61 KiB
61 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 | SQC_TC_INST_REQ | SQC_TC_DATA_READ_REQ | SQC_TC_DATA_WRITE_REQ | GRBM_COUNT | GRBM_GUI_ACTIVE | SQC_TC_DATA_ATOMIC_REQ | SQC_TC_STALL | SQC_TC_REQ | SQC_DCACHE_REQ_READ_16 | SQC_ICACHE_REQ | SQC_ICACHE_HITS | SQC_ICACHE_MISSES | SQC_ICACHE_MISSES_DUPLICATE | SQC_DCACHE_INPUT_VALID_READYB | SQC_DCACHE_ATOMIC | SQC_DCACHE_REQ_READ_8 | SQC_DCACHE_REQ | SQC_DCACHE_HITS | SQC_DCACHE_MISSES | SQC_DCACHE_MISSES_DUPLICATE | SQC_DCACHE_REQ_READ_1 | SQC_DCACHE_REQ_READ_2 | SQC_DCACHE_REQ_READ_4 | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 143633 | 143633 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f52c3c04280 | 3060888 | 2970020 | 38588351 | 524288 | 239990325 | 392 | 224 | 0 | 382610 | 382610 | 0 | 0 | 616 | 0 | 4718592 | 4714698 | 112 | 3782 | 898846 | 0 | 524288 | 3670016 | 3663163 | 224 | 6629 | 1048576 | 1048576 | 1048576 | 16022625257429 | 16025461787106 | 16025462025348 | 16022774125203 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 143633 | 143633 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f52c3c23f80 | 194472 | 98162 | 1048056 | 512 | 1290098 | 504 | 56 | 0 | 24308 | 24308 | 0 | 0 | 560 | 0 | 8192 | 6207 | 56 | 1929 | 676 | 0 | 0 | 512 | 0 | 56 | 456 | 0 | 512 | 0 | 16022779363606 | 16025466939141 | 16025466947461 | 16022779509623 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f52d2570380 | 0x7f52c3c23fc0 | 1307784 | 1207045 | 15600643 | 65536 | 96894331 | 392 | 56 | 0 | 163472 | 163472 | 0 | 0 | 448 | 0 | 917504 | 913427 | 0 | 4077 | 525176 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 16022779562971 | 16025467041542 | 16025467133862 | 16022779919993 |
| 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 | 8 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f52d2570200 | 0x7f52c3c24000 | 2485536 | 2381284 | 30829891 | 65536 | 228057929 | 560 | 56 | 0 | 310691 | 310691 | 0 | 0 | 616 | 0 | 1114112 | 1110580 | 56 | 3476 | 265619 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 16022779976252 | 16025467168263 | 16025467348104 | 16022780363544 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f52d2570080 | 0x7f52c3c24040 | 2488064 | 2380666 | 30804448 | 65536 | 227103134 | 448 | 56 | 0 | 311007 | 311007 | 0 | 0 | 504 | 0 | 917504 | 912947 | 56 | 4501 | 400465 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 16022780413722 | 16025467373864 | 16025467554665 | 16022780800264 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f52d00edf00 | 0x7f52c3c24080 | 1331520 | 1225292 | 15832933 | 65536 | 100757294 | 504 | 56 | 0 | 166439 | 166439 | 0 | 0 | 560 | 0 | 1048576 | 1044369 | 56 | 4151 | 403264 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 16022780848583 | 16025467579785 | 16025467672106 | 16022781144766 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f52d00edd80 | 0x7f52c3c240c0 | 1320416 | 1217452 | 15727784 | 65536 | 99089678 | 448 | 56 | 0 | 165051 | 165051 | 0 | 0 | 504 | 0 | 983040 | 979103 | 56 | 3881 | 560239 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 65536 | 0 | 16022781192175 | 16025467698346 | 16025467789707 | 16022781487739 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f52d00edc00 | 0x7f52c3c24100 | 1310016 | 1209304 | 15651387 | 65536 | 106793154 | 504 | 56 | 0 | 163751 | 163751 | 0 | 0 | 560 | 0 | 1114112 | 1111669 | 0 | 2443 | 493854 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022781552447 | 16025467832267 | 16025467923948 | 16022781838751 |
| 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 | 23 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f52d00eda80 | 0x7f52c3c24140 | 2470584 | 2368988 | 30682929 | 65536 | 231084448 | 616 | 56 | 0 | 308822 | 308822 | 0 | 0 | 672 | 0 | 1310720 | 1307332 | 56 | 3332 | 258637 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022781887540 | 16025467955948 | 16025468136269 | 16022782307810 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f52d00ed900 | 0x7f52c3c24180 | 2467936 | 2363572 | 30606968 | 65536 | 226400763 | 560 | 56 | 0 | 308491 | 308491 | 0 | 0 | 616 | 0 | 1179648 | 1175526 | 56 | 4066 | 343342 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022782355879 | 16025468184750 | 16025468364271 | 16022782758200 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f52d00ed780 | 0x7f52c3c241c0 | 1322856 | 1216007 | 15741213 | 65536 | 108355915 | 560 | 56 | 0 | 165356 | 165356 | 0 | 0 | 616 | 0 | 1245184 | 1241159 | 56 | 3969 | 260831 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022782807129 | 16025468391471 | 16025468484272 | 16022783099903 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f52d00ed600 | 0x7f52c3c24200 | 1317456 | 1217671 | 15753317 | 65536 | 109083145 | 560 | 56 | 0 | 164681 | 164681 | 0 | 0 | 616 | 0 | 1245184 | 1241335 | 56 | 3793 | 394333 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022783148742 | 16025468544752 | 16025468637233 | 16022783410106 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f52d2570480 | 0x7f52c3c24240 | 1314120 | 1212310 | 15696132 | 65536 | 112877346 | 560 | 56 | 0 | 164264 | 164264 | 0 | 0 | 616 | 0 | 1245184 | 1241364 | 56 | 3764 | 365566 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022783468045 | 16025468699313 | 16025468791794 | 16022783725899 |
| 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 | 38 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f52d2570300 | 0x7f52c3c24280 | 2479352 | 2375691 | 30772296 | 65536 | 232392346 | 672 | 56 | 0 | 309918 | 309918 | 0 | 0 | 728 | 0 | 1441792 | 1438285 | 56 | 3451 | 296136 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022783775258 | 16025468821394 | 16025469000915 | 16022784126250 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f52d2570180 | 0x7f52c3c242c0 | 2452712 | 2351397 | 30459426 | 65536 | 224393209 | 616 | 56 | 0 | 306588 | 306588 | 0 | 0 | 672 | 0 | 1310720 | 1306315 | 56 | 4349 | 343692 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022784174269 | 16025469027315 | 16025469208757 | 16022784527441 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f52d2570000 | 0x7f52c3c24300 | 1305736 | 1204928 | 15597087 | 65536 | 107085538 | 616 | 56 | 0 | 163216 | 163216 | 0 | 0 | 672 | 0 | 1376256 | 1371158 | 56 | 5042 | 317688 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022784577330 | 16025469240917 | 16025469334197 | 16022784835634 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f52d00ede80 | 0x7f52c3c24340 | 1306408 | 1204108 | 15592085 | 65536 | 109310527 | 672 | 56 | 0 | 163300 | 163300 | 0 | 0 | 728 | 0 | 1441792 | 1438133 | 56 | 3603 | 258211 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022784884863 | 16025469361718 | 16025469453558 | 16022785144408 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f52d00edd00 | 0x7f52c3c24380 | 1300248 | 1195411 | 15479148 | 65536 | 107793913 | 616 | 56 | 0 | 162530 | 162530 | 0 | 0 | 672 | 0 | 1310720 | 1306623 | 112 | 3985 | 440242 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022785201586 | 16025469488599 | 16025469580439 | 16022785456191 |
