63 KiB
63 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_fillBuffer.kd | 0 | 0 | 0 | 856407 | 856412 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fa1ea204180 | 4041424 | 3834729 | 57369470 | 524288 | 363773308 | 336 | 144 | 0 | 505177 | 505177 | 0 | 0 | 480 | 0 | 6291456 | 6289306 | 96 | 2549 | 2002436 | 0 | 0 | 4194304 | 4189867 | 144 | 4293 | 2097152 | 524288 | 1572864 | 12074982604635657 | 12074986773041058 | 12074986773364415 | 12074982846593824 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 856407 | 856412 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fa1ea235100 | 226080 | 76798 | 1088889 | 512 | 1161151 | 432 | 48 | 0 | 28259 | 28259 | 0 | 0 | 480 | 0 | 8192 | 6567 | 48 | 1577 | 1118 | 0 | 0 | 512 | 0 | 48 | 464 | 0 | 512 | 0 | 12074982860884361 | 12074986788051185 | 12074986788058225 | 12074982861244270 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fa2f5f14900 | 0x7fa1ea235140 | 1792800 | 1624185 | 24108712 | 65536 | 128855123 | 384 | 48 | 0 | 224099 | 224099 | 0 | 0 | 432 | 0 | 917504 | 914532 | 48 | 7542 | 235921 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074982861317877 | 12074986788122704 | 12074986788249903 | 12074982861699696 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fa2f5f14800 | 0x7fa1ea235180 | 3146256 | 2985140 | 44527426 | 65536 | 273866128 | 480 | 48 | 0 | 393281 | 393281 | 0 | 0 | 528 | 0 | 1245184 | 1242920 | 56 | 5064 | 181688 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074982861784865 | 12074986788308463 | 12074986788551821 | 12074982862299591 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fa2f5f14700 | 0x7fa1ea2351c0 | 3229024 | 3041710 | 45282820 | 65536 | 219942227 | 384 | 48 | 0 | 403627 | 403627 | 0 | 0 | 432 | 0 | 983040 | 979773 | 48 | 3449 | 196174 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074982862333274 | 12074986788681100 | 12074986788928298 | 12074982862874760 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fa2f5f14600 | 0x7fa1ea235200 | 1844816 | 1674996 | 24789273 | 65536 | 123580204 | 432 | 48 | 0 | 230601 | 230601 | 0 | 0 | 480 | 0 | 1048576 | 1045696 | 48 | 7403 | 177099 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074982862904495 | 12074986789063337 | 12074986789189256 | 12074982863256780 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fa2f5f14500 | 0x7fa1ea235240 | 1811936 | 1640906 | 24302737 | 65536 | 116753371 | 432 | 48 | 0 | 226491 | 226491 | 0 | 0 | 480 | 0 | 983040 | 980302 | 48 | 7452 | 181865 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 65536 | 0 | 12074982863323975 | 12074986789232456 | 12074986789357415 | 12074982863666381 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fa2f5f14400 | 0x7fa1ea235280 | 1727120 | 1568898 | 23189734 | 65536 | 145531199 | 432 | 48 | 0 | 215889 | 215889 | 0 | 0 | 480 | 0 | 1048576 | 1046535 | 48 | 4728 | 201309 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982863761378 | 12074986789426055 | 12074986789550374 | 12074982864086211 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fa2f5f14300 | 0x7fa1ea2352c0 | 3271328 | 3093792 | 46089727 | 65536 | 296968953 | 624 | 48 | 0 | 408915 | 408915 | 0 | 0 | 672 | 0 | 1572864 | 1568417 | 111 | 6948 | 185651 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982864152455 | 12074986789591813 | 12074986789873091 | 12074982864664646 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fa2f5f14a00 | 0x7fa1ea235300 | 3221776 | 3057498 | 45663685 | 65536 | 347127245 | 480 | 48 | 0 | 402721 | 402721 | 0 | 0 | 528 | 0 | 1179648 | 1177217 | 48 | 3885 | 186689 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982864702998 | 12074986790002370 | 12074986790245248 | 12074982865223946 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fa2f5f14900 | 0x7fa1ea235340 | 1748960 | 1560592 | 23065526 | 65536 | 156100828 | 480 | 48 | 0 | 218619 | 218619 | 0 | 0 | 528 | 0 | 1114112 | 1111942 | 48 | 5060 | 198425 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982865251968 | 12074986790374847 | 12074986790499647 | 12074982865597390 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fa2f5f14800 | 0x7fa1ea235380 | 1710480 | 1548323 | 22947821 | 65536 | 145782254 | 480 | 48 | 0 | 213809 | 213809 | 0 | 0 | 528 | 0 | 1114112 | 1112150 | 48 | 4561 | 201924 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982865664134 | 12074986790540286 | 12074986790665245 | 12074982865991572 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fa2f5f14700 | 0x7fa1ea2353c0 | 1714464 | 1540391 | 22822514 | 65536 | 153771320 | 480 | 48 | 0 | 214307 | 214307 | 0 | 0 | 528 | 0 | 1179648 | 1177189 | 48 | 4583 | 201297 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982866071962 | 12074986790718205 | 12074986790843324 | 12074982866392137 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fa2f5f14600 | 0x7fa1ea235400 | 3234960 | 3057679 | 45495016 | 65536 | 252163204 | 720 | 48 | 0 | 404369 | 404369 | 0 | 0 | 768 | 0 | 1835008 | 1831351 | 96 | 8036 | 185281 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982866456366 | 12074986790884764 | 12074986791133722 | 12074982866976823 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fa2f5f14500 | 0x7fa1ea235440 | 3234976 | 3066124 | 45722476 | 65536 | 330962519 | 528 | 48 | 0 | 404371 | 404371 | 0 | 0 | 576 | 0 | 1310720 | 1308448 | 48 | 3532 | 184665 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982867009805 | 12074986791266201 | 12074986791548759 | 12074982867548736 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fa2f5f14400 | 0x7fa1ea235480 | 1720080 | 1561126 | 23156498 | 65536 | 154968610 | 528 | 48 | 0 | 215009 | 215009 | 0 | 0 | 576 | 0 | 1245184 | 1242697 | 48 | 4870 | 249763 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982867573973 | 12074986791651318 | 12074986791775637 | 12074982867915718 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fa2f5f14300 | 0x7fa1ea2354c0 | 1749472 | 1583655 | 23442894 | 65536 | 139305948 | 528 | 48 | 0 | 218683 | 218683 | 0 | 0 | 576 | 0 | 1310720 | 1308618 | 48 | 4921 | 207271 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982867989125 | 12074986791818197 | 12074986791943476 | 12074982868315411 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fa2f5f14a00 | 0x7fa1ea235500 | 1711120 | 1547888 | 22927568 | 65536 | 152212096 | 528 | 48 | 0 | 213889 | 213889 | 0 | 0 | 576 | 0 | 1310720 | 1308316 | 48 | 4575 | 229007 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982868393987 | 12074986791995315 | 12074986792119794 | 12074982868712589 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fa2f5f14900 | 0x7fa1ea235540 | 3232096 | 3055591 | 45574845 | 65536 | 263306351 | 816 | 48 | 0 | 404011 | 404011 | 0 | 0 | 864 | 0 | 2097152 | 2092621 | 96 | 9480 | 189409 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982868778011 | 12074986792163314 | 12074986792411952 | 12074982869300932 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fa2f5f14800 | 0x7fa1ea235580 | 3240272 | 3077809 | 45819252 | 65536 | 291449214 | 576 | 48 | 0 | 405033 | 405033 | 0 | 0 | 624 | 0 | 1441792 | 1439450 | 48 | 3636 | 183577 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982869327722 | 12074986792513712 | 12074986792757550 | 12074982869859260 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fa2f5f14700 | 0x7fa1ea2355c0 | 1728992 | 1561573 | 23060272 | 65536 | 138662430 | 576 | 48 | 0 | 216123 | 216123 | 0 | 0 | 624 | 0 | 1376256 | 1373428 | 48 | 5220 | 235824 