 27919 | 0 | 0 | 363360 | 0 | 77085 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355790358846 | 12075372601998078 | 12075372602243036 | 12075355790932292 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f4cf1757300 | 0x7f4be5a364c0 | 1805944 | 1634343 | 65536 | 24167809 | 146659164 | 225742 | 225742 | 22436881 | 22065263 | 225742 | 0 | 0 | 0 | 19657028 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22297388 | 22249372 | 747 | 226774 | 0 | 0 | 11331 | 2043 | 0 | 2097152 | 3582 | 216835 | 2097152 | 0 | 0 | 23731 | 0 | 0 | 193360 | 0 | 43604 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355791118387 | 12075372602293436 | 12075372602419034 | 12075355791544038 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f4cf1757a00 | 0x7f4be5a36500 | 2098568 | 1940825 | 65536 | 28829846 | 234753465 | 262320 | 262320 | 7010465 | 5434376 | 262320 | 0 | 0 | 0 | 3286604 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5895721 | 5125433 | 717 | 262316 | 0 | 0 | 12127 | 2051 | 0 | 2097152 | 2904 | 262098 | 2097152 | 0 | 0 | 29022 | 0 | 0 | 228582 | 0 | 772232 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355791768986 | 12075372602446714 | 12075372602612312 | 12075355792229322 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f4cf1757900 | 0x7f4be5a36540 | 1737608 | 1570348 | 65536 | 23194479 | 154752977 | 217200 | 217200 | 21815113 | 21586178 | 217200 | 0 | 0 | 0 | 19841180 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21541951 | 21503223 | 747 | 218870 | 0 | 0 | 11574 | 2065 | 0 | 2097152 | 3069 | 210740 | 2097152 | 0 | 0 | 24814 | 0 | 0 | 187752 | 0 | 21788 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355792462365 | 12075372602653112 | 12075372602778871 | 12075355792874621 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f4cf1757800 | 0x7f4be5a36580 | 3297104 | 3121499 | 65536 | 46362766 | 321126713 | 412137 | 412137 | 34495953 | 32472276 | 412137 | 0 | 0 | 0 | 25404255 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 27988818 | 27365810 | 717 | 412548 | 0 | 0 | 12936 | 1947 | 0 | 2097152 | 3315 | 405134 | 2097152 | 0 | 0 | 35460 | 0 | 0 | 374363 | 0 | 364877 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355793100781 | 12075372602806711 | 12075372603068148 | 12075355793722616 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f4cf1757700 | 0x7f4be5a365c0 | 3202464 | 3021197 | 65536 | 45018472 | 322878689 | 400307 | 400307 | 44158536 | 44127148 | 400307 | 0 | 0 | 0 | 35599079 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44322603 | 44316659 | 747 | 399518 | 0 | 0 | 12415 | 2067 | 0 | 2097152 | 3844 | 396934 | 2097152 | 0 | 0 | 28882 | 0 | 0 | 366270 | 0 | 18795 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355793883485 | 12075372603113908 | 12075372603360145 | 12075355794493569 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f4cf1757600 | 0x7f4be5a36600 | 1780384 | 1606571 | 65536 | 23756490 | 148242588 | 222547 | 222547 | 21784969 | 21406235 | 222547 | 0 | 0 | 0 | 19363383 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21564397 | 21497245 | 717 | 223172 | 0 | 0 | 11978 | 2072 | 0 | 2097152 | 2898 | 215120 | 2097152 | 0 | 0 | 24240 | 0 | 0 | 192662 | 0 | 36884 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355794654869 | 12075372603402065 | 12075372603527664 | 12075355795077674 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f4cf1757500 | 0x7f4be5a36640 | 2212512 | 2050662 | 65536 | 30454860 | 244918571 | 276563 | 276563 | 6992668 | 5461998 | 276563 | 0 | 0 | 0 | 2456691 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4985349 | 4258327 | 747 | 275598 | 0 | 0 | 12227 | 1984 | 0 | 2097152 | 3487 | 273858 | 2097152 | 0 | 0 | 30174 | 0 | 0 | 240054 | 0 | 785651 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355795304025 | 12075372603555503 | 12075372603727822 | 12075355795761936 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f4cf1757400 | 0x7f4be5a36680 | 1784632 | 1623595 | 65536 | 23948937 | 155740595 | 223078 | 223078 | 22120927 | 21804669 | 223078 | 0 | 0 | 0 | 18786011 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22505861 | 22471723 | 717 | 224700 | 0 | 0 | 11650 | 2058 | 0 | 2097152 | 2930 | 216352 | 2097152 | 0 | 0 | 24177 | 0 | 0 | 194540 | 0 | 16278 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355795992324 | 12075372603770061 | 12075372603895980 | 12075355796413827 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f4cf1757300 | 0x7f4be5a366c0 | 3234080 | 3050770 | 65536 | 45367288 | 327231894 | 404259 | 404259 | 27308197 | 24617623 | 404259 | 0 | 0 | 0 | 20826413 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 23492261 | 22719116 | 747 | 412230 | 0 | 0 | 12686 | 2065 | 0 | 2097152 | 2901 | 401781 | 2097152 | 0 | 0 | 37530 | 0 | 0 | 363055 | 0 | 723897 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355796634788 | 12075372603924620 | 12075372604179817 | 12075355797252455 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f4cf1757a00 | 0x7f4be5a36700 | 3262944 | 3095079 | 65536 | 46123006 | 307792593 | 407867 | 407867 | 44617971 | 44518598 | 407867 | 0 | 0 | 0 | 33763778 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44039806 | 44032959 | 717 | 399108 | 0 | 0 | 12607 | 2067 | 0 | 2097152 | 2804 | 394045 | 2097152 | 0 | 0 | 30330 | 0 | 0 | 357806 | 0 | 159515 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355797409948 | 12075372604223977 | 12075372604473095 | 12075355798022516 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f4cf1757900 | 0x7f4be5a36740 | 1794704 | 1625644 | 65536 | 24002617 | 146765806 | 224337 | 224337 | 21894761 | 21416510 | 224337 | 0 | 0 | 0 | 19785183 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 22244769 | 22199260 | 747 | 226054 | 0 | 0 | 11654 | 2037 | 0 | 2097152 | 2902 | 221347 | 2097152 | 0 | 0 | 23308 | 0 | 0 | 195186 | 0 | 27884 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355798177564 | 12075372604514694 | 12075372604641253 | 12075355798600440 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f4cf1757800 | 0x7f4be5a36780 | 2311688 | 2158634 | 65536 | 32109743 | 261133183 | 288960 | 288960 | 6850274 | 5395499 | 288960 | 0 | 0 | 0 | 2455014 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5065450 | 4337020 | 717 | 288796 | 0 | 0 | 12513 | 2066 | 0 | 2097152 | 2899 | 287174 | 2097152 | 0 | 0 | 31844 | 0 | 0 | 252900 | 0 | 796750 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355798822453 | 12075372604668773 | 12075372604851011 | 12075355799365461 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f4cf1757700 | 0x7f4be5a367c0 | 1852360 | 1673259 | 65536 | 24745545 | 147376391 | 231544 | 231544 | 21912593 | 21398154 | 231544 | 0 | 0 | 0 | 20059384 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20876245 | 20806266 | 747 | 223446 | 0 | 0 | 11631 | 2433 | 0 | 2097152 | 2844 | 223485 | 2097152 | 0 | 0 | 24568 | 0 | 0 | 190524 | 0 | 43400 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355799530067 | 12075372604891811 | 12075372605018209 | 12075355799953434 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f4cf1757600 | 0x7f4be5a36800 | 3287712 | 3123249 | 65536 | 46464123 | 377355114 | 410963 | 410963 | 22575819 | 15253253 | 410963 | 0 | 0 | 0 | 2789741 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9732109 | 6299661 | 717 | 409652 | 0 | 0 | 13027 | 2058 | 0 | 2097152 | 2904 | 406601 | 2097152 | 0 | 0 | 35607 | 0 | 0 | 364706 | 0 | 3587142 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355800172601 | 12075372605047489 | 12075372605310686 | 12075355800782555 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f4cf1757500 | 0x7f4be5a36840 | 3184416 | 2998148 | 65536 | 44510709 | 284062141 | 398051 | 398051 | 43015001 | 42847265 | 398051 | 0 | 0 | 0 | 35716823 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44093271 | 44085211 | 747 | 399334 | 0 | 0 | 12531 | 2056 | 0 | 2097152 | 2909 | 398293 | 2097152 | 0 | 0 | 33195 | 0 | 0 | 356708 | 0 | 66233 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355800937362 | 12075372605354366 | 12075372605601564 | 12075355801842133 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f4cf1757400 | 0x7f4be5a36880 | 1747208 | 1590279 | 65536 | 23475296 | 145205791 | 218400 | 218400 | 21792711 | 21335858 | 218400 | 0 | 0 | 0 | 19396654 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21350544 | 21326285 | 717 | 212252 | 0 | 0 | 11739 | 2049 | 0 | 2097152 | 2907 | 225830 | 2097152 | 0 | 0 | 21517 | 0 | 0 | 198976 | 0 | 49483 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355802058626 | 12075372605644123 | 12075372605769562 | 12075355802640066 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f4cf1757300 | 0x7f4be5a368c0 | 2416008 | 2251541 | 65536 | 33479758 | 272804584 | 302000 | 302000 | 6682024 | 5220295 | 302000 | 0 | 0 | 0 | 2223268 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4896124 | 4179956 | 763 | 304990 | 0 | 0 | 12357 | 1985 | 0 | 2097152 | 2900 | 301310 | 2097152 | 0 | 0 | 31609 | 0 | 0 | 263978 | 0 | 770590 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355802902163 | 12075372605798522 | 12075372605989880 | 12075355803566457 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f4cf1757a00 | 0x7f4be5a36900 | 1781432 | 1624703 | 65536 | 23911572 | 147795427 | 222678 | 222678 | 21502818 | 20930702 | 222678 | 0 | 0 | 0 | 19200505 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 21325402 | 21262903 | 717 | 221644 | 0 | 0 | 11951 | 2048 | 0 | 2097152 | 2796 | 209118 | 2097152 | 0 | 0 | 26954 | 0 | 0 | 186455 | 0 | 34930 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355803772410 | 12075372606035960 | 12075372606162678 | 12075355804324666 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f4cf1757900 | 0x7f4be5a36940 | 3483792 | 3319735 | 65536 | 49437588 | 403789174 | 435473 | 435473 | 22602412 | 14686917 | 435473 | 0 | 0 | 0 | 1618607 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8920320 | 5316518 | 747 | 434182 | 0 | 0 | 13365 | 2050 | 0 | 2097152 | 2800 | 431737 | 2097152 | 0 | 0 | 39579 | 0 | 0 | 392260 | 0 | 3716409 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355804578959 | 12075372606190678 | 12075372606472755 | 12075355805328672 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f4cf1757800 | 0x7f4be5a36980 | 3156728 | 2995188 | 65536 | 44538575 | 318684912 | 394590 | 394590 | 43494333 | 43447214 | 394590 | 0 | 0 | 0 | 35070425 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 40827446 | 40726306 | 717 | 407044 | 0 | 0 | 12452 | 2067 | 0 | 2097152 | 2794 | 404207 | 2097152 | 0 | 0 | 32546 | 0 | 0 | 366631 | 0 | 69431 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355805520819 | 12075372606516755 | 12075372606766512 | 12075355806247549 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f4cf1757700 | 0x7f4be5a369c0 | 1800776 | 1612589 | 65536 | 23833829 | 149840530 | 225096 | 225096 | 21584169 | 21037669 | 225096 | 0 | 0 | 0 | 18479217 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20864576 | 20784391 | 747 | 223318 | 0 | 0 | 11734 | 2041 | 0 | 2097152 | 3196 | 225950 | 2097152 | 0 | 0 | 27886 | 0 | 0 | 198215 | 0 | 52836 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355806431521 | 12075372606812112 | 12075372606937391 | 12075355806971084 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f4cf1757600 | 0x7f4be5a36a00 | 2625032 | 2475226 | 65536 | 36794099 | 299719922 | 328128 | 328128 | 6904215 | 5365667 | 328128 | 0 | 0 | 0 | 2371819 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5201949 | 4401774 | 717 | 329460 | 0 | 0 | 12579 | 2056 | 0 | 2097152 | 3402 | 