| 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 | 53 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f52d00edb80 | 0x7f52c3c243c0 | 2452824 | 2350268 | 30446247 | 65536 | 229137240 | 728 | 56 | 0 | 306602 | 306602 | 0 | 0 | 784 | 0 | 1572864 | 1569515 | 56 | 3293 | 263884 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022785506250 | 16025469620279 | 16025469800921 | 16022785855902 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f52d00eda00 | 0x7f52c3c24400 | 2422424 | 2321057 | 30083301 | 65536 | 221028463 | 616 | 56 | 0 | 302802 | 302802 | 0 | 0 | 672 | 0 | 1441792 | 1439192 | 0 | 2600 | 488316 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022785907761 | 16025469830201 | 16025470011322 | 16022786257763 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f52d00ed880 | 0x7f52c3c24440 | 1311240 | 1210826 | 15677552 | 65536 | 112852817 | 672 | 56 | 0 | 163904 | 163904 | 0 | 0 | 728 | 0 | 1507328 | 1503315 | 56 | 3957 | 260488 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022786308872 | 16025470042522 | 16025470135323 | 16022786575936 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f52d00ed700 | 0x7f52c3c24480 | 1306048 | 1202032 | 15554789 | 65536 | 108963260 | 728 | 56 | 0 | 163255 | 163255 | 0 | 0 | 784 | 0 | 1638400 | 1634333 | 56 | 4011 | 338818 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022786625055 | 16025470163643 | 16025470255484 | 16022786890229 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f52d2570580 | 0x7f52c3c244c0 | 1307032 | 1204605 | 15604123 | 65536 | 113000543 | 616 | 56 | 0 | 163378 | 163378 | 0 | 0 | 672 | 0 | 1441792 | 1438131 | 56 | 3605 | 491703 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022786948778 | 16025470289244 | 16025470380925 | 16022787200962 |
| 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 | 68 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f52d2570400 | 0x7f52c3c24500 | 2459960 | 2354753 | 30509809 | 65536 | 228841035 | 784 | 56 | 0 | 307494 | 307494 | 0 | 0 | 840 | 0 | 1703936 | 1700484 | 56 | 3396 | 380713 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022787250191 | 16025470413085 | 16025470592446 | 16022787599943 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f52d2570280 | 0x7f52c3c24540 | 2472280 | 2370791 | 30718922 | 65536 | 224571528 | 728 | 56 | 0 | 309034 | 309034 | 0 | 0 | 784 | 0 | 1572864 | 1568535 | 56 | 4273 | 257386 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022787649422 | 16025470636766 | 16025470815808 | 16022788000754 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f52d2570100 | 0x7f52c3c24580 | 1305640 | 1202399 | 15567160 | 65536 | 111795367 | 672 | 56 | 0 | 163204 | 163204 | 0 | 0 | 728 | 0 | 1638400 | 1633260 | 0 | 5140 | 483175 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022788051163 | 16025470847968 | 16025470940449 | 16022788311477 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f52d00edf80 | 0x7f52c3c245c0 | 1301296 | 1195586 | 15452099 | 65536 | 97523929 | 784 | 56 | 0 | 162661 | 162661 | 0 | 0 | 840 | 0 | 1835008 | 1830763 | 0 | 4245 | 493514 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022788362406 | 16025470968289 | 16025471059969 | 16022788622560 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f52d00ede00 | 0x7f52c3c24600 | 1299776 | 1197890 | 15506578 | 65536 | 112526484 | 728 | 56 | 0 | 162471 | 162471 | 0 | 0 | 784 | 0 | 1507328 | 1502600 | 112 | 4616 | 257540 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022788681059 | 16025471093730 | 16025471185090 | 16022788933744 |
| 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 | 83 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f52d00edc80 | 0x7f52c3c24640 | 2472328 | 2358148 | 30555664 | 65536 | 231658138 | 784 | 56 | 0 | 309040 | 309040 | 0 | 0 | 840 | 0 | 1835008 | 1830581 | 0 | 4427 | 492947 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022788983772 | 16025471217250 | 16025471397252 | 16022789343804 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f52d00edb00 | 0x7f52c3c24680 | 2442160 | 2333327 | 30216391 | 65536 | 222072168 | 784 | 56 | 0 | 305269 | 305269 | 0 | 0 | 840 | 0 | 1703936 | 1700089 | 56 | 3791 | 506971 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022789392033 | 16025471424932 | 16025471606533 | 16022789759375 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f52d00ed980 | 0x7f52c3c246c0 | 1303112 | 1199522 | 15531297 | 65536 | 103953008 | 784 | 56 | 0 | 162888 | 162888 | 0 | 0 | 840 | 0 | 1769472 | 1764361 | 56 | 5055 | 256135 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022789808184 | 16025471634693 | 16025471726694 | 16022790070778 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f52d00ed800 | 0x7f52c3c24700 | 1316976 | 1208438 | 15598290 | 65536 | 102149716 | 896 | 56 | 0 | 164621 | 164621 | 0 | 0 | 952 | 0 | 2031616 | 2023649 | 112 | 7855 | 259661 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022790120797 | 16025471753414 | 16025471846055 | 16022790398771 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f52d00ed680 | 0x7f52c3c24740 | 1300264 | 1196594 | 15492937 | 65536 | 103537235 | 728 | 56 | 0 | 162532 | 162532 | 0 | 0 | 784 | 0 | 1638400 | 1632971 | 56 | 5373 | 260318 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022790456990 | 16025471878535 | 16025471970536 | 16022790714644 |
| 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 | 98 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f52d2570500 | 0x7f52c3c24780 | 2447096 | 2345138 | 30375131 | 65536 | 230047817 | 840 | 56 | 0 | 305886 | 305886 | 0 | 0 | 896 | 0 | 1966080 | 1962095 | 0 | 3985 | 490378 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022790764743 | 16025472011496 | 16025472191817 | 16022791112015 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f52d2570380 | 0x7f52c3c247c0 | 2446568 | 2335951 | 30251471 | 65536 | 222598539 | 840 | 56 | 0 | 305820 | 305820 | 0 | 0 | 896 | 0 | 1835008 | 1830617 | 56 | 4335 | 332859 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022791162134 | 16025472233577 | 16025472413899 | 16022791518276 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f52d2570200 | 0x7f52c3c24800 | 1307768 | 1204750 | 15578435 | 65536 | 108812983 | 840 | 56 | 0 | 163470 | 163470 | 0 | 0 | 896 | 0 | 1900544 | 1895720 | 112 | 4712 | 436291 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022791568335 | 16025472456779 | 16025472549100 | 16022791831699 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f52d2570080 | 0x7f52c3c24840 | 1294248 | 1189413 | 15349826 | 65536 | 100244253 | 1008 | 56 | 0 | 161780 | 161780 | 0 | 0 | 1064 | 0 | 2228224 | 2222640 | 56 | 5528 | 259924 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022791881728 | 16025472583340 | 16025472675821 | 16022792144662 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f52d00edf00 | 0x7f52c3c24880 | 1299016 | 1198294 | 15502320 | 65536 | 108668680 | 784 | 56 | 0 | 162376 | 162376 | 0 | 0 | 840 | 0 | 1703936 | 1698754 | 56 | 5126 | 322466 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022792202091 | 16025472708141 | 16025472799821 | 16022792457235 |
| 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 | 113 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f52d00edd80 | 0x7f52c3c248c0 | 2444920 | 2341721 | 30339133 | 65536 | 230460648 | 952 | 56 | 0 | 305614 | 305614 | 0 | 0 | 1008 | 0 | 2097152 | 2092138 | 56 | 4958 | 257944 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022792506934 | 16025472832142 | 16025473011823 | 16022792856627 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f52d00edc00 | 0x7f52c3c24900 | 2456264 | 2348467 | 30415439 | 65536 | 225185633 | 840 | 56 | 0 | 307032 | 307032 | 0 | 0 | 896 | 0 | 1966080 | 1962806 | 56 | 3218 | 532307 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022792901966 | 16025473038223 | 16025473217264 | 16022793253748 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f52d00eda80 | 0x7f52c3c24940 | 1308664 | 1202596 | 15561633 | 65536 | 106412699 | 896 | 56 | 0 | 163582 | 163582 | 0 | 0 | 952 | 0 | 2031616 | 2025171 | 56 | 6389 | 255557 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022793302747 | 16025473250864 | 16025473343185 | 16022793569331 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f52d00ed900 | 0x7f52c3c24980 | 1299880 | 1192604 | 15373904 | 65536 | 97128296 | 1064 | 56 | 0 | 162484 | 162484 | 0 | 0 | 1120 | 0 | 2424832 | 2418198 | 56 | 6578 | 338578 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022793618920 | 16025473376625 | 16025473469586 | 16022793886544 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f52d00ed780 | 0x7f52c3c249c0 | 1300520 | 1199022 | 15501216 | 65536 | 105412242 | 840 | 56 | 0 | 162564 | 162564 | 0 | 0 | 896 | 0 | 1835008 | 1829368 | 56 | 5584 | 361848 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022793943532 | 16025473502226 | 16025473594227 | 16022794207757 |