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982869886701 | 12074986792855949 | 12074986792980908 | 12074982870239326 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fa2f5f14600 | 0x7fa1ea235600 | 1687824 | 1528004 | 22627147 | 65536 | 150702809 | 624 | 48 | 0 | 210977 | 210977 | 0 | 0 | 672 | 0 | 1507328 | 1502931 | 48 | 6555 | 192362 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982870305599 | 12074986793029708 | 12074986793154667 | 12074982870634030 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fa2f5f14500 | 0x7fa1ea235640 | 1727328 | 1562722 | 23177560 | 65536 | 142527898 | 576 | 48 | 0 | 215915 | 215915 | 0 | 0 | 624 | 0 | 1441792 | 1438833 | 48 | 5245 | 208675 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982870711955 | 12074986793213706 | 12074986793337865 | 12074982871024405 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fa2f5f14400 | 0x7fa1ea235680 | 3199504 | 3042899 | 45408334 | 65536 | 340372614 | 912 | 48 | 0 | 399937 | 399937 | 0 | 0 | 960 | 0 | 2359296 | 2354950 | 118 | 7018 | 179685 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982871090157 | 12074986793386025 | 12074986793632903 | 12074982871604373 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fa2f5f14300 | 0x7fa1ea2356c0 | 3218592 | 3040642 | 45271321 | 65536 | 288308385 | 624 | 48 | 0 | 402323 | 402323 | 0 | 0 | 672 | 0 | 1572864 | 1570495 | 48 | 3593 | 186880 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982871632906 | 12074986793740742 | 12074986793986981 | 12074982872159745 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fa2f5f14a00 | 0x7fa1ea235700 | 1743632 | 1582642 | 23421419 | 65536 | 137577671 | 624 | 48 | 0 | 217953 | 217953 | 0 | 0 | 672 | 0 | 1507328 | 1504685 | 48 | 4766 | 199747 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982872186044 | 12074986794113700 | 12074986794237859 | 12074982872528009 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fa2f5f14900 | 0x7fa1ea235740 | 1785696 | 1607371 | 23730887 | 65536 | 136051940 | 672 | 48 | 0 | 223211 | 223211 | 0 | 0 | 720 | 0 | 1703936 | 1700379 | 48 | 5774 | 189562 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982872592189 | 12074986794280258 | 12074986794405377 | 12074982872924266 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fa2f5f14800 | 0x7fa1ea235780 | 1731664 | 1572223 | 23258644 | 65536 | 147139492 | 576 | 48 | 0 | 216457 | 216457 | 0 | 0 | 624 | 0 | 1572864 | 1570247 | 48 | 4690 | 201888 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982872999025 | 12074986794461057 | 12074986794585376 | 12074982873321153 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fa2f5f14700 | 0x7fa1ea2357c0 | 3127904 | 2961101 | 44151296 | 65536 | 347852491 | 1008 | 48 | 0 | 390987 | 390987 | 0 | 0 | 1056 | 0 | 2621440 | 2617903 | 48 | 8303 | 176682 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982873381485 | 12074986794627776 | 12074986794873534 | 12074982873894078 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fa2f5f14600 | 0x7fa1ea235800 | 3212944 | 3038279 | 45259498 | 65536 | 309457239 | 672 | 48 | 0 | 401617 | 401617 | 0 | 0 | 720 | 0 | 1703936 | 1701003 | 48 | 3982 | 175135 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982873920207 | 12074986794973853 | 12074986795221211 | 12074982874454479 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fa2f5f14500 | 0x7fa1ea235840 | 1753120 | 1568638 | 23296815 | 65536 | 147252294 | 672 | 48 | 0 | 219139 | 219139 | 0 | 0 | 720 | 0 | 1638400 | 1634836 | 48 | 6239 | 195290 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982874480588 | 12074986795330491 | 12074986795454650 | 12074982874817564 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fa2f5f14400 | 0x7fa1ea235880 | 1797200 | 1641410 | 24258099 | 65536 | 145442862 | 768 | 48 | 0 | 224649 | 224649 | 0 | 0 | 816 | 0 | 1900544 | 1894761 | 96 | 7856 | 199738 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982874882655 | 12074986795495929 | 12074986795621528 | 12074982875207699 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fa2f5f14300 | 0x7fa1ea2358c0 | 1716448 | 1552233 | 22995648 | 65536 | 137830719 | 672 | 48 | 0 | 214555 | 214555 | 0 | 0 | 720 | 0 | 1703936 | 1698598 | 48 | 8603 | 205191 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982875286826 | 12074986795671928 | 12074986795796407 | 12074982875600830 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fa2f5f14a00 | 0x7fa1ea235900 | 3247248 | 3086949 | 46050401 | 65536 | 351589894 | 1104 | 48 | 0 | 405905 | 405905 | 0 | 0 | 1152 | 0 | 2883584 | 2879496 | 48 | 8704 | 230899 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982875665560 | 12074986795837527 | 12074986796085525 | 12074982876182641 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fa2f5f14900 | 0x7fa1ea235940 | 3212768 | 3021956 | 45048411 | 65536 | 225092545 | 720 | 48 | 0 | 401595 | 401595 | 0 | 0 | 768 | 0 | 1835008 | 1832531 | 48 | 3905 | 191687 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982876209250 | 12074986796178164 | 12074986796423122 | 12074982876738324 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fa2f5f14800 | 0x7fa1ea235980 | 1711504 | 1546985 | 22916875 | 65536 | 151264613 | 720 | 48 | 0 | 213937 | 213937 | 0 | 0 | 768 | 0 | 1769472 | 1764920 | 96 | 7756 | 248701 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982876764683 | 12074986796508882 | 12074986796633681 | 12074982877097541 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fa2f5f14700 | 0x7fa1ea2359c0 | 1850208 | 1678815 | 24818549 | 65536 | 144940668 | 816 | 48 | 0 | 231275 | 231275 | 0 | 0 | 864 | 0 | 2097152 | 2091128 | 48 | 8522 | 205235 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982877164355 | 12074986796674641 | 12074986796800080 | 12074982877502704 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fa2f5f14600 | 0x7fa1ea235a00 | 1662160 | 1491781 | 22168943 | 65536 | 136296977 | 720 | 48 | 0 | 207769 | 207769 | 0 | 0 | 768 | 0 | 1835008 | 1832203 | 48 | 5845 | 200520 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982877581451 | 12074986796851279 | 12074986796975598 | 12074982877889663 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fa2f5f14500 | 0x7fa1ea235a40 | 3248800 | 3081791 | 45937245 | 65536 | 354272540 | 1200 | 48 | 0 | 406099 | 406099 | 0 | 0 | 1248 | 0 | 3145728 | 3141676 | 96 | 8674 | 183155 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982877955586 | 12074986797024558 | 12074986797272716 | 12074982878482295 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fa2f5f14400 | 0x7fa1ea235a80 | 3194960 | 3027623 | 45173745 | 65536 | 340947454 | 768 | 48 | 0 | 399369 | 399369 | 0 | 0 | 816 | 0 | 1966080 | 1963233 | 48 | 3986 | 177058 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982878508073 | 12074986797328076 | 12074986797573034 | 12074982879035042 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fa2f5f14300 | 0x7fa1ea235ac0 | 1720352 | 1551759 | 23013274 | 65536 | 149557949 | 768 | 48 | 0 | 215043 | 215043 | 0 | 0 | 816 | 0 | 1900544 | 1893633 | 48 | 9222 | 211524 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982879061551 | 12074986797631273 | 12074986797756552 | 12074982879401443 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fa2f5f14a00 | 0x7fa1ea235b00 | 1826640 | 1651298 | 24377499 | 65536 | 142221911 | 912 | 48 | 0 | 228329 | 228329 | 0 | 0 | 960 | 0 | 2293760 | 2289273 | 48 | 6706 | 192137 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982879466173 | 