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_BUSY_CU_CYCLES | SQ_WAVES | SQ_WAVE_CYCLES | GRBM_COUNT | GRBM_GUI_ACTIVE | TCP_GATE_EN1_sum | TCP_GATE_EN2_sum | TCP_TD_TCP_STALL_CYCLES_sum | TCP_TCR_TCP_STALL_CYCLES_sum | TCP_READ_TAGCONFLICT_STALL_CYCLES_sum | TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum | TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum | TCP_TA_TCP_STATE_READ_sum | TCP_VOLATILE_sum | TCP_TOTAL_ACCESSES_sum | TCP_TOTAL_READ_sum | TCP_TOTAL_WRITE_sum | TCP_TOTAL_ATOMIC_WITH_RET_sum | TCP_TOTAL_ATOMIC_WITHOUT_RET_sum | TCP_TOTAL_WRITEBACK_INVALIDATES_sum | TCP_TOTAL_CACHE_ACCESSES_sum | TCP_UTCL1_TRANSLATION_MISS_sum | TCP_UTCL1_TRANSLATION_HIT_sum | TCP_UTCL1_PERMISSION_MISS_sum | TCP_UTCL1_REQUEST_sum | TCP_TCP_LATENCY_sum | TCP_TCC_READ_REQ_LATENCY_sum | TCP_TCC_WRITE_REQ_LATENCY_sum | TCP_TCC_READ_REQ_sum | TCP_TCC_WRITE_REQ_sum | TCP_TCC_ATOMIC_WITH_RET_REQ_sum | TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum | TCP_TCC_NC_READ_REQ_sum | TCP_TCC_NC_WRITE_REQ_sum | TCP_TCC_NC_ATOMIC_REQ_sum | TCP_TCC_UC_READ_REQ_sum | TCP_TCC_UC_WRITE_REQ_sum | TCP_TCC_UC_ATOMIC_REQ_sum | TCP_TCC_CC_READ_REQ_sum | TCP_TCC_CC_WRITE_REQ_sum | TCP_TCC_CC_ATOMIC_REQ_sum | TCP_TCC_RW_READ_REQ_sum | TCP_TCC_RW_WRITE_REQ_sum | TCP_TCC_RW_ATOMIC_REQ_sum | TCP_PENDING_STALL_CYCLES_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 862685 | 862690 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f0bba004180 | 4050064 | 3843144 | 57232741 | 524288 | 368076551 | 506257 | 506257 | 58058469 | 55385035 | 79 | 12247551 | 0 | 0 | 0 | 1048576 | 67108864 | 67108864 | 0 | 67108864 | 0 | 0 | 360 | 33554432 | 15339 | 16608641 | 0 | 16777216 | 639589777 | 0 | 2792631690 | 0 | 8388608 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 8388608 | 0 | 42220429 | 12075136458560390 | 12075147439751938 | 12075147440072415 | 12075136699500264 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 862685 | 862690 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f0bba035100 | 226920 | 77847 | 1062129 | 512 | 1133979 | 28364 | 28364 | 1554407 | 637475 | 291 | 132899 | 0 | 0 | 0 | 4096 | 65536 | 65536 | 65536 | 0 | 0 | 0 | 360 | 16384 | 120 | 15064 | 0 | 16384 | 12492250 | 17737144 | 0 | 8192 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 8192 | 0 | 0 | 432660 | 12075136714450868 | 12075147454470885 | 12075147454477285 | 12075136714965805 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f0cc5b86900 | 0x7f0bba035140 | 1840808 | 1667146 | 24636127 | 65536 | 120864602 | 230100 | 230100 | 25423007 | 24090444 | 29114 | 4906443 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7602 | 2018400 | 0 | 2097152 | 960258060 | 1572300696 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16147101 | 12075136715314513 | 12075147454541604 | 12075147454675843 | 12075136715955484 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f0cc5b86800 | 0x7f0bba035180 | 3143856 | 2981932 | 44527900 | 65536 | 268978647 | 392981 | 392981 | 45144977 | 44045433 | 0 | 22944685 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14544 | 8232196 | 0 | 8388608 | 1044450704 | 3907480224 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 31918362 | 12075136716303541 | 12075147454733442 | 12075147454975840 | 12075136717047033 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f0cc5b86700 | 0x7f0bba0351c0 | 3218624 | 3042747 | 45394595 | 65536 | 312045947 | 402327 | 402327 | 46060007 | 44995503 | 0 | 25322196 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14810 | 8232319 | 0 | 8388608 | 1067568010 | 3723472485 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35506908 | 12075136717323907 | 12075147455111999 | 12075147455360957 | 12075136718021013 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f0cc5b86600 | 0x7f0bba035200 | 1739800 | 1578259 | 23359807 | 65536 | 134638580 | 217474 | 217474 | 24092717 | 22844829 | 30441 | 10737930 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7544 | 2018524 | 0 | 2097152 | 1255635724 | 2343698257 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17406083 | 12075136718283791 | 12075147455495676 | 12075147455621114 | 12075136718774503 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f0cc5b86500 | 0x7f0bba035240 | 1825304 | 1660065 | 24595157 | 65536 | 125303449 | 228162 | 228162 | 25320827 | 24061035 | 28775 | 5429629 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7545 | 2017229 | 0 | 2097152 | 1194931391 | 2169639209 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17817258 | 12075136719102993 | 12075147455663354 | 12075147455788953 | 12075136719646203 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f0cc5b86400 | 0x7f0bba035280 | 1674496 | 1520275 | 22511562 | 65536 | 165962226 | 209311 | 209311 | 23222897 | 22053226 | 31743 | 14354889 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7625 | 2056109 | 0 | 2097152 | 997498611 | 1696207988 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15922341 | 12075136719996935 | 12075147455856152 | 12075147455979831 | 12075136720512012 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f0cc5b86300 | 0x7f0bba0352c0 | 3255768 | 3053369 | 45539176 | 65536 | 274253662 | 406970 | 406970 | 46219217 | 45013896 | 0 | 26269265 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14844 | 8231520 | 0 | 8388608 | 1190952986 | 4166784683 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 33936934 | 12075136720836445 | 12075147456026871 | 12075147456277269 | 12075136721596738 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f0cc5b86a00 | 0x7f0bba035300 | 3283888 | 3096256 | 46088265 | 65536 | 312486168 | 410485 | 410485 | 46859687 | 45716321 | 0 | 22336617 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14444 | 8234643 | 0 | 8388608 | 1106778880 | 4216740737 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 31391659 | 12075136721863173 | 12075147456411667 | 12075147456654705 | 12075136722548186 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f0cc5b86900 | 0x7f0bba035340 | 1721112 | 1553027 | 22926684 | 65536 | 156683575 | 215138 | 215138 | 23713967 | 22429099 | 32901 | 12724296 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7596 | 2055017 | 0 | 2097152 | 1079462112 | 1844767325 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18488025 | 12075136722813880 | 12075147456788304 | 12075147456912623 | 12075136723320872 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f0cc5b86800 | 0x7f0bba035380 | 1798704 | 1638299 | 24237573 | 65536 | 124073973 | 224837 | 224837 | 24993107 | 23684468 | 30280 | 7517030 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7645 | 2057423 | 0 | 2097152 | 1193663120 | 2176228060 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14631816 | 12075136723643992 | 12075147456957582 | 12075147457082701 | 12075136724183745 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f0cc5b86700 | 0x7f0bba0353c0 | 1746856 | 1576965 | 23379988 | 65536 | 137671467 | 218356 | 218356 | 24072977 | 22859565 | 31818 | 11071255 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7619 | 2052936 | 0 | 2097152 | 965918762 | 1580258068 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17170200 | 12075136724517576 | 12075147457143501 | 12075147457267500 | 12075136725063590 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f0cc5b86600 | 0x7f0bba035400 | 3174808 | 3012100 | 44942276 | 65536 | 339834061 | 396850 | 396850 | 45599987 | 44413474 | 0 | 25753888 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14740 | 8232600 | 0 | 8388608 | 1191860062 | 4778881224 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 31265191 | 12075136725386841 | 12075147457309259 | 12075147457560137 | 12075136726109434 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f0cc5b86500 | 0x7f0bba035440 | 3224832 | 3054334 | 45503710 | 65536 | 312916673 | 403103 | 403103 | 46238177 | 45104070 | 0 | 28329932 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14689 | 8233564 | 0 | 8388608 | 1150969805 | 4065162231 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34880051 | 12075136726369507 | 12075147457668296 | 12075147457952293 | 12075136727050563 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f0cc5b86400 | 0x7f0bba035480 | 1742696 | 1587594 | 23534923 | 65536 | 152829925 | 217836 | 217836 | 24232457 | 23045493 | 31594 | 9652535 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7588 | 2055990 | 0 | 2097152 | 1220295133 | 2212097765 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18460762 | 12075136727315325 | 12075147458055013 | 12075147458179971 | 12075136727795908 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f0cc5b86300 | 0x7f0bba0354c0 | 1764800 | 1592395 | 23554348 | 65536 | 138426566 | 220599 | 220599 | 24301787 | 22978592 | 31351 | 9620613 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7578 | 2057272 | 0 | 2097152 | 1165702863 | 2122330623 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17650171 | 12075136728124389 | 12075147458220131 | 12075147458346050 | 12075136728684770 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f0cc5b86a00 | 0x7f0bba035500 | 1739096 | 1575905 | 23377613 | 65536 | 151614439 | 217386 | 217386 | 24057287 | 22903388 | 31743 | 10535268 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7603 | 2051895 | 0 | 2097152 | 1238678238 | 2277812771 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 19051273 | 12075136729032576 | 