| 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 | 128 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f52d00ed600 | 0x7f52c3c24a00 | 2442904 | 2339640 | 30270761 | 65536 | 227944809 | 1008 | 56 | 0 | 305362 | 305362 | 0 | 0 | 1064 | 0 | 2228224 | 2223824 | 112 | 4288 | 419174 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022794257795 | 16025473627827 | 16025473806868 | 16022794609978 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f52d2570480 | 0x7f52c3c24a40 | 2441048 | 2339065 | 30306127 | 65536 | 221953974 | 952 | 56 | 0 | 305130 | 305130 | 0 | 0 | 1008 | 0 | 2097152 | 2091139 | 56 | 5957 | 393837 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022794659906 | 16025473840789 | 16025474021110 | 16022795010009 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f52d2570300 | 0x7f52c3c24a80 | 1305392 | 1199682 | 15499586 | 65536 | 103396769 | 896 | 56 | 0 | 163173 | 163173 | 0 | 0 | 952 | 0 | 2162688 | 2157820 | 0 | 4868 | 498975 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022795059348 | 16025474054070 | 16025474146231 | 16022795321802 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f52d2570180 | 0x7f52c3c24ac0 | 1292536 | 1185410 | 15284107 | 65536 | 100133997 | 1120 | 56 | 0 | 161566 | 161566 | 0 | 0 | 1176 | 0 | 2621440 | 2613158 | 56 | 8226 | 543581 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022795371731 | 16025474189431 | 16025474282872 | 16022795639605 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f52d2570000 | 0x7f52c3c24b00 | 1289256 | 1187326 | 15353570 | 65536 | 103093279 | 840 | 56 | 0 | 161156 | 161156 | 0 | 0 | 896 | 0 | 1966080 | 1960514 | 0 | 5566 | 491364 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022795697903 | 16025474316792 | 16025474408312 | 16022795954398 |
| 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 | 143 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f52d00ede80 | 0x7f52c3c24b40 | 2432512 | 2322302 | 30073711 | 65536 | 224534925 | 1064 | 56 | 0 | 304063 | 304063 | 0 | 0 | 1120 | 0 | 2359296 | 2352522 | 56 | 6718 | 365910 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022796004206 | 16025474441593 | 16025474620634 | 16022796357549 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f52d00edd00 | 0x7f52c3c24b80 | 2419528 | 2314224 | 29973630 | 65536 | 219998891 | 1008 | 56 | 0 | 302440 | 302440 | 0 | 0 | 1064 | 0 | 2228224 | 2220079 | 56 | 8089 | 348792 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022796406677 | 16025474655034 | 16025474833755 | 16022796758310 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f52d00edb80 | 0x7f52c3c24bc0 | 1304376 | 1200979 | 15494793 | 65536 | 102753367 | 1008 | 56 | 0 | 163046 | 163046 | 0 | 0 | 1064 | 0 | 2293760 | 2286948 | 112 | 6700 | 335715 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022796808328 | 16025474867356 | 16025474960956 | 16022797071273 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f52d00eda00 | 0x7f52c3c24c00 | 1304904 | 1196333 | 15425493 | 65536 | 103666012 | 1232 | 56 | 0 | 163112 | 163112 | 0 | 0 | 1288 | 0 | 2752512 | 2745671 | 56 | 6785 | 410308 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022797120122 | 16025474987676 | 16025475080637 | 16022797385546 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f52d00ed880 | 0x7f52c3c24c40 | 1306704 | 1200843 | 15532108 | 65536 | 107011277 | 952 | 56 | 0 | 163337 | 163337 | 0 | 0 | 1008 | 0 | 2031616 | 2024871 | 56 | 6689 | 366164 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022797442524 | 16025475115837 | 16025475207838 | 16022797698359 |
| 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 | 158 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f52d00ed700 | 0x7f52c3c24c80 | 2427232 | 2324418 | 30112092 | 65536 | 224321273 | 1064 | 56 | 0 | 303403 | 303403 | 0 | 0 | 1120 | 0 | 2490368 | 2485815 | 56 | 4497 | 491028 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022797749327 | 16025475232958 | 16025475411999 | 16022798099370 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f52d2570580 | 0x7f52c3c24cc0 | 2416184 | 2311768 | 29940331 | 65536 | 215408787 | 1064 | 56 | 0 | 302022 | 302022 | 0 | 0 | 1120 | 0 | 2359296 | 2353046 | 56 | 6194 | 256838 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022798148489 | 16025475437600 | 16025475616001 | 16022798505781 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f52d2570400 | 0x7f52c3c24d00 | 1303992 | 1197911 | 15452373 | 65536 | 101959788 | 1064 | 56 | 0 | 162998 | 162998 | 0 | 0 | 1120 | 0 | 2424832 | 2414043 | 56 | 10733 | 378573 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022798554720 | 16025475639041 | 16025475731362 | 16022798816364 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f52d2570280 | 0x7f52c3c24d40 | 1351136 | 1245506 | 16034443 | 65536 | 109754586 | 1344 | 56 | 0 | 168891 | 168891 | 0 | 0 | 1400 | 0 | 2949120 | 2932089 | 122 | 16909 | 258685 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022798866423 | 16025475756642 | 16025475854082 | 16022799131137 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f52d2570100 | 0x7f52c3c24d80 | 1297296 | 1195102 | 15444608 | 65536 | 102783656 | 952 | 56 | 0 | 162161 | 162161 | 0 | 0 | 1008 | 0 | 2162688 | 2157097 | 56 | 5535 | 268288 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022799188585 | 16025475885923 | 16025475978403 | 16022799448310 |
| 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 | 173 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f52d00edf80 | 0x7f52c3c24dc0 | 2409592 | 2306885 | 29874469 | 65536 | 222513177 | 1120 | 56 | 0 | 301198 | 301198 | 0 | 0 | 1176 | 0 | 2621440 | 2615418 | 0 | 6022 | 504848 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022799499739 | 16025476001603 | 16025476179365 | 16022799845131 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f52d00ede00 | 0x7f52c3c24e00 | 2432704 | 2323352 | 30075769 | 65536 | 215610282 | 1064 | 56 | 0 | 304087 | 304087 | 0 | 0 | 1120 | 0 | 2490368 | 2485279 | 56 | 5033 | 494011 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022799895960 | 16025476203685 | 16025476384806 | 16022800242462 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f52d00edc80 | 0x7f52c3c24e40 | 1302272 | 1194343 | 15395207 | 65536 | 97707914 | 1120 | 56 | 0 | 162783 | 162783 | 0 | 0 | 1176 | 0 | 2555904 | 2538764 | 56 | 17084 | 360641 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022800290461 | 16025476409446 | 16025476502567 | 16022800565455 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f52d00edb00 | 0x7f52c3c24e80 | 1401832 | 1295560 | 16698455 | 65536 | 113575848 | 1400 | 56 | 0 | 175228 | 175228 | 0 | 0 | 1456 | 0 | 3145728 | 3130925 | 73 | 14730 | 348507 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022800613044 | 16025476525927 | 16025476628328 | 16022800889338 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f52d00ed980 | 0x7f52c3c24ec0 | 1292376 | 1188757 | 15358652 | 65536 | 101207770 | 952 | 56 | 0 | 161546 | 161546 | 0 | 0 | 1008 | 0 | 2228224 | 2220799 | 56 | 7369 | 534104 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022800947336 | 16025476660488 | 16025476752969 | 16022801207771 |