12074986797797192 | 12074986797923591 | 12074982879798831 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fa2f5f14900 | 0x7fa1ea235b40 | 1757472 | 1567997 | 23256470 | 65536 | 152111154 | 768 | 48 | 0 | 219683 | 219683 | 0 | 0 | 816 | 0 | 1966080 | 1961322 | 96 | 7086 | 193633 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982879874913 | 12074986797975751 | 12074986798101190 | 12074982880196560 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fa2f5f14800 | 0x7fa1ea235b80 | 3385872 | 3219021 | 47957497 | 65536 | 360489658 | 1296 | 48 | 0 | 423233 | 423233 | 0 | 0 | 1344 | 0 | 3407872 | 3403240 | 48 | 9550 | 177967 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982880262693 | 12074986798144870 | 12074986798402628 | 12074982880793860 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fa2f5f14700 | 0x7fa1ea235bc0 | 3739616 | 3049257 | 45413601 | 65536 | 288768513 | 816 | 48 | 0 | 467451 | 467451 | 0 | 0 | 864 | 0 | 2097152 | 2094402 | 48 | 4028 | 183770 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982880819037 | 12074986798457507 | 12074986798702785 | 12074982881393405 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fa2f5f14600 | 0x7fa1ea235c00 | 1675152 | 1500320 | 22225748 | 65536 | 166976487 | 816 | 48 | 0 | 209393 | 209393 | 0 | 0 | 864 | 0 | 2031616 | 2026848 | 96 | 6955 | 247598 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982881424512 | 12074986798757185 | 12074986798882144 | 12074982881751280 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fa2f5f14500 | 0x7fa1ea235c40 | 1793504 | 1619751 | 23875428 | 65536 | 157766535 | 960 | 48 | 0 | 224187 | 224187 | 0 | 0 | 1008 | 0 | 2490368 | 2482653 | 48 | 10070 | 200870 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982881815799 | 12074986798924544 | 12074986799050943 | 12074982882146013 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fa2f5f14400 | 0x7fa1ea235c80 | 1704336 | 1536436 | 22747393 | 65536 | 139746040 | 816 | 48 | 0 | 213041 | 213041 | 0 | 0 | 864 | 0 | 2097152 | 2092365 | 48 | 7439 | 198741 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982882224790 | 12074986799106622 | 12074986799231741 | 12074982882536529 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fa2f5f14300 | 0x7fa1ea235cc0 | 3384032 | 3212802 | 47838751 | 65536 | 344372313 | 1392 | 48 | 0 | 423003 | 423003 | 0 | 0 | 1440 | 0 | 3670016 | 3661748 | 97 | 13568 | 185498 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982882600888 | 12074986799277021 | 12074986799536859 | 12074982883132096 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fa2f5f14a00 | 0x7fa1ea235d00 | 3207312 | 3037338 | 45287222 | 65536 | 316340847 | 864 | 48 | 0 | 400913 | 400913 | 0 | 0 | 912 | 0 | 2228224 | 2221595 | 48 | 7992 | 178689 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982883158705 | 12074986799590779 | 12074986799873497 | 12074982883684091 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fa2f5f14900 | 0x7fa1ea235d40 | 1702560 | 1520645 | 22644981 | 65536 | 157760991 | 864 | 48 | 0 | 212819 | 212819 | 0 | 0 | 912 | 0 | 2162688 | 2155648 | 48 | 9790 | 202078 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982883708998 | 12074986799929176 | 12074986800053815 | 12074982884040323 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fa2f5f14800 | 0x7fa1ea235d80 | 1843536 | 1657880 | 24465401 | 65536 | 148228818 | 1056 | 48 | 0 | 230441 | 230441 | 0 | 0 | 1104 | 0 | 2686976 | 2678901 | 96 | 11373 | 199433 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982884105064 | 12074986800096535 | 12074986800224854 | 12074982884440738 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fa2f5f14700 | 0x7fa1ea235dc0 | 1675808 | 1508555 | 22312473 | 65536 | 163745443 | 864 | 48 | 0 | 209475 | 209475 | 0 | 0 | 912 | 0 | 2228224 | 2222422 | 48 | 9360 | 194481 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982884518763 | 12074986800277974 | 12074986800403413 | 12074982884829109 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fa2f5f14600 | 0x7fa1ea235e00 | 3326928 | 3153153 | 46883185 | 65536 | 301345935 | 1488 | 48 | 0 | 415865 | 415865 | 0 | 0 | 1536 | 0 | 3932160 | 3928432 | 50 | 6848 | 197957 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982884894230 | 12074986800444532 | 12074986800702610 | 12074982885429054 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fa2f5f14500 | 0x7fa1ea235e40 | 3171872 | 3005452 | 44856801 | 65536 | 334666200 | 912 | 48 | 0 | 396483 | 396483 | 0 | 0 | 960 | 0 | 2359296 | 2355584 | 96 | 5011 | 175109 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982885455974 | 12074986800757650 | 12074986801005968 | 12074982885973817 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fa2f5f14400 | 0x7fa1ea235e80 | 1716240 | 1551060 | 22907810 | 65536 | 148757016 | 912 | 48 | 0 | 214529 | 214529 | 0 | 0 | 960 | 0 | 2293760 | 2287761 | 48 | 8344 | 196811 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982885999985 | 12074986801067728 | 12074986801193167 | 12074982886337933 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fa2f5f14300 | 0x7fa1ea235ec0 | 1823648 | 1645436 | 24123366 | 65536 | 168842945 | 1104 | 48 | 0 | 227955 | 227955 | 0 | 0 | 1152 | 0 | 2883584 | 2873209 | 48 | 12481 | 193789 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982886402273 | 12074986801234927 | 12074986801362766 | 12074982886737325 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fa2f5f14a00 | 0x7fa1ea235f00 | 1778704 | 1609017 | 23799813 | 65536 | 149475955 | 912 | 48 | 0 | 222337 | 222337 | 0 | 0 | 960 | 0 | 2359296 | 2351873 | 96 | 10094 | 220808 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982886815030 | 12074986801415885 | 12074986801540524 | 12074982887131939 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fa2f5f14900 | 0x7fa1ea235f40 | 3286688 | 3101841 | 46097052 | 65536 | 311983356 | 1584 | 48 | 0 | 410835 | 410835 | 0 | 0 | 1632 | 0 | 4194304 | 4187166 | 48 | 11895 | 196155 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982887196729 | 12074986801581804 | 12074986801837962 | 12074982887718870 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fa2f5f14800 | 0x7fa1ea235f80 | 3210896 | 3044110 | 45438754 | 65536 | 348297501 | 960 | 48 | 0 | 401361 | 401361 | 0 | 0 | 1008 | 0 | 2490368 | 2484840 | 48 | 6711 | 180206 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982887744217 | 12074986801896522 | 12074986802142920 | 12074982888265926 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fa2f5f14700 | 0x7fa1ea235fc0 | 1778976 | 1611917 | 23856321 | 65536 | 152903654 | 960 | 48 | 0 | 222371 | 222371 | 0 | 0 | 1008 | 0 | 2424832 | 2418196 | 48 | 9171 | 201272 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982888292916 | 12074986802203399 | 12074986802328998 | 12074982888636886 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fa2f5f14600 | 0x7fa1ea236000 | 1794000 | 1613339 | 23885474 | 65536 | 178484215 | 1200 | 48 | 0 | 224249 | 224249 | 0 | 0 | 1248 | 0 | 3080192 | 3067206 | 48 | 16188 | 201789 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982888702017 | 12074986802372358 | 12074986802509317 | 12074982889031319 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fa2f5f14500 | 0x7fa1ea236040 | 1686432 | 1524812 | 22535267 | 65536 | 152340405 | 960 | 48 | 0 | 210803 | 210803 | 0 | 0 | 1008 | 0 | 2490368 | 2483188 | 48 | 9599 | 207134 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982889111417 | 12074986802564517 | 12074986802689316 | 