12075147458395650 | 12075147458520128 | 12075136729546832 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f0cc5b86900 | 0x7f0bba035540 | 3649240 | 3011317 | 44899160 | 65536 | 326202182 | 456154 | 456154 | 45896942 | 44365151 | 0 | 25713662 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14291 | 8238049 | 0 | 8388608 | 1182259174 | 4439208441 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35554906 | 12075136729868640 | 12075147458560288 | 12075147458814366 | 12075136730657807 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f0cc5b86800 | 0x7f0bba035580 | 3234072 | 3054969 | 45462667 | 65536 | 306686002 | 404258 | 404258 | 46243367 | 45080901 | 0 | 25874605 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13535 | 8245852 | 0 | 8388608 | 1188529685 | 4386666449 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34293042 | 12075136730920435 | 12075147458919005 | 12075147459161403 | 12075136731599416 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f0cc5b86700 | 0x7f0bba0355c0 | 1717800 | 1550408 | 22920516 | 65536 | 147447764 | 214724 | 214724 | 23674997 | 22380045 | 31428 | 11819248 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7589 | 2052463 | 0 | 2097152 | 1080306376 | 1890616817 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17147165 | 12075136731862065 | 12075147459262842 | 12075147459387321 | 12075136732356213 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f0cc5b86600 | 0x7f0bba035600 | 1696280 | 1524673 | 22599376 | 65536 | 164401467 | 212034 | 212034 | 23286017 | 22085440 | 31795 | 13958965 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7633 | 2051728 | 0 | 2097152 | 1209383398 | 2147051440 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16351248 | 12075136732684783 | 12075147459427320 | 12075147459552439 | 12075136733212164 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f0cc5b86500 | 0x7f0bba035640 | 1718312 | 1545710 | 22874473 | 65536 | 159603740 | 214788 | 214788 | 23604497 | 22392554 | 32305 | 12609870 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7608 | 2050432 | 0 | 2097152 | 1306702011 | 2466587668 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16195282 | 12075136733551634 | 12075147459603799 | 12075147459728278 | 12075136734077201 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f0cc5b86400 | 0x7f0bba035680 | 3276208 | 3102678 | 46255439 | 65536 | 261491144 | 409525 | 409525 | 46956137 | 45719252 | 0 | 22909468 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14531 | 8234050 | 0 | 8388608 | 1102923806 | 4096487598 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34732248 | 12075136734401133 | 12075147459768277 | 12075147460018035 | 12075136735122413 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f0cc5b86300 | 0x7f0bba0356c0 | 3699248 | 3061396 | 45585619 | 65536 | 297182578 | 462405 | 462405 | 46581347 | 45174916 | 0 | 29897201 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14704 | 8233226 | 0 | 8388608 | 1158311226 | 4022966867 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34640085 | 12075136735384000 | 12075147460128594 | 12075147460373392 | 12075136736107444 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f0cc5b86a00 | 0x7f0bba035700 | 1712728 | 1540631 | 22844120 | 65536 | 153134242 | 214090 | 214090 | 23525627 | 22336005 | 31329 | 12596306 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7637 | 2052371 | 0 | 2097152 | 1123645682 | 1994658940 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15625851 | 12075136736374470 | 12075147460471951 | 12075147460596430 | 12075136736853911 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f0cc5b86900 | 0x7f0bba035740 | 1807960 | 1639743 | 24212248 | 65536 | 134727813 | 225994 | 225994 | 25014947 | 23550303 | 29913 | 6760741 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7611 | 2052241 | 0 | 2097152 | 1178239205 | 2121285338 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17529297 | 12075136737181169 | 12075147460636909 | 12075147460761708 | 12075136737729188 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f0cc5b86800 | 0x7f0bba035780 | 1711584 | 1550938 | 22962126 | 65536 | 149046347 | 213947 | 213947 | 23682887 | 22432461 | 30897 | 12113326 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7636 | 2052737 | 0 | 2097152 | 1283298724 | 2447508747 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17864672 | 12075136738067476 | 12075147460809868 | 12075147460934827 | 12075136738580370 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f0cc5b86700 | 0x7f0bba0357c0 | 3213592 | 3043364 | 45301761 | 65536 | 247987948 | 401698 | 401698 | 46069127 | 44751847 | 0 | 24021399 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14728 | 8231665 | 0 | 8388608 | 1144746063 | 4020961487 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 36311863 | 12075136738901436 | 12075147460974026 | 12075147461226664 | 12075136739649647 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f0cc5b86600 | 0x7f0bba035800 | 3274992 | 3104836 | 46321319 | 65536 | 340037149 | 409373 | 409373 | 46991237 | 45959802 | 0 | 26335385 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14049 | 8239939 | 0 | 8388608 | 1070026244 | 3742825200 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35305690 | 12075136739910832 | 12075147461359623 | 12075147461602661 | 12075136740596837 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f0cc5b86500 | 0x7f0bba035840 | 1655664 | 1490688 | 22147013 | 65536 | 170292012 | 206957 | 206957 | 22786157 | 21643436 | 33410 | 16118902 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7651 | 2053687 | 0 | 2097152 | 1189942156 | 2227137387 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14899555 | 12075136740856970 | 12075147461711300 | 12075147461835459 | 12075136741348925 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f0cc5b86400 | 0x7f0bba035880 | 1772672 | 1599314 | 23580307 | 65536 | 143375038 | 221583 | 221583 | 24408437 | 22860784 | 30898 | 9839706 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7597 | 2054142 | 0 | 2097152 | 1044718067 | 1774214285 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16324163 | 12075136741673528 | 12075147461875138 | 12075147462000737 | 12075136742211017 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f0cc5b86300 | 0x7f0bba0358c0 | 1705112 | 1539839 | 22788309 | 65536 | 152774099 | 213138 | 213138 | 23516177 | 22259608 | 32851 | 12632979 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7583 | 2054042 | 0 | 2097152 | 1030456098 | 1750571431 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15415922 | 12075136742542272 | 12075147462054337 | 12075147462178975 | 12075136743074341 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f0cc5b86a00 | 0x7f0bba035900 | 3183056 | 3014024 | 44952144 | 65536 | 279506283 | 397881 | 397881 | 45628937 | 44442330 | 0 | 25570166 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13891 | 8242993 | 0 | 8388608 | 1172409397 | 4500858248 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35048482 | 12075136743398443 | 12075147462219455 | 12075147462470493 | 12075136744121567 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f0cc5b86900 | 0x7f0bba035940 | 3190576 | 3015708 | 45036812 | 65536 | 346649488 | 398821 | 398821 | 45685427 | 44616132 | 0 | 26162812 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14923 | 8231300 | 0 | 8388608 | 1155642865 | 4076081972 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34626330 | 12075136744381510 | 12075147462563932 | 12075147462807130 | 12075136745043791 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f0cc5b86800 | 0x7f0bba035980 | 1722152 | 1562005 | 23062128 | 65536 | 144025781 | 215268 | 215268 | 23845787 | 22505334 | 31287 | 11081841 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7590 | 2051249 | 0 | 2097152 | 1037532416 | 1817986976 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16387727 | 12075136745309445 | 12075147462916409 | 12075147463041368 | 12075136745799145 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f0cc5b86700 | 0x7f0bba0359c0 | 1770304 | 1599588 | 23638300 | 65536 | 146301852 | 221287 | 221287 | 24412397 | 22930153 | 30921 | 8995038 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7589 | 2053082 | 0 | 2097152 | 1126686463 | 2015611738 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15633385 | 12075136746127916 | 12075147463081207 | 12075147463207606 | 12075136746654504 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f0cc5b86600 | 0x7f0bba035a00 | 1755504 | 1593934 | 23585575 | 65536 | 148560583 | 219437 | 219437 | 24364769 | 23048114 | 31128 | 9105696 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7583 | 2052175 | 0 | 2097152 | 991301917 | 1607489944 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18647213 | 12075136746990709 | 12075147463261526 | 12075147463386005 | 12075136747544298 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f0cc5b86500 | 0x7f0bba035a40 | 3273192 | 3107868 | 46337396 | 65536 | 320023435 | 409148 | 409148 | 47036717 | 45748088 | 0 | 23117602 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14712 | 8233257 | 0 | 8388608 | 1043555632 | 4034499078 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35847912 | 12075136747867098 | 12075147463427444 | 12075147463680562 | 12075136748596042 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f0cc5b86400 | 0x7f0bba035a80 | 3194544 | 