329432 | 2097152 | 0 | 0 | 33945 | 0 | 0 | 290338 | 0 | 826750 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355807233221 | 12075372606966351 | 12075372607211148 | 12075355807911421 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f4cf1757500 | 0x7f4be5a36a40 | 1840912 | 1662170 | 65536 | 24542925 | 152111744 | 230113 | 230113 | 21599644 | 20901002 | 230113 | 0 | 0 | 0 | 19271105 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20003370 | 19898242 | 747 | 220374 | 0 | 0 | 11789 | 2050 | 0 | 2097152 | 3181 | 221572 | 2097152 | 0 | 0 | 25191 | 0 | 0 | 194979 | 0 | 66175 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355808118436 | 12075372607271628 | 12075372607399946 | 12075355808670672 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f4cf1757400 | 0x7f4be5a36a80 | 4126176 | 3604740 | 65536 | 53694051 | 438244581 | 515771 | 515771 | 23249588 | 14800234 | 453243 | 62528 | 0 | 0 | 1319247 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8713540 | 5021088 | 717 | 468004 | 0 | 0 | 13412 | 2008 | 0 | 2097152 | 3343 | 512243 | 2097152 | 0 | 0 | 16688 | 0 | 0 | 422892 | 0 | 3801656 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355808922930 | 12075372607428106 | 12075372607734503 | 12075355809736091 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f4cf1757300 | 0x7f4be5a36ac0 | 3193464 | 3015716 | 65536 | 44898239 | 354427926 | 399182 | 399182 | 44008432 | 43986247 | 399182 | 0 | 0 | 0 | 35078716 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 44576121 | 44569716 | 747 | 404014 | 0 | 0 | 12603 | 2433 | 0 | 2097152 | 3339 | 400494 | 2097152 | 0 | 0 | 33792 | 0 | 0 | 362615 | 0 | 84132 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355809929581 | 12075372607773543 | 12075372608020740 | 12075355810659778 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f4cf1757a00 | 0x7f4be5a36b00 | 1795040 | 1617966 | 65536 | 23813308 | 154923549 | 224379 | 224379 | 21191411 | 20656482 | 224379 | 0 | 0 | 0 | 18042955 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20072652 | 19969506 | 717 | 222676 | 0 | 0 | 11904 | 2018 | 0 | 2097152 | 2899 | 226127 | 2097152 | 0 | 0 | 24875 | 0 | 0 | 188979 | 0 | 62454 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355810846334 | 12075372608064580 | 12075372608192099 | 12075355811397759 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f4cf1757900 | 0x7f4be5a36b40 | 2858064 | 2694517 | 65536 | 39991122 | 325037415 | 357257 | 357257 | 6938295 | 5349472 | 357257 | 0 | 0 | 0 | 2359290 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5121705 | 4320917 | 763 | 356806 | 0 | 0 | 12830 | 2432 | 0 | 2097152 | 2922 | 353488 | 2097152 | 0 | 0 | 36858 | 0 | 0 | 315762 | 0 | 830803 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355811657512 | 12075372608219939 | 12075372608447456 | 12075355812363083 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f4cf1757800 | 0x7f4be5a36b80 | 1813664 | 1648362 | 65536 | 24227120 | 149072045 | 226707 | 226707 | 20725086 | 19813360 | 226707 | 0 | 0 | 0 | 19221541 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 20370453 | 20264407 | 717 | 220972 | 0 | 0 | 11649 | 2049 | 0 | 2097152 | 3831 | 217538 | 2097152 | 0 | 0 | 25877 | 0 | 0 | 201032 | 0 | 75553 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355812569376 | 12075372608503296 | 12075372608630175 | 12075355813103318 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f4cf1757700 | 0x7f4be5a36bc0 | 4363168 | 3867703 | 65536 | 57596999 | 472038022 | 545395 | 545395 | 23058084 | 14494061 | 483037 | 62358 | 0 | 0 | 1427360 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8662386 | 4956790 | 747 | 501814 | 0 | 0 | 12000 | 2431 | 0 | 2097152 | 3456 | 500769 | 2097152 | 0 | 0 | 44322 | 0 | 0 | 454134 | 0 | 3812730 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355813356829 | 12075372608658014 | 12075372609015611 | 12075355814181442 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f4cf1757600 | 0x7f4be5a36c00 | 3258656 | 3077500 | 65536 | 45685830 | 271868066 | 407331 | 407331 | 43240157 | 42892386 | 407331 | 0 | 0 | 0 | 36511970 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43426798 | 43414410 | 717 | 396980 | 0 | 0 | 12911 | 2065 | 0 | 2097152 | 2908 | 389165 | 2097152 | 0 | 0 | 35893 | 0 | 0 | 359812 | 0 | 3870 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355814366465 | 12075372609059130 | 12075372609314008 | 12075355815096662 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f4cf1757500 | 0x7f4be5a36c40 | 1817336 | 1645741 | 65536 | 24253287 | 154002812 | 227166 | 227166 | 20440818 | 19539942 | 227166 | 0 | 0 | 0 | 17451520 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 18721933 | 18570514 | 747 | 214446 | 0 | 0 | 11665 | 2064 | 0 | 2097152 | 2897 | 220337 | 2097152 | 0 | 0 | 27336 | 0 | 0 | 190899 | 0 | 85183 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355815281536 | 12075372609358648 | 12075372609486646 | 12075355815817772 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f4cf1757400 | 0x7f4be5a36c80 | 3056632 | 2898715 | 65536 | 43088760 | 352253448 | 382078 | 382078 | 6706576 | 5152620 | 382078 | 0 | 0 | 0 | 2433660 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5083195 | 4297330 | 717 | 380852 | 0 | 0 | 13094 | 2064 | 0 | 2097152 | 2892 | 378654 | 2097152 | 0 | 0 | 37142 | 0 | 0 | 338640 | 0 | 831487 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355816058760 | 12075372609519126 | 12075372609763764 | 12075355816717474 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f4cf1757300 | 0x7f4be5a36cc0 | 1807736 | 1630447 | 65536 | 23887859 | 167720875 | 225966 | 225966 | 19383250 | 18234880 | 225966 | 0 | 0 | 0 | 16334370 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 17785987 | 17557239 | 763 | 222078 | 0 | 0 | 12487 | 2051 | 0 | 2097152 | 2796 | 217173 | 2097152 | 0 | 0 | 26732 | 0 | 0 | 186218 | 0 | 187218 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355816869446 | 12075372609821843 | 12075372609950802 | 12075355817393029 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f4cf1757a00 | 0x7f4be5a36d00 | 4581904 | 4423398 | 65536 | 65955121 | 541604596 | 572737 | 572737 | 23694331 | 14697726 | 572737 | 0 | 0 | 0 | 1285061 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9098862 | 5340093 | 717 | 573468 | 0 | 0 | 14207 | 2060 | 0 | 2097152 | 2774 | 570739 | 2097152 | 0 | 0 | 48867 | 0 | 0 | 519260 | 0 | 3861495 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355817627134 | 12075372609978482 | 12075372610353838 | 12075355818407965 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f4cf1757900 | 0x7f4be5a36d40 | 3299192 | 3133396 | 65536 | 46529690 | 322370858 | 412398 | 412398 | 43383870 | 43130973 | 412398 | 0 | 0 | 0 | 32989059 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 43178373 | 43125142 | 747 | 410638 | 0 | 0 | 12968 | 2067 | 0 | 2097152 | 2896 | 407377 | 2097152 | 0 | 0 | 37550 | 0 | 0 | 354843 | 0 | 144410 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355818573402 | 12075372610399598 | 12075372610652075 | 12075355819241894 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f4cf1757800 | 0x7f4be5a36d80 | 1757920 | 1593323 | 65536 | 23398847 | 170506778 | 219739 | 219739 | 18042195 | 16444737 | 219739 | 0 | 0 | 0 | 16530614 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 17209058 | 16940615 | 717 | 229268 | 0 | 0 | 12189 | 2051 | 0 | 2097152 | 3389 | 226036 | 2097152 | 0 | 0 | 27846 | 0 | 0 | 191284 | 0 | 206120 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355819402112 | 12075372610693995 | 12075372610822153 | 12075355819887133 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f4cf1757700 | 0x7f4be5a36dc0 | 3483104 | 3317681 | 65536 | 49396731 | 405187892 | 435387 | 435387 | 6830178 | 5271139 | 435387 | 0 | 0 | 0 | 2264287 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5049301 | 4229182 | 741 | 433892 | 0 | 0 | 13291 | 1988 | 0 | 2097152 | 3016 | 432170 | 2097152 | 0 | 0 | 40268 | 0 | 0 | 388372 | 0 | 802060 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355820121088 | 12075372610849833 | 12075372611128551 | 12075355820802705 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f4cf1757600 | 0x7f4be5a36e00 | 1741344 | 1586064 | 65536 | 23401276 | 186635401 | 217667 | 217667 | 14247300 | 12252081 | 217667 | 0 | 0 | 0 | 9644087 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 9809507 | 9201249 | 717 | 222476 | 0 | 0 | 12332 | 2060 | 0 | 2097152 | 2813 | 221380 | 2097152 | 0 | 0 | 26300 | 0 | 0 | 191446 | 0 | 360283 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355820981306 | 12075372611188070 | 12075372611322149 | 12075355821457662 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f4cf1757500 | 0x7f4be5a36e40 | 5139664 | 4985066 | 65536 | 74394920 | 612258804 | 642457 | 642457 | 23970849 | 14781880 | 642457 | 0 | 0 | 0 | 1608318 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9160288 | 5372570 | 1019 | 679254 | 0 | 0 | 14784 | 2067 | 0 | 2097152 | 3153 | 641472 | 2097152 | 0 | 0 | 52279 | 0 | 0 | 586394 | 0 | 3880741 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355821683702 | 12075372611350148 | 12075372611773184 | 12075355822529944 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f4cf1757400 | 0x7f4be5a36e80 | 3281528 | 3063207 | 65536 | 45382344 | 287869219 | 410190 | 410190 | 31488164 | 30180967 | 410190 | 0 | 0 | 0 | 27174117 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 37657339 | 37483572 | 774 | 417739 | 0 | 0 | 12549 | 2048 | 0 | 2097152 | 2892 | 402093 | 2097152 | 0 | 0 | 34814 | 0 | 0 | 372679 | 0 | 265013 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355822693929 | 12075372611822624 | 12075372612081501 | 12075355823348926 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f4cf1757300 | 0x7f4be5a36ec0 | 1759696 | 1600406 | 65536 | 23706402 | 189666095 | 219961 | 219961 | 13565355 | 11510641 | 219961 | 0 | 0 | 0 | 9334152 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 10580267 | 10006623 | 754 | 225135 | 0 | 0 | 11798 | 2051 | 0 | 2097152 | 2793 | 220385 | 2097152 | 0 | 0 | 28236 | 0 | 0 | 191812 | 0 | 580540 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355823517780 | 12075372612129021 | 12075372612265180 | 12075355823980790 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f4cf1757a00 | 0x7f4be5a36f00 | 3903136 | 3741956 | 65536 | 55682867 | 455862184 | 487891 | 487891 | 6878691 | 5258946 | 487891 | 0 | 0 | 0 | 2242389 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5032244 | 4269716 | 747 | 486966 | 0 | 0 | 13742 | 2059 | 0 | 2097152 | 2895 | 485403 | 2097152 | 0 | 0 | 16730 | 0 | 0 | 439188 | 0 | 775356 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355824217590 | 12075372612293179 | 12075372612637016 | 12075355824927459 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f4cf1757900 | 0x7f4be5a36f40 | 1930704 | 1774031 | 65536 | 26360489 | 213089916 | 241337 | 241337 | 7471577 | 5107890 | 241337 | 0 | 0 | 0 | 2003317 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4883852 | 4024607 | 717 | 241404 | 0 | 0 | 12038 | 1977 | 0 | 2097152 | 3459 | 239622 | 2097152 | 0 | 0 | 28040 | 0 | 0 | 207810 | 0 | 864007 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355825107373 | 12075372612697175 | 12075372612848534 | 12075355825586233 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f4cf1757800 | 0x7f4be5a36f80 | 6281032 | 6114394 | 65536 | 91195090 | 749378477 | 785128 | 785128 | 24951013 | 15191727 | 785128 | 0 | 0 | 0 | 1345249 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8552017 | 4678329 | 1019 | 809862 | 0 | 0 | 