12074982889421403 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fa2f5f14400 | 0x7fa1ea236080 | 3337168 | 3157201 | 46949916 | 65536 | 348341600 | 1680 | 48 | 0 | 417145 | 417145 | 0 | 0 | 1728 | 0 | 4456448 | 4451429 | 49 | 9776 | 230967 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982889487256 | 12074986802730115 | 12074986802984193 | 12074982890015067 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fa2f5f14300 | 0x7fa1ea2360c0 | 3198304 | 2991229 | 44646615 | 65536 | 317914841 | 1008 | 48 | 0 | 399787 | 399787 | 0 | 0 | 1056 | 0 | 2621440 | 2618362 | 48 | 4358 | 188964 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982890046054 | 12074986803047713 | 12074986803292191 | 12074982890564508 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fa2f5f14a00 | 0x7fa1ea236100 | 1792784 | 1618917 | 23980035 | 65536 | 150137930 | 1008 | 48 | 0 | 224097 | 224097 | 0 | 0 | 1056 | 0 | 2555904 | 2548053 | 96 | 10507 | 243163 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982890589184 | 12074986803349951 | 12074986803474910 | 12074982890927933 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fa2f5f14900 | 0x7fa1ea236140 | 1880224 | 1689447 | 25011499 | 65536 | 197538535 | 1248 | 48 | 0 | 235027 | 235027 | 0 | 0 | 1296 | 0 | 3276800 | 3265571 | 48 | 16392 | 183126 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982890993946 | 12074986803517949 | 12074986803660188 | 12074982891339137 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fa2f5f14800 | 0x7fa1ea236180 | 1755856 | 1582449 | 23406650 | 65536 | 145498613 | 1008 | 48 | 0 | 219481 | 219481 | 0 | 0 | 1056 | 0 | 2621440 | 2611559 | 48 | 12874 | 202091 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982891418555 | 12074986803712188 | 12074986803837307 | 12074982891732418 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fa2f5f14700 | 0x7fa1ea2361c0 | 3339616 | 3161924 | 46945141 | 65536 | 355024953 | 1776 | 48 | 0 | 417451 | 417451 | 0 | 0 | 1824 | 0 | 4718592 | 4705006 | 97 | 20975 | 214629 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982891799503 | 12074986803880667 | 12074986804131865 | 12074982892319600 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fa2f5f14600 | 0x7fa1ea236200 | 3226000 | 3052688 | 45417454 | 65536 | 274545853 | 1056 | 48 | 0 | 403249 | 403249 | 0 | 0 | 1104 | 0 | 2752512 | 2748129 | 48 | 5619 | 229354 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982892345558 | 12074986804194424 | 12074986804443383 | 12074982892869622 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fa2f5f14500 | 0x7fa1ea236240 | 1785504 | 1622500 | 23949404 | 65536 | 150892143 | 1056 | 48 | 0 | 223187 | 223187 | 0 | 0 | 1104 | 0 | 2686976 | 2679002 | 96 | 10258 | 192980 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982892894067 | 12074986804503222 | 12074986804628821 | 12074982893238668 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fa2f5f14400 | 0x7fa1ea236280 | 1933200 | 1765150 | 26132979 | 65536 | 203462900 | 1344 | 48 | 0 | 241649 | 241649 | 0 | 0 | 1392 | 0 | 3473408 | 3461496 | 48 | 18169 | 185459 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982893304189 | 12074986804670421 | 12074986804820340 | 12074982893645574 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fa2f5f14300 | 0x7fa1ea2362c0 | 1731360 | 1566130 | 23076417 | 65536 | 159535073 | 1056 | 48 | 0 | 216419 | 216419 | 0 | 0 | 1104 | 0 | 2752512 | 2743070 | 98 | 13508 | 230288 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982893737464 | 12074986804890739 | 12074986805015858 | 12074982894051238 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fa2f5f14a00 | 0x7fa1ea236300 | 3291664 | 3090845 | 45929512 | 65536 | 292602880 | 1872 | 48 | 0 | 411457 | 411457 | 0 | 0 | 1920 | 0 | 4980736 | 4974802 | 49 | 9405 | 229901 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982894117972 | 12074986805060178 | 12074986805320816 | 12074982894645302 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fa2f5f14900 | 0x7fa1ea236340 | 3189856 | 3022179 | 45086545 | 65536 | 339460774 | 1104 | 48 | 0 | 398731 | 398731 | 0 | 0 | 1152 | 0 | 2883584 | 2880145 | 97 | 4538 | 210845 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982894670759 | 12074986805374256 | 12074986805620494 | 12074982895193590 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fa2f5f14800 | 0x7fa1ea236380 | 1783184 | 1616298 | 23877171 | 65536 | 153421342 | 1104 | 48 | 0 | 222897 | 222897 | 0 | 0 | 1152 | 0 | 2818048 | 2810992 | 48 | 9697 | 242907 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982895223416 | 12074986805676013 | 12074986805801452 | 12074982895559440 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fa2f5f14700 | 0x7fa1ea2363c0 | 2013664 | 1850830 | 27495159 | 65536 | 221324140 | 1392 | 48 | 0 | 251707 | 251707 | 0 | 0 | 1440 | 0 | 3670016 | 3655611 | 48 | 17915 | 192173 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982895623760 | 12074986805845292 | 12074986806002251 | 12074982895970023 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fa2f5f14600 | 0x7fa1ea236400 | 1714192 | 1547699 | 22875581 | 65536 | 148747985 | 1104 | 48 | 0 | 214273 | 214273 | 0 | 0 | 1152 | 0 | 2883584 | 2876832 | 96 | 9425 | 190059 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982896047297 | 12074986806059371 | 12074986806184810 | 12074982896366170 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fa2f5f14500 | 0x7fa1ea236440 | 3298848 | 3122619 | 46111545 | 65536 | 294895847 | 1968 | 48 | 0 | 412355 | 412355 | 0 | 0 | 2016 | 0 | 5177344 | 5170331 | 49 | 10394 | 202511 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982896432142 | 12074986806228809 | 12074986806488967 | 12074982896948983 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fa2f5f14400 | 0x7fa1ea236480 | 3208464 | 3043919 | 45415958 | 65536 | 351546226 | 1152 | 48 | 0 | 401057 | 401057 | 0 | 0 | 1200 | 0 | 3014656 | 3009503 | 96 | 6259 | 183248 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982896975151 | 12074986806542087 | 12074986806785925 | 12074982897510646 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fa2f5f14300 | 0x7fa1ea2364c0 | 1781088 | 1610529 | 23857351 | 65536 | 146396066 | 1152 | 48 | 0 | 222635 | 222635 | 0 | 0 | 1200 | 0 | 2949120 | 2937051 | 48 | 17961 | 203028 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982897536504 | 12074986806839685 | 12074986806965284 | 12074982897874102 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fa2f5f14a00 | 0x7fa1ea236500 | 2100496 | 1941072 | 28851136 | 65536 | 232588892 | 1488 | 48 | 0 | 262561 | 262561 | 0 | 0 | 1536 | 0 | 3866624 | 3849017 | 96 | 21701 | 200968 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982897941447 | 12074986807005924 | 12074986807170402 | 12074982898305243 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fa2f5f14900 | 0x7fa1ea236540 | 1742496 | 1579685 | 23342663 | 65536 | 160012447 | 1152 | 48 | 0 | 217811 | 217811 | 0 | 0 | 1200 | 0 | 3014656 | 3004933 | 63 | 14509 | 198473 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982898383909 | 12074986807227042 | 12074986807352321 | 12074982898696711 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fa2f5f14800 | 0x7fa1ea236580 | 3294416 | 3115416 | 46150539 | 65536 | 314714342 | 2064 | 48 | 0 | 411801 | 411801 | 0 | 0 | 2112 | 0 | 5439488 | 5427565 | 99 | 16225 | 181967 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982898762663 | 12074986807394881 | 12074986807648639 | 12074982899282549 