3012845 | 44952042 | 65536 | 296456467 | 399317 | 399317 | 45611357 | 44532045 | 0 | 26862945 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14405 | 8237039 | 0 | 8388608 | 1175479104 | 4364391036 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34149379 | 12075136748861736 | 12075147463734801 | 12075147463977679 | 12075136749545336 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f0cc5b86300 | 0x7f0bba035ac0 | 1754224 | 1592010 | 23510225 | 65536 | 141932877 | 219277 | 219277 | 24298967 | 22958020 | 31392 | 9148219 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7631 | 2052866 | 0 | 2097152 | 1323197807 | 2530178900 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18150227 | 12075136749809618 | 12075147464058959 | 12075147464183597 | 12075136750307192 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f0cc5b86a00 | 0x7f0bba035b00 | 1765352 | 1593671 | 23489613 | 65536 | 156914003 | 220668 | 220668 | 24357375 | 22757123 | 31465 | 9623023 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7628 | 2052953 | 0 | 2097152 | 1163456112 | 2114386609 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17178038 | 12075136750629481 | 12075147464227437 | 12075147464353836 | 12075136751169575 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f0cc5b86900 | 0x7f0bba035b40 | 1729200 | 1565663 | 23210709 | 65536 | 151381498 | 216149 | 216149 | 23903837 | 22683344 | 31441 | 9496382 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7620 | 2050688 | 0 | 2097152 | 1187096242 | 2179208333 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18017112 | 12075136751501652 | 12075147464403755 | 12075147464528874 | 12075136752031447 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f0cc5b86800 | 0x7f0bba035b80 | 3330560 | 3136082 | 46639733 | 65536 | 298313291 | 416319 | 416319 | 47457137 | 46042297 | 0 | 30261659 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13431 | 8246453 | 0 | 8388608 | 935883288 | 3375246567 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34378314 | 12075136752320864 | 12075147464568714 | 12075147464828232 | 12075136753043778 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f0cc5b86700 | 0x7f0bba035bc0 | 3219176 | 3031532 | 45227523 | 65536 | 247294944 | 402396 | 402396 | 45888887 | 44804626 | 0 | 27088013 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14828 | 8232184 | 0 | 8388608 | 1185251781 | 4788070053 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 33652184 | 12075136753264538 | 12075147464884071 | 12075147465128389 | 12075136753973165 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f0cc5b86600 | 0x7f0bba035c00 | 1741208 | 1564916 | 23169074 | 65536 | 148014977 | 217650 | 217650 | 23892527 | 22635379 | 31880 | 10120641 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7623 | 2049733 | 0 | 2097152 | 1140259327 | 2043721497 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15985399 | 12075136754196360 | 12075147465186468 | 12075147465310467 | 12075136754705756 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f0cc5b86500 | 0x7f0bba035c40 | 1764032 | 1598404 | 23528586 | 65536 | 159974057 | 220503 | 220503 | 24394847 | 22616852 | 32200 | 9611507 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7740 | 2050799 | 0 | 2097152 | 1009358643 | 1733591119 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15819464 | 12075136754989995 | 12075147465350467 | 12075147465476706 | 12075136755539125 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f0cc5b86400 | 0x7f0bba035c80 | 1714240 | 1542813 | 22844786 | 65536 | 149627580 | 214279 | 214279 | 23560847 | 22307819 | 31594 | 12947914 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7604 | 2052959 | 0 | 2097152 | 1189522152 | 2151885604 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15472076 | 12075136755829946 | 12075147465527585 | 12075147465652064 | 12075136756347588 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f0cc5b86300 | 0x7f0bba035cc0 | 3333864 | 3124907 | 46473711 | 65536 | 280387483 | 416732 | 416732 | 47289407 | 45858750 | 0 | 24146436 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14552 | 8234695 | 0 | 8388608 | 1152674716 | 3911576557 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35387994 | 12075136756627057 | 12075147465692544 | 12075147465951421 | 12075136757331817 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f0cc5b86a00 | 0x7f0bba035d00 | 3216512 | 3053562 | 45574002 | 65536 | 342980406 | 402063 | 402063 | 46222217 | 45167988 | 0 | 26434578 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14197 | 8237228 | 0 | 8388608 | 1029178059 | 3747976926 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35196190 | 12075136757593092 | 12075147466013501 | 12075147466258299 | 12075136758287032 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f0cc5b86900 | 0x7f0bba035d40 | 1725288 | 1559031 | 23110584 | 65536 | 155405990 | 215660 | 215660 | 23804207 | 22525478 | 31803 | 10674958 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7598 | 2054704 | 0 | 2097152 | 1004715766 | 1666550421 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18789274 | 12075136758541745 | 12075147466322618 | 12075147466448217 | 12075136759073633 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f0cc5b86800 | 0x7f0bba035d80 | 1804440 | 1634065 | 23965689 | 65536 | 160860508 | 225554 | 225554 | 24929687 | 22752577 | 31127 | 7069334 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7883 | 2046698 | 0 | 2097152 | 1073080347 | 1991852210 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14741590 | 12075136759354946 | 12075147466488537 | 12075147466616856 | 12075136759903406 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f0cc5b86700 | 0x7f0bba035dc0 | 1719128 | 1556808 | 23032784 | 65536 | 153756763 | 214890 | 214890 | 23770817 | 22427888 | 31765 | 11845177 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7600 | 2054794 | 0 | 2097152 | 1136454245 | 2033686586 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18659018 | 12075136760201540 | 12075147466666775 | 12075147466791574 | 12075136760735562 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f0cc5b86600 | 0x7f0bba035e00 | 3314392 | 3146835 | 46859310 | 65536 | 334931342 | 414298 | 414298 | 47621477 | 46203390 | 0 | 30475759 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13653 | 8244010 | 0 | 8388608 | 1164044526 | 4387938066 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 36723256 | 12075136761017005 | 12075147466830934 | 12075147467085971 | 12075136761730311 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f0cc5b86500 | 0x7f0bba035e40 | 3244352 | 3076152 | 45841552 | 65536 | 304492261 | 405543 | 405543 | 46558157 | 45393271 | 0 | 23888706 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13481 | 8246715 | 0 | 8388608 | 1099903497 | 4385473970 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34832056 | 12075136761992067 | 12075147467141331 | 12075147467389169 | 12075136762699131 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f0cc5b86400 | 0x7f0bba035e80 | 1734912 | 1573873 | 23199277 | 65536 | 153489004 | 216863 | 216863 | 24024107 | 22622615 | 31728 | 10407795 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7560 | 2052450 | 0 | 2097152 | 966163142 | 1581183562 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14486200 | 12075136762956850 | 12075147467445808 | 12075147467570767 | 12075136763511050 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f0cc5b86300 | 0x7f0bba035ec0 | 1762712 | 1594139 | 23411695 | 65536 | 171869262 | 220338 | 220338 | 24327977 | 21405762 | 31680 | 6697808 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7993 | 2041583 | 0 | 2097152 | 799600485 | 1332150656 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13504244 | 12075136763787854 | 12075147467611567 | 12075147467739085 | 12075136764326666 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f0cc5b86a00 | 0x7f0bba035f00 | 1727664 | 1560262 | 23023597 | 65536 | 154533065 | 215957 | 215957 | 23822717 | 22508768 | 31500 | 11740059 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7605 | 2052849 | 0 | 2097152 | 1107250340 | 1999956356 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15550338 | 12075136764615613 | 12075147467789325 | 12075147467914124 | 12075136765143173 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f0cc5b86900 | 0x7f0bba035f40 | 3331240 | 3159316 | 46936741 | 65536 | 331419582 | 416404 | 416404 | 47805587 | 46284180 | 0 | 27924254 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13853 | 8240874 | 0 | 8388608 | 1064077713 | 4154550497 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34388096 | 12075136765421330 | 12075147467955243 | 12075147468212361 | 12075136766117634 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f0cc5b86800 | 0x7f0bba035f80 | 3084800 | 2928347 | 43714802 | 65536 | 352578926 | 385599 | 385599 | 44343977 | 43244917 | 0 | 29282451 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13417 | 8247383 | 0 | 8388608 | 1148861314 | 3781239043 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35452707 | 12075136766377296 | 12075147468272201 | 12075147468516198 | 12075136767035359 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f0cc5b86700 | 0x7f0bba035fc0 | 1706136 | 1535580 | 22760732 | 65536 | 162606529 | 213266 | 213266 | 23452367 | 22171519 | 32225 | 13069603 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7608 | 