73 KiB
73 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_CYCLES | SQ_BUSY_CYCLES | SQ_WAVES | GRBM_COUNT | GRBM_GUI_ACTIVE | TCC_CYCLE_sum | TCC_BUSY_sum | TCC_PROBE_sum | TCC_PROBE_ALL_sum | TCC_EA_ATOMIC_LEVEL_sum | TCC_NC_REQ_sum | TCC_UC_REQ_sum | TCC_CC_REQ_sum | TCC_RW_REQ_sum | TCC_REQ_sum | TCC_STREAMING_REQ_sum | TCC_HIT_sum | TCC_MISS_sum | TCC_READ_sum | TCC_WRITE_sum | TCC_ATOMIC_sum | TCC_WRITEBACK_sum | TCC_EA_WRREQ_sum | TCC_EA_WRREQ_64B_sum | TCC_EA_WR_UNCACHED_32B_sum | TCC_EA_WRREQ_STALL_sum | TCC_EA_WRREQ_IO_CREDIT_STALL_sum | TCC_EA_WRREQ_GMI_CREDIT_STALL_sum | TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum | TCC_TOO_MANY_EA_WRREQS_STALL_sum | TCC_EA_ATOMIC_sum | TCC_EA_RDREQ_sum | TCC_EA_RDREQ_32B_sum | TCC_EA_RD_UNCACHED_32B_sum | TCC_EA_RDREQ_IO_CREDIT_STALL_sum | TCC_EA_RDREQ_GMI_CREDIT_STALL_sum | TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum | TCC_TAG_STALL_sum | TCC_NORMAL_WRITEBACK_sum | TCC_ALL_TC_OP_WB_WRITEBACK_sum | TCC_NORMAL_EVICT_sum | TCC_ALL_TC_OP_INV_EVICT_sum | TCC_EA_RDREQ_DRAM_sum | TCC_EA_WRREQ_DRAM_sum | TCC_EA_RDREQ_LEVEL_sum | TCC_EA_WRREQ_LEVEL_sum | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 864972 | 864977 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f090a604180 | 4083024 | 3882683 | 524288 | 510377 | 510377 | 16332064 | 15438920 | 0 | 0 | 0 | 96 | 10706 | 0 | 8388944 | 8399654 | 0 | 4194727 | 4204927 | 11207 | 8388608 | 0 | 4194378 | 4194386 | 4194386 | 0 | 229584 | 0 | 0 | 216344 | 0 | 0 | 10877 | 0 | 21736 | 0 | 0 | 0 | 147145 | 4128850 | 65536 | 4063243 | 0 | 10595 | 4194349 | 13173364 | 611242633 | 12075191621159880 | 12075203455198412 | 12075203455524809 | 12075191864510615 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 864972 | 864977 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f090a635100 | 217704 | 74338 | 512 | 27212 | 27212 | 870784 | 191747 | 0 | 0 | 0 | 48 | 172 | 0 | 8624 | 8891 | 0 | 470 | 8421 | 8891 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 8374 | 0 | 344 | 0 | 0 | 0 | 52670 | 0 | 0 | 0 | 0 | 8373 | 0 | 3091898 | 0 | 12075191879361132 | 12075203470647997 | 12075203470655037 | 12075191879878283 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f091615d900 | 0x7f090a635140 | 1715592 | 1546607 | 65536 | 214448 | 214448 | 6862336 | 6110609 | 0 | 0 | 0 | 48 | 5465 | 0 | 2097536 | 2098946 | 0 | 423 | 2098523 | 2099804 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098745 | 0 | 3168 | 0 | 0 | 332108 | 384983 | 0 | 0 | 1966100 | 0 | 2102035 | 0 | 831698689 | 0 | 12075191880009557 | 12075203470706876 | 12075203470837595 | 12075191880624029 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f091615d800 | 0x7f090a635180 | 3063856 | 2907594 | 65536 | 382981 | 382981 | 12255392 | 11523728 | 0 | 0 | 0 | 48 | 1936 | 0 | 4194784 | 4196965 | 0 | 517 | 4196448 | 4196714 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4198475 | 0 | 8320 | 0 | 0 | 1074607 | 1128108 | 0 | 0 | 4063245 | 0 | 4197011 | 0 | 2217122689 | 0 | 12075191880794656 | 12075203470885915 | 12075203471131193 | 12075191881498595 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f091615d700 | 0x7f090a6351c0 | 3120136 | 2957317 | 65536 | 390016 | 390016 | 12480512 | 11777512 | 0 | 0 | 0 | 48 | 2156 | 0 | 4194688 | 4197525 | 0 | 423 | 4197102 | 4195950 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196722 | 0 | 4818 | 0 | 0 | 813701 | 866392 | 0 | 0 | 4063243 | 0 | 4196263 | 0 | 1985357410 | 0 | 12075191881573323 | 12075203471261272 | 12075203471507669 | 12075191882248548 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f091615d600 | 0x7f090a635200 | 1723184 | 1563306 | 65536 | 215397 | 215397 | 6892704 | 6163624 | 0 | 0 | 0 | 48 | 4718 | 0 | 2097584 | 2099293 | 0 | 470 | 2098823 | 2101446 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099630 | 0 | 4936 | 0 | 0 | 900891 | 954341 | 0 | 0 | 1966104 | 0 | 2102571 | 0 | 807283818 | 0 | 12075191882347422 | 12075203471639348 | 12075203471764627 | 12075191882868210 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f091615d500 | 0x7f090a635240 | 1808880 | 1650508 | 65536 | 226109 | 226109 | 7235488 | 6512184 | 0 | 0 | 0 | 48 | 4222 | 0 | 2097584 | 2101825 | 0 | 470 | 2101355 | 2100702 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099845 | 0 | 5366 | 0 | 0 | 715454 | 768417 | 0 | 0 | 1966099 | 0 | 2100387 | 0 | 1096655296 | 0 | 12075191883015103 | 12075203471794547 | 12075203471920146 | 12075191883532835 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f091615d400 | 0x7f090a635280 | 1720192 | 1566333 | 65536 | 215023 | 215023 | 6880736 | 6181056 | 0 | 0 | 0 | 48 | 2742 | 0 | 2097584 | 2100111 | 0 | 470 | 2099641 | 2099885 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099809 | 0 | 5294 | 0 | 0 | 629506 | 681606 | 0 | 0 | 1966094 | 0 | 2100055 | 0 | 1127499835 | 0 | 12075191883726525 | 12075203471977745 | 12075203472102224 | 12075191884230161 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f091615d300 | 0x7f090a6352c0 | 3163888 | 3003778 | 65536 | 395485 | 395485 | 12655520 | 11907469 | 0 | 0 | 0 | 48 | 2627 | 0 | 4194928 | 4195699 | 0 | 658 | 4195041 | 4196137 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195144 | 0 | 1652 | 0 | 0 | 1464878 | 1519019 | 0 | 0 | 4063248 | 0 | 4195443 | 0 | 2552377255 | 0 | 12075191884404274 | 12075203472130864 | 12075203472376622 | 12075191885090029 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f091615da00 | 0x7f090a635300 | 3142600 | 2974743 | 65536 | 392824 | 392824 | 12570368 | 11852334 | 0 | 0 | 0 | 48 | 2220 | 0 | 4194784 | 4196120 | 0 | 517 | 4195603 | 4196236 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196423 | 0 | 4216 | 0 | 0 | 635650 | 691562 | 0 | 0 | 4063245 | 0 | 4196051 | 0 | 2010572809 | 0 | 12075191885174967 | 12075203472509901 | 12075203472753419 | 12075191885859098 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f091615d900 | 0x7f090a635340 | 1708656 | 1548602 | 65536 | 213581 | 213581 | 6834592 | 6100076 | 0 | 0 | 0 | 48 | 3365 | 0 | 2097632 | 2100275 | 0 | 517 | 2099758 | 2099161 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098050 | 0 | 1774 | 0 | 0 | 572766 | 622103 | 0 | 0 | 1966101 | 0 | 2099538 | 0 | 1216229674 | 0 | 12075191885971807 | 12075203472885897 | 12075203473011016 | 12075191886478619 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f091615d800 | 0x7f090a635380 | 1697152 | 1545629 | 65536 | 212143 | 212143 | 6788576 | 6071609 | 0 | 0 | 0 | 48 | 3355 | 0 | 2097632 | 2099424 | 0 | 517 | 2098907 | 2099955 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099086 | 0 | 3846 | 0 | 0 | 305197 | 358283 | 0 | 0 | 1966096 | 0 | 2102003 | 0 | 855462017 | 0 | 12075191886660287 | 12075203473043816 | 12075203473168615 | 12075191887148494 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f091615d700 | 0x7f090a6353c0 | 1675736 | 1519501 | 65536 | 209466 | 209466 | 6702912 | 5991943 | 0 | 0 | 0 | 48 | 4158 | 0 | 2097632 | 2100235 | 0 | 517 | 2099718 | 2098694 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099160 | 0 | 3994 | 0 | 0 | 575934 | 626049 | 0 | 0 | 1966101 | 0 | 2099137 | 0 | 1262360466 | 0 | 12075191887339309 | 12075203473212135 | 12075203473336454 | 12075191887826314 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f091615d600 | 0x7f090a635400 | 3116952 | 2963163 | 65536 | 389618 | 389618 | 12467776 | 11745474 | 0 | 0 | 0 | 48 | 1804 | 0 | 4195024 | 4196491 | 0 | 752 | 4195739 | 4196031 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196959 | 0 | 5278 | 0 | 0 | 979397 | 1033378 | 0 | 0 | 4063250 | 0 | 4195194 | 0 | 1903319451 | 0 | 12075191887933743 | 12075203473368453 | 12075203473614851 | 12075191888667437 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f091615d500 | 0x7f090a635440 | 3163568 | 3000206 | 65536 | 395445 | 395445 | 12654240 | 11961223 | 0 | 0 | 0 | 48 | 1739 | 0 | 4194832 | 4195860 | 0 | 564 | 4195296 | 4196023 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195457 | 0 | 2282 | 0 | 0 | 914992 | 968736 | 0 | 0 | 4063246 | 0 | 4195288 | 0 | 2004543644 | 0 | 12075191888774766 | 12075203473751650 | 12075203473995008 | 12075191889462023 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f091615d400 | 0x7f090a635480 | 1723608 | 1574384 | 65536 | 215450 | 215450 | 6894400 | 6193956 | 0 | 0 | 0 | 48 | 3478 | 0 | 2097680 | 2099218 | 0 | 564 | 2098654 | 2100210 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099361 | 0 | 4394 | 0 | 0 | 759590 | 809239 | 0 | 0 | 1966107 | 0 | 2099551 | 0 | 1193817523 | 0 | 12075191889572429 | 12075203474087807 | 12075203474212126 | 12075191890062169 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f091615d300 | 0x7f090a6354c0 | 1770504 | 1611786 | 65536 | 221312 | 221312 | 7081984 | 6342549 | 0 | 0 | 0 | 48 | 1937 | 0 | 2097680 | 2099766 | 0 | 564 | 2099202 | 2099713 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099728 | 0 | 5128 | 0 | 0 | 634762 | 687619 | 0 | 0 | 1966101 | 0 | 2100980 | 0 | 962412653 | 0 | 12075191890237414 | 12075203474240286 | 12075203474365245 | 12075191890728808 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f091615da00 | 0x7f090a635500 | 1671920 | 1516070 | 65536 | 208989 | 208989 | 6687648 | 5984541 | 0 | 0 | 0 | 48 | 1317 | 0 | 2097680 | 2100520 | 0 | 564 | 2099956 | 2099852 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099311 | 0 | 4294 | 0 | 0 | 617663 | 668314 | 0 | 0 | 1966103 | 0 | 2099198 | 0 | 1248796906 | 0 | 12075191890910826 | 12075203474411484 | 12075203474535803 | 12075191891398492 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f091615d900 | 0x7f090a635540 | 3254920 | 3088588 | 65536 | 406864 | 406864 | 13019648 | 12267616 | 0 | 0 | 0 | 48 | 1340 | 0 | 4195120 | 4196240 | 0 | 846 | 4195394 | 4196368 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194998 | 0 | 1352 | 0 | 0 | 513736 | 567471 | 0 | 0 | 4063256 | 0 | 4197048 | 0 | 2048759033 | 0 | 12075191891503257 | 12075203474563963 | 12075203474816921 | 12075191892239305 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f091615d800 | 0x7f090a635580 | 3177968 | 3020518 | 65536 | 397245 | 397245 | 12711840 | 11990319 | 0 | 0 | 0 | 48 | 1906 | 0 | 4194880 | 4196356 | 0 | 611 | 4195745 | 4196940 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195941 | 0 | 3248 | 0 | 0 | 737027 | 789994 | 0 | 0 | 4063247 | 0 | 4195236 | 0 | 2701879389 | 0 | 12075191892343909 | 12075203474879960 | 12075203475124758 | 12075191893020687 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f091615d700 | 0x7f090a6355c0 | 1707464 | 1544906 | 65536 | 213432 | 213432 | 6829824 | 6104750 | 0 | 0 | 0 | 48 | 2650 | 0 | 2097728 | 2100873 | 0 | 611 | 2100262 | 2101166 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098807 | 0 | 3284 | 0 | 0 | 930031 | 981983 | 0 | 0 | 1966106 | 0 | 2100170 | 0 | 1056513934 | 0 | 12075191893102088 | 12075203475224597 | 12075203475349876 | 12075191893586568 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f091615d600 | 0x7f090a635600 | 1698048 | 1543453 | 65536 | 212255 | 212255 | 6792160 | 6055960 | 0 | 0 | 0 | 48 | 3408 | 0 | 2097776 | 2100543 | 0 | 658 | 2099885 | 2100346 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098687 | 0 | 3042 | 0 | 0 | 399258 | 452123 | 0 | 0 | 1966101 | 0 | 2099670 | 0 | 1136368675 | 0 | 12075191893759480 | 12075203475383796 | 12075203475509235 | 12075191894244481 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f091615d500 | 0x7f090a635640 | 1712432 | 1554109 | 65536 | 214053 | 214053 | 6849696 | 6116117 | 0 | 0 | 0 | 48 | 4341 | 0 | 2097728 | 2100914 | 0 | 611 | 2100303 | 2099513 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099846 | 0 | 5362 | 0 | 0 | 638661 | 688582 | 0 | 0 | 1966101 | 0 | 2099924 | 0 | 1145226270 | 0 | 12075191894434504 | 12075203475550994 | 12075203475675473 | 12075191894912182 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f091615d400 | 0x7f090a635680 | 3152392 | 2991346 | 65536 | 394048 | 394048 | 12609536 | 11851849 | 0 | 0 | 0 | 48 | 2415 | 0 | 4195216 | 4196164 | 0 | 940 | 4195224 | 4196088 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196956 | 0 | 5264 | 0 | 0 | 708974 | 763155 | 0 | 0 | 4063254 | 0 | 4195925 | 0 | 2119390022 | 0 | 12075191895087357 | 12075203475706833 | 12075203475957871 | 12075191895754467 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f091615d300 | 0x7f090a6356c0 | 3691568 | 3043441 | 65536 | 461445 | 461445 | 14766240 | 12141785 | 0 | 0 | 0 | 48 | 1652 | 0 | 4194928 | 4197422 | 0 | 658 | 4196764 | 4195858 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195560 | 0 | 2484 | 0 | 0 | 868510 | 922025 | 0 | 0 | 4063248 | 0 | 4196233 | 0 | 2049220925 | 0 | 12075191895862388 | 12075203476027150 | 12075203476271308 | 12075191896582526 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f091615da00 | 0x7f090a635700 | 1731272 | 1566492 | 65536 | 216408 | 216408 | 6925056 | 6180044 | 0 | 0 | 0 | 48 | 3962 | 0 | 2097776 | 2100045 | 0 | 658 | 2099387 | 2099775 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099902 | 0 | 5472 | 0 | 0 | 752168 | 802231 | 0 | 0 | 1966106 | 0 | 2100235 | 0 | 1096459391 | 0 | 12075191896689535 | 12075203476359627 | 12075203476483786 | 12075191897176780 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f091615d900 | 0x7f090a635740 | 1776968 | 1618430 | 65536 | 222120 | 222120 | 7107840 | 6320202 | 0 | 0 | 0 | 48 | 3214 | 0 | 2097824 | 2099886 | 0 | 705 | 2099181 | 2099584 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099767 | 0 | 5200 | 0 | 0 | 656209 | 709928 | 0 | 0 | 1966102 | 0 | 2100405 | 0 | 1038289177 | 0 | 12075191897354140 | 12075203476522186 | 12075203476647145 | 12075191897838310 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f091615d800 | 0x7f090a635780 | 1698184 | 1541257 | 65536 | 212272 | 212272 | 6792704 | 6081767 | 0 | 0 | 0 | 48 | 2401 | 0 | 2097728 | 2100466 | 0 | 611 | 2099855 | 2100027 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098441 | 0 | 2552 | 0 | 0 | 554179 | 603864 | 0 | 0 | 1966103 | 0 | 2099321 | 0 | 1247475087 | 0 | 12075191897993668 | 12075203476687944 | 12075203476812263 | 12075191898476726 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f091615d700 | 0x7f090a6357c0 | 3209032 | 3042558 | 65536 | 401128 | 401128 | 12836096 | 12096737 | 0 | 0 | 0 | 48 | 1652 | 0 | 4195312 | 4197204 | 0 | 1034 | 4196170 | 4197336 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195108 | 0 | 1564 | 0 | 0 | 1007104 | 1060228 | 0 | 0 | 4063256 | 0 | 4196852 | 0 | 2371273094 | 0 | 12075191898650028 | 12075203476840423 | 12075203477090501 | 12075191899323800 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f091615d600 | 0x7f090a635800 | 3123328 | 2969489 | 65536 | 390415 | 390415 | 12493280 | 11799713 | 0 | 0 | 0 | 48 | 1897 | 0 | 4194976 | 4196394 | 0 | 705 | 4195689 | 4196160 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196881 | 0 | 5124 | 0 | 0 | 1407313 | 1461110 | 0 | 0 | 4063249 | 0 | 4196279 | 0 | 2093845204 | 0 | 12075191899434576 | 12075203477227620 | 12075203477474498 | 12075191900098149 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f091615d500 | 0x7f090a635840 | 1703616 | 1544015 | 65536 | 212951 | 212951 | 6814432 | 6092114 | 0 | 0 | 0 | 48 | 3045 | 0 | 2097824 | 2100886 | 0 | 705 | 2100181 | 2101216 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099844 | 0 | 5354 | 0 | 0 | 828738 | 877185 | 0 | 0 | 1966108 | 0 | 2100143 | 0 | 1145546712 | 0 | 12075191900206731 | 12075203477609856 | 12075203477734975 | 12075191900686142 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f091615d400 | 0x7f090a635880 | 1709360 | 1547993 | 65536 | 213669 | 213669 | 6837408 | 6054358 | 0 | 0 | 0 | 48 | 4205 | 0 | 2097920 | 2100704 | 0 | 799 | 2099905 | 2099060 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100465 | 0 | 6592 | 0 | 0 | 765675 | 819281 | 0 | 0 | 1966102 | 0 | 2099926 | 0 | 1143354828 | 0 | 12075191900861618 | 12075203477765855 | 12075203477890974 | 12075191901351218 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f091615d300 | 0x7f090a6358c0 | 1735880 | 1570499 | 65536 | 216984 | 216984 | 6943488 | 6185743 | 0 | 0 | 0 | 48 | 3229 | 0 | 2097824 | 2100250 | 0 | 705 | 2099545 | 2100254 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098477 | 0 | 2620 | 0 | 0 | 924773 | 977689 | 0 | 0 | 1966104 | 0 | 2099053 | 0 | 1325954960 | 0 | 12075191901537294 | 12075203477933534 | 12075203478058652 | 12075191902019820 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f091615da00 | 0x7f090a635900 | 3146504 | 2991939 | 65536 | 393312 | 393312 | 12585984 | 11859228 | 0 | 0 | 0 | 48 | 2011 | 0 | 4195408 | 4196890 | 0 | 1128 | 4195762 | 4196564 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197400 | 0 | 6144 | 0 | 0 | 1290199 | 1344277 | 0 | 0 | 4063258 | 0 | 4197394 | 0 | 2022930949 | 0 | 12075191902195166 | 12075203478086972 | 12075203478340090 | 12075191902865452 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f091615d900 | 0x7f090a635940 | 3153032 | 2992181 | 65536 | 394128 | 394128 | 12612096 | 11894821 | 0 | 0 | 0 | 48 | 1096 | 0 | 4195024 | 4197196 | 0 | 752 | 4196444 | 4196108 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196671 | 0 | 4702 | 0 | 0 | 749761 | 802908 | 0 | 0 | 4063250 | 0 | 4196335 | 0 | 2339520525 | 0 | 12075191902972310 | 12075203478458169 | 12075203478706647 | 12075191903644890 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f091615d800 | 0x7f090a635980 | 1695856 | 1542138 | 65536 | 211981 | 211981 | 6783392 | 6065361 | 0 | 0 | 0 | 48 | 4283 | 0 | 2097872 | 2101644 | 0 | 752 | 2100892 | 2101401 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099280 | 0 | 4224 | 0 | 0 | 643151 | 695770 | 0 | 0 | 1966098 | 0 | 2101292 | 0 | 934386300 | 0 | 12075191903751729 | 12075203478774806 | 12075203478899605 | 12075191904240537 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f091615d700 | 0x7f090a6359c0 | 1795696 | 1630567 | 65536 | 224461 | 224461 | 7182752 | 6364619 | 0 | 0 | 0 | 48 | 5061 | 0 | 2097968 | 2099826 | 0 | 846 | 2098980 | 2102168 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098943 | 0 | 3546 | 0 | 0 | 619748 | 672345 | 0 | 0 | 1966104 | 0 | 2101455 | 0 | 901763964 | 0 | 12075191904415482 | 12075203478932245 | 12075203479058164 | 12075191904907667 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f091615d600 | 0x7f090a635a00 | 1650184 | 1493361 | 65536 | 206272 | 206272 | 6600704 | 5889320 | 0 | 0 | 0 | 48 | 2282 | 0 | 2097872 | 2100578 | 0 | 752 | 2099826 | 2101561 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098999 | 0 | 3662 | 0 | 0 | 532464 | 582652 | 0 | 0 | 1966101 | 0 | 2099308 | 0 | 1228620700 | 0 | 12075191905097540 | 12075203479098963 | 12075203479222962 | 12075191905574787 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f091615d500 | 0x7f090a635a40 | 3207768 | 3035897 | 65536 | 400970 | 400970 | 12831040 | 12039996 | 0 | 0 | 0 | 48 | 1954 | 0 | 4195504 | 4197920 | 0 | 1222 | 4196698 | 4196721 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195911 | 0 | 3162 | 0 | 0 | 669849 | 723925 | 0 | 0 | 4063260 | 0 | 4197110 | 0 | 2165890546 | 0 | 12075191905678820 | 12075203479252242 | 12075203479500240 | 12075191906411221 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f091615d400 | 0x7f090a635a80 | 3126744 | 2960257 | 65536 | 390842 | 390842 | 12506944 | 11757336 | 0 | 0 | 0 | 48 | 1693 | 0 | 4195072 | 4197513 | 0 | 799 | 4196714 | 4196969 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195565 | 0 | 2488 | 0 | 0 | 746072 | 799432 | 0 | 0 | 4063251 | 0 | 4196825 | 0 | 1977346100 | 0 | 12075191906495788 | 12075203479545840 | 12075203479793357 | 12075191907162217 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f091615d300 | 0x7f090a635ac0 | 1753560 | 1595804 | 65536 | 219194 | 219194 | 7014208 | 6247913 | 0 | 0 | 0 | 48 | 2427 | 0 | 2097920 | 2100987 | 0 | 799 | 2100188 | 2100569 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100073 | 0 | 5808 | 0 | 0 | 454954 | 504361 | 0 | 0 | 1966105 | 0 | 2099236 | 0 | 1276196500 | 0 | 12075191907269025 | 12075203479838957 | 12075203479963596 | 12075191907752283 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f091615da00 | 0x7f090a635b00 | 1759176 | 1591847 | 65536 | 219896 | 219896 | 7036672 | 6195153 | 0 | 0 | 0 | 48 | 2941 | 0 | 2098064 | 2100317 | 0 | 940 | 2099377 | 2100175 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100211 | 0 | 6078 | 0 | 0 | 399751 | 453091 | 0 | 0 | 1966110 | 0 | 2101082 | 0 | 916318753 | 0 | 12075191907924303 | 12075203479992716 | 12075203480119595 | 12075191908420986 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f091615d900 | 0x7f090a635b40 | 1728368 | 1566638 | 65536 | 216045 | 216045 | 6913440 | 6143207 | 0 | 0 | 0 | 48 | 2538 | 0 | 2097920 | 2100666 | 0 | 799 | 2099867 | 2100336 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099023 | 0 | 3708 | 0 | 0 | 560309 | 611204 | 0 | 0 | 1966109 | 0 | 2100510 | 0 | 1052248824 | 0 | 12075191908603676 | 12075203480161514 | 12075203480286633 | 12075191909084529 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f091615d800 | 0x7f090a635b80 | 3255664 | 3083596 | 65536 | 406957 | 406957 | 13022624 | 12208229 | 0 | 0 | 0 | 48 | 1988 | 0 | 4195600 | 4198326 | 0 | 1316 | 4197010 | 4197383 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197920 | 0 | 7176 | 0 | 0 | 435983 | 488604 | 0 | 0 | 4063262 | 0 | 4196476 | 0 | 1854530255 | 0 | 12075191909256248 | 12075203480316233 | 12075203480580871 | 12075191909907018 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f091615d700 | 0x7f090a635bc0 | 3120704 | 2953683 | 65536 | 390087 | 390087 | 12482784 | 11774060 | 0 | 0 | 0 | 48 | 1072 | 0 | 4195120 | 4196359 | 0 | 846 | 4195513 | 4196305 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195638 | 0 | 2632 | 0 | 0 | 697376 | 750216 | 0 | 0 | 4063252 | 0 | 4196280 | 0 | 1676476333 | 0 | 12075191910019056 | 12075203480627270 | 12075203480872228 | 12075191910687829 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f091615d600 | 0x7f090a635c00 | 1710984 | 1549959 | 65536 | 213872 | 213872 | 6843904 | 6077188 | 0 | 0 | 0 | 48 | 4012 | 0 | 2097968 | 2098631 | 0 | 846 | 2097785 | 2101259 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098843 | 0 | 3346 | 0 | 0 | 693282 | 743051 | 0 | 0 | 1966104 | 0 | 2100407 | 0 | 1080353316 | 0 | 12075191910799737 | 12075203480922948 | 12075203481047586 | 12075191911287543 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f091615d500 | 0x7f090a635c40 | 1773000 | 1601686 | 65536 | 221624 | 221624 | 7091968 | 6226234 | 0 | 0 | 0 | 48 | 1775 | 0 | 2098112 | 2100908 | 0 | 987 | 2099921 | 2102037 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099625 | 0 | 4904 | 0 | 0 | 667248 | 720599 | 0 | 0 | 1966114 | 0 | 2100735 | 0 | 996355751 | 0 | 12075191911465253 | 12075203481077826 | 12075203481204225 | 12075191911948241 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f091615d400 | 0x7f090a635c80 | 1670336 | 1510688 | 65536 | 208791 | 208791 | 6681312 | 5939982 | 0 | 0 | 0 | 48 | 3053 | 0 | 2097968 | 2099405 | 0 | 846 | 2098559 | 2099574 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099844 | 0 | 5348 | 0 | 0 | 306175 | 356746 | 0 | 0 | 1966100 | 0 | 2098449 | 0 | 1335357846 | 0 | 12075191912115512 | 12075203481246305 | 12075203481371424 | 12075191912592418 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f091615d300 | 0x7f090a635cc0 | 3218032 | 3027944 | 65536 | 402253 | 402253 | 12872096 | 12079277 | 0 | 0 | 0 | 48 | 2012 | 0 | 4195696 | 4198033 | 0 | 1410 | 4196623 | 4197916 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4198214 | 0 | 7760 | 0 | 0 | 946021 | 998138 | 0 | 0 | 4063264 | 0 | 4196383 | 0 | 1816474797 | 0 | 12075191912697043 | 12075203481402463 | 12075203481660861 | 12075191913421779 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f091615da00 | 0x7f090a635d00 | 3153968 | 2980327 | 65536 | 394245 | 394245 | 12615840 | 11918259 | 0 | 0 | 0 | 48 | 1370 | 0 | 4195168 | 4196625 | 0 | 893 | 4195732 | 4196416 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197007 | 0 | 5368 | 0 | 0 | 1394479 | 1448527 | 0 | 0 | 4063253 | 0 | 4196292 | 0 | 2197798980 | 0 | 12075191913529690 | 12075203481707741 | 12075203481952219 | 12075191914199835 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f091615d900 | 0x7f090a635d40 | 1707264 | 1544604 | 65536 | 213407 | 213407 | 6829024 | 6074874 | 0 | 0 | 0 | 48 | 3675 | 0 | 2098016 | 2100919 | 0 | 893 | 2100026 | 2101512 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099251 | 0 | 4160 | 0 | 0 | 492326 | 543083 | 0 | 0 | 1966117 | 0 | 2099810 | 0 | 1212076433 | 0 | 12075191914279583 | 12075203481996378 | 12075203482121017 | 12075191914768332 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f091615d800 | 0x7f090a635d80 | 1812296 | 1648635 | 65536 | 226536 | 226536 | 7249152 | 6412176 | 0 | 0 | 0 | 48 | 4502 | 0 | 2098208 | 2102410 | 0 | 1081 | 2101329 | 2101409 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100606 | 0 | 6862 | 0 | 0 | 560145 | 613449 | 0 | 0 | 1966106 | 0 | 2101191 | 0 | 940412536 | 0 | 12075191914940892 | 12075203482149977 | 12075203482278296 | 12075191915433899 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f091615d700 | 0x7f090a635dc0 | 1728136 | 1541390 | 65536 | 216016 | 216016 | 6912512 | 6082439 | 0 | 0 | 0 | 48 | 2051 | 0 | 2098016 | 2100244 | 0 | 893 | 2099351 | 2100286 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098267 | 0 | 2192 | 0 | 0 | 919985 | 972453 | 0 | 0 | 1966106 | 0 | 2098881 | 0 | 1324483811 | 0 | 12075191915616758 | 12075203482321655 | 12075203482447094 | 12075191916098143 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f091615d600 | 0x7f090a635e00 | 3179824 | 3011129 | 65536 | 397477 | 397477 | 12719264 | 11943814 | 0 | 0 | 0 | 48 | 1240 | 0 | 4195792 | 4197021 | 0 | 1504 | 4195517 | 4198792 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195223 | 0 | 1774 | 0 | 0 | 965598 | 1019643 | 0 | 0 | 4063266 | 0 | 4197095 | 0 | 2041279750 | 0 | 12075191916273369 | 12075203482479254 | 12075203482738452 | 12075191916942292 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f091615d500 | 0x7f090a635e40 | 3130048 | 2965374 | 65536 | 391255 | 391255 | 12520160 | 11782267 | 0 | 0 | 0 | 48 | 2209 | 0 | 4195216 | 4197250 | 0 | 940 | 4196310 | 4197057 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196736 | 0 | 4824 | 0 | 0 | 1239372 | 1292640 | 0 | 0 | 4063254 | 0 | 4196639 | 0 | 2299558624 | 0 | 12075191917057526 | 12075203482782771 | 12075203483032529 | 12075191917723303 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f091615d400 | 0x7f090a635e80 | 1737264 | 1582801 | 65536 | 217157 | 217157 | 6949024 | 6208585 | 0 | 0 | 0 | 48 | 3074 | 0 | 2098064 | 2100420 | 0 | 940 | 2099480 | 2100478 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098775 | 0 | 3206 | 0 | 0 | 693211 | 746486 | 0 | 0 | 1966110 | 0 | 2100365 | 0 | 1052390577 | 0 | 12075191917829531 | 12075203483082449 | 12075203483207568 | 12075191918319822 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f091615d300 | 0x7f090a635ec0 | 1802440 | 1632823 | 65536 | 225304 | 225304 | 7209728 | 6362739 | 0 | 0 | 0 | 48 | 4323 | 0 | 2098256 | 2102067 | 0 | 1128 | 2100939 | 2102151 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2101471 | 0 | 8590 | 0 | 0 | 485072 | 541856 | 0 | 0 | 1966112 | 0 | 2100393 | 0 | 1041490412 | 0 | 12075191918493284 | 12075203483240687 | 12075203483367886 | 12075191918977063 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f091615da00 | 0x7f090a635f00 | 1695816 | 1541157 | 65536 | 211976 | 211976 | 6783232 | 6036021 | 0 | 0 | 0 | 48 | 3062 | 0 | 2098064 | 2101188 | 0 | 940 | 2100248 | 2100106 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098758 | 0 | 3172 | 0 | 0 | 560850 | 609541 | 0 | 0 | 1966104 | 0 | 2100644 | 0 | 1003204562 | 0 | 12075191919160985 | 12075203483410446 | 12075203483535725 | 12075191919636839 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f091615d900 | 0x7f090a635f40 | 3240560 | 3056906 | 65536 | 405069 | 405069 | 12962208 | 12128106 | 0 | 0 | 0 | 48 | 2057 | 0 | 4195888 | 4197410 | 0 | 1598 | 4195812 | 4197166 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195099 | 0 | 1522 | 0 | 0 | 544622 | 598714 | 0 | 0 | 4063268 | 0 | 4195687 | 0 | 2525683269 | 0 | 12075191919809620 | 12075203483565005 | 12075203483817642 | 12075191920489083 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f091615d800 | 0x7f090a635f80 | 3118552 | 2961127 | 65536 | 389818 | 389818 | 12474176 | 11749912 | 0 | 0 | 0 | 48 | 2640 | 0 | 4195264 | 4197900 | 0 | 987 | 4196913 | 4196329 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195880 | 0 | 3110 | 0 | 0 | 646176 | 698130 | 0 | 0 | 4063255 | 0 | 4196275 | 0 | 2147002030 | 0 | 12075191920600130 | 12075203483870282 | 12075203484113480 | 12075191921267810 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f091615d700 | 0x7f090a635fc0 | 1712840 | 1548654 | 65536 | 214104 | 214104 | 6851328 | 6086730 | 0 | 0 | 0 | 48 | 4214 | 0 | 2098112 | 2099265 | 0 | 987 | 2098278 | 2100009 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099528 | 0 | 4710 | 0 | 0 | 790810 | 841556 | 0 | 0 | 1966103 | 0 | 2098378 | 0 | 1357240885 | 0 | 12075191921377805 | 12075203484163559 | 12075203484289158 | 12075191921853579 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f091615d600 | 0x7f090a636000 | 1761480 | 1602009 | 65536 | 220184 | 220184 | 7045888 | 6279463 | 0 | 0 | 0 | 48 | 2992 | 0 | 2098352 | 2100420 | 0 | 1222 | 2099198 | 2101292 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099916 | 0 | 5476 | 0 | 0 | 540278 | 592863 | 0 | 0 | 1966108 | 0 | 2099589 | 0 | 1006878056 | 0 | 12075191921998959 | 12075203484320838 | 12075203484458597 | 12075191922497516 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f091615d500 | 0x7f090a636040 | 1727872 | 1572487 | 65536 | 215983 | 215983 | 6911456 | 6171692 | 0 | 0 | 0 | 48 | 3046 | 0 | 2098112 | 2100735 | 0 | 987 | 2099748 | 2099791 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098551 | 0 | 2756 | 0 | 0 | 882473 | 931054 | 0 | 0 | 1966111 | 0 | 2100151 | 0 | 1091587429 | 0 | 12075191922680315 | 12075203484500356 | 12075203484625475 | 12075191923161990 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f091615d400 | 0x7f090a636080 | 3187504 | 3009436 | 65536 | 398437 | 398437 | 12749984 | 11948426 | 0 | 0 | 0 | 48 | 2253 | 0 | 4195984 | 4198312 | 0 | 1692 | 4196620 | 4197788 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197918 | 0 | 7156 | 0 | 0 | 517923 | 571289 | 0 | 0 | 4063270 | 0 | 4196381 | 0 | 1669747979 | 0 | 12075191923334832 | 12075203484657475 | 12075203484913793 | 12075191924015076 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f091615d300 | 0x7f090a6360c0 | 3185112 | 3013111 | 65536 | 398138 | 398138 | 12740416 | 11984256 | 0 | 0 | 0 | 48 | 1175 | 0 | 4195312 | 4197164 | 0 | 1034 | 4196130 | 4196425 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196490 | 0 | 4328 | 0 | 0 | 978227 | 1031200 | 0 | 0 | 4063256 | 0 | 4196808 | 0 | 2044035920 | 0 | 12075191924100004 | 12075203484958592 | 12075203485244030 | 12075191924768346 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f091615da00 | 0x7f090a636100 | 1686216 | 1532640 | 65536 | 210776 | 210776 | 6744832 | 6009991 | 0 | 0 | 0 | 48 | 4835 | 0 | 2098160 | 2099801 | 0 | 1034 | 2098767 | 2102267 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098545 | 0 | 2742 | 0 | 0 | 496738 | 546946 | 0 | 0 | 1966104 | 0 | 2100724 | 0 | 1028575233 | 0 | 12075191924877088 | 12075203485293790 | 12075203485418908 | 12075191925362780 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f091615d900 | 0x7f090a636140 | 1833304 | 1670406 | 65536 | 229162 | 229162 | 7333184 | 6508258 | 0 | 0 | 0 | 48 | 1368 | 0 | 2098400 | 2099420 | 0 | 1269 | 2098151 | 2099450 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098121 | 0 | 1884 | 0 | 0 | 619290 | 672116 | 0 | 0 | 1966109 | 0 | 2098424 | 0 | 1136300098 | 0 | 12075191925539789 | 12075203485448028 | 12075203485590907 | 12075191926030621 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f091615d800 | 0x7f090a636180 | 1717000 | 1553617 | 65536 | 214624 | 214624 | 6867968 | 6115510 | 0 | 0 | 0 | 48 | 2955 | 0 | 2098160 | 2101083 | 0 | 1034 | 2100049 | 2100287 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098709 | 0 | 3070 | 0 | 0 | 624228 | 675640 | 0 | 0 | 1966108 | 0 | 2099693 | 0 | 1166428244 | 0 | 12075191926214754 | 12075203485632987 | 12075203485758106 | 12075191926692992 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f091615d700 | 0x7f090a6361c0 | 3214384 | 3023920 | 65536 | 401797 | 401797 | 12857504 | 11994864 | 0 | 0 | 0 | 48 | 2728 | 0 | 4196080 | 4199181 | 0 | 1786 | 4197395 | 4199844 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197424 | 0 | 6164 | 0 | 0 | 728027 | 781801 | 0 | 0 | 4063272 | 0 | 4198286 | 0 | 2016851243 | 0 | 12075191926863870 | 12075203485787225 | 12075203486048823 | 12075191927542902 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f091615d600 | 0x7f090a636200 | 3088776 | 2902448 | 65536 | 386096 | 386096 | 12355072 | 11618776 | 0 | 0 | 0 | 48 | 1905 | 0 | 4195360 | 4197771 | 0 | 1081 | 4196690 | 4196692 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195511 | 0 | 2368 | 0 | 0 | 569045 | 621264 | 0 | 0 | 4063257 | 0 | 4196520 | 0 | 2279451458 | 0 | 12075191927615096 | 12075203486095063 | 12075203486338740 | 12075191928289970 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f091615d500 | 0x7f090a636240 | 1763376 | 1596956 | 65536 | 220421 | 220421 | 7053472 | 6261256 | 0 | 0 | 0 | 48 | 5059 | 0 | 2098208 | 2101152 | 0 | 1081 | 2100071 | 2101397 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100790 | 0 | 7230 | 0 | 0 | 492170 | 543632 | 0 | 0 | 1966111 | 0 | 2099317 | 0 | 1225478910 | 0 | 12075191928395737 | 12075203486387860 | 12075203486513619 | 12075191928878223 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f091615d400 | 0x7f090a636280 | 1908104 | 1754446 | 65536 | 238512 | 238512 | 7632384 | 6876204 | 0 | 0 | 0 | 48 | 901 | 0 | 2098496 | 2099325 | 0 | 1363 | 2097962 | 2099587 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098018 | 0 | 1674 | 0 | 0 | 421617 | 474516 | 0 | 0 | 1966111 | 0 | 2097798 | 0 | 977037129 | 0 | 12075191929061704 | 12075203486542259 | 12075203486691537 | 12075191929558127 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f091615d300 | 0x7f090a6362c0 | 1730992 | 1567109 | 65536 | 216373 | 216373 | 6923936 | 6131355 | 0 | 0 | 0 | 48 | 1674 | 0 | 2098208 | 2099281 | 0 | 1081 | 2098200 | 2099894 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098651 | 0 | 2952 | 0 | 0 | 587618 | 638904 | 0 | 0 | 1966107 | 0 | 2100742 | 0 | 1012448139 | 0 | 12075191929758609 | 12075203486749457 | 12075203486875056 | 12075191930242198 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f091615da00 | 0x7f090a636300 | 3233864 | 3047474 | 65536 | 404232 | 404232 | 12935424 | 12098634 | 0 | 0 | 0 | 48 | 2038 | 0 | 4196176 | 4199720 | 0 | 1880 | 4197840 | 4199181 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4198331 | 0 | 7974 | 0 | 0 | 823906 | 877853 | 0 | 0 | 4063274 | 0 | 4196467 | 0 | 1808971008 | 0 | 12075191930418205 | 12075203486904336 | 12075203487168493 | 12075191931096125 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f091615d900 | 0x7f090a636340 | 3106568 | 2943399 | 65536 | 388320 | 388320 | 12426240 | 11669462 | 0 | 0 | 0 | 48 | 1918 | 0 | 4195408 | 4196584 | 0 | 1128 | 4195456 | 4198530 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196697 | 0 | 4738 | 0 | 0 | 689088 | 741878 | 0 | 0 | 4063261 | 0 | 4196568 | 0 | 1876353678 | 0 | 12075191931206400 | 12075203487218253 | 12075203487462731 | 12075191931868380 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f091615d800 | 0x7f090a636380 | 1789512 | 1628385 | 65536 | 223688 | 223688 | 7158016 | 6384364 | 0 | 0 | 0 | 48 | 2293 | 0 | 2098256 | 2101330 | 0 | 1128 | 2100202 | 2102331 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098287 | 0 | 2222 | 0 | 0 | 591630 | 641445 | 0 | 0 | 1966107 | 0 | 2100219 | 0 | 1129469962 | 0 | 12075191931978204 | 12075203487510730 | 12075203487636489 | 12075191932471060 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f091615d700 | 0x7f090a6363c0 | 2005040 | 1847988 | 65536 | 250629 | 250629 | 8020128 | 7214171 | 0 | 0 | 0 | 48 | 780 | 0 | 2098544 | 2099275 | 0 | 1410 | 2097865 | 2099448 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097897 | 0 | 1430 | 0 | 0 | 323137 | 376588 | 0 | 0 | 1966112 | 0 | 2097671 | 0 | 773161571 | 0 | 12075191932646917 | 12075203487669129 | 12075203487825768 | 12075191933148038 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f091615d600 | 0x7f090a636400 | 1707376 | 1552129 | 65536 | 213421 | 213421 | 6829472 | 6050502 | 0 | 0 | 0 | 48 | 2432 | 0 | 2098256 | 2101218 | 0 | 1128 | 2100090 | 2101473 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2101466 | 0 | 8580 | 0 | 0 | 403209 | 455082 | 0 | 0 | 1966117 | 0 | 2099388 | 0 | 1186856705 | 0 | 12075191933333733 | 12075203487867367 | 12075203487992486 | 12075191933811251 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f091615d500 | 0x7f090a636440 | 3256856 | 3075466 | 65536 | 407106 | 407106 | 13027392 | 12197661 | 0 | 0 | 0 | 48 | 2828 | 0 | 4196272 | 4198042 | 0 | 1974 | 4196068 | 4198070 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4198092 | 0 | 7492 | 0 | 0 | 907489 | 959358 | 0 | 0 | 4063276 | 0 | 4196607 | 0 | 2201311261 | 0 | 12075191933952082 | 12075203488024326 | 12075203488278404 | 12075191934651833 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f091615d400 | 0x7f090a636480 | 3145664 | 2960394 | 65536 | 393207 | 393207 | 12582624 | 11798411 | 0 | 0 | 0 | 48 | 1808 | 0 | 4195456 | 4196768 | 0 | 1175 | 4195593 | 4196586 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197297 | 0 | 5936 | 0 | 0 | 585893 | 638591 | 0 | 0 | 4063259 | 0 | 4196447 | 0 | 2107289118 | 0 | 12075191934759713 | 12075203488321923 | 12075203488570561 | 12075191935424939 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f091615d300 | 0x7f090a6364c0 | 1757784 | 1600260 | 65536 | 219722 | 219722 | 7031104 | 6232826 | 0 | 0 | 0 | 48 | 4952 | 0 | 2098304 | 2101356 | 0 | 1175 | 2100181 | 2101909 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100320 | 0 | 6286 | 0 | 0 | 518704 | 568420 | 0 | 0 | 1966121 | 0 | 2098797 | 0 | 1271883685 | 0 | 12075191935536547 | 12075203488614401 | 12075203488740160 | 12075191936018913 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f091615da00 | 0x7f090a636500 | 2109040 | 1954208 | 65536 | 263629 | 263629 | 8436128 | 7568481 | 0 | 0 | 0 | 48 | 482 | 0 | 2098640 | 2099297 | 0 | 1504 | 2097793 | 2099165 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097766 | 0 | 1164 | 0 | 0 | 46084 | 99098 | 0 | 0 | 1966114 | 0 | 2097678 | 0 | 759500774 | 0 | 12075191936193448 | 12075203488767999 | 12075203488932798 | 12075191936705169 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f091615d900 | 0x7f090a636540 | 1741232 | 1574387 | 65536 | 217653 | 217653 | 6964896 | 6166664 | 0 | 0 | 0 | 48 | 4911 | 0 | 2098304 | 2100537 | 0 | 1175 | 2099362 | 2102235 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100607 | 0 | 6860 | 0 | 0 | 540406 | 596531 | 0 | 0 | 1966114 | 0 | 2102170 | 0 | 825438924 | 0 | 12075191936891845 | 12075203488972958 | 12075203489140316 | 12075191937380363 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f091615d800 | 0x7f090a636580 | 3255600 | 3072578 | 65536 | 406949 | 406949 | 13022368 | 12163965 | 0 | 0 | 0 | 48 | 2191 | 0 | 4196368 | 4199072 | 0 | 2068 | 4197004 | 4198537 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197345 | 0 | 5994 | 0 | 0 | 858524 | 912303 | 0 | 0 | 4063278 | 0 | 4196120 | 0 | 1912557336 | 0 | 12075191937552583 | 12075203489168316 | 12075203489432154 | 12075191938234941 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f091615d700 | 0x7f090a6365c0 | 3616904 | 2980033 | 65536 | 452112 | 452112 | 14467584 | 11863505 | 0 | 0 | 0 | 48 | 976 | 0 | 4195504 | 4197942 | 0 | 1222 | 4196720 | 4196526 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195362 | 0 | 2064 | 0 | 0 | 683637 | 737334 | 0 | 0 | 4063260 | 0 | 4195283 | 0 | 2115927341 | 0 | 12075191938341049 | 12075203489477273 | 12075203489722711 | 12075191939050727 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f091615d600 | 0x7f090a636600 | 1778440 | 1610887 | 65536 | 222304 | 222304 | 7113728 | 6305098 | 0 | 0 | 0 | 48 | 3493 | 0 | 2098352 | 2102676 | 0 | 1222 | 2101454 | 2101497 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099963 | 0 | 5570 | 0 | 0 | 314438 | 363411 | 0 | 0 | 1966108 | 0 | 2100911 | 0 | 1041843373 | 0 | 12075191939161183 | 12075203489765751 | 12075203489892470 | 12075191939643108 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f091615d500 | 0x7f090a636640 | 2200200 | 2036974 | 65536 | 275024 | 275024 | 8800768 | 7976229 | 0 | 0 | 0 | 48 | 437 | 0 | 2098688 | 2099188 | 0 | 1551 | 2097637 | 2099305 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097605 | 0 | 840 | 0 | 0 | 57408 | 113594 | 0 | 0 | 1966115 | 0 | 2097737 | 0 | 639722772 | 0 | 12075191939794319 | 12075203489921909 | 12075203490094068 | 12075191940322190 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f091615d400 | 0x7f090a636680 | 1769800 | 1611818 | 