| 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 | 188 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f52d00ed800 | 0x7f52c3c24f00 | 2440680 | 2335133 | 30219145 | 65536 | 223736867 | 1232 | 56 | 0 | 305084 | 305084 | 0 | 0 | 1288 | 0 | 2752512 | 2746297 | 56 | 6159 | 259803 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022801256550 | 16025476777609 | 16025476957290 | 16022801605902 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f52d00ed680 | 0x7f52c3c24f40 | 2411408 | 2303950 | 29824851 | 65536 | 223598598 | 1176 | 56 | 0 | 301425 | 301425 | 0 | 0 | 1232 | 0 | 2621440 | 2614625 | 56 | 6759 | 314567 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022801656631 | 16025476983210 | 16025477163211 | 16022802004443 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f52d2570500 | 0x7f52c3c24f80 | 1290704 | 1187928 | 15302418 | 65536 | 86571288 | 1120 | 56 | 0 | 161337 | 161337 | 0 | 0 | 1176 | 0 | 2686976 | 2678249 | 60 | 8667 | 489859 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022802054242 | 16025477187052 | 16025477280012 | 16022802330976 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f52d2570380 | 0x7f52c3c24fc0 | 1461176 | 1352597 | 17447178 | 65536 | 121186724 | 1456 | 56 | 0 | 182646 | 182646 | 0 | 0 | 1512 | 0 | 3342336 | 3318394 | 3 | 23939 | 509215 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022802379955 | 16025477303532 | 16025477408813 | 16022802659149 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f52d2570200 | 0x7f52c3c25000 | 1295344 | 1191393 | 15385780 | 65536 | 104333574 | 1064 | 56 | 0 | 161917 | 161917 | 0 | 0 | 1120 | 0 | 2359296 | 2350202 | 56 | 9038 | 325160 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022802729257 | 16025477440973 | 16025477533774 | 16022802971012 |
| 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 | 203 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f52d2570080 | 0x7f52c3c25040 | 2420632 | 2315927 | 29974206 | 65536 | 221887397 | 1288 | 56 | 0 | 302578 | 302578 | 0 | 0 | 1344 | 0 | 2883584 | 2875006 | 112 | 8466 | 257880 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022803018901 | 16025477558894 | 16025477737935 | 16022803374473 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f52d00edf00 | 0x7f52c3c25080 | 2406872 | 2303408 | 29819899 | 65536 | 220820622 | 1232 | 56 | 0 | 300858 | 300858 | 0 | 0 | 1288 | 0 | 2686976 | 2680884 | 56 | 6036 | 258989 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022803424002 | 16025477764496 | 16025477944497 | 16022803769014 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f52d00edd80 | 0x7f52c3c250c0 | 1292904 | 1189565 | 15334587 | 65536 | 97905351 | 1232 | 56 | 0 | 161612 | 161612 | 0 | 0 | 1288 | 0 | 2818048 | 2809123 | 56 | 8869 | 259774 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022803818543 | 16025477969617 | 16025478063058 | 16022804077317 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f52d00edc00 | 0x7f52c3c25100 | 1535312 | 1423319 | 18330287 | 65536 | 127106914 | 1568 | 56 | 0 | 191913 | 191913 | 0 | 0 | 1624 | 0 | 3538944 | 3513535 | 113 | 25296 | 259883 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022804127046 | 16025478131698 | 16025478244499 | 16022804406880 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f52d00eda80 | 0x7f52c3c25140 | 1290440 | 1189090 | 15350815 | 65536 | 103689777 | 1120 | 56 | 0 | 161304 | 161304 | 0 | 0 | 1176 | 0 | 2424832 | 2417740 | 56 | 7036 | 338344 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022804465028 | 16025478293619 | 16025478386100 | 16022804722083 |
| 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 | 218 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f52d00ed900 | 0x7f52c3c25180 | 2432832 | 2332500 | 30219640 | 65536 | 226359747 | 1344 | 56 | 0 | 304103 | 304103 | 0 | 0 | 1400 | 0 | 3014656 | 3002453 | 112 | 12091 | 261776 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022804770572 | 16025478410260 | 16025478590421 | 16022805119374 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f52d00ed780 | 0x7f52c3c251c0 | 2416216 | 2306501 | 29861223 | 65536 | 221788801 | 1288 | 56 | 0 | 302026 | 302026 | 0 | 0 | 1344 | 0 | 2818048 | 2811311 | 56 | 6681 | 390155 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022805167933 | 16025478613781 | 16025478794743 | 16022805521015 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f52d00ed600 | 0x7f52c3c25200 | 1303536 | 1196824 | 15418604 | 65536 | 99711175 | 1288 | 56 | 0 | 162941 | 162941 | 0 | 0 | 1344 | 0 | 2949120 | 2938755 | 56 | 10309 | 254996 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022805570474 | 16025478818903 | 16025478912344 | 16022805833728 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f52d2570480 | 0x7f52c3c25240 | 1595968 | 1492801 | 19198687 | 65536 | 131830325 | 1680 | 56 | 0 | 199495 | 199495 | 0 | 0 | 1736 | 0 | 3735552 | 3717624 | 124 | 17804 | 267800 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022805881137 | 16025478937464 | 16025479055385 | 16022806170711 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f52d2570300 | 0x7f52c3c25280 | 1286424 | 1180950 | 15241230 | 65536 | 97495535 | 1120 | 56 | 0 | 160802 | 160802 | 0 | 0 | 1176 | 0 | 2555904 | 2549820 | 56 | 6028 | 344977 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022806228779 | 16025479087545 | 16025479179705 | 16022806485114 |
| 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 | 233 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f52d2570180 | 0x7f52c3c252c0 | 2414992 | 2311585 | 29946264 | 65536 | 221766493 | 1344 | 56 | 0 | 301873 | 301873 | 0 | 0 | 1400 | 0 | 3145728 | 3137854 | 56 | 7818 | 261251 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022806533133 | 16025479204666 | 16025479384507 | 16022806887585 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f52d2570000 | 0x7f52c3c25300 | 2392120 | 2288475 | 29645617 | 65536 | 215543706 | 1344 | 56 | 0 | 299014 | 299014 | 0 | 0 | 1400 | 0 | 2949120 | 2940419 | 56 | 8645 | 396081 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022806938194 | 16025479408187 | 16025479587388 | 16022807284776 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f52d00ede80 | 0x7f52c3c25340 | 1288544 | 1186732 | 15283222 | 65536 | 101014043 | 1344 | 56 | 0 | 161067 | 161067 | 0 | 0 | 1400 | 0 | 3080192 | 3067397 | 56 | 12739 | 353479 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022807332935 | 16025479611388 | 16025479705469 | 16022807593439 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f52d00edd00 | 0x7f52c3c25380 | 1696752 | 1591244 | 20514634 | 65536 | 141672568 | 1736 | 56 | 0 | 212093 | 212093 | 0 | 0 | 1792 | 0 | 3932160 | 3914294 | 112 | 17754 | 402914 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022807641348 | 16025479729469 | 16025479853630 | 16022807938611 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f52d00edb80 | 0x7f52c3c253c0 | 1302472 | 1188110 | 15328433 | 65536 | 93156156 | 1176 | 56 | 0 | 162808 | 162808 | 0 | 0 | 1232 | 0 | 2621440 | 2613513 | 56 | 7871 | 339902 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022807994260 | 16025479886110 | 16025479979071 | 16022808249935 |