2054284 | 0 | 2097152 | 1162289366 | 2071770830 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15195377 | 12075136767295944 | 12075147468570918 | 12075147468696037 | 12075136767839253 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f0cc5b86600 | 0x7f0bba036000 | 1807064 | 1627151 | 23973793 | 65536 | 179781982 | 225882 | 225882 | 24825947 | 20073223 | 31288 | 7182270 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7887 | 2030860 | 0 | 2097152 | 779506629 | 1680028246 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15076060 | 12075136768122820 | 12075147468737636 | 12075147468874115 | 12075136768657544 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f0cc5b86500 | 0x7f0bba036040 | 1746496 | 1583619 | 23426819 | 65536 | 155795704 | 218311 | 218311 | 24170117 | 22854468 | 31603 | 9969896 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7570 | 2050950 | 0 | 2097152 | 1067091887 | 1858429649 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16287357 | 12075136768949476 | 12075147468924995 | 12075147469049634 | 12075136769485503 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f0cc5b86400 | 0x7f0bba036080 | 3315800 | 3136016 | 46568527 | 65536 | 296641378 | 414474 | 414474 | 47458937 | 45929096 | 0 | 24234204 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14116 | 8238066 | 0 | 8388608 | 1072562850 | 3871635609 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 32836933 | 12075136769763900 | 12075147469090753 | 12075147469351551 | 12075136770464612 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f0cc5b86300 | 0x7f0bba0360c0 | 3640536 | 3021301 | 45029494 | 65536 | 324757261 | 455066 | 455066 | 45999767 | 44553308 | 0 | 26347733 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14213 | 8237647 | 0 | 8388608 | 1165523334 | 3981283695 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34003076 | 12075136770722652 | 12075147469410910 | 12075147469655548 | 12075136771447388 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f0cc5b86a00 | 0x7f0bba036100 | 1715328 | 1541943 | 22764111 | 65536 | 160219747 | 214415 | 214415 | 23547977 | 22159101 | 32184 | 12905339 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7637 | 2051268 | 0 | 2097152 | 1256622649 | 2358597077 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16820794 | 12075136771705999 | 12075147469715868 | 12075147469841146 | 12075136772236485 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f0cc5b86900 | 0x7f0bba036140 | 1852776 | 1688650 | 24913108 | 65536 | 201061917 | 231596 | 231596 | 25745627 | 19609407 | 30782 | 4836701 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7830 | 2026634 | 0 | 2097152 | 794248087 | 1801313259 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16145448 | 12075136772516525 | 12075147469880186 | 12075147470022265 | 12075136773062240 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f0cc5b86800 | 0x7f0bba036180 | 1746328 | 1582489 | 23329732 | 65536 | 158975838 | 218290 | 218290 | 24156107 | 22708193 | 32034 | 10246178 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7566 | 2053278 | 0 | 2097152 | 1086838970 | 1954217471 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18736322 | 12075136773355204 | 12075147470073144 | 12075147470198583 | 12075136773887062 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f0cc5b86700 | 0x7f0bba0361c0 | 3390912 | 3217455 | 47822428 | 65536 | 359547803 | 423863 | 423863 | 48680627 | 47095424 | 0 | 27028463 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 12792 | 8252138 | 0 | 8388608 | 1056847866 | 3820270071 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34477909 | 12075136774166622 | 12075147470239063 | 12075147470489941 | 12075136774861113 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f0cc5b86600 | 0x7f0bba036200 | 3195840 | 3017756 | 44856309 | 65536 | 221968450 | 399479 | 399479 | 45683867 | 44360721 | 0 | 27157386 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14912 | 8230200 | 0 | 8388608 | 1036553819 | 3672167667 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34642196 | 12075136775124712 | 12075147470547540 | 12075147470794738 | 12075136775813843 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f0cc5b86500 | 0x7f0bba036240 | 1778648 | 1616700 | 23872625 | 65536 | 145135043 | 222330 | 222330 | 24669317 | 23224750 | 30867 | 7888354 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7537 | 2051802 | 0 | 2097152 | 1289074382 | 2383025898 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14586141 | 12075136776078755 | 12075147470851537 | 12075147470976976 | 12075136776617186 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f0cc5b86400 | 0x7f0bba036280 | 1938984 | 1779000 | 26327907 | 65536 | 211724703 | 242372 | 242372 | 27103667 | 19142478 | 30959 | 4640029 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7755 | 2022645 | 0 | 2097152 | 642785794 | 1486519314 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15393103 | 12075136776894501 | 12075147471021616 | 12075147471170255 | 12075136777455664 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f0cc5b86300 | 0x7f0bba0362c0 | 1721664 | 1553644 | 22961018 | 65536 | 147983505 | 215207 | 215207 | 23723357 | 22327575 | 31852 | 12116723 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7564 | 2053329 | 0 | 2097152 | 1029632221 | 1788677420 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18686656 | 12075136777764047 | 12075147471236974 | 12075147471361933 | 12075136778278764 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f0cc5b86a00 | 0x7f0bba036300 | 3333032 | 3127472 | 46495131 | 65536 | 328214108 | 416628 | 416628 | 47330897 | 45758278 | 0 | 23692810 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14145 | 8238392 | 0 | 8388608 | 884618959 | 3439893950 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 31829379 | 12075136778557071 | 12075147471401932 | 12075147471655850 | 12075136779253104 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f0cc5b86900 | 0x7f0bba036340 | 3162088 | 3005639 | 44795880 | 65536 | 308617367 | 395260 | 395260 | 45503267 | 44255312 | 0 | 26077924 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13329 | 8248166 | 0 | 8388608 | 1103180979 | 4425944792 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34275210 | 12075136779511294 | 12075147471707370 | 12075147471955527 | 12075136780193282 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f0cc5b86800 | 0x7f0bba036380 | 1782360 | 1608652 | 23882086 | 65536 | 148106190 | 222794 | 222794 | 24548447 | 23210379 | 31256 | 8465537 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7553 | 2051616 | 0 | 2097152 | 1298827544 | 2534229556 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15738440 | 12075136780449087 | 12075147472016167 | 12075147472142086 | 12075136780991966 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f0cc5b86700 | 0x7f0bba0363c0 | 2013104 | 1857304 | 27586577 | 65536 | 223336116 | 251637 | 251637 | 28275347 | 17404783 | 30484 | 3198060 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7726 | 2022566 | 0 | 2097152 | 530251875 | 1273144095 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14221569 | 12075136781274060 | 12075147472181285 | 12075147472339524 | 12075136781834522 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f0cc5b86600 | 0x7f0bba036400 | 1722544 | 1546507 | 22953882 | 65536 | 158872175 | 215317 | 215317 | 23613467 | 22272153 | 32418 | 11493050 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7574 | 2053645 | 0 | 2097152 | 1037649029 | 1834364439 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15992519 | 12075136782126825 | 12075147472389924 | 12075147472515362 | 12075136782660757 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f0cc5b86500 | 0x7f0bba036440 | 3346008 | 3153583 | 46815420 | 65536 | 320644973 | 418250 | 418250 | 47722457 | 45985156 | 0 | 21455649 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14243 | 8235395 | 0 | 8388608 | 1125857342 | 3847402431 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 32617749 | 12075136782940236 | 12075147472554402 | 12075147472812320 | 12075136783633314 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f0cc5b86400 | 0x7f0bba036480 | 3211928 | 3050348 | 45507210 | 65536 | 325164983 | 401490 | 401490 | 46176017 | 44972525 | 0 | 22845416 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14762 | 8233271 | 0 | 8388608 | 1180387489 | 4180502234 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 35206760 | 12075136783898988 | 12075147472863999 | 12075147473108157 | 12075136784588359 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f0cc5b86300 | 0x7f0bba0364c0 | 1716200 | 1554938 | 22958858 | 65536 | 152868618 | 214524 | 214524 | 23742857 | 22390974 | 31270 | 10901187 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7555 | 2053536 | 0 | 2097152 | 1148054448 | 2055310984 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14778047 | 12075136784841870 | 12075147473168477 | 12075147473293755 | 12075136785389618 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f0cc5b86a00 | 0x7f0bba036500 | 2104920 | 1942755 | 28900607 | 65536 | 234546437 | 263114 | 263114 | 29559887 | 16937261 | 29642 | 2661733 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7727 | 2021678 | 0 | 2097152 | 438977377 | 1076504709 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13128353 | 12075136785669518 | 12075147473333435 | 