65536 | 221224 | 221224 | 7079168 | 6334443 | 0 | 0 | 0 | 48 | 1171 | 0 | 2098352 | 2101141 | 0 | 1222 | 2099919 | 2101613 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099306 | 0 | 4256 | 0 | 0 | 742908 | 793569 | 0 | 0 | 1966116 | 0 | 2100876 | 0 | 1001378730 | 0 | 12075191940508136 | 12075203490137587 | 12075203490262706 | 12075191940990512 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f091615d300 | 0x7f090a6366c0 | 3171504 | 3002193 | 65536 | 396437 | 396437 | 12685984 | 11863685 | 0 | 0 | 0 | 48 | 1734 | 0 | 4196464 | 4198282 | 0 | 2162 | 4196120 | 4197894 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196411 | 0 | 4122 | 0 | 0 | 896096 | 949203 | 0 | 0 | 4063280 | 0 | 4196295 | 0 | 2197006820 | 0 | 12075191941163945 | 12075203490291506 | 12075203490545424 | 12075191941831255 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f091615da00 | 0x7f090a636700 | 3160408 | 2994481 | 65536 | 395050 | 395050 | 12641600 | 11911670 | 0 | 0 | 0 | 48 | 2705 | 0 | 4195552 | 4196844 | 0 | 1269 | 4195575 | 4196905 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195631 | 0 | 2600 | 0 | 0 | 1259496 | 1313053 | 0 | 0 | 4063261 | 0 | 4195376 | 0 | 2223031604 | 0 | 12075191941939706 | 12075203490587824 | 12075203490832781 | 12075191942619730 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f091615d900 | 0x7f090a636740 | 1756544 | 1598413 | 65536 | 219567 | 219567 | 7026144 | 6244472 | 0 | 0 | 0 | 48 | 4670 | 0 | 2098400 | 2102434 | 0 | 1269 | 2101165 | 2102396 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099969 | 0 | 5580 | 0 | 0 | 323692 | 377595 | 0 | 0 | 1966112 | 0 | 2101216 | 0 | 987279537 | 0 | 12075191942727370 | 12075203490876141 | 12075203491002220 | 12075191943217140 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f091615d800 | 0x7f090a636780 | 2307328 | 2153354 | 65536 | 288415 | 288415 | 9229280 | 8425085 | 0 | 0 | 0 | 48 | 485 | 0 | 2098784 | 2099323 | 0 | 1645 | 2097678 | 2099342 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097552 | 0 | 730 | 0 | 0 | 54889 | 107607 | 0 | 0 | 1966117 | 0 | 2097772 | 0 | 607440859 | 0 | 12075191943390943 | 12075203491031180 | 12075203491213738 | 12075191943988624 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f091615d700 | 0x7f090a6367c0 | 1778248 | 1606756 | 65536 | 222280 | 222280 | 7112960 | 6279888 | 0 | 0 | 0 | 48 | 4541 | 0 | 2098400 | 2101800 | 0 | 1269 | 2100531 | 2101959 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2101237 | 0 | 8116 | 0 | 0 | 595736 | 649369 | 0 | 0 | 1966114 | 0 | 2100966 | 0 | 997843528 | 0 | 12075191944114688 | 12075203491256138 | 12075203491381897 | 12075191944601543 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f091615d600 | 0x7f090a636800 | 3276800 | 3115722 | 65536 | 409599 | 409599 | 13107168 | 12334981 | 0 | 0 | 0 | 48 | 1327 | 0 | 4195504 | 4197180 | 0 | 1222 | 4195958 | 4196926 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195779 | 0 | 2898 | 0 | 0 | 393506 | 450486 | 0 | 0 | 4063260 | 0 | 4195795 | 0 | 1839887704 | 0 | 12075191944773613 | 12075203491409736 | 12075203491673254 | 12075191945457554 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f091615d500 | 0x7f090a636840 | 3179440 | 2998853 | 65536 | 397429 | 397429 | 12717728 | 11906919 | 0 | 0 | 0 | 48 | 1946 | 0 | 4195600 | 4198214 | 0 | 1316 | 4196898 | 4196632 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195513 | 0 | 2362 | 0 | 0 | 598215 | 651892 | 0 | 0 | 4063265 | 0 | 4196271 | 0 | 1705078735 | 0 | 12075191945533455 | 12075203491718054 | 12075203491964132 | 12075191946227925 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f091615d400 | 0x7f090a636880 | 1771328 | 1615764 | 65536 | 221415 | 221415 | 7085280 | 6312481 | 0 | 0 | 0 | 48 | 5009 | 0 | 2098448 | 2102149 | 0 | 1316 | 2100833 | 2101719 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100207 | 0 | 6054 | 0 | 0 | 333233 | 384422 | 0 | 0 | 1966111 | 0 | 2100760 | 0 | 991934798 | 0 | 12075191946332540 | 12075203492011811 | 12075203492138210 | 12075191946816319 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f091615d300 | 0x7f090a6368c0 | 2409840 | 2254824 | 65536 | 301229 | 301229 | 9639328 | 8768270 | 0 | 0 | 0 | 48 | 390 | 0 | 2098832 | 2099300 | 0 | 1692 | 2097608 | 2099455 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097589 | 0 | 802 | 0 | 0 | 76963 | 129694 | 0 | 0 | 1966118 | 0 | 2097584 | 0 | 606749995 | 0 | 12075191946992115 | 12075203492167010 | 12075203492358048 | 12075191947600075 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f091615da00 | 0x7f090a636900 | 1747888 | 1584022 | 65536 | 218485 | 218485 | 6991520 | 6203594 | 0 | 0 | 0 | 48 | 2238 | 0 | 2098496 | 2103007 | 0 | 1363 | 2101644 | 2102572 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100113 | 0 | 5864 | 0 | 0 | 288790 | 338866 | 0 | 0 | 1966116 | 0 | 2101648 | 0 | 881520033 | 0 | 12075191947717163 | 12075203492401248 | 12075203492527327 | 12075191948204088 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f091615d900 | 0x7f090a636940 | 3479664 | 3318331 | 65536 | 434957 | 434957 | 13918624 | 13120016 | 0 | 0 | 0 | 48 | 1013 | 0 | 4195408 | 4196420 | 0 | 1128 | 4195292 | 4196305 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195230 | 0 | 1804 | 0 | 0 | 47930 | 105052 | 0 | 0 | 4063258 | 0 | 4195037 | 0 | 1251659666 | 0 | 12075191948377320 | 12075203492556286 | 12075203492837884 | 12075191949073734 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f091615d800 | 0x7f090a636980 | 3146952 | 2979199 | 65536 | 393368 | 393368 | 12587776 | 11819214 | 0 | 0 | 0 | 48 | 1972 | 0 | 4195696 | 4197381 | 0 | 1410 | 4195971 | 4197412 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197257 | 0 | 5846 | 0 | 0 | 539250 | 592694 | 0 | 0 | 4063264 | 0 | 4196456 | 0 | 1811697143 | 0 | 12075191949181614 | 12075203492882844 | 12075203493131641 | 12075191949848514 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f091615d700 | 0x7f090a6369c0 | 1760968 | 1604173 | 65536 | 220120 | 220120 | 7043840 | 6264076 | 0 | 0 | 0 | 48 | 3244 | 0 | 2098544 | 2102828 | 0 | 1410 | 2101418 | 2102044 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100794 | 0 | 7224 | 0 | 0 | 242639 | 292883 | 0 | 0 | 1966116 | 0 | 2099843 | 0 | 1194167856 | 0 | 12075191949959830 | 12075203493177721 | 12075203493303000 | 12075191950449881 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f091615d600 | 0x7f090a636a00 | 2626312 | 2469531 | 65536 | 328288 | 328288 | 10505216 | 9620280 | 0 | 0 | 0 | 48 | 467 | 0 | 2098976 | 2099450 | 0 | 1833 | 2097617 | 2099673 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097541 | 0 | 700 | 0 | 0 | 39851 | 92735 | 0 | 0 | 1966121 | 0 | 2097553 | 0 | 596947924 | 0 | 12075191950624826 | 12075203493331480 | 12075203493541078 | 12075191951248095 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f091615d500 | 0x7f090a636a40 | 1798768 | 1634345 | 65536 | 224845 | 224845 | 7195040 | 6379779 | 0 | 0 | 0 | 48 | 3011 | 0 | 2098592 | 2103108 | 0 | 1457 | 2101651 | 2101410 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100395 | 0 | 6424 | 0 | 0 | 340660 | 390157 | 0 | 0 | 1966116 | 0 | 2100802 | 0 | 994465107 | 0 | 12075191951369079 | 12075203493601557 | 12075203493729716 | 12075191951852678 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f091615d400 | 0x7f090a636a80 | 3762952 | 3605794 | 65536 | 470368 | 470368 | 15051776 | 14259091 | 0 | 0 | 0 | 48 | 973 | 0 | 4195120 | 4195948 | 0 | 846 | 4195102 | 4196177 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195163 | 0 | 1682 | 0 | 0 | 36933 | 93353 | 0 | 0 | 4063248 | 0 | 4195390 | 0 | 1123914962 | 0 | 12075191951999421 | 12075203493761236 | 12075203494068113 | 12075191952734787 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f091615d300 | 0x7f090a636ac0 | 3240896 | 3058825 | 65536 | 405111 | 405111 | 12963552 | 12087045 | 0 | 0 | 0 | 48 | 1724 | 0 | 4195792 | 4197868 | 0 | 1504 | 4196364 | 4196923 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197631 | 0 | 6590 | 0 | 0 | 710376 | 764716 | 0 | 0 | 4063266 | 0 | 4196255 | 0 | 1987141675 | 0 | 12075191952840524 | 12075203494117553 | 12075203494365231 | 12075191953517332 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f091615da00 | 0x7f090a636b00 | 1780336 | 1620890 | 65536 | 222541 | 222541 | 7121312 | 6315234 | 0 | 0 | 0 | 48 | 2900 | 0 | 2098640 | 2102559 | 0 | 1504 | 2101055 | 2101158 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100718 | 0 | 7068 | 0 | 0 | 497085 | 553060 | 0 | 0 | 1966114 | 0 | 2101527 | 0 | 896426965 | 0 | 12075191953624631 | 12075203494407950 | 12075203494535309 | 12075191954108701 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f091615d900 | 0x7f090a636b40 | 2861696 | 2697742 | 65536 | 357711 | 357711 | 11446752 | 10331344 | 0 | 0 | 0 | 48 | 558 | 0 | 2099120 | 2099613 | 0 | 1974 | 2097639 | 2099751 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097598 | 0 | 808 | 0 | 0 | 59388 | 112776 | 0 | 0 | 1966124 | 0 | 2097580 | 0 | 562974772 | 0 | 12075191954283285 | 12075203494564269 | 12075203494792267 | 12075191954920108 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f091615d800 | 0x7f090a636b80 | 1793280 | 1624389 | 65536 | 224159 | 224159 | 7173088 | 6283590 | 0 | 0 | 0 | 48 | 4062 | 0 | 2098688 | 2102217 | 0 | 1551 | 2100666 | 2102493 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100336 | 0 | 6302 | 0 | 0 | 490792 | 541012 | 0 | 0 | 1966126 | 0 | 2100728 | 0 | 1041386023 | 0 | 12075191955043778 | 12075203494849706 | 12075203494976745 | 12075191955527367 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f091615d700 | 0x7f090a636bc0 | 4038704 | 3878137 | 65536 | 504837 | 504837 | 16154784 | 15358015 | 0 | 0 | 0 | 48 | 802 | 0 | 4195504 | 4196452 | 0 | 1222 | 4195230 | 4196459 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195040 | 0 | 1420 | 0 | 0 | 28487 | 84413 | 0 | 0 | 4063257 | 0 | 4195071 | 0 | 1097544764 | 0 | 12075191955700819 | 12075203495005385 | 12075203495333862 | 12075191956452196 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f091615d600 | 0x7f090a636c00 | 3143624 | 2965861 | 65536 | 392952 | 392952 | 12574464 | 11777092 | 0 | 0 | 0 | 48 | 2502 | 0 | 4195888 | 4197563 | 0 | 1598 | 4195965 | 4197513 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4197606 | 0 | 6536 | 0 | 0 | 472492 | 525043 | 0 | 0 | 4063268 | 0 | 4196878 | 0 | 1992440124 | 0 | 12075191956561769 | 12075203495378342 | 12075203495626660 | 12075191957227557 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f091615d500 | 0x7f090a636c40 | 1784688 | 1622899 | 65536 | 223085 | 223085 | 7138720 | 6250456 | 0 | 0 | 0 | 48 | 1680 | 0 | 2098736 | 2103114 | 0 | 1598 | 2101516 | 2103059 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100642 | 0 | 6912 | 0 | 0 | 640427 | 689641 | 0 | 0 | 1966125 | 0 | 2101247 | 0 | 953782905 | 0 | 12075191957334726 | 12075203495670499 | 12075203495799138 | 12075191957816170 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f091615d400 | 0x7f090a636c80 | 3065304 | 2906571 | 65536 | 383162 | 383162 | 12261184 | 11109624 | 0 | 0 | 0 | 48 | 366 | 0 | 2099264 | 2099811 | 0 | 2115 | 2097696 | 2099774 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097662 | 0 | 930 | 0 | 0 | 79352 | 132123 | 0 | 0 | 1966127 | 0 | 2097735 | 0 | 564098623 | 0 | 12075191957959978 | 12075203495828098 | 12075203496072416 | 12075191958637938 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f091615d300 | 0x7f090a636cc0 | 1822856 | 1655419 | 65536 | 227856 | 227856 | 7291392 | 6402969 | 0 | 0 | 0 | 48 | 3305 | 0 | 2098880 | 2102619 | 0 | 1739 | 2100880 | 2102602 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100286 | 0 | 6194 | 0 | 0 | 504764 | 554388 | 0 | 0 | 1966126 | 0 | 2101136 | 0 | 936542774 | 0 | 12075191958755626 | 12075203496130815 | 12075203496260094 | 12075191959248683 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f091615da00 | 0x7f090a636d00 | 4593416 | 4436986 | 65536 | 574176 | 574176 | 18373632 | 17591213 | 0 | 0 | 0 | 48 | 948 | 0 | 4195600 | 4196218 | 0 | 1316 | 4194902 | 4196519 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195253 | 0 | 1842 | 0 | 0 | 16571 | 73032 | 0 | 0 | 4063262 | 0 | 4195002 | 0 | 1048068933 | 0 | 12075191959421353 | 12075203496288894 | 12075203496663611 | 12075191960218445 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f091615d900 | 0x7f090a636d40 | 3251080 | 3067918 | 65536 | 406384 | 406384 | 13004288 | 12184990 | 0 | 0 | 0 | 48 | 1823 | 0 | 4196032 | 4199176 | 0 | 1739 | 4197437 | 4197162 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196617 | 0 | 4552 | 0 | 0 | 619894 | 673693 | 0 | 0 | 4063273 | 0 | 4196009 | 0 | 2096494133 | 0 | 12075191960330844 | 12075203496706810 | 12075203496959448 | 12075191961024753 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f091615d800 | 0x7f090a636d80 | 1825584 | 1656827 | 65536 | 228197 | 228197 | 7302304 | 6370815 | 0 | 0 | 0 | 48 | 3195 | 0 | 2098928 | 2103205 | 0 | 1786 | 2101419 | 2103321 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2100193 | 0 | 6006 | 0 | 0 | 456443 | 503456 | 0 | 0 | 1966124 | 0 | 2101510 | 0 | 941101832 | 0 | 12075191961099682 | 12075203497002968 | 12075203497132247 | 12075191961588651 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f091615d700 | 0x7f090a636dc0 | 3472576 | 3311392 | 65536 | 434071 | 434071 | 13890272 | 12837295 | 0 | 0 | 0 | 48 | 385 | 0 | 2099552 | 2100069 | 0 | 2397 | 2097672 | 2100203 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097625 | 0 | 844 | 0 | 0 | 25604 | 79570 | 0 | 0 | 1966133 | 0 | 2097683 | 0 | 569390450 | 0 | 12075191961763276 | 12075203497163766 | 12075203497441684 | 12075191962465501 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f091615d600 | 0x7f090a636e00 | 1776432 | 1608244 | 65536 | 222053 | 222053 | 7105696 | 6121805 | 0 | 0 | 0 | 48 | 2412 | 0 | 2099072 | 2101330 | 0 | 1927 | 2099403 | 2102718 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2098567 | 0 | 2748 | 0 | 0 | 684840 | 736928 | 0 | 0 | 1966124 | 0 | 2099580 | 0 | 1080478575 | 0 | 12075191962586125 | 12075203497499283 | 12075203497633042 | 12075191963070305 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f091615d500 | 0x7f090a636e40 | 5157640 | 4994113 | 65536 | 644704 | 644704 | 20630528 | 19821606 | 0 | 0 | 0 | 48 | 825 | 0 | 4195312 | 4195952 | 0 | 1034 | 4194918 | 4196134 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195186 | 0 | 1720 | 0 | 0 | 11435 | 67882 | 0 | 0 | 4063256 | 0 | 4195246 | 0 | 1033080250 | 0 | 12075191963245700 | 12075203497665682 | 12075203498089038 | 12075191964079460 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f091615d400 | 0x7f090a636e80 | 3204672 | 3031238 | 65536 | 400583 | 400583 | 12818656 | 11946707 | 0 | 0 | 0 | 48 | 2464 | 0 | 4196272 | 4198601 | 0 | 1974 | 4196627 | 4198003 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4196408 | 0 | 4124 | 0 | 0 | 1085386 | 1139619 | 0 | 0 | 4063276 | 0 | 4195909 | 0 | 2089260805 | 0 | 12075191964196057 | 12075203498137198 | 12075203498407916 | 12075191964867054 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f091615d300 | 0x7f090a636ec0 | 1760176 | 1603019 | 65536 | 220021 | 220021 | 7040672 | 6104978 | 0 | 0 | 0 | 48 | 2176 | 0 | 2099120 | 2101011 | 0 | 1974 | 2099037 | 2100857 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2099766 | 0 | 5144 | 0 | 0 | 600511 | 653398 | 0 | 0 | 1966124 | 0 | 2098401 | 0 | 1153417789 | 0 | 12075191964951991 | 12075203498455755 | 12075203498590954 | 12075191965459965 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f091615da00 | 0x7f090a636f00 | 3909040 | 3743200 | 65536 | 488629 | 488629 | 15636128 | 14403349 | 0 | 0 | 0 | 48 | 383 | 0 | 2099840 | 2100276 | 0 | 2679 | 2097597 | 2100511 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097620 | 0 | 822 | 0 | 0 | 51742 | 105018 | 0 | 0 | 1966139 | 0 | 2097665 | 0 | 588737034 | 0 | 12075191965637085 | 12075203498620714 | 12075203498935111 | 12075191966366580 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f091615d900 | 0x7f090a636f40 | 1955056 | 1794097 | 65536 | 244381 | 244381 | 7820192 | 6883440 | 0 | 0 | 0 | 48 | 430 | 0 | 2099456 | 2100064 | 0 | 2303 | 2097761 | 2099987 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097615 | 0 | 828 | 0 | 0 | 82844 | 133589 | 0 | 0 | 1966131 | 0 | 2097737 | 0 | 594741765 | 0 | 12075191966484389 | 12075203498993990 | 12075203499144709 | 12075191966983947 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f091615d800 | 0x7f090a636f80 | 6267144 | 6114385 | 65536 | 783392 | 783392 | 25068544 | 24262918 | 0 | 0 | 0 | 48 | 835 | 0 | 4195408 | 4196170 | 0 | 1128 | 4195042 | 4196312 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195181 | 0 | 1706 | 0 | 0 | 17672 | 74131 | 0 | 0 | 4063258 | 0 | 4194912 | 0 | 1014299329 | 0 | 12075191967157009 | 12075203499173989 | 12075203499689664 | 12075191968087438 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f091615d700 | 0x7f090a636fc0 | 3688584 | 3507082 | 65536 | 461072 | 461072 | 14754304 | 13803631 | 0 | 0 | 0 | 48 | 1021 | 0 | 4196656 | 4197916 | 0 | 2350 | 4195566 | 4197669 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195335 | 0 | 1962 | 0 | 0 | 980835 | 1035176 | 0 | 0 | 4063284 | 0 | 4195393 | 0 | 2145801380 | 0 | 12075191968200098 | 12075203499737824 | 12075203500035901 | 12075191968913604 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f091615d600 | 0x7f090a637000 | 1978888 | 1822239 | 65536 | 247360 | 247360 | 7915520 | 6985583 | 0 | 0 | 0 | 48 | 413 | 0 | 2099504 | 2100107 | 0 | 2350 | 2097757 | 2100077 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097835 | 0 | 1266 | 0 | 0 | 132612 | 183521 | 0 | 0 | 1966132 | 0 | 2097633 | 0 | 634873751 | 0 | 12075191969031833 | 12075203500085021 | 12075203500239580 | 12075191969533315 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f091615d500 | 0x7f090a637040 | 4757888 | 4589983 | 65536 | 594735 | 594735 | 19031520 | 16656029 | 0 | 0 | 0 | 48 | 408 | 0 | 2100416 | 2100911 | 0 | 3243 | 2097668 | 2100946 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097537 | 0 | 632 | 0 | 0 | 18341 | 71673 | 0 | 0 | 1966151 | 0 | 2097764 | 0 | 580584528 | 0 | 12075191969709853 | 12075203500267579 | 12075203500652696 | 12075191970516823 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f091615d400 | 0x7f090a637080 | 2225864 | 2072927 | 65536 | 278232 | 278232 | 8903424 | 7909499 | 0 | 0 | 0 | 48 | 594 | 0 | 2099840 | 2100463 | 0 | 2679 | 2097784 | 2100390 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097717 | 0 | 1016 | 0 | 0 | 85645 | 135299 | 0 | 0 | 1966139 | 0 | 2097803 | 0 | 566891033 | 0 | 12075191970641344 | 12075203500712855 | 12075203500889014 | 12075191971164477 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f091615d300 | 0x7f090a6370c0 | 7401024 | 7238488 | 65536 | 925127 | 925127 | 29604064 | 28694057 | 0 | 0 | 0 | 48 | 618 | 0 | 4195504 | 4196539 | 0 | 1222 | 4195317 | 4196367 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195019 | 0 | 1378 | 0 | 0 | 10113 | 65241 | 0 | 0 | 4063260 | 0 | 4195107 | 0 | 1008081440 | 0 | 12075191971339702 | 12075203500918454 | 12075203501527408 | 12075191972361822 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f091615da00 | 0x7f090a637100 | 4027080 | 3835584 | 65536 | 503384 | 503384 | 16108288 | 15095124 | 0 | 0 | 0 | 48 | 813 | 0 | 4197040 | 4197958 | 0 | 2726 | 4195232 | 4197907 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195283 | 0 | 1842 | 0 | 0 | 436341 | 489609 | 0 | 0 | 4063292 | 0 | 4195063 | 0 | 1398613315 | 0 | 12075191972468320 | 12075203501583088 | 12075203501909165 | 12075191973210389 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f091615d900 | 0x7f090a637140 | 2283760 | 2124938 | 65536 | 285469 | 285469 | 9135008 | 8044411 | 0 | 0 | 0 | 48 | 534 | 0 | 2099888 | 2100428 | 0 | 2726 | 2097702 | 2100477 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097685 | 0 | 950 | 0 | 0 | 84433 | 135234 | 0 | 0 | 1966140 | 0 | 2097620 | 0 | 547711889 | 0 | 12075191973321705 | 12075203501959885 | 12075203502137803 | 12075191973910289 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f091615d800 | 0x7f090a637180 | 5591000 | 5432782 | 65536 | 698874 | 698874 | 22363968 | 16909824 | 0 | 0 | 0 | 48 | 453 | 0 | 2100992 | 2101464 | 0 | 3807 | 2097657 | 2101540 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097560 | 0 | 654 | 0 | 0 | 29103 | 82571 | 0 | 0 | 1966163 | 0 | 2097676 | 0 | 611312526 | 0 | 12075191974024822 | 12075203502170603 | 12075203502625799 | 12075191974897003 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f091615d700 | 0x7f090a6371c0 | 2496112 | 2339096 | 65536 | 312013 | 312013 | 9984416 | 9057095 | 0 | 0 | 0 | 48 | 590 | 0 | 2100224 | 2100734 | 0 | 3055 | 2097679 | 2100787 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097670 | 0 | 906 | 0 | 0 | 28348 | 80790 | 0 | 0 | 1966147 | 0 | 2097687 | 0 | 545919714 | 0 | 12075191975025682 | 12075203502686278 | 12075203502884837 | 12075191975635335 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f091615d600 | 0x7f090a637200 | 8514312 | 8354958 | 65536 | 1064288 | 1064288 | 34057216 | 33041238 | 0 | 0 | 0 | 48 | 909 | 0 | 4195600 | 4196607 | 0 | 1316 | 4195291 | 4196462 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194846 | 0 | 1028 | 0 | 0 | 1272 | 56644 | 0 | 0 | 4063259 | 0 | 4194880 | 0 | 1013961441 | 0 | 12075191975750289 | 12075203502932836 | 12075203503635710 | 12075191976864229 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f091615d500 | 0x7f090a637240 | 4549896 | 4390774 | 65536 | 568736 | 568736 | 18199552 | 17248604 | 0 | 0 | 0 | 48 | 797 | 0 | 4197424 | 4198298 | 0 | 3102 | 4195196 | 4198265 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195206 | 0 | 1672 | 0 | 0 | 95451 | 148542 | 0 | 0 | 4063299 | 0 | 4195153 | 0 | 1206451086 | 0 | 12075191976978271 | 12075203503684510 | 12075203504057306 | 12075191977769611 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f091615d400 | 0x7f090a637280 | 2540808 | 2390754 | 65536 | 317600 | 317600 | 10163200 | 9088329 | 0 | 0 | 0 | 48 | 528 | 0 | 2100272 | 2100884 | 0 | 3102 | 2097782 | 2100902 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097727 | 0 | 1018 | 0 | 0 | 89259 | 138446 | 0 | 0 | 1966148 | 0 | 2097698 | 0 | 564928536 | 0 | 12075191977881479 | 12075203504107066 | 12075203504309304 | 12075191978504547 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f091615d300 | 0x7f090a6372c0 | 6436464 | 6270493 | 65536 | 804557 | 804557 | 25745824 | 23339989 | 0 | 0 | 0 | 48 | 523 | 0 | 2101568 | 2102022 | 0 | 4371 | 2097651 | 2102044 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097673 | 0 | 856 | 0 | 0 | 20368 | 73899 | 0 | 0 | 1966175 | 0 | 2097716 | 0 | 624674395 | 0 | 12075191978612097 | 12075203504359064 | 12075203504884179 | 12075191979552975 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f091615da00 | 0x7f090a637300 | 2792392 | 2636715 | 65536 | 349048 | 349048 | 11169536 | 10047935 | 0 | 0 | 0 | 48 | 458 | 0 | 2100608 | 2101117 | 0 | 3431 | 2097686 | 2101191 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097714 | 0 | 978 | 0 | 0 | 54524 | 103831 | 0 | 0 | 1966155 | 0 | 2097664 | 0 | 590132631 | 0 | 12075191979674551 | 12075203504948339 | 12075203505171377 | 12075191980320081 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f091615d900 | 0x7f090a637340 | 9648600 | 9491640 | 65536 | 1206074 | 1206074 | 38594368 | 37032428 | 0 | 0 | 0 | 48 | 949 | 0 | 4195312 | 4195926 | 0 | 1034 | 4194892 | 4196267 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194873 | 0 | 1094 | 0 | 0 | 1870 | 57310 | 0 | 0 | 4063253 | 0 | 4195151 | 0 | 1010419375 | 0 | 12075191980429885 | 12075203505226256 | 12075203506024169 | 12075191981638942 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f091615d800 | 0x7f090a637380 | 5107656 | 4941335 | 65536 | 638456 | 638456 | 20430592 | 19384612 | 0 | 0 | 0 | 48 | 752 | 0 | 4197808 | 4198612 | 0 | 3478 | 4195134 | 4198616 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194993 | 0 | 1230 | 0 | 0 | 90175 | 143777 | 0 | 0 | 4063308 | 0 | 4195157 | 0 | 1226089354 | 0 | 12075191981749908 | 12075203506073129 | 12075203506493605 | 12075191982583016 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f091615d700 | 0x7f090a6373c0 | 2832064 | 2672880 | 65536 | 354007 | 354007 | 11328224 | 10100102 | 0 | 0 | 0 | 48 | 544 | 0 | 2100656 | 2101207 | 0 | 3478 | 2097729 | 2101204 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097688 | 0 | 924 | 0 | 0 | 63109 | 108615 | 0 | 0 | 1966156 | 0 | 2097727 | 0 | 555230955 | 0 | 12075191982692660 | 12075203506540005 | 12075203506764323 | 12075191983334944 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f091615d600 | 0x7f090a637400 | 7269640 | 7113532 | 65536 | 908704 | 908704 | 29078528 | 22006