11677 | 2437 | 0 | 2097152 | 2917 | 781333 | 2097152 | 0 | 0 | 59836 | 0 | 0 | 718426 | 0 | 3938055 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355825815469 | 12075372612876534 | 12075372613393329 | 12075355826745768 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f4cf1757700 | 0x7f4be5a36fc0 | 3644856 | 3462200 | 65536 | 51181456 | 365884431 | 455606 | 455606 | 25098874 | 23560186 | 455606 | 0 | 0 | 0 | 16625109 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 21953824 | 21470426 | 774 | 461299 | 0 | 0 | 13170 | 2065 | 0 | 2097152 | 2922 | 456295 | 2097152 | 0 | 0 | 44013 | 0 | 0 | 410483 | 0 | 436532 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355826916715 | 12075372613443408 | 12075372613742125 | 12075355827621084 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f4cf1757600 | 0x7f4be5a37000 | 1970832 | 1816159 | 65536 | 27004167 | 217063412 | 246353 | 246353 | 7321818 | 4975904 | 246353 | 0 | 0 | 0 | 1600496 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4786339 | 3929882 | 754 | 245999 | 0 | 0 | 12127 | 2067 | 0 | 2097152 | 2790 | 243283 | 2097152 | 0 | 0 | 28914 | 0 | 0 | 211912 | 0 | 835475 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355827785540 | 12075372613787565 | 12075372613941163 | 12075355828284226 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f4cf1757500 | 0x7f4be5a37040 | 4746040 | 4585018 | 65536 | 68387415 | 560258460 | 593254 | 593254 | 6825733 | 5353138 | 593254 | 0 | 0 | 0 | 2340651 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5212234 | 4431456 | 747 | 594670 | 0 | 0 | 14243 | 2060 | 0 | 2097152 | 3349 | 629148 | 2097152 | 0 | 0 | 49174 | 0 | 0 | 538276 | 0 | 968203 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355828509365 | 12075372613974443 | 12075372614359719 | 12075355829303811 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f4cf1757400 | 0x7f4be5a37080 | 2227384 | 2069647 | 65536 | 30781132 | 250546892 | 278422 | 278422 | 7543979 | 5211632 | 278422 | 0 | 0 | 0 | 1587880 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4885579 | 4034502 | 717 | 277564 | 0 | 0 | 12265 | 2051 | 0 | 2097152 | 3247 | 276586 | 2097152 | 0 | 0 | 30835 | 0 | 0 | 241848 | 0 | 867680 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355829486220 | 12075372614424039 | 12075372614599717 | 12075355829987692 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f4cf1757300 | 0x7f4be5a370c0 | 7392400 | 7235436 | 65536 | 107995272 | 888709373 | 924049 | 924049 | 24578034 | 14786002 | 924049 | 0 | 0 | 0 | 1262967 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8503174 | 4651967 | 747 | 924982 | 0 | 0 | 16414 | 2304 | 0 | 2097152 | 2893 | 922652 | 2097152 | 0 | 0 | 70560 | 0 | 0 | 850202 | 0 | 3915847 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355830215054 | 12075372614629157 | 12075372615252511 | 12075355831218338 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f4cf1757a00 | 0x7f4be5a37100 | 4004344 | 3845538 | 65536 | 57161138 | 463174515 | 500542 | 500542 | 17702892 | 15792371 | 500542 | 0 | 0 | 0 | 7338113 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 13529265 | 12846718 | 717 | 501004 | 0 | 0 | 13743 | 2049 | 0 | 2097152 | 2906 | 500600 | 2097152 | 0 | 0 | 43812 | 0 | 0 | 453271 | 0 | 655371 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355831360562 | 12075372615299230 | 12075372615655387 | 12075355832118771 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f4cf1757900 | 0x7f4be5a37140 | 2257848 | 2099771 | 65536 | 31249713 | 254843512 | 282230 | 282230 | 7507011 | 5176974 | 282230 | 0 | 0 | 0 | 1525968 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4659660 | 3800017 | 747 | 280238 | 0 | 0 | 12295 | 2052 | 0 | 2097152 | 2781 | 277949 | 2097152 | 0 | 0 | 30668 | 0 | 0 | 245036 | 0 | 837184 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355832284269 | 12075372615705627 | 12075372615883545 | 12075355832794066 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f4cf1757800 | 0x7f4be5a37180 | 5574904 | 5417855 | 65536 | 80865818 | 664544189 | 696862 | 696862 | 6890865 | 5381620 | 696862 | 0 | 0 | 0 | 2455474 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5226887 | 4504254 | 717 | 698820 | 0 | 0 | 15036 | 2051 | 0 | 2097152 | 2891 | 694918 | 2097152 | 0 | 0 | 55060 | 0 | 0 | 638244 | 0 | 891866 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355833032860 | 12075372615915545 | 12075372616370260 | 12075355833884432 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f4cf1757700 | 0x7f4be5a371c0 | 2506512 | 2343281 | 65536 | 34870266 | 284801257 | 313313 | 313313 | 7356113 | 5046030 | 313313 | 0 | 0 | 0 | 1592934 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4756058 | 3908208 | 747 | 312870 | 0 | 0 | 12442 | 2060 | 0 | 2097152 | 2884 | 311749 | 2097152 | 0 | 0 | 31914 | 0 | 0 | 275132 | 0 | 867732 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355834072762 | 12075372616433460 | 12075372616633618 | 12075355834665183 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f4cf1757600 | 0x7f4be5a37200 | 8587472 | 8359052 | 65536 | 124746234 | 1028397316 | 1073433 | 1073433 | 24849439 | 14821325 | 1010773 | 62660 | 0 | 0 | 1179869 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9038108 | 5155984 | 717 | 1064820 | 0 | 0 | 17528 | 2058 | 0 | 2097152 | 2914 | 1062752 | 2097152 | 0 | 0 | 76176 | 0 | 0 | 982892 | 0 | 3950924 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355834829939 | 12075372616677137 | 12075372617381130 | 12075355835945001 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f4cf1757500 | 0x7f4be5a37240 | 4559800 | 4375440 | 65536 | 65169894 | 515132633 | 569974 | 569974 | 15789894 | 13938861 | 569974 | 0 | 0 | 0 | 4491317 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 12211612 | 11504421 | 1019 | 606950 | 0 | 0 | 14090 | 2003 | 0 | 2097152 | 2790 | 566948 | 2097152 | 0 | 0 | 48096 | 0 | 0 | 513034 | 0 | 700656 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355836113474 | 12075372617428810 | 12075372617800806 | 12075355836879277 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f4cf1757400 | 0x7f4be5a37280 | 2530440 | 2374359 | 65536 | 35339634 | 288775890 | 316304 | 316304 | 7314930 | 4939369 | 316304 | 0 | 0 | 0 | 1651411 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4652277 | 3891858 | 791 | 319298 | 0 | 0 | 12311 | 2050 | 0 | 2097152 | 2808 | 315682 | 2097152 | 0 | 0 | 32737 | 0 | 0 | 279776 | 0 | 839867 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355837052719 | 12075372617846886 | 12075372618048804 | 12075355837648136 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f4cf1757300 | 0x7f4be5a372c0 | 6417976 | 6257577 | 65536 | 93385635 | 768585886 | 802246 | 802246 | 7080861 | 5528320 | 802246 | 0 | 0 | 0 | 2613984 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5433029 | 4704021 | 768 | 802129 | 0 | 0 | 15726 | 2058 | 0 | 2097152 | 2892 | 803094 | 2097152 | 0 | 0 | 62388 | 0 | 0 | 735434 | 0 | 923361 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355837815967 | 12075372618098404 | 12075372618624478 | 12075355838752418 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f4cf1757a00 | 0x7f4be5a37300 | 2782288 | 2628926 | 65536 | 39140817 | 319913455 | 347785 | 347785 | 7177001 | 4933073 | 347785 | 0 | 0 | 0 | 1499070 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4843168 | 4017669 | 747 | 348198 | 0 | 0 | 12627 | 2018 | 0 | 2097152 | 2905 | 347385 | 2097152 | 0 | 0 | 34141 | 0 | 0 | 309416 | 0 | 859169 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355838928805 | 12075372618687358 | 12075372618911036 | 12075355839557574 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f4cf1757900 | 0x7f4be5a37340 | 9679560 | 9486134 | 65536 | 141660695 | 1169661942 | 1209944 | 1209944 | 25484974 | 15280212 | 1147349 | 62595 | 0 | 0 | 937895 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8765665 | 4850574 | 717 | 1206876 | 0 | 0 | 18422 | 2056 | 0 | 2097152 | 3784 | 1204818 | 2097152 | 0 | 0 | 84430 | 0 | 0 | 1116146 | 0 | 3976272 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355839724494 | 12075372618957595 | 12075372619757108 | 12075355840925545 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f4cf1757800 | 0x7f4be5a37380 | 5110352 | 4939885 | 65536 | 73632199 | 603230709 | 638793 | 638793 | 16046809 | 14032926 | 638793 | 0 | 0 | 0 | 4139367 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 11697727 | 10964788 | 1019 | 670486 | 0 | 0 | 14676 | 2065 | 0 | 2097152 | 2801 | 636081 | 2097152 | 0 | 0 | 52898 | 0 | 0 | 578520 | 0 | 701460 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355841093618 | 12075372619805267 | 12075372620226543 | 12075355841904805 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f4cf1757700 | 0x7f4be5a373c0 | 2810312 | 2655595 | 65536 | 39532271 | 322985139 | 351288 | 351288 | 7337072 | 4971271 | 351288 | 0 | 0 | 0 | 1524731 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 4742472 | 3881699 | 774 | 352275 | 0 | 0 | 12571 | 2065 | 0 | 2097152 | 2893 | 350829 | 2097152 | 0 | 0 | 34407 | 0 | 0 | 312312 | 0 | 857898 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355842065083 | 12075372620279983 | 12075372620505100 | 12075355842706665 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f4cf1757600 | 0x7f4be5a37400 | 7281168 | 7116319 | 65536 | 106247177 | 874930087 | 910145 | 910145 | 7422970 | 5837470 | 910145 | 0 | 0 | 0 | 2760011 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5685174 | 4913823 | 754 | 909927 | 0 | 0 | 16414 | 2314 | 0 | 2097152 | 2914 | 906167 | 2097152 | 0 | 0 | 67093 | 0 | 0 | 835292 | 0 | 906137 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355842874938 | 12075372620555820 | 12075372621151494 | 12075355843879955 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f4cf1757500 | 0x7f4be5a37440 | 3342984 | 3186022 | 65536 | 47383616 | 386680345 | 417872 | 417872 | 7623678 | 5461630 | 417872 | 0 | 0 | 0 | 2126269 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5247712 | 4384814 | 747 | 419574 | 0 | 0 | 13327 | 2051 | 0 | 2097152 | 2900 | 414766 | 2097152 | 0 | 0 | 40395 | 0 | 0 | 373822 | 0 | 1044541 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355844062164 | 12075372621211654 | 12075372621480611 | 12075355844726618 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f4cf1757400 | 0x7f4be5a37480 | 11906016 | 11740428 | 65536 | 175243013 | 1445916133 | 1488251 | 1488251 | 25188835 | 14894718 | 1488251 | 0 | 0 | 0 | 903918 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9025064 | 5135402 | 717 | 1485300 | 0 | 0 | 20328 | 2051 | 0 | 2097152 | 2898 | 1485783 | 2097152 | 0 | 0 | 101940 | 0 | 0 | 1381027 | 0 | 3985717 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355844891875 | 12075372621526531 | 12075372622512281 | 12075355846301264 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f4cf1757300 | 0x7f4be5a374c0 | 6206288 | 6041279 | 65536 | 90149329 | 738984464 | 775785 | 775785 | 14728887 | 12865741 | 775785 | 0 | 0 | 0 | 4420833 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 11366976 | 10698805 | 1019 | 803454 | 0 | 0 | 15680 | 2051 | 0 | 2097152 | 2787 | 774502 | 2097152 | 0 | 0 | 60571 | 0 | 0 | 710520 | 0 | 722535 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355846469787 | 12075372622559481 | 12075372623074836 | 12075355847384036 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f4cf1757a00 | 0x7f4be5a37500 | 3378488 | 3212961 | 65536 | 47793188 | 390656560 | 422310 | 422310 | 7578655 | 5440515 | 422310 | 0 | 0 | 0 | 2199211 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5297962 | 