| 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 | 248 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f52d00eda00 | 0x7f52c3c25400 | 2382536 | 2274501 | 29468533 | 65536 | 220800337 | 1400 | 56 | 0 | 297816 | 297816 | 0 | 0 | 1456 | 0 | 3276800 | 3267664 | 0 | 9136 | 495916 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022808298493 | 16025480003871 | 16025480182272 | 16022808647066 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f52d00ed880 | 0x7f52c3c25440 | 2393864 | 2291548 | 29658756 | 65536 | 217868217 | 1400 | 56 | 0 | 299232 | 299232 | 0 | 0 | 1456 | 0 | 3080192 | 3069784 | 56 | 10352 | 257918 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022808698345 | 16025480206112 | 16025480386274 | 16022809045057 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f52d00ed700 | 0x7f52c3c25480 | 1288112 | 1185216 | 15272727 | 65536 | 103415185 | 1344 | 56 | 0 | 161013 | 161013 | 0 | 0 | 1400 | 0 | 3211264 | 3198608 | 0 | 12656 | 503186 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022809094776 | 16025480410114 | 16025480503395 | 16022809356730 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f52d2570580 | 0x7f52c3c254c0 | 1746312 | 1640427 | 21178811 | 65536 | 149508315 | 1792 | 56 | 0 | 218288 | 218288 | 0 | 0 | 1848 | 0 | 4128768 | 4109740 | 68 | 18960 | 488741 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022809406939 | 16025480526275 | 16025480655236 | 16022809703722 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f52d2570400 | 0x7f52c3c25500 | 1284200 | 1183438 | 15252143 | 65536 | 101157840 | 1176 | 56 | 0 | 160524 | 160524 | 0 | 0 | 1232 | 0 | 2752512 | 2744547 | 0 | 7965 | 505725 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022809761111 | 16025480687876 | 16025480780356 | 16022810019255 |
| 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 | 263 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f52d2570280 | 0x7f52c3c25540 | 2374520 | 2273708 | 29449033 | 65536 | 216620593 | 1512 | 56 | 0 | 296814 | 296814 | 0 | 0 | 1568 | 0 | 3407872 | 3399539 | 112 | 8221 | 400336 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022810068684 | 16025480805477 | 16025480984838 | 16022810430416 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f52d2570100 | 0x7f52c3c25580 | 2373128 | 2268644 | 29396219 | 65536 | 216420909 | 1456 | 56 | 0 | 296640 | 296640 | 0 | 0 | 1512 | 0 | 3211264 | 3201354 | 56 | 9854 | 356579 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022810480265 | 16025481009318 | 16025481188039 | 16022810827567 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f52d00edf80 | 0x7f52c3c255c0 | 1300440 | 1194087 | 15399213 | 65536 | 104026657 | 1456 | 56 | 0 | 162554 | 162554 | 0 | 0 | 1512 | 0 | 3276800 | 3262141 | 56 | 14603 | 257557 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022810876516 | 16025481211879 | 16025481305800 | 16022811140780 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f52d00ede00 | 0x7f52c3c25600 | 1834496 | 1729963 | 22350141 | 65536 | 161597897 | 1904 | 56 | 0 | 229311 | 229311 | 0 | 0 | 1960 | 0 | 4325376 | 4296470 | 165 | 28741 | 365440 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022811191019 | 16025481329640 | 16025481464841 | 16022811499272 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f52d00edc80 | 0x7f52c3c25640 | 1295544 | 1192297 | 15375931 | 65536 | 102826700 | 1232 | 56 | 0 | 161942 | 161942 | 0 | 0 | 1288 | 0 | 2818048 | 2810821 | 57 | 7170 | 374578 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022811555071 | 16025481497321 | 16025481590282 | 16022811832945 |
| 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 | 278 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f52d00edb00 | 0x7f52c3c25680 | 2377000 | 2271624 | 29407340 | 65536 | 216559023 | 1568 | 56 | 0 | 297124 | 297124 | 0 | 0 | 1624 | 0 | 3538944 | 3520658 | 112 | 18174 | 261166 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022811880744 | 16025481614442 | 16025481792843 | 16022812234746 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f52d00ed980 | 0x7f52c3c256c0 | 2369056 | 2268209 | 29393811 | 65536 | 216399702 | 1512 | 56 | 0 | 296131 | 296131 | 0 | 0 | 1568 | 0 | 3407872 | 3399147 | 56 | 8669 | 327433 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022812283225 | 16025481816844 | 16025481995725 | 16022812635907 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f52d00ed800 | 0x7f52c3c25700 | 1304152 | 1196443 | 15445957 | 65536 | 105708024 | 1512 | 56 | 0 | 163018 | 163018 | 0 | 0 | 1568 | 0 | 3407872 | 3396139 | 112 | 11621 | 256757 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022812684446 | 16025482019405 | 16025482114126 | 16022812948670 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f52d00ed680 | 0x7f52c3c25740 | 1902072 | 1801599 | 23274636 | 65536 | 171192221 | 2016 | 56 | 0 | 237758 | 237758 | 0 | 0 | 2072 | 0 | 4521984 | 4496402 | 74 | 25508 | 438594 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022812997479 | 16025482139246 | 16025482281007 | 16022813309762 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f52d2570500 | 0x7f52c3c25780 | 1300656 | 1185122 | 15270592 | 65536 | 102617145 | 1344 | 56 | 0 | 162581 | 162581 | 0 | 0 | 1400 | 0 | 3014656 | 3004074 | 112 | 10470 | 285401 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022813366801 | 16025482313327 | 16025482406928 | 16022813626555 |
| 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 | 293 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f52d2570380 | 0x7f52c3c257c0 | 2371672 | 2268521 | 29334711 | 65536 | 211898560 | 1680 | 56 | 0 | 296458 | 296458 | 0 | 0 | 1736 | 0 | 3801088 | 3779355 | 56 | 21677 | 261618 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022813676704 | 16025482431248 | 16025482610609 | 16022814021626 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f52d2570200 | 0x7f52c3c25800 | 2371944 | 2268036 | 29369317 | 65536 | 213787473 | 1624 | 56 | 0 | 296492 | 296492 | 0 | 0 | 1680 | 0 | 3670016 | 3655775 | 112 | 14129 | 272207 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022814070675 | 16025482634609 | 16025482814450 | 16022814423167 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f52d2570080 | 0x7f52c3c25840 | 1354008 | 1249680 | 16128812 | 65536 | 111656734 | 1568 | 56 | 0 | 169250 | 169250 | 0 | 0 | 1624 | 0 | 3670016 | 3643592 | 0 | 26424 | 483773 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022814472476 | 16025482838451 | 16025482937491 | 16022814747710 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f52d00edf00 | 0x7f52c3c25880 | 2069608 | 1967645 | 25419639 | 65536 | 185901138 | 2128 | 56 | 0 | 258700 | 258700 | 0 | 0 | 2184 | 0 | 4915200 | 4879561 | 94 | 35545 | 491353 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022814795769 | 16025482961171 | 16025483114453 | 16022815125041 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f52d00edd80 | 0x7f52c3c258c0 | 1286064 | 1174679 | 15130631 | 65536 | 98857137 | 1400 | 56 | 0 | 160757 | 160757 | 0 | 0 | 1456 | 0 | 3145728 | 3130411 | 67 | 15250 | 587352 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022815181770 | 16025483146773 | 16025483239573 | 16022815436525 |