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fa2f5f14700 | 0x7fa1ea2365c0 | 3200288 | 3017890 | 44793609 | 65536 | 248430484 | 1200 | 48 | 0 | 400035 | 400035 | 0 | 0 | 1248 | 0 | 3145728 | 3141583 | 48 | 5354 | 179793 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982899308427 | 12074986807706558 | 12074986807952956 | 12074982899832832 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fa2f5f14600 | 0x7fa1ea236600 | 1829200 | 1664840 | 24590486 | 65536 | 157070749 | 1200 | 48 | 0 | 228649 | 228649 | 0 | 0 | 1248 | 0 | 3080192 | 3067368 | 73 | 21763 | 197491 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982899857858 | 12074986808016156 | 12074986808140795 | 12074982900204733 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fa2f5f14500 | 0x7fa1ea236640 | 2204704 | 2045940 | 30399275 | 65536 | 243699624 | 1536 | 48 | 0 | 275587 | 275587 | 0 | 0 | 1584 | 0 | 4063232 | 4049501 | 96 | 16909 | 196062 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982900270375 | 12074986808186875 | 12074986808359193 | 12074982900639230 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fa2f5f14400 | 0x7fa1ea236680 | 1787728 | 1618447 | 23890579 | 65536 | 147493258 | 1200 | 48 | 0 | 223465 | 223465 | 0 | 0 | 1248 | 0 | 3145728 | 3134543 | 48 | 14449 | 200892 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982900717285 | 12074986808413593 | 12074986808539192 | 12074982901037941 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fa2f5f14300 | 0x7fa1ea2366c0 | 3187552 | 3017752 | 44777029 | 65536 | 351611500 | 2160 | 48 | 0 | 398443 | 398443 | 0 | 0 | 2208 | 0 | 5701632 | 5692324 | 97 | 13015 | 191107 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982901103613 | 12074986808583672 | 12074986808836630 | 12074982901618881 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fa2f5f14a00 | 0x7fa1ea236700 | 3189648 | 3024756 | 45076528 | 65536 | 338783489 | 1248 | 48 | 0 | 398705 | 398705 | 0 | 0 | 1296 | 0 | 3276800 | 3272526 | 49 | 5471 | 232934 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982901644208 | 12074986808893589 | 12074986809138228 | 12074982902161890 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fa2f5f14900 | 0x7fa1ea236740 | 1800416 | 1626759 | 24040720 | 65536 | 153139822 | 1248 | 48 | 0 | 225051 | 225051 | 0 | 0 | 1296 | 0 | 3211264 | 3197129 | 101 | 20372 | 195130 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982902188740 | 12074986809194867 | 12074986809320946 | 12074982902527960 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fa2f5f14800 | 0x7fa1ea236780 | 2323024 | 2154252 | 31969386 | 65536 | 243071525 | 1632 | 48 | 0 | 290377 | 290377 | 0 | 0 | 1680 | 0 | 4259840 | 4244017 | 48 | 19052 | 200248 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982902593652 | 12074986809363666 | 12074986809546865 | 12074982902970994 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fa2f5f14700 | 0x7fa1ea2367c0 | 1781088 | 1617147 | 23832172 | 65536 | 146507904 | 1248 | 48 | 0 | 222635 | 222635 | 0 | 0 | 1296 | 0 | 3276800 | 3261620 | 115 | 25709 | 195104 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982903072352 | 12074986809600624 | 12074986809726223 | 12074982903391886 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fa2f5f14600 | 0x7fa1ea236800 | 3280208 | 3115323 | 46348616 | 65536 | 378256522 | 1200 | 48 | 0 | 410025 | 410025 | 0 | 0 | 1248 | 0 | 7733248 | 7730226 | 48 | 3385 | 199060 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982903457628 | 12074986809768943 | 12074986810031821 | 12074982903979738 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fa2f5f14500 | 0x7fa1ea236840 | 3131040 | 2959443 | 44111822 | 65536 | 339952512 | 1296 | 48 | 0 | 391379 | 391379 | 0 | 0 | 1344 | 0 | 3407872 | 3402138 | 96 | 6889 | 178811 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982904010325 | 12074986810090541 | 12074986810337739 | 12074982904531934 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fa2f5f14400 | 0x7fa1ea236880 | 1758096 | 1583043 | 23451900 | 65536 | 152345739 | 1296 | 48 | 0 | 219761 | 219761 | 0 | 0 | 1344 | 0 | 3342336 | 3327330 | 48 | 25508 | 247398 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982904556280 | 12074986810397098 | 12074986810523657 | 12074982904892955 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fa2f5f14300 | 0x7fa1ea2368c0 | 2429856 | 2267894 | 33623345 | 65536 | 247641206 | 1680 | 48 | 0 | 303731 | 303731 | 0 | 0 | 1728 | 0 | 4456448 | 4441381 | 96 | 19770 | 207938 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982904956403 | 12074986810566217 | 12074986810757256 | 12074982905414715 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fa2f5f14a00 | 0x7fa1ea236900 | 1722512 | 1547469 | 22747862 | 65536 | 150470908 | 1344 | 48 | 0 | 215313 | 215313 | 0 | 0 | 1392 | 0 | 3538944 | 3525364 | 71 | 24347 | 249065 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982905452044 | 12074986810811975 | 12074986810938374 | 12074982905770626 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fa2f5f14900 | 0x7fa1ea236940 | 3506400 | 3327881 | 49564294 | 65536 | 406209792 | 1104 | 48 | 0 | 438299 | 438299 | 0 | 0 | 1152 | 0 | 8978432 | 8976668 | 48 | 2006 | 211415 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982905834786 | 12074986810981254 | 12074986811262852 | 12074982906381702 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fa2f5f14800 | 0x7fa1ea236980 | 3254608 | 3084507 | 45906326 | 65536 | 319914861 | 1392 | 48 | 0 | 406825 | 406825 | 0 | 0 | 1440 | 0 | 3670016 | 3662935 | 48 | 8426 | 179908 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982906409464 | 12074986811322051 | 12074986811569729 | 12074982906937805 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fa2f5f14700 | 0x7fa1ea2369c0 | 1758560 | 1594538 | 23548286 | 65536 | 149005828 | 1392 | 48 | 0 | 219819 | 219819 | 0 | 0 | 1440 | 0 | 3604480 | 3589214 | 48 | 20842 | 204819 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982906963894 | 12074986811626049 | 12074986811752448 | 12074982907305879 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fa2f5f14600 | 0x7fa1ea236a00 | 2640016 | 2476970 | 36783432 | 65536 | 283369045 | 1824 | 48 | 0 | 330001 | 330001 | 0 | 0 | 1872 | 0 | 4849664 | 4828478 | 104 | 26599 | 199035 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982907371982 | 12074986811795968 | 12074986812005246 | 12074982907833951 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fa2f5f14500 | 0x7fa1ea236a40 | 1772896 | 1592998 | 23459395 | 65536 | 154942849 | 1440 | 48 | 0 | 221611 | 221611 | 0 | 0 | 1488 | 0 | 3801088 | 3788233 | 75 | 23750 | 209269 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982907871731 | 12074986812077726 | 12074986812205885 | 12074982908199330 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fa2f5f14400 | 0x7fa1ea236a80 | 3769872 | 3610658 | 53832172 | 65536 | 441256879 | 816 | 48 | 0 | 471233 | 471233 | 0 | 0 | 864 | 0 | 14548992 | 14547457 | 48 | 1796 | 247330 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982908266475 | 12074986812247964 | 12074986812554202 | 12074982908828349 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fa2f5f14300 | 0x7fa1ea236ac0 | 3191392 | 3021342 | 44950576 | 65536 | 272500045 | 1488 | 48 | 0 | 398923 | 398923 | 0 | 0 | 1536 | 0 | 3932160 | 3926429 | 48 | 7117 | 190721 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982908854016 | 12074986812611802 | 12074986812861880 | 12074982909386706 