4439603 | 774 | 420651 | 0 | 0 | 13183 | 1996 | 0 | 2097152 | 3330 | 419079 | 2097152 | 0 | 0 | 40969 | 0 | 0 | 375258 | 0 | 975503 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355847547620 | 12075372623125875 | 12075372623397233 | 12075355848218707 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f4cf1757900 | 0x7f4be5a37540 | 9004920 | 8848443 | 65536 | 132114984 | 1090846001 | 1125614 | 1125614 | 18686004 | 8624201 | 1125614 | 0 | 0 | 0 | 715696 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7676581 | 3987787 | 754 | 1125287 | 0 | 0 | 17769 | 2049 | 0 | 2097152 | 2902 | 1123235 | 2097152 | 0 | 0 | 79890 | 0 | 0 | 1040676 | 0 | 3764106 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355848356553 | 12075372623443792 | 12075372624181705 | 12075355849514565 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f4cf1757800 | 0x7f4be5a37580 | 3894920 | 3738743 | 65536 | 55690707 | 456593272 | 486864 | 486864 | 7547854 | 5384374 | 486864 | 0 | 0 | 0 | 2070120 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5123775 | 4268686 | 747 | 487030 | 0 | 0 | 13992 | 2043 | 0 | 2097152 | 2912 | 485569 | 2097152 | 0 | 0 | 43438 | 0 | 0 | 439084 | 0 | 1003469 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355849691694 | 12075372624242344 | 12075372624557701 | 12075355850393739 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f4cf1757700 | 0x7f4be5a375c0 | 14164296 | 13981967 | 65536 | 208831282 | 1725335108 | 1770536 | 1770536 | 26008904 | 15078726 | 1770536 | 0 | 0 | 0 | 1349939 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 9074413 | 5105881 | 717 | 1766932 | 0 | 0 | 21971 | 2059 | 0 | 2097152 | 3998 | 1764820 | 2097152 | 0 | 0 | 118446 | 0 | 0 | 1644210 | 0 | 4038133 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355850557152 | 12075372624602981 | 12075372625776890 | 12075355852118654 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f4cf1757600 | 0x7f4be5a37600 | 7377424 | 7217460 | 65536 | 107631102 | 807035834 | 922177 | 922177 | 16039021 | 13909585 | 922177 | 0 | 0 | 0 | 4230009 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 11413601 | 10693666 | 764 | 921445 | 0 | 0 | 16192 | 2067 | 0 | 2097152 | 2897 | 915689 | 2097152 | 0 | 0 | 65080 | 0 | 0 | 851395 | 0 | 765377 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355852286686 | 12075372625823609 | 12075372626434643 | 12075355853302984 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f4cf1757500 | 0x7f4be5a37640 | 3939128 | 3783681 | 65536 | 56374641 | 461998681 | 492390 | 492390 | 7426231 | 5425074 | 492390 | 0 | 0 | 0 | 2009422 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5163452 | 4297767 | 717 | 491244 | 0 | 0 | 14145 | 2052 | 0 | 2097152 | 2740 | 490862 | 2097152 | 0 | 0 | 44259 | 0 | 0 | 444440 | 0 | 1004858 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355853463974 | 12075372626486803 | 12075372626807120 | 12075355854187899 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f4cf1757400 | 0x7f4be5a37680 | 10690312 | 10530900 | 65536 | 157285369 | 1299553825 | 1336288 | 1336288 | 18053779 | 8349808 | 1336288 | 0 | 0 | 0 | 616009 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7827650 | 4106536 | 1019 | 1335886 | 0 | 0 | 19398 | 2051 | 0 | 2097152 | 2899 | 1333831 | 2097152 | 0 | 0 | 93100 | 0 | 0 | 1238252 | 0 | 3735016 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355854356362 | 12075372626852399 | 12075372627730311 | 12075355855632503 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f4cf1757300 | 0x7f4be5a376c0 | 5045328 | 4876118 | 65536 | 72590309 | 596630222 | 630665 | 630665 | 7596681 | 5371510 | 630665 | 0 | 0 | 0 | 2013067 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 5087831 | 4272182 | 774 | 628339 | 0 | 0 | 14657 | 2051 | 0 | 2097152 | 2892 | 627709 | 2097152 | 0 | 0 | 17102 | 0 | 0 | 569490 | 0 | 1014145 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355855811636 | 12075372627798310 | 12075372628231746 | 12075355856631078 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f4cf1757a00 | 0x7f4be5a37700 | 18655696 | 18498308 | 65536 | 276314236 | 2285047268 | 2331961 | 2331961 | 25668267 | 15004674 | 2269366 | 62595 | 0 | 0 | 804289 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8925646 | 5001924 | 972 | 2331477 | 0 | 0 | 25753 | 2595 | 0 | 2097152 | 2897 | 2329545 | 2097152 | 0 | 0 | 153032 | 0 | 0 | 2175648 | 0 | 4018862 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355856795454 | 12075372628283266 | 12075372629835251 | 12075355858745397 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f4cf1757900 | 0x7f4be5a37740 | 9616224 | 9439307 | 65536 | 140903454 | 1161214248 | 1202027 | 1202027 | 25188266 | 14914577 | 1138649 | 63378 | 0 | 0 | 1391483 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8576022 | 4677591 | 747 | 1199478 | 0 | 0 | 18136 | 2427 | 0 | 2097152 | 2799 | 1196659 | 2097152 | 0 | 0 | 83932 | 0 | 0 | 1109448 | 0 | 3968613 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355858912327 | 12075372629908370 | 12075372630704042 | 12075355860114010 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f4cf1757800 | 0x7f4be5a37780 | 5111888 | 4954478 | 65536 | 73916129 | 607401855 | 638985 | 638985 | 18592704 | 8740560 | 638985 | 0 | 0 | 0 | 573249 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7738883 | 4024179 | 717 | 638612 | 0 | 0 | 14595 | 2050 | 0 | 2097152 | 3809 | 671601 | 2097152 | 0 | 0 | 50507 | 0 | 0 | 581992 | 0 | 3794776 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355860277835 | 12075372630781162 | 12075372631195718 | 12075355861069896 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f4cf1757700 | 0x7f4be5a377c0 | 14052600 | 13896432 | 65536 | 207565694 | 1714887051 | 1756574 | 1756574 | 18429648 | 8396653 | 1756574 | 0 | 0 | 0 | 691410 