| 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 | 308 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f52d00edc00 | 0x7f52c3c25900 | 2371688 | 2265688 | 29315797 | 65536 | 210988962 | 1736 | 56 | 0 | 296460 | 296460 | 0 | 0 | 1792 | 0 | 4063232 | 4052764 | 0 | 10468 | 492196 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022815486603 | 16025483263414 | 16025483442295 | 16022815833166 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f52d00eda80 | 0x7f52c3c25940 | 2369768 | 2266387 | 29350998 | 65536 | 215882744 | 1736 | 56 | 0 | 296220 | 296220 | 0 | 0 | 1792 | 0 | 3932160 | 3915837 | 56 | 16267 | 373095 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022815883475 | 16025483466775 | 16025483646936 | 16022816230927 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f52d00ed900 | 0x7f52c3c25980 | 1437656 | 1332201 | 17187782 | 65536 | 120092201 | 1736 | 56 | 0 | 179706 | 179706 | 0 | 0 | 1792 | 0 | 3932160 | 3909098 | 56 | 23006 | 396742 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022816280436 | 16025483670616 | 16025483776537 | 16022816555990 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f52d00ed780 | 0x7f52c3c259c0 | 2224640 | 2122148 | 27424068 | 65536 | 201808430 | 2352 | 56 | 0 | 278079 | 278079 | 0 | 0 | 2408 | 0 | 5308416 | 5274458 | 95 | 33863 | 308146 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022816605029 | 16025483800217 | 16025483967578 | 16022816941401 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f52d00ed600 | 0x7f52c3c25a00 | 1295000 | 1183157 | 15256297 | 65536 | 104116998 | 1512 | 56 | 0 | 161874 | 161874 | 0 | 0 | 1568 | 0 | 3342336 | 3328541 | 113 | 13682 | 590366 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022816999410 | 16025484000539 | 16025484094459 | 16022817265224 |
| 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 | 323 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f52d2570480 | 0x7f52c3c25a40 | 2366776 | 2258036 | 29218072 | 65536 | 209444414 | 1904 | 56 | 0 | 295846 | 295846 | 0 | 0 | 1960 | 0 | 4325376 | 4309301 | 56 | 16019 | 340715 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022817313293 | 16025484118939 | 16025484298621 | 16022817662385 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f52d2570300 | 0x7f52c3c25a80 | 2369944 | 2264635 | 29305943 | 65536 | 214431322 | 1848 | 56 | 0 | 296242 | 296242 | 0 | 0 | 1904 | 0 | 4194304 | 4177628 | 112 | 16564 | 406794 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022817713214 | 16025484322941 | 16025484504862 | 16022818062516 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f52d2570180 | 0x7f52c3c25ac0 | 1488168 | 1382625 | 17842265 | 65536 | 125601204 | 1792 | 56 | 0 | 186020 | 186020 | 0 | 0 | 1848 | 0 | 4194304 | 4174756 | 0 | 19548 | 523301 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022818113295 | 16025484527902 | 16025484636703 | 16022818398029 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f52d2570000 | 0x7f52c3c25b00 | 2377616 | 2277014 | 29422927 | 65536 | 216390778 | 2464 | 56 | 0 | 297201 | 297201 | 0 | 0 | 2520 | 0 | 5701632 | 5665388 | 81 | 36163 | 505251 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022818447238 | 16025484660863 | 16025484839584 | 16022818796260 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f52d00ede80 | 0x7f52c3c25b40 | 1369736 | 1261626 | 16252305 | 65536 | 111541508 | 1624 | 56 | 0 | 171216 | 171216 | 0 | 0 | 1680 | 0 | 3735552 | 3720690 | 13 | 14849 | 585611 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022818852749 | 16025484872065 | 16025484971745 | 16022819113723 |
| 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 | 338 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f52d00edd00 | 0x7f52c3c25b80 | 2378528 | 2270374 | 29273729 | 65536 | 202238888 | 2128 | 56 | 0 | 297315 | 297315 | 0 | 0 | 2184 | 0 | 4849664 | 4825050 | 120 | 24494 | 294701 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022819163012 | 16025484996066 | 16025485178307 | 16022819512254 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f52d00edb80 | 0x7f52c3c25bc0 | 2371560 | 2258553 | 29175154 | 65536 | 199256865 | 2072 | 56 | 0 | 296444 | 296444 | 0 | 0 | 2128 | 0 | 4718592 | 4694904 | 112 | 23576 | 258278 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022819559303 | 16025485201507 | 16025485384548 | 16022819911285 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f52d00eda00 | 0x7f52c3c25c00 | 1651632 | 1544919 | 19917068 | 65536 | 142142063 | 2016 | 56 | 0 | 206453 | 206453 | 0 | 0 | 2072 | 0 | 4718592 | 4682044 | 1 | 36547 | 509487 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022819960054 | 16025485410148 | 16025485531429 | 16022820252518 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f52d00ed880 | 0x7f52c3c25c40 | 2713208 | 2607216 | 33722743 | 65536 | 252149207 | 2800 | 56 | 0 | 339150 | 339150 | 0 | 0 | 2856 | 0 | 6488064 | 6439775 | 166 | 48123 | 535777 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022820301227 | 16025485554789 | 16025485759431 | 16022820694418 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f52d00ed700 | 0x7f52c3c25c80 | 1472040 | 1368329 | 17654503 | 65536 | 124098462 | 1848 | 56 | 0 | 184004 | 184004 | 0 | 0 | 1904 | 0 | 4128768 | 4109141 | 72 | 19555 | 591382 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022820732257 | 16025485801351 | 16025485909512 | 16022821011741 |
| 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 | 353 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f52d2570580 | 0x7f52c3c25cc0 | 2385872 | 2260020 | 29172796 | 65536 | 191972934 | 2296 | 56 | 0 | 298233 | 298233 | 0 | 0 | 2352 | 0 | 5373952 | 5346447 | 56 | 27449 | 511081 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022821060560 | 16025485934472 | 16025486116393 | 16022821413982 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f52d2570400 | 0x7f52c3c25d00 | 2382136 | 2267639 | 29300962 | 65536 | 198105915 | 2296 | 56 | 0 | 297766 | 297766 | 0 | 0 | 2352 | 0 | 5242880 | 5212141 | 112 | 30627 | 269093 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022821463481 | 16025486141993 | 16025486326475 | 16022821816003 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f52d2570280 | 0x7f52c3c25d40 | 1787176 | 1682251 | 21758479 | 65536 | 160417302 | 2240 | 56 | 0 | 223396 | 223396 | 0 | 0 | 2296 | 0 | 5242880 | 5215835 | 0 | 27045 | 496068 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022821863492 | 16025486350315 | 16025486483276 | 16022822175665 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f52d2570100 | 0x7f52c3c25d80 | 3026200 | 2923136 | 37796003 | 65536 | 281164904 | 3136 | 56 | 0 | 378274 | 378274 | 0 | 0 | 3192 | 0 | 7274496 | 7230492 | 90 | 43914 | 484251 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022822226674 | 16025486506636 | 16025486737198 | 16022822648365 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f52d00edf80 | 0x7f52c3c25dc0 | 1674008 | 1574664 | 20331555 | 65536 | 145035901 | 2128 | 56 | 0 | 209250 | 209250 | 0 | 0 | 2184 | 0 | 4915200 | 4884081 | 73 | 31046 | 575758 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022822688024 | 16025486778158 | 16025486903279 | 16022822973867 |