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fa2f5f14a00 | 0x7fa1ea236b00 | 1746512 | 1573489 | 23168485 | 65536 | 155846558 | 1488 | 48 | 0 | 218313 | 218313 | 0 | 0 | 1536 | 0 | 3866624 | 3853979 | 115 | 20333 | 197161 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982909412224 | 12074986812920599 | 12074986813048438 | 12074982909754660 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fa2f5f14900 | 0x7fa1ea236b40 | 2839520 | 2683098 | 39884604 | 65536 | 326184527 | 1968 | 48 | 0 | 354939 | 354939 | 0 | 0 | 2016 | 0 | 5242880 | 5219214 | 48 | 29047 | 205357 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982909820372 | 12074986813091638 | 12074986813319316 | 12074982910299934 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fa2f5f14800 | 0x7fa1ea236b80 | 1736272 | 1575411 | 23179964 | 65536 | 154582446 | 1536 | 48 | 0 | 217033 | 217033 | 0 | 0 | 1584 | 0 | 4063232 | 4048765 | 144 | 26122 | 199248 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982910337233 | 12074986813395156 | 12074986813521075 | 12074982910656216 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fa2f5f14700 | 0x7fa1ea236bc0 | 4024032 | 3863285 | 57555965 | 65536 | 472222532 | 1200 | 48 | 0 | 503003 | 503003 | 0 | 0 | 1248 | 0 | 10027008 | 10025199 | 48 | 2204 | 193710 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982910720185 | 12074986813563315 | 12074986813891792 | 12074982911305332 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fa2f5f14600 | 0x7fa1ea236c00 | 3207888 | 3015184 | 44799527 | 65536 | 260816171 | 1584 | 48 | 0 | 400985 | 400985 | 0 | 0 | 1632 | 0 | 4194304 | 4182508 | 96 | 13106 | 176134 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982911331991 | 12074986813950672 | 12074986814200430 | 12074982911856015 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fa2f5f14500 | 0x7fa1ea236c40 | 1837024 | 1670568 | 24673862 | 65536 | 157297789 | 1584 | 48 | 0 | 229627 | 229627 | 0 | 0 | 1632 | 0 | 4128768 | 4113751 | 52 | 20078 | 207727 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982911881703 | 12074986814258349 | 12074986814385869 | 12074982912229209 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fa2f5f14400 | 0x7fa1ea236c80 | 3049488 | 2895074 | 42973459 | 65536 | 348713063 | 2112 | 48 | 0 | 381185 | 381185 | 0 | 0 | 2160 | 0 | 5636096 | 5615318 | 96 | 24928 | 213358 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982912287708 | 12074986814427628 | 12074986814672106 | 12074982912796423 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fa2f5f14300 | 0x7fa1ea236cc0 | 1797792 | 1620641 | 23780986 | 65536 | 175880066 | 1728 | 48 | 0 | 224723 | 224723 | 0 | 0 | 1776 | 0 | 4587520 | 4569803 | 76 | 31451 | 195250 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982912834043 | 12074986814740106 | 12074986814869225 | 12074982913171300 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fa2f5f14a00 | 0x7fa1ea236d00 | 4609424 | 4441249 | 66124217 | 65536 | 541011940 | 1296 | 48 | 0 | 576177 | 576177 | 0 | 0 | 1344 | 0 | 11075584 | 11073473 | 50 | 2509 | 197153 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982913229498 | 12074986814912105 | 12074986815287622 | 12074982913872252 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fa2f5f14900 | 0x7fa1ea236d40 | 3304224 | 3106755 | 46095053 | 65536 | 308904657 | 1728 | 48 | 0 | 413027 | 413027 | 0 | 0 | 1776 | 0 | 4718592 | 4704510 | 49 | 15879 | 187380 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982913898451 | 12074986815342501 | 12074986815593380 | 12074982914435359 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fa2f5f14800 | 0x7fa1ea236d80 | 1836432 | 1659647 | 24479311 | 65536 | 164081225 | 1776 | 48 | 0 | 229553 | 229553 | 0 | 0 | 1824 | 0 | 4653056 | 4636879 | 57 | 24181 | 249309 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982914461627 | 12074986815649859 | 12074986815779458 | 12074982914804284 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fa2f5f14700 | 0x7fa1ea236dc0 | 3479328 | 3308466 | 49184650 | 65536 | 402499334 | 2400 | 48 | 0 | 434915 | 434915 | 0 | 0 | 2448 | 0 | 6422528 | 6398135 | 96 | 29184 | 215162 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982914868113 | 12074986815822018 | 12074986816100096 | 12074982915408918 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fa2f5f14600 | 0x7fa1ea236e00 | 1767696 | 1596775 | 23553784 | 65536 | 184971812 | 1920 | 48 | 0 | 220961 | 220961 | 0 | 0 | 1968 | 0 | 5111808 | 5091673 | 87 | 35568 | 197049 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982915446688 | 12074986816167135 | 12074986816302334 | 12074982915769418 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fa2f5f14500 | 0x7fa1ea236e40 | 5172384 | 5007207 | 74641652 | 65536 | 613247651 | 1008 | 48 | 0 | 646547 | 646547 | 0 | 0 | 1056 | 0 | 15007744 | 15006412 | 48 | 1680 | 193659 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982915833727 | 12074986816344894 | 12074986816767291 | 12074982916527457 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fa2f5f14400 | 0x7fa1ea236e80 | 3286288 | 3071298 | 45480779 | 65536 | 300123138 | 1968 | 48 | 0 | 410785 | 410785 | 0 | 0 | 2016 | 0 | 5242880 | 5219927 | 48 | 26077 | 220292 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982916554507 | 12074986816822490 | 12074986817078488 | 12074982917087878 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fa2f5f14300 | 0x7fa1ea236ec0 | 1808096 | 1639830 | 24198648 | 65536 | 176630071 | 1968 | 48 | 0 | 226011 | 226011 | 0 | 0 | 2016 | 0 | 5177344 | 5157707 | 167 | 37543 | 216910 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982917115259 | 12074986817138168 | 12074986817273687 | 12074982917463386 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fa2f5f14a00 | 0x7fa1ea236f00 | 3915408 | 3738147 | 55662278 | 65536 | 445313090 | 2688 | 48 | 0 | 489425 | 489425 | 0 | 0 | 2736 | 0 | 7208960 | 7176297 | 97 | 40380 | 199593 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982917529168 | 12074986817316087 | 12074986817629844 | 12074982918072378 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fa2f5f14900 | 0x7fa1ea236f40 | 1957536 | 1774635 | 26391902 | 65536 | 213739612 | 2304 | 48 | 0 | 244691 | 244691 | 0 | 0 | 2352 | 0 | 6160384 | 6136194 | 117 | 38036 | 205229 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982918135515 | 12074986817696564 | 12074986817847603 | 12074982918469355 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fa2f5f14800 | 0x7fa1ea236f80 | 6309136 | 6135755 | 91459775 | 65536 | 752010460 | 1104 | 48 | 0 | 788641 | 788641 | 0 | 0 | 1152 | 0 | 17104896 | 17103128 | 49 | 1982 | 199848 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982918538484 | 12074986817890162 | 12074986818406159 | 12074982919314125 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fa2f5f14700 | 0x7fa1ea236fc0 | 3660000 | 3474274 | 51421027 | 65536 | 381817609 | 2352 | 48 | 0 | 457499 | 457499 | 0 | 0 | 2400 | 0 | 6291456 | 6270846 | 96 | 22084 | 187758 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982919340133 | 12074986818461358 | 12074986818760716 | 12074982919902469 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fa2f5f14600 | 0x7fa1ea237000 | 1964752 | 1803650 | 26831908 | 65536 | 218135063 | 2352 | 48 | 0 | 245593 | 245593 | 0 | 0 | 2400 | 0 | 6225920 | 6200324 | 153 | 43213 | 246694 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982919927776 | 12074986818816075 | 12074986818969674 | 12074982920300969 