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7574863 | 3875764 | 747 | 1757206 | 0 | 0 | 22007 | 2067 | 0 | 2097152 | 2905 | 1758073 | 2097152 | 0 | 0 | 116535 | 0 | 0 | 1634588 | 0 | 3733944 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355861252486 | 12075372631269235 | 12075372632428265 | 12075355862800522 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f4cf1757600 | 0x7f4be5a37800 | 9574864 | 9420515 | 65536 | 140647001 | 1160720397 | 1196857 | 1196857 | 18923926 | 8709377 | 1196857 | 0 | 0 | 0 | 673982 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7735616 | 4058148 | 717 | 1197092 | 0 | 0 | 18269 | 2058 | 0 | 2097152 | 2909 | 1194652 | 2097152 | 0 | 0 | 84550 | 0 | 0 | 1109114 | 0 | 3739274 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355862980106 | 12075372632534983 | 12075372633320257 | 12075355864167242 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f4cf1757500 | 0x7f4be5a37840 | 36670520 | 36507787 | 65536 | 545552451 | 4515296589 | 4583814 | 4583814 | 26657449 | 15598219 | 4520828 | 62986 | 0 | 0 | 1259104 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8830903 | 4875387 | 1019 | 4582822 | 0 | 0 | 40728 | 2043 | 0 | 2097152 | 3664 | 4580674 | 2097152 | 0 | 0 | 213272 | 0 | 0 | 4295824 | 0 | 4006514 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355864333310 | 12075372633410336 | 12075372636463911 | 12075355867785936 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f4cf1757400 | 0x7f4be5a37880 | 18599248 | 18428662 | 65536 | 275242531 | 2275874629 | 2324905 | 2324905 | 25350810 | 14835539 | 2324905 | 0 | 0 | 0 | 859644 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8832398 | 4889301 | 774 | 2325907 | 0 | 0 | 25813 | 2050 | 0 | 2097152 | 3143 | 2322002 | 2097152 | 0 | 0 | 151133 | 0 | 0 | 2167240 | 0 | 3965617 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355867951573 | 12075372636558470 | 12075372638100537 | 12075355869890226 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f4cf1757300 | 0x7f4be5a378c0 | 9614136 | 9457158 | 65536 | 141247084 | 1166431675 | 1201766 | 1201766 | 18808465 | 8666186 | 1201766 | 0 | 0 | 0 | 510487 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7788394 | 4005724 | 752 | 1201753 | 0 | 0 | 18191 | 2051 | 0 | 2097152 | 2901 | 1199749 | 2097152 | 0 | 0 | 83831 | 0 | 0 | 1112653 | 0 | 3848464 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355870060773 | 12075372638196216 | 12075372638985810 | 12075355871241807 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f4cf1757a00 | 0x7f4be5a37900 | 27542776 | 27379873 | 65536 | 409097126 | 3385270822 | 3442846 | 3442846 | 18213216 | 8440068 | 3442846 | 0 | 0 | 0 | 755259 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7398471 | 4072098 | 747 | 3443798 | 0 | 0 | 33459 | 2052 | 0 | 2097152 | 2907 | 3439279 | 2097152 | 0 | 0 | 215256 | 0 | 0 | 3221058 | 0 | 3564668 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355871408867 | 12075372639080529 | 12075372641362590 | 12075355874082756 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f4cf1757900 | 0x7f4be5a37940 | 18576992 | 18417916 | 65536 | 275149063 | 2274886702 | 2322123 | 2322123 | 19324876 | 8805478 | 2322123 | 0 | 0 | 0 | 808453 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7523382 | 3907753 | 717 | 2322772 | 0 | 0 | 18430 | 2378 | 0 | 2097152 | 3443 | 2321390 | 2097152 | 0 | 0 | 150861 | 0 | 0 | 2166242 | 0 | 3781312 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355874258583 | 12075372641465469 | 12075372643001776 | 12075355876185252 |
| 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 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f4cf1757800 | 0x7f4be5a37980 | 72682360 | 72528478 | 65536 | 1084032499 | 8977574166 | 9085294 | 9085294 | 25823393 | 14997028 | 9085294 | 0 | 0 | 0 | 680871 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8779835 | 4813241 | 747 | 9087238 | 0 | 0 | 63253 | 2381 | 0 | 2097152 | 3215 | 9083218 | 2097152 | 0 | 0 | 544465 | 0 | 0 | 8539133 | 0 | 4017839 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355876351431 | 12075372643091696 | 12075372649149085 | 12075355882817777 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f4cf1757700 | 0x7f4be5a379c0 | 36581512 | 36412874 | 65536 | 544157272 | 4502413508 | 4572688 | 4572688 | 24185433 | 14498112 | 4572688 | 0 | 0 | 0 | 759793 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 0 | 8459023 | 4768165 | 731 | 4571494 | 0 | 0 | 40772 | 2004 | 0 | 2097152 | 2906 | 4569776 | 2097152 | 0 | 0 | 283727 | 0 | 0 | 4284210 | 0 | 3832160 | 0 | 0 | 0 | 0 | 0 | 0 | 12075355882981641 | 12075372649238685 | 12075372652281219 | 12075355886437483 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f4cf1757600 | 0x7f4be5a37a00 | 18621280 | 18464977 | 65536 | 275879354 | 2281488482 | 2327659 | 2327659 | 18976197 | 8608138 | 2327659 | 0 | 0 | 0 | 634027 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7819928 | 4046863 | 1035 | 2326950 | 0 | 0 | 25681 | 2504 | 0 | 2097152 | 2910 | 2324740 | 2097152 | 0 | 0 | 149470 | 0 | 0 | 2172146 | 0 | 3779272 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355886599233 | 12075372652370179 | 12075372653909206 | 12075355888529470 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 871499 | 871504 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f4cf1757500 | 0x7f4be5a37a40 | 54490320 | 54333553 | 65536 | 812031466 | 6723676883 | 6811289 | 6811289 | 18024155 | 8230517 | 6811289 | 0 | 0 | 0 | 632833 | 524288 | 0 | 0 | 524288 | 524288 | 0 | 0 | 524288 | 7586756 | 4021357 | 1099 | 6812574 | 0 | 0 | 55923 | 2067 | 0 | 2097152 | 3301 | 6809109 | 2097152 | 0 | 0 | 411163 | 0 | 0 | 6395187 | 0 | 3558032 | 0 | 0 | 0 | 0 | 0 | 524288 | 12075355888696149 | 12075372653998485 | 12075372658524528 | 12075355893627833 |