12075147473498874 | 12075136786229179 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f0cc5b86900 | 0x7f0bba036540 | 1833448 | 1666212 | 24599424 | 65536 | 144654996 | 229180 | 229180 | 25412957 | 23900293 | 30974 | 4863667 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7621 | 2051404 | 0 | 2097152 | 1257212831 | 2314761886 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17695433 | 12075136786516993 | 12075147473547033 | 12075147473672472 | 12075136787054302 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f0cc5b86800 | 0x7f0bba036580 | 3374040 | 3157032 | 46858375 | 65536 | 329570626 | 421754 | 421754 | 47771357 | 45723890 | 0 | 15464343 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13836 | 8239033 | 0 | 8388608 | 884809857 | 3332564860 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 32052537 | 12075136787332890 | 12075147473713432 | 12075147473971189 | 12075136788013855 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f0cc5b86700 | 0x7f0bba0365c0 | 3106416 | 2939847 | 43879392 | 65536 | 355246791 | 388301 | 388301 | 44513657 | 43430697 | 0 | 28771326 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14688 | 8234011 | 0 | 8388608 | 1167556943 | 3989870904 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34673562 | 12075136788272406 | 12075147474032149 | 12075147474316466 | 12075136788950826 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f0cc5b86600 | 0x7f0bba036600 | 1752096 | 1574112 | 23278189 | 65536 | 161145910 | 219011 | 219011 | 24061787 | 22630178 | 31496 | 9788646 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7573 | 2054006 | 0 | 2097152 | 1104081273 | 1965689393 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17554848 | 12075136789218784 | 12075147474377906 | 12075147474503825 | 12075136789751384 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f0cc5b86500 | 0x7f0bba036640 | 2200856 | 2043207 | 30339895 | 65536 | 245361689 | 275106 | 275106 | 31066877 | 16523766 | 28977 | 2497898 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7684 | 2020290 | 0 | 2097152 | 414281063 | 1047815151 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12506097 | 12075136790035532 | 12075147474544624 | 12075147474717743 | 12075136790627172 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f0cc5b86400 | 0x7f0bba036680 | 1773656 | 1612759 | 23792263 | 65536 | 151662266 | 221706 | 221706 | 24610127 | 23140677 | 30967 | 7885792 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7638 | 2050916 | 0 | 2097152 | 1179677618 | 2112131251 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17776331 | 12075136791067049 | 12075147474767502 | 12075147474892941 | 12075136791654721 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f0cc5b86300 | 0x7f0bba0366c0 | 3229400 | 3048758 | 45208281 | 65536 | 323278691 | 403674 | 403674 | 46150157 | 43876652 | 0 | 10169134 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13742 | 8239331 | 0 | 8388608 | 835103884 | 3559883735 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 33275775 | 12075136791959287 | 12075147474933741 | 12075147475184938 | 12075136792714440 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f0cc5b86a00 | 0x7f0bba036700 | 3136048 | 2971244 | 44319718 | 65536 | 353042107 | 392005 | 392005 | 44984417 | 43799213 | 0 | 29527736 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14486 | 8235912 | 0 | 8388608 | 1160690650 | 4594753638 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34225235 | 12075136793012895 | 12075147475242538 | 12075147475487016 | 12075136793732603 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f0cc5b86900 | 0x7f0bba036740 | 1811456 | 1642171 | 24289766 | 65536 | 160451780 | 226431 | 226431 | 25048247 | 23593290 | 30469 | 6636430 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7580 | 2050420 | 0 | 2097152 | 1076541893 | 1896567258 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13915848 | 12075136794019015 | 12075147475543015 | 12075147475668294 | 12075136794621745 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f0cc5b86800 | 0x7f0bba036780 | 2306456 | 2144124 | 31866846 | 65536 | 258518125 | 288306 | 288306 | 32551157 | 15879867 | 24610 | 2399114 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7693 | 2019920 | 0 | 2097152 | 397796761 | 991018394 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12885916 | 12075136794928766 | 12075147475709094 | 12075147475891172 | 12075136795595925 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f0cc5b86700 | 0x7f0bba0367c0 | 1796784 | 1619777 | 23920275 | 65536 | 154566895 | 224597 | 224597 | 24713207 | 23139675 | 31069 | 7313931 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7530 | 2051981 | 0 | 2097152 | 1000420719 | 1729811545 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15855833 | 12075136795904980 | 12075147475943332 | 12075147476069090 | 12075136796480810 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f0cc5b86600 | 0x7f0bba036800 | 3266712 | 3105197 | 46202406 | 65536 | 373153528 | 408338 | 408338 | 46996577 | 45774827 | 0 | 930231 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15318 | 8220171 | 0 | 8388608 | 449948947 | 2424318530 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 36823590 | 12075136796791587 | 12075147476110210 | 12075147476372928 | 12075136797542843 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f0cc5b86500 | 0x7f0bba036840 | 3213976 | 3040439 | 45251363 | 65536 | 316758185 | 401746 | 401746 | 46030097 | 44745228 | 0 | 26022587 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14757 | 8232576 | 0 | 8388608 | 1061696048 | 3738142639 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34779971 | 12075136797834926 | 12075147476432287 | 12075147476677085 | 12075136798566325 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f0cc5b86400 | 0x7f0bba036880 | 1748272 | 1567097 | 23160531 | 65536 | 153313216 | 218533 | 218533 | 23922467 | 22472613 | 32315 | 10676558 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7585 | 2051209 | 0 | 2097152 | 1023310344 | 1727739882 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16218560 | 12075136798855363 | 12075147476732764 | 12075147476858043 | 12075136799453194 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f0cc5b86300 | 0x7f0bba0368c0 | 2449664 | 2273286 | 33693774 | 65536 | 263215297 | 306207 | 306207 | 34517927 | 16502844 | 24774 | 2228392 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7691 | 2020846 | 0 | 2097152 | 366457266 | 949572221 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12547301 | 12075136799770443 | 12075147476898843 | 12075147477089881 | 12075136800437322 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f0cc5b86a00 | 0x7f0bba036900 | 1806144 | 1633300 | 24065700 | 65536 | 152281543 | 225767 | 225767 | 24918077 | 23282178 | 29801 | 6397079 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7596 | 2051114 | 0 | 2097152 | 1117617884 | 1981857641 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14198626 | 12075136800746657 | 12075147477139001 | 12075147477265080 | 12075136801316136 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f0cc5b86900 | 0x7f0bba036940 | 3484952 | 3319312 | 49435548 | 65536 | 403375871 | 435618 | 435618 | 50208347 | 48883493 | 0 | 429866 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15345 | 8219835 | 0 | 8388608 | 297793402 | 1797752606 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 39942988 | 12075136801630480 | 12075147477304119 | 12075147477586037 | 12075136802360937 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f0cc5b86800 | 0x7f0bba036980 | 3202024 | 3012769 | 44820637 | 65536 | 293558105 | 400252 | 400252 | 45607157 | 44260951 | 0 | 25607650 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14534 | 8234593 | 0 | 8388608 | 1144820485 | 4490418197 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34849182 | 12075136802647209 | 12075147477639316 | 12075147477887154 | 12075136803381063 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f0cc5b86700 | 0x7f0bba0369c0 | 1716520 | 1545176 | 22827508 | 65536 | 157316151 | 214564 | 214564 | 23596397 | 22061776 | 31980 | 11356934 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7579 | 2051836 | 0 | 2097152 | 1052700851 | 1885409297 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15006988 | 12075136803676161 | 12075147477943314 | 12075147478068912 | 12075136804277118 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f0cc5b86600 | 0x7f0bba036a00 | 2649968 | 2480800 | 36792945 | 65536 | 276025602 | 331245 | 331245 | 37630847 | 16319172 | 24230 | 2233694 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7689 | 2021077 | 0 | 2097152 | 368922373 | 952465708 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12998486 | 12075136804585621 | 12075147478109392 | 12075147478319470 | 12075136805276255 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f0cc5b86500 | 0x7f0bba036a40 | 1803224 | 1634486 | 24023000 | 65536 | 154211002 | 225402 | 225402 | 24937487 | 22866538 | 29795 | 7814778 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7593 | 2051604 | 0 | 2097152 | 987233200 | 1686871107 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15618874 | 12075136805551737 | 12075147478388910 | 12075147478516908 | 12075136806104133 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f0cc5b86400 | 0x7f0bba036a80 | 3773096 | 3603852 | 53689407 | 65536 | 439711408 | 471636 | 471636 | 54476627 | 52943460 | 0 | 467151 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15357 | 8220045 | 0 | 8388608 | 250166360 | 1616118371 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 43551089 | 12075136806387390 | 12075147478557068 | 12075147478893385 | 12075136807134739 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f0cc5b86300 | 0x7f0bba036ac0 | 3212648 | 3035721 | 45182031 | 65536 | 329092893 | 401580 | 401580 | 45951707 | 44600500 | 0 | 29204407 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14732 | 8233484 | 0 | 8388608 | 1149873940 | 3863024468 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34347688 | 12075136807394201 | 12075147478952104 | 12075147479205382 | 12075136808086457 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f0cc5b86a00 | 0x7f0bba036b00 | 1752536 | 1588812 | 23388416 | 65536 | 159979272 | 219066 | 219066 | 24252017 | 22633606 | 31228 | 9929180 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7614 | 2053256 | 0 | 2097152 | 972929872 | 1628841123 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16925459 | 12075136808343575 | 12075147479267622 | 12075147479394820 | 12075136808888969 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f0cc5b86900 | 0x7f0bba036b40 | 2842216 | 2676488 | 39761872 | 65536 | 323745525 | 355276 | 355276 | 40563317 | 16708935 | 23256 | 2398390 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7688 | 2020252 | 0 | 2097152 | 365314235 | 939716531 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12686205 | 12075136809174259 | 12075147479434020 | 12075147479660898 | 12075136809833374 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f0cc5b86800 | 0x7f0bba036b80 | 1825816 | 1659504 | 24351067 | 65536 | 158049708 | 228226 | 228226 | 25312397 | 23087559 | 30267 | 6595982 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7678 | 2050161 | 0 | 2097152 | 968111415 | 1626907194 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14602356 | 12075136810108505 | 12075147479730177 | 12075147479857696 | 12075136810634563 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f0cc5b86700 | 0x7f0bba036bc0 | 4384536 | 3881564 | 57785645 | 65536 | 472515886 | 548066 | 548066 | 58894967 | 56986131 | 0 | 362386 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15359 | 8219667 | 0 | 8388608 | 237527197 | 1565694994 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 47372680 | 12075136810912118 | 12075147479897856 | 12075147480226333 | 12075136811702898 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f0cc5b86600 | 0x7f0bba036c00 | 3274688 | 3080617 | 45797954 | 65536 | 275152214 | 409335 | 409335 | 46625237 | 45173274 | 0 | 23994153 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13343 | 8248548 | 0 | 8388608 | 1080586333 | 4352395164 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 34441540 | 12075136811960817 | 12075147480286172 | 12075147480539610 | 12075136812672450 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f0cc5b86500 | 0x7f0bba036c40 | 1762408 | 1600513 | 23574857 | 65536 | 159091293 | 220300 | 220300 | 24430367 | 22321937 | 31329 | 10429199 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7741 | 2050040 | 0 | 2097152 | 1043416852 | 1854649827 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 15454457 | 12075136812927504 | 12075147480599610 | 12075147480727608 | 12075136813485551 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f0cc5b86400 | 0x7f0bba036c80 | 3084016 | 2896171 | 43073583 | 65536 | 350438305 | 385501 | 385501 | 43858727 | 16956102 | 22444 | 2351715 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7684 | 2020079 | 0 | 2097152 | 354518688 | 917786988 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12891453 | 12075136813761333 | 12075147480767608 | 12075147481011446 | 12075136814442960 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f0cc5b86300 | 0x7f0bba036cc0 | 1793944 | 1608907 | 23799072 | 65536 | 166699681 | 224242 | 224242 | 24552467 | 22390794 | 30487 | 7896495 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7930 | 2049160 | 0 | 2097152 | 885728238 | 1484419632 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16041542 | 12075136814715336 | 12075147481078325 | 12075147481208564 | 12075136815254478 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f0cc5b86a00 | 0x7f0bba036d00 | 4609880 | 4439054 | 66119058 | 65536 | 539952963 | 576234 | 576234 | 67004717 | 64827565 | 0 | 357561 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219957 | 0 | 8388608 | 230616334 | 1539981434 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 54421253 | 12075136815532385 | 12075147481248564 | 12075147481622800 | 12075136816335968 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f0cc5b86900 | 0x7f0bba036d40 | 3270424 | 3100146 | 45988714 | 65536 | 303361528 | 408802 | 408802 | 46920977 | 44779776 | 0 | 21033191 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13680 | 8244750 | 0 | 8388608 | 1125461677 | 3973095018 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 30158321 | 12075136816590882 | 12075147481679280 | 12075147481934798 | 12075136817281405 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f0cc5b86800 | 0x7f0bba036d80 | 1798128 | 1631618 | 23995413 | 65536 | 155684308 | 224765 | 224765 | 24893177 | 22256463 | 29662 | 5026365 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7920 | 2049775 | 0 | 2097152 | 793072567 | 1276711147 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14749492 | 12075136817536298 | 12075147481991757 | 12075147482119916 | 12075136818084187 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f0cc5b86700 | 0x7f0bba036dc0 | 3465536 | 3309526 | 49215259 | 65536 | 403072211 | 433191 | 433191 | 50061737 | 17112730 | 22238 | 2054204 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7681 | 2019984 | 0 | 2097152 | 345803095 | 885339888 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13044802 | 12075136818360811 | 12075147482161036 | 12075147482439913 | 12075136819048138 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f0cc5b86600 | 0x7f0bba036e00 | 1753192 | 1580781 | 23417477 | 65536 | 156928275 | 219148 | 219148 | 24130547 | 21279600 | 30538 | 6181160 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7894 | 2041207 | 0 | 2097152 | 811770945 | 1606990908 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14845826 | 12075136819316637 | 12075147482509192 | 12075147482644871 | 12075136819857101 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f0cc5b86500 | 0x7f0bba036e40 | 5147568 | 4993683 | 74475690 | 65536 | 610820439 | 643445 | 643445 | 75324227 | 71377169 | 0 | 323493 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219751 | 0 | 8388608 | 226626962 | 1519903447 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 58785191 | 12075136820140087 | 12075147482685511 | 12075147483108547 | 12075136820983765 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f0cc5b86400 | 0x7f0bba036e80 | 3259760 | 3082278 | 45646961 | 65536 | 272766401 | 407469 | 407469 | 46650017 | 42800979 | 0 | 11148214 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14542 | 8230585 | 0 | 8388608 | 991869648 | 3835773515 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 28658848 | 12075136821246483 | 12075147483168867 | 12075147483428064 | 12075136821941425 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f0cc5b86300 | 0x7f0bba036ec0 | 1823656 | 1646548 | 24238268 | 65536 | 183658169 | 227956 | 227956 | 25116977 | 21787410 | 29015 | 4580274 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7876 | 2042158 | 0 | 2097152 | 901273122 | 1859486035 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18718983 | 12075136822205396 | 12075147483487424 | 12075147483624062 | 12075136822756049 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f0cc5b86a00 | 0x7f0bba036f00 | 3893784 | 3735838 | 55623190 | 65536 | 449414681 | 486722 | 486722 | 56456417 | 16598670 | 23442 | 2009254 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7688 | 2020217 | 0 | 2097152 | 357080984 | 913115193 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13225390 | 12075136823038574 | 12075147483663262 | 12075147484006939 | 12075136823777537 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f0cc5b86900 | 0x7f0bba036f40 | 1950096 | 1786638 | 26555866 | 65536 | 214102328 | 243761 | 243761 | 27215507 | 22957801 | 21419 | 2739364 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7699 | 2051018 | 0 | 2097152 | 382159675 | 984406475 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17202545 | 12075136824047198 | 12075147484077018 | 12075147484228377 | 12075136824592912 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f0cc5b86800 | 0x7f0bba036f80 | 6266304 | 6107434 | 91127109 | 65536 | 750375499 | 783287 | 783287 | 92030387 | 84352596 | 0 | 484172 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219648 | 0 | 8388608 | 222025460 | 1497606214 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 70857851 | 12075136824870478 | 12075147484268697 | 12075147484784052 | 12075136825822778 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f0cc5b86700 | 0x7f0bba036fc0 | 3658472 | 3451929 | 51073951 | 65536 | 360739151 | 457308 | 457308 | 52197707 | 40116060 | 0 | 10070379 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 13953 | 8237248 | 0 | 8388608 | 727426912 | 3275815940 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 