| 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 | 368 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f52d00ede00 | 0x7f52c3c25e00 | 2446616 | 2324128 | 29942822 | 65536 | 199800215 | 2800 | 56 | 0 | 305826 | 305826 | 0 | 0 | 2856 | 0 | 6422528 | 6380098 | 202 | 42228 | 486110 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022823021966 | 16025486927599 | 16025487119120 | 16022823418348 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f52d00edc80 | 0x7f52c3c25e40 | 2504264 | 2358380 | 30420292 | 65536 | 177739999 | 2744 | 56 | 0 | 313032 | 313032 | 0 | 0 | 2800 | 0 | 6291456 | 6253210 | 56 | 38190 | 256743 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022823448397 | 16025487142320 | 16025487336242 | 16022823852368 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f52d00edb00 | 0x7f52c3c25e80 | 2114968 | 2009418 | 25993936 | 65536 | 193778300 | 2688 | 56 | 0 | 264370 | 264370 | 0 | 0 | 2744 | 0 | 6291456 | 6246522 | 57 | 44877 | 496716 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022823863298 | 16025487360562 | 16025487518963 | 16022824200060 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f52d00ed980 | 0x7f52c3c25ec0 | 3670888 | 3564262 | 46158014 | 65536 | 348171686 | 3752 | 56 | 0 | 458860 | 458860 | 0 | 0 | 3808 | 0 | 8847360 | 8785234 | 125 | 62001 | 497644 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022824249599 | 16025487542803 | 16025487823925 | 16022824716069 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f52d00ed800 | 0x7f52c3c25f00 | 1943776 | 1841086 | 23793416 | 65536 | 175292074 | 2520 | 56 | 0 | 242971 | 242971 | 0 | 0 | 2576 | 0 | 5701632 | 5662370 | 141 | 39121 | 586884 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022824759308 | 16025487864245 | 16025488010646 | 16022825071931 |
| 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 | 383 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f52d00ed680 | 0x7f52c3c25f40 | 2687880 | 2572501 | 33133235 | 65536 | 211272360 | 3192 | 56 | 0 | 335984 | 335984 | 0 | 0 | 3248 | 0 | 7471104 | 7431340 | 81 | 39683 | 581183 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022825122120 | 16025488035766 | 16025488244408 | 16022825513641 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f52d2570500 | 0x7f52c3c25f80 | 2632568 | 2518014 | 32494431 | 65536 | 219959875 | 3192 | 56 | 0 | 329070 | 329070 | 0 | 0 | 3248 | 0 | 7340032 | 7306438 | 112 | 33482 | 431727 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022825548050 | 16025488276568 | 16025488488570 | 16022825938152 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f52d2570380 | 0x7f52c3c25fc0 | 2429480 | 2327008 | 30127077 | 65536 | 228590515 | 3136 | 56 | 0 | 303684 | 303684 | 0 | 0 | 3192 | 0 | 7340032 | 7289593 | 56 | 50383 | 540803 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022825973531 | 16025488521370 | 16025488704731 | 16022826338873 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f52d2570200 | 0x7f52c3c26000 | 4328424 | 4222736 | 54674048 | 65536 | 418409617 | 4424 | 56 | 0 | 541052 | 541052 | 0 | 0 | 4480 | 0 | 10420224 | 10342256 | 158 | 77810 | 522944 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022826388422 | 16025488728891 | 16025489061534 | 16022826930790 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f52d2570080 | 0x7f52c3c26040 | 2159632 | 2059023 | 26615188 | 65536 | 197418358 | 2856 | 56 | 0 | 269953 | 269953 | 0 | 0 | 2912 | 0 | 6488064 | 6440056 | 198 | 47810 | 583030 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022826952169 | 16025489098014 | 16025489262495 | 16022827293281 |
| 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 | 398 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f52d00edf00 | 0x7f52c3c26080 | 2938728 | 2822125 | 36349768 | 65536 | 247039783 | 3696 | 56 | 0 | 367340 | 367340 | 0 | 0 | 3752 | 0 | 8519680 | 8458531 | 199 | 60950 | 589310 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022827342980 | 16025489286495 | 16025489518497 | 16022827778051 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f52d00edd80 | 0x7f52c3c260c0 | 2932488 | 2821163 | 36281038 | 65536 | 255423186 | 3640 | 56 | 0 | 366560 | 366560 | 0 | 0 | 3696 | 0 | 8388608 | 8333631 | 112 | 54865 | 367440 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022827789490 | 16025489551777 | 16025489780579 | 16022828239280 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f52d00edc00 | 0x7f52c3c26100 | 2758224 | 2656246 | 34412233 | 65536 | 261934453 | 3584 | 56 | 0 | 344777 | 344777 | 0 | 0 | 3640 | 0 | 8388608 | 8325248 | 56 | 63304 | 495566 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022828249910 | 16025489810339 | 16025490020100 | 16022828675381 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f52d00eda80 | 0x7f52c3c26140 | 4978752 | 4870709 | 63076997 | 65536 | 478325866 | 5096 | 56 | 0 | 622343 | 622343 | 0 | 0 | 5152 | 0 | 11993088 | 11911912 | 133 | 81043 | 491390 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022828687710 | 16025490053540 | 16025490436583 | 16022829288997 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f52d00ed900 | 0x7f52c3c26180 | 2417688 | 2310537 | 29900009 | 65536 | 223147493 | 3192 | 56 | 0 | 302210 | 302210 | 0 | 0 | 3248 | 0 | 7274496 | 7213248 | 230 | 61018 | 587319 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022829307946 | 16025490478503 | 16025490662345 | 16022829664388 |
| 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 | 413 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f52d00ed780 | 0x7f52c3c261c0 | 3200592 | 3095371 | 39927658 | 65536 | 277714146 | 4088 | 56 | 0 | 400073 | 400073 | 0 | 0 | 4144 | 0 | 9568256 | 9503411 | 219 | 64626 | 578736 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022829714517 | 16025490687305 | 16025490938987 | 16022830181907 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f52d00ed600 | 0x7f52c3c26200 | 3129000 | 3024755 | 39163076 | 65536 | 297249103 | 4088 | 56 | 0 | 391124 | 391124 | 0 | 0 | 4144 | 0 | 9437184 | 9382377 | 112 | 54695 | 256119 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022830193147 | 16025490977867 | 16025491225548 | 16022830636927 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f52d2570480 | 0x7f52c3c26240 | 3088936 | 2988748 | 38724216 | 65536 | 297331058 | 3976 | 56 | 0 | 386116 | 386116 | 0 | 0 | 4032 | 0 | 9437184 | 9347084 | 61 | 90039 | 485719 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022830670256 | 16025491254989 | 16025491490190 | 16022831096807 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f52d2570300 | 0x7f52c3c26280 | 5716824 | 5604861 | 72576511 | 65536 | 553632381 | 1960 | 56 | 0 | 714602 | 714602 | 0 | 0 | 2016 | 0 | 16056320 | 16051482 | 57 | 4781 | 584740 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022831130036 | 16025491520911 | 16025491970834 | 16022831760822 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f52d2570180 | 0x7f52c3c262c0 | 2924232 | 2819019 | 36479764 | 65536 | 277980006 | 3864 | 56 | 0 | 365528 | 365528 | 0 | 0 | 3920 | 0 | 8847360 | 8769097 | 297 | 77966 | 588757 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022831806171 | 16025492009074 | 16025492231475 | 16022832212352 |
| 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 | 428 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f52d2570000 | 0x7f52c3c26300 | 3746680 | 3646583 | 47222355 | 65536 | 358319499 | 4984 | 56 | 0 | 468334 | 468334 | 0 | 0 | 5040 | 0 | 11665408 | 11596091 | 112 | 69205 | 586575 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022832244811 | 16025492267476 | 16025492565878 | 16022832726371 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f52d00ede80 | 0x7f52c3c26340 | 3777064 | 3667339 | 47436177 | 65536 | 350150514 | 4984 | 56 | 0 | 472132 | 472132 | 0 | 0 | 5040 | 0 | 11468800 | 11393410 | 308 | 75082 | 264949 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022832760500 | 16025492600118 | 16025492899000 | 16022833244269 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f52d00edd00 | 0x7f52c3c26380 | 3829528 | 3721181 | 48176175 | 65536 | 364705446 | 1736 | 56 | 0 | 478690 | 478690 | 0 | 0 | 1792 | 0 | 14090240 | 14086473 | 0 | 3767 | 575632 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022833277078 | 16025492934520 | 16025493228602 | 16022833756548 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f52d00edb80 | 0x7f52c3c263c0 | 6998832 | 6897334 | 89350030 | 65536 | 683599009 | 2296 | 56 | 0 | 874853 | 874853 | 0 | 0 | 2352 | 0 | 19202048 | 19195241 | 112 | 6695 | 586879 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022833792447 | 16025493263163 | 16025493816926 | 16022834535240 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f52d00eda00 | 0x7f52c3c26400 | 3398512 | 3293610 | 42659380 | 65536 | 323593269 | 4424 | 56 | 0 | 424813 | 424813 | 0 | 0 | 4480 | 0 | 10420224 | 10349883 | 57 | 70284 | 583266 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022834573730 | 16025493854847 | 16025494116928 | 16022835027599 |