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fa2f5f14500 | 0x7fa1ea237040 | 4746656 | 4578601 | 68323635 | 65536 | 561409019 | 3264 | 48 | 0 | 593331 | 593331 | 0 | 0 | 3312 | 0 | 8781824 | 8748392 | 107 | 51958 | 198370 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982920367713 | 12074986819016714 | 12074986819400711 | 12074982921018873 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fa2f5f14400 | 0x7fa1ea237080 | 2236304 | 2078203 | 30932416 | 65536 | 252107569 | 2688 | 48 | 0 | 279537 | 279537 | 0 | 0 | 2736 | 0 | 7208960 | 7176864 | 107 | 58106 | 192619 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982921058096 | 12074986819468231 | 12074986819644389 | 12074982921422453 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fa2f5f14300 | 0x7fa1ea2370c0 | 7545376 | 7235674 | 107957352 | 65536 | 889235538 | 1200 | 48 | 0 | 943171 | 943171 | 0 | 0 | 1248 | 0 | 19202048 | 19200167 | 48 | 2903 | 193800 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982921513442 | 12074986819686949 | 12074986820296384 | 12074982922384591 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fa2f5f14a00 | 0x7fa1ea237100 | 4006928 | 3828682 | 57014243 | 65536 | 460990432 | 2736 | 48 | 0 | 500865 | 500865 | 0 | 0 | 2784 | 0 | 7340032 | 7316984 | 96 | 24532 | 178554 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982922410028 | 12074986820356704 | 12074986820682622 | 12074982923004754 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fa2f5f14900 | 0x7fa1ea237140 | 2259872 | 2096921 | 31150463 | 65536 | 253569743 | 2736 | 48 | 0 | 282483 | 282483 | 0 | 0 | 2784 | 0 | 7274496 | 7246835 | 256 | 64892 | 209107 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982923036002 | 12074986820742781 | 12074986820921340 | 12074982923420897 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fa2f5f14800 | 0x7fa1ea237180 | 5614480 | 5422816 | 80945782 | 65536 | 653523291 | 3840 | 48 | 0 | 701809 | 701809 | 0 | 0 | 3888 | 0 | 10354688 | 10315074 | 99 | 62751 | 195017 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982923515022 | 12074986820962299 | 12074986821416856 | 12074982924216486 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fa2f5f14700 | 0x7fa1ea2371c0 | 2495200 | 2334330 | 34771928 | 65536 | 283722829 | 3072 | 48 | 0 | 311899 | 311899 | 0 | 0 | 3120 | 0 | 8257536 | 8229441 | 201 | 58088 | 218396 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982924253504 | 12074986821490296 | 12074986821689174 | 12074982924706646 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fa2f5f14600 | 0x7fa1ea237200 | 8539408 | 8360868 | 124792857 | 65536 | 1028146477 | 1296 | 48 | 0 | 1067425 | 1067425 | 0 | 0 | 1344 | 0 | 21299200 | 21297182 | 50 | 2862 | 196227 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982924731503 | 12074986821741174 | 12074986822444208 | 12074982925703769 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fa2f5f14500 | 0x7fa1ea237240 | 4544544 | 4375172 | 65238111 | 65536 | 535332674 | 3120 | 48 | 0 | 568067 | 568067 | 0 | 0 | 3168 | 0 | 8388608 | 8356323 | 96 | 33690 | 188123 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982925730529 | 12074986822506288 | 12074986822878285 | 12074982926370498 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fa2f5f14400 | 0x7fa1ea237280 | 2553040 | 2391700 | 35578054 | 65536 | 290013435 | 3120 | 48 | 0 | 319129 | 319129 | 0 | 0 | 3168 | 0 | 8323072 | 8289986 | 242 | 73194 | 196121 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982926398851 | 12074986822936685 | 12074986823138923 | 12074982926866130 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fa2f5f14300 | 0x7fa1ea2372c0 | 6430112 | 6265130 | 93504356 | 65536 | 769737556 | 4416 | 48 | 0 | 803763 | 803763 | 0 | 0 | 4464 | 0 | 11927552 | 11878386 | 144 | 71362 | 205230 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982926894673 | 12074986823205163 | 12074986823730279 | 12074982927690111 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fa2f5f14a00 | 0x7fa1ea237300 | 2792976 | 2629466 | 39141039 | 65536 | 319489656 | 3456 | 48 | 0 | 349121 | 349121 | 0 | 0 | 3504 | 0 | 9306112 | 9264950 | 207 | 74959 | 246257 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982927728402 | 12074986823805318 | 12074986824028517 | 12074982928203986 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fa2f5f14900 | 0x7fa1ea237340 | 9649632 | 9486611 | 141686444 | 65536 | 1168323955 | 1008 | 48 | 0 | 1206203 | 1206203 | 0 | 0 | 1056 | 0 | 29163520 | 29162094 | 48 | 1693 | 207522 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982928229193 | 12074986824086916 | 12074986824884030 | 12074982929300934 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fa2f5f14800 | 0x7fa1ea237380 | 5381584 | 4938946 | 73598335 | 65536 | 597772754 | 3504 | 48 | 0 | 672697 | 672697 | 0 | 0 | 3552 | 0 | 9437184 | 9402500 | 96 | 36416 | 230085 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982929333735 | 12074986824938110 | 12074986825357787 | 12074982930020642 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fa2f5f14700 | 0x7fa1ea2373c0 | 3248480 | 2659226 | 39588569 | 65536 | 323334639 | 3504 | 48 | 0 | 406059 | 406059 | 0 | 0 | 3552 | 0 | 9371648 | 9338393 | 326 | 76220 | 192259 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982930071546 | 12074986825421786 | 12074986825645305 | 12074982930578919 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fa2f5f14600 | 0x7fa1ea237400 | 7282960 | 7119005 | 106277868 | 65536 | 874685401 | 4992 | 48 | 0 | 910369 | 910369 | 0 | 0 | 5040 | 0 | 13500416 | 13444135 | 144 | 84120 | 200632 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982930610308 | 12074986825701624 | 12074986826298260 | 12074982931470767 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fa2f5f14500 | 0x7fa1ea237440 | 3331360 | 3168762 | 47158786 | 65536 | 384411343 | 4224 | 48 | 0 | 416419 | 416419 | 0 | 0 | 4272 | 0 | 11403264 | 11370697 | 532 | 97397 | 202323 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982931509108 | 12074986826368499 | 12074986826637297 | 12074982932027641 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fa2f5f14400 | 0x7fa1ea237480 | 11895312 | 11732703 | 175252631 | 65536 | 1447769829 | 1104 | 48 | 0 | 1486913 | 1486913 | 0 | 0 | 1152 | 0 | 33357824 | 33355731 | 96 | 2344 | 218477 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982932052428 | 12074986826696177 | 12074986827680329 | 12074982933304845 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fa2f5f14300 | 0x7fa1ea2374c0 | 6243360 | 6071262 | 90541225 | 65536 | 728060709 | 4272 | 48 | 0 | 780419 | 780419 | 0 | 0 | 4320 | 0 | 11534336 | 11493857 | 96 | 54919 | 186459 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982933331324 | 12074986827738089 | 12074986828254565 | 12074982934129257 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fa2f5f14a00 | 0x7fa1ea237500 | 3372240 | 3208111 | 47721283 | 65536 | 390921060 | 4272 | 48 | 0 | 421529 | 421529 | 0 | 0 | 4320 | 0 | 11534336 | 11496109 | 515 | 117408 | 197838 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982934162579 | 12074986828315205 | 12074986828585923 | 12074982934699727 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fa2f5f14900 | 0x7fa1ea237540 | 9061984 | 8842633 | 132058654 | 65536 | 1089802537 | 1968 | 48 | 0 | 1132747 | 1132747 | 0 | 0 | 2016 | 0 | 19267584 | 19261617 | 48 | 5964 | 197828 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982934724884 | 