28917536 | 12075136826073213 | 12075147484843251 | 12075147485140369 | 12075136826797840 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f0cc5b86600 | 0x7f0bba037000 | 1988136 | 1827891 | 27138898 | 65536 | 217745149 | 248516 | 248516 | 27868457 | 22387610 | 20632 | 2739238 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7697 | 2047507 | 0 | 2097152 | 366027363 | 957900269 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17121241 | 12075136827058244 | 12075147485200848 | 12075147485353807 | 12075136827618295 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f0cc5b86500 | 0x7f0bba037040 | 4738088 | 4581387 | 68368467 | 65536 | 561701713 | 592260 | 592260 | 69139577 | 16759219 | 24311 | 2328063 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7704 | 2020973 | 0 | 2097152 | 365606382 | 931115417 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12696055 | 12075136827898696 | 12075147485394446 | 12075147485778763 | 12075136828719591 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f0cc5b86400 | 0x7f0bba037080 | 2220632 | 2060364 | 30663860 | 65536 | 250050057 | 277578 | 277578 | 31324397 | 22070099 | 22713 | 2444055 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7691 | 2045609 | 0 | 2097152 | 347564331 | 930561134 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 18192757 | 12075136828983201 | 12075147485847722 | 12075147486022921 | 12075136829559592 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f0cc5b86300 | 0x7f0bba0370c0 | 7411160 | 7237307 | 107989100 | 65536 | 889239678 | 926394 | 926394 | 108978437 | 94567195 | 0 | 318858 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219707 | 0 | 8388608 | 219974466 | 1491216528 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 77130198 | 12075136829837048 | 12075147486063240 | 12075147486671875 | 12075136830870068 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f0cc5b86a00 | 0x7f0bba037100 | 4030448 | 3859966 | 57348825 | 65536 | 456491145 | 503805 | 503805 | 58315457 | 37406528 | 0 | 3139336 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14485 | 8229626 | 0 | 8388608 | 356051437 | 1910091369 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 24930512 | 12075136831130361 | 12075147486731714 | 12075147487060031 | 12075136831883461 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f0cc5b86900 | 0x7f0bba037140 | 2251352 | 2088654 | 31081310 | 65536 | 253758737 | 281418 | 281418 | 31748687 | 22903277 | 21368 | 2181211 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7697 | 2047079 | 0 | 2097152 | 348151074 | 924137178 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17463576 | 12075136832139677 | 12075147487124511 | 12075147487300989 | 12075136832731918 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f0cc5b86800 | 0x7f0bba037180 | 5848424 | 5426148 | 80969515 | 65536 | 663052143 | 731052 | 731052 | 82098131 | 17537685 | 22532 | 2299313 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7691 | 2019452 | 0 | 2097152 | 385130130 | 938120232 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13578662 | 12075136833011187 | 12075147487339869 | 12075147487794105 | 12075136833911309 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f0cc5b86700 | 0x7f0bba0371c0 | 2518080 | 2344137 | 34893893 | 65536 | 285036423 | 314759 | 314759 | 35578037 | 21860202 | 22146 | 2257042 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7691 | 2043232 | 0 | 2097152 | 336269081 | 883483341 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16528433 | 12075136834179458 | 12075147487858264 | 12075147488057783 | 12075136834814678 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f0cc5b86600 | 0x7f0bba037200 | 8510464 | 8354503 | 124703802 | 65536 | 1028717202 | 1063807 | 1063807 | 125736467 | 99761659 | 0 | 258206 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219694 | 0 | 8388608 | 221966845 | 1503331796 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 81439922 | 12075136835078969 | 12075147488115702 | 12075147488817776 | 12075136836212486 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f0cc5b86500 | 0x7f0bba037240 | 4545880 | 4375194 | 65157075 | 65536 | 526767057 | 568234 | 568234 | 66046757 | 36351237 | 0 | 1962280 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15239 | 8221108 | 0 | 8388608 | 310314722 | 1745919214 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 23341523 | 12075136836473451 | 12075147488879215 | 12075147489252332 | 12075136837285039 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f0cc5b86400 | 0x7f0bba037280 | 2538968 | 2383419 | 35485458 | 65536 | 289446890 | 317370 | 317370 | 36170117 | 21491199 | 21656 | 2248379 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7695 | 2039888 | 0 | 2097152 | 332338661 | 890255446 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16264213 | 12075136837538069 | 12075147489317451 | 12075147489519689 | 12075136838160606 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f0cc5b86300 | 0x7f0bba0372c0 | 6440344 | 6270808 | 93564149 | 65536 | 770457088 | 805042 | 805042 | 94480997 | 18523811 | 28908 | 2323699 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7706 | 2020002 | 0 | 2097152 | 482326702 | 1046626843 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14862569 | 12075136838415289 | 12075147489574729 | 12075147490100004 | 12075136839370184 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f0cc5b86a00 | 0x7f0bba037300 | 2782040 | 2624751 | 39091723 | 65536 | 319604919 | 347754 | 347754 | 39790097 | 21690441 | 21808 | 2144648 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7690 | 2044877 | 0 | 2097152 | 330622427 | 890436482 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 17522500 | 12075136839634685 | 12075147490170563 | 12075147490394401 | 12075136840259457 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f0cc5b86900 | 0x7f0bba037340 | 9671080 | 9491569 | 141718817 | 65536 | 1169408584 | 1208884 | 1208884 | 142867067 | 111356625 | 0 | 359235 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219648 | 0 | 8388608 | 218177529 | 1486266888 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 90754843 | 12075136840514611 | 12075147490450401 | 12075147491247834 | 12075136841751479 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f0cc5b86800 | 0x7f0bba037380 | 5127680 | 4947160 | 73747736 | 65536 | 597523526 | 640959 | 640959 | 74627207 | 34427638 | 0 | 1550659 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14024 | 8234508 | 0 | 8388608 | 334626347 | 1823496290 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 24285004 | 12075136842009819 | 12075147491308473 | 12075147491728629 | 12075136842861001 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f0cc5b86700 | 0x7f0bba0373c0 | 2843032 | 2671815 | 39783972 | 65536 | 325433552 | 355378 | 355378 | 40496057 | 24335049 | 19387 | 1974462 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7689 | 2042440 | 0 | 2097152 | 330289530 | 893683451 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 16364744 | 12075136843119832 | 12075147491786869 | 12075147492012627 | 12075136843791050 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f0cc5b86600 | 0x7f0bba037400 | 7266752 | 7101704 | 106003952 | 65536 | 872131957 | 908343 | 908343 | 106941527 | 18336961 | 29477 | 2278973 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7712 | 2020673 | 0 | 2097152 | 499283403 | 1067916769 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14590618 | 12075136844058907 | 12075147492071346 | 12075147492667021 | 12075136845108658 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f0cc5b86500 | 0x7f0bba037440 | 3339928 | 3171677 | 47183661 | 65536 | 386684355 | 417490 | 417490 | 47994017 | 18404549 | 20948 | 2294359 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7696 | 2025318 | 0 | 2097152 | 342887877 | 901871999 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14519614 | 12075136845358663 | 12075147492734380 | 12075147493002058 | 12075136846051641 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f0cc5b86400 | 0x7f0bba037480 | 11903848 | 11739014 | 175267819 | 65536 | 1447601472 | 1487980 | 1487980 | 176504057 | 117170431 | 0 | 292187 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219648 | 0 | 8388608 | 219987614 | 1498237037 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 96273317 | 12075136846293791 | 12075147493059977 | 12075147494043969 | 12075136847717166 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f0cc5b86300 | 0x7f0bba0374c0 | 6437784 | 6074953 | 90527251 | 65536 | 740367948 | 804722 | 804722 | 91801787 | 39075268 | 0 | 2784372 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14141 | 8233456 | 0 | 8388608 | 327000781 | 1775077803 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 22389845 | 12075136847982749 | 12075147494102208 | 12075147494615483 | 12075136848932033 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f0cc5b86a00 | 0x7f0bba037500 | 3376664 | 3201122 | 47627448 | 65536 | 389989258 | 422082 | 422082 | 48435707 | 17915411 | 22168 | 2196741 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7703 | 2025412 | 0 | 2097152 | 337973834 | 892282735 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14020925 | 12075136849198609 | 12075147494675483 | 12075147494945721 | 12075136849869295 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f0cc5b86900 | 0x7f0bba037540 | 9004504 | 8844810 | 