| 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 | 443 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f52d00ed880 | 0x7f52c3c26440 | 4435176 | 4331385 | 55954780 | 65536 | 411676747 | 5936 | 56 | 0 | 554396 | 554396 | 0 | 0 | 5992 | 0 | 13762560 | 13660240 | 590 | 101730 | 588223 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022835061079 | 16025494151169 | 16025494502691 | 16022835600007 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f52d00ed700 | 0x7f52c3c26480 | 4423288 | 4312252 | 55786086 | 65536 | 421630939 | 5880 | 56 | 0 | 552910 | 552910 | 0 | 0 | 5936 | 0 | 13565952 | 13462136 | 562 | 103254 | 278533 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022835635906 | 16025494537251 | 16025494887014 | 16022836172154 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f52d2570580 | 0x7f52c3c264c0 | 4470392 | 4361853 | 56478335 | 65536 | 425767512 | 2408 | 56 | 0 | 558798 | 558798 | 0 | 0 | 2464 | 0 | 15466496 | 15454988 | 1 | 11507 | 601028 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022836207253 | 16025494921574 | 16025495266536 | 16022836748241 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f52d2570400 | 0x7f52c3c26500 | 8306704 | 8198171 | 106206271 | 65536 | 814960068 | 2632 | 56 | 0 | 1038337 | 1038337 | 0 | 0 | 2688 | 0 | 22347776 | 22336628 | 112 | 11036 | 584173 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022836772521 | 16025495302697 | 16025495959501 | 16022837614172 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f52d2570280 | 0x7f52c3c26540 | 5734816 | 5625156 | 72871617 | 65536 | 554299247 | 2408 | 56 | 0 | 716851 | 716851 | 0 | 0 | 2464 | 0 | 20250624 | 20242684 | 115 | 7825 | 627526 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022837656761 | 16025496000301 | 16025496443824 | 16022838302167 |
| 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 | 458 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f52d2570100 | 0x7f52c3c26580 | 5757536 | 5649549 | 73165448 | 65536 | 559962612 | 2464 | 56 | 0 | 719691 | 719691 | 0 | 0 | 2520 | 0 | 20447232 | 20437892 | 57 | 9283 | 584187 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022838314107 | 16025496477585 | 16025496939028 | 16022838996641 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f52d00edf80 | 0x7f52c3c265c0 | 5739016 | 5632883 | 72980760 | 65536 | 559400526 | 2408 | 56 | 0 | 717376 | 717376 | 0 | 0 | 2464 | 0 | 19595264 | 19585235 | 113 | 9916 | 258631 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022839007741 | 16025496972468 | 16025497430391 | 16022839687016 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f52d00ede00 | 0x7f52c3c26600 | 5775688 | 5665697 | 73363284 | 65536 | 561677588 | 2464 | 56 | 0 | 721960 | 721960 | 0 | 0 | 2520 | 0 | 20381696 | 20373253 | 113 | 8330 | 583183 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022839697246 | 16025497466072 | 16025497913435 | 16022840376861 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f52d00edc80 | 0x7f52c3c26640 | 10911464 | 10803237 | 139966562 | 65536 | 1082283162 | 1960 | 56 | 0 | 1363932 | 1363932 | 0 | 0 | 2016 | 0 | 31522816 | 31517071 | 57 | 5688 | 592831 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022840387131 | 16025497941755 | 16025498807041 | 16022841470637 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f52d00edb00 | 0x7f52c3c26680 | 10920224 | 10816579 | 140188575 | 65536 | 1086830394 | 2408 | 56 | 0 | 1365027 | 1365027 | 0 | 0 | 2464 | 0 | 38993920 | 38986056 | 112 | 7752 | 592461 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022841491346 | 16025498850721 | 16025499700967 | 16022842575022 |
| 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 | 473 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f52d00ed980 | 0x7f52c3c266c0 | 10947480 | 10833824 | 140390244 | 65536 | 1083991972 | 2464 | 56 | 0 | 1368434 | 1368434 | 0 | 0 | 2520 | 0 | 39124992 | 39116367 | 112 | 8513 | 576361 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022842586742 | 16025499736167 | 16025500617773 | 16022843713697 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f52d00ed800 | 0x7f52c3c26700 | 10935232 | 10827837 | 140307008 | 65536 | 1084091149 | 2408 | 56 | 0 | 1366903 | 1366903 | 0 | 0 | 2464 | 0 | 38469632 | 38461675 | 57 | 7900 | 378665 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022843724736 | 16025500654574 | 16025501530900 | 16022844859531 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f52d00ed680 | 0x7f52c3c26740 | 10966032 | 10856996 | 140650119 | 65536 | 1087126323 | 2464 | 56 | 0 | 1370753 | 1370753 | 0 | 0 | 2520 | 0 | 39059456 | 39050494 | 114 | 8848 | 588305 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022844870391 | 16025501564020 | 16025502420026 | 16022845994406 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f52d2570500 | 0x7f52c3c26780 | 21267000 | 21161613 | 274213592 | 65536 | 2133487973 | 1960 | 56 | 0 | 2658374 | 2658374 | 0 | 0 | 2016 | 0 | 60489728 | 60483258 | 112 | 6358 | 590641 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022846005945 | 16025502455866 | 16025504150438 | 16022847977452 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f52d2570380 | 0x7f52c3c267c0 | 21312688 | 21204913 | 274773047 | 65536 | 2135871519 | 2408 | 56 | 0 | 2664085 | 2664085 | 0 | 0 | 2464 | 0 | 77266944 | 77259742 | 57 | 7145 | 583946 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022847996701 | 16025504216518 | 16025505877170 | 16022849910219 |
| 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 | 488 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f52d2570200 | 0x7f52c3c26800 | 21312920 | 21209349 | 274868675 | 65536 | 2138350875 | 2464 | 56 | 0 | 2664114 | 2664114 | 0 | 0 | 2520 | 0 | 77398016 | 77388643 | 112 | 9261 | 585137 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 0 | 131072 | 0 | 16022849921429 | 16025505953650 | 16025507675742 | 16022851920684 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f52d2570080 | 0x7f52c3c26840 | 21315880 | 21203155 | 274737679 | 65536 | 2133617489 | 2408 | 56 | 0 | 2664484 | 2664484 | 0 | 0 | 2464 | 0 | 76218368 | 76210398 | 112 | 7858 | 258565 | 0 | 0 | 65536 | 63800 | 56 | 1680 | 0 | 0 | 65536 | 16022851932384 | 16025507735582 | 16025509447434 | 16022853916530 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f52d00edf00 | 0x7f52c3c26880 | 21339768 | 21234842 | 275161772 | 65536 | 2135596206 | 2464 | 56 | 0 | 2667470 | 2667470 | 0 | 0 | 2520 | 0 | 77332480 | 77322954 | 57 | 9469 | 590751 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022853927820 | 16025509506475 | 16025511176246 | 16022855876807 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 143633 | 143633 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f52d00edd80 | 0x7f52c3c268c0 | 42014136 | 41901998 | 543065855 | 65536 | 4233457226 | 1960 | 56 | 0 | 5251766 | 5251766 | 0 | 0 | 2016 | 0 | 120258560 | 120253115 | 112 | 5333 | 588622 | 0 | 0 | 131072 | 129336 | 56 | 1680 | 65536 | 65536 | 0 | 16022855888126 | 16025511236567 | 16025514590990 | 16022859532115 |