12074986828642242 | 12074986829379197 | 12074982935743377 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fa2f5f14800 | 0x7fa1ea237580 | 3939664 | 3758616 | 55953767 | 65536 | 457639609 | 4992 | 48 | 0 | 492457 | 492457 | 0 | 0 | 5040 | 0 | 13500416 | 13463735 | 650 | 118761 | 215857 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982935780536 | 12074986829450556 | 12074986829764794 | 12074982936357698 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fa2f5f14700 | 0x7fa1ea2375c0 | 14145440 | 13983206 | 208796817 | 65536 | 1725205001 | 1200 | 48 | 0 | 1768179 | 1768179 | 0 | 0 | 1248 | 0 | 37552128 | 37550238 | 50 | 2181 | 206503 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982936382234 | 12074986829823033 | 12074986830994705 | 12074982937824554 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fa2f5f14600 | 0x7fa1ea237600 | 7344592 | 7180630 | 107159738 | 65536 | 812200003 | 5040 | 48 | 0 | 918073 | 918073 | 0 | 0 | 5088 | 0 | 13631488 | 13583059 | 144 | 66868 | 177822 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982937857776 | 12074986831062544 | 12074986831670540 | 12074982938741268 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fa2f5f14500 | 0x7fa1ea237640 | 3950176 | 3785266 | 56350702 | 65536 | 461971903 | 5040 | 48 | 0 | 493771 | 493771 | 0 | 0 | 5088 | 0 | 13631488 | 13590402 | 686 | 134829 | 200220 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982938770713 | 12074986831728459 | 12074986832047817 | 12074982939362382 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fa2f5f14400 | 0x7fa1ea237680 | 10689744 | 10529568 | 157240502 | 65536 | 1298258097 | 2832 | 48 | 0 | 1336217 | 1336217 | 0 | 0 | 2880 | 0 | 21692416 | 21681348 | 97 | 11269 | 204385 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982939387860 | 12074986832111976 | 12074986832989090 | 12074982940538468 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fa2f5f14300 | 0x7fa1ea2376c0 | 5036576 | 4868088 | 72506705 | 65536 | 595036805 | 6528 | 48 | 0 | 629571 | 629571 | 0 | 0 | 6576 | 0 | 17694720 | 17646969 | 1116 | 187258 | 193506 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982940575326 | 12074986833064129 | 12074986833473886 | 12074982941238889 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fa2f5f14a00 | 0x7fa1ea237700 | 18655696 | 18495483 | 276323920 | 65536 | 2285150188 | 1008 | 48 | 0 | 2331961 | 2331961 | 0 | 0 | 1056 | 0 | 57475072 | 57473846 | 48 | 1561 | 202528 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982941271721 | 12074986833534846 | 12074986835082994 | 12074982943088667 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fa2f5f14900 | 0x7fa1ea237740 | 9639008 | 9441897 | 140919092 | 65536 | 1162859435 | 2064 | 48 | 0 | 1204875 | 1204875 | 0 | 0 | 2112 | 0 | 19660800 | 19655004 | 51 | 5996 | 192328 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982943121137 | 12074986835186433 | 12074986835979708 | 12074982944184343 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fa2f5f14800 | 0x7fa1ea237780 | 5121232 | 4958416 | 73938163 | 65536 | 606951006 | 2112 | 48 | 0 | 640153 | 640153 | 0 | 0 | 2160 | 0 | 20381696 | 20372356 | 48 | 10159 | 237585 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982944210792 | 12074986836086106 | 12074986836499384 | 12074982944899983 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fa2f5f14700 | 0x7fa1ea2377c0 | 14065632 | 13897287 | 207593991 | 65536 | 1715300839 | 2832 | 48 | 0 | 1758203 | 1758203 | 0 | 0 | 2880 | 0 | 28704768 | 28695259 | 97 | 10004 | 193765 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982944924188 | 12074986836601783 | 12074986837759536 | 12074982946363363 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fa2f5f14600 | 0x7fa1ea237800 | 9591568 | 9425242 | 140735228 | 65536 | 1162425215 | 3600 | 48 | 0 | 1198945 | 1198945 | 0 | 0 | 3648 | 0 | 36634624 | 36613787 | 98 | 22622 | 204630 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982946404128 | 12074986837873295 | 12074986838657610 | 12074982947457696 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fa2f5f14500 | 0x7fa1ea237840 | 36674208 | 36505384 | 545532149 | 65536 | 4514740509 | 1008 | 48 | 0 | 4584275 | 4584275 | 0 | 0 | 1056 | 0 | 105840640 | 105839207 | 98 | 1742 | 227692 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982947490337 | 12074986838765289 | 12074986841817109 | 12074982950809064 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fa2f5f14400 | 0x7fa1ea237880 | 18601040 | 18430871 | 275262403 | 65536 | 2275460200 | 2064 | 48 | 0 | 2325129 | 2325129 | 0 | 0 | 2112 | 0 | 38535168 | 38528599 | 48 | 6964 | 233555 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982950842837 | 12074986841918869 | 12074986843460939 | 12074982952659744 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fa2f5f14300 | 0x7fa1ea2378c0 | 9630176 | 9457412 | 141205984 | 65536 | 1164425666 | 2112 | 48 | 0 | 1203771 | 1203771 | 0 | 0 | 2160 | 0 | 39124992 | 39118540 | 99 | 6706 | 189623 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982952691853 | 12074986843568618 | 12074986844357253 | 12074982953755039 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fa2f5f14a00 | 0x7fa1ea237900 | 27547728 | 27380162 | 409089277 | 65536 | 3383537837 | 2832 | 48 | 0 | 3443465 | 3443465 | 0 | 0 | 2880 | 0 | 55771136 | 55756757 | 97 | 15905 | 199048 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982953781618 | 12074986844460133 | 12074986846742198 | 12074982956336486 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fa2f5f14900 | 0x7fa1ea237940 | 18580384 | 18417492 | 275138560 | 65536 | 2274603495 | 3600 | 48 | 0 | 2322547 | 2322547 | 0 | 0 | 3648 | 0 | 72548352 | 72533014 | 99 | 15559 | 202795 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982956380899 | 12074986846857397 | 12074986848392747 | 12074982958162389 |
| 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 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fa2f5f14800 | 0x7fa1ea237980 | 72718224 | 72536328 | 1084083108 | 65536 | 8975916802 | 1008 | 48 | 0 | 9089777 | 9089777 | 0 | 0 | 1056 | 0 | 210698240 | 210696915 | 50 | 1829 | 202592 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 0 | 131072 | 0 | 12074982958193868 | 12074986848499627 | 12074986854554308 | 12074982964524553 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fa2f5f14700 | 0x7fa1ea2379c0 | 36582624 | 36417997 | 544133355 | 65536 | 4502987273 | 2064 | 48 | 0 | 4572827 | 4572827 | 0 | 0 | 2112 | 0 | 76283904 | 76279392 | 100 | 5032 | 183331 | 0 | 0 | 65536 | 64048 | 48 | 1440 | 0 | 0 | 65536 | 12074982964559538 | 12074986854657027 | 12074986857698928 | 12074982967879167 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fa2f5f14600 | 0x7fa1ea237a00 | 18622544 | 18460719 | 275853716 | 65536 | 2281572893 | 2112 | 48 | 0 | 2327817 | 2327817 | 0 | 0 | 2160 | 0 | 77398016 | 77390032 | 97 | 8226 | 199342 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982967914522 | 12074986857800207 | 12074986859338117 | 12074982969737330 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 856407 | 856412 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fa2f5f14500 | 0x7fa1ea237a40 | 54497632 | 54335450 | 812038192 | 65536 | 6724166281 | 2832 | 48 | 0 | 6812203 | 6812203 | 0 | 0 | 2880 | 0 | 110821376 | 110811222 | 97 | 10277 | 207278 | 0 | 0 | 131072 | 129584 | 48 | 1440 | 65536 | 65536 | 0 | 12074982969770642 | 12074986859439556 | 12074986863965447 | 12074982974573527 |