132097747 | 65536 | 1090173345 | 1125562 | 1125562 | 133091147 | 106785718 | 341 | 83643 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8144 | 2059243 | 0 | 2097152 | 220424666 | 766386757 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 91843177 | 12075136850137844 | 12075147495004600 | 12075147495741073 | 12075136851282471 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f0cc5b86800 | 0x7f0bba037580 | 3915328 | 3743143 | 55683283 | 65536 | 455812037 | 489415 | 489415 | 56563097 | 17867962 | 22325 | 2143853 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7688 | 2026119 | 0 | 2097152 | 345068680 | 884912141 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 12633044 | 12075136851540711 | 12075147495812273 | 12075147496125870 | 12075136852271589 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f0cc5b86700 | 0x7f0bba0375c0 | 14144320 | 13981496 | 208788456 | 65536 | 1723714125 | 1768039 | 1768039 | 210141227 | 141655379 | 0 | 343236 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219670 | 0 | 8388608 | 214845501 | 1493365524 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 112421206 | 12075136852521534 | 12075147496185069 | 12075147497354979 | 12075136854111188 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f0cc5b86600 | 0x7f0bba037600 | 7356952 | 7184770 | 107152409 | 65536 | 809697896 | 919618 | 919618 | 108190457 | 34820709 | 0 | 1490798 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 14853 | 8225486 | 0 | 8388608 | 293115771 | 1616033698 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 26162375 | 12075136854377243 | 12075147497412738 | 12075147498022173 | 12075136855403470 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f0cc5b86500 | 0x7f0bba037640 | 3942232 | 3779296 | 56244794 | 65536 | 461155472 | 492778 | 492778 | 57108227 | 17686698 | 22325 | 2131998 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7689 | 2025312 | 0 | 2097152 | 345901419 | 898510848 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 14142834 | 12075136855666488 | 12075147498083932 | 12075147498402649 | 12075136856391345 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f0cc5b86400 | 0x7f0bba037680 | 10694952 | 10529821 | 157277026 | 65536 | 1299017315 | 1336868 | 1336868 | 158363387 | 109409666 | 420 | 61405 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8174 | 2059968 | 0 | 2097152 | 222170482 | 774425500 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 93770996 | 12075136856654995 | 12075147498461849 | 12075147499338801 | 12075136857952006 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f0cc5b86300 | 0x7f0bba0376c0 | 5056600 | 4885633 | 72734517 | 65536 | 596668093 | 632074 | 632074 | 73704317 | 16951445 | 23376 | 2308441 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7693 | 2024072 | 0 | 2097152 | 334089130 | 870645024 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 13158549 | 12075136858227307 | 12075147499410160 | 12075147499844076 | 12075136859055637 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f0cc5b86a00 | 0x7f0bba037700 | 18661224 | 18498626 | 276302804 | 65536 | 2284519728 | 2332652 | 2332652 | 277895417 | 147771898 | 0 | 492198 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219826 | 0 | 8388608 | 219696255 | 1516993896 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 112970765 | 12075136859320709 | 12075147499901836 | 12075147501449662 | 12075136861285641 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f0cc5b86900 | 0x7f0bba037740 | 9613288 | 9438870 | 140885723 | 65536 | 1161715040 | 1201660 | 1201660 | 142001987 | 116796004 | 0 | 281515 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219975 | 0 | 8388608 | 215912078 | 1489230780 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 94563688 | 12075136861550984 | 12075147501535901 | 12075147502330774 | 12075136862762545 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f0cc5b86800 | 0x7f0bba037780 | 5111232 | 4952051 | 73972065 | 65536 | 609288340 | 638903 | 638903 | 74699657 | 69137558 | 649 | 91778 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8412 | 2060856 | 0 | 2097152 | 220546796 | 762399493 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 64040669 | 12075136863031555 | 12075147502432527 | 12075147502845804 | 12075136863854535 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f0cc5b86700 | 0x7f0bba0377c0 | 14060632 | 13898200 | 207568246 | 65536 | 1715688839 | 1757578 | 1757578 | 208891817 | 127589692 | 315 | 51496 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7938 | 2060058 | 0 | 2097152 | 227336793 | 787548666 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 102634697 | 12075136864118315 | 12075147502952522 | 12075147504109794 | 12075136865698181 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f0cc5b86600 | 0x7f0bba037800 | 9601944 | 9426028 | 140707391 | 65536 | 1160707032 | 1200242 | 1200242 | 141886847 | 104958176 | 397 | 50629 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8307 | 2061001 | 0 | 2097152 | 228952800 | 786607260 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 84860403 | 12075136865971088 | 12075147504224673 | 12075147505008827 | 12075136867173112 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f0cc5b86500 | 0x7f0bba037840 | 36688320 | 36510276 | 545548203 | 65536 | 4515113098 | 4586039 | 4586039 | 548070227 | 188073533 | 0 | 345253 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219974 | 0 | 8388608 | 251476713 | 1679752723 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 152441826 | 12075136867436141 | 12075147505113146 | 12075147508162723 | 12075136870901120 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f0cc5b86400 | 0x7f0bba037880 | 18594200 | 18428990 | 275278725 | 65536 | 2276046857 | 2324274 | 2324274 | 276850817 | 154262551 | 0 | 350365 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219657 | 0 | 8388608 | 224791710 | 1537369789 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 122374783 | 12075136871174478 | 12075147508266402 | 12075147509806871 | 12075136873126987 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f0cc5b86300 | 0x7f0bba0378c0 | 9627416 | 9459163 | 141256887 | 65536 | 1165405657 | 1203426 | 1203426 | 142306127 | 100514323 | 504 | 59593 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8357 | 2061124 | 0 | 2097152 | 223596820 | 776643643 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 82671398 | 12075136873392290 | 12075147509911030 | 12075147510699024 | 12075136874596938 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f0cc5b86a00 | 0x7f0bba037900 | 27535896 | 27376928 | 409106273 | 65536 | 3385612593 | 3441986 | 3441986 | 411072887 | 139548076 | 437 | 80323 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7899 | 2057880 | 0 | 2097152 | 261949986 | 877010668 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 123420719 | 12075136874862742 | 12075147510807983 | 12075147513088926 | 12075136877571236 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f0cc5b86900 | 0x7f0bba037940 | 18585768 | 18413031 | 275096466 | 65536 | 2272307476 | 2323220 | 2323220 | 276614387 | 140444635 | 908 | 95823 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8437 | 2060180 | 0 | 2097152 | 255427500 | 854269480 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 113801724 | 12075136877845666 | 12075147513205885 | 12075147514740593 | 12075136879804215 |
| 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 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f0cc5b86800 | 0x7f0bba037980 | 72680168 | 72524281 | 1083988491 | 65536 | 8976979577 | 9085020 | 9085020 | 1088283077 | 189644050 | 0 | 319237 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219765 | 0 | 8388608 | 262864041 | 1726026573 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 157691811 | 12075136880067324 | 12075147514843953 | 12075147520895587 | 12075136886537729 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f0cc5b86700 | 0x7f0bba0379c0 | 36588992 | 36422636 | 544166060 | 65536 | 4502034619 | 4573623 | 4573623 | 546755537 | 199447035 | 0 | 391392 | 0 | 0 | 0 | 524288 | 33554432 | 33554432 | 33554432 | 0 | 0 | 0 | 360 | 8388608 | 15360 | 8219757 | 0 | 8388608 | 304187986 | 1858256501 | 0 | 4194304 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194304 | 0 | 0 | 158812677 | 12075136886804003 | 12075147521002786 | 12075147524042763 | 12075136890286515 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f0cc5b86600 | 0x7f0bba037a00 | 18633664 | 18459195 | 275749976 | 65536 | 2279212373 | 2329207 | 2329207 | 277306787 | 146255465 | 392 | 88265 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 8518 | 2060563 | 0 | 2097152 | 249236963 | 845560522 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 114624135 | 12075136890543272 | 12075147524147883 | 12075147525685951 | 12075136892500510 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 862685 | 862690 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f0cc5b86500 | 0x7f0bba037a40 | 54494552 | 54330444 | 812005471 | 65536 | 6723548167 | 6811818 | 6811818 | 815375477 | 161901085 | 395 | 59997 | 0 | 0 | 0 | 524288 | 8388608 | 8388608 | 8388608 | 0 | 0 | 0 | 360 | 2097152 | 7930 | 2061009 | 0 | 2097152 | 259501295 | 892872295 | 0 | 2097152 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097152 | 0 | 0 | 138951435 | 12075136892763729 | 12075147525792830 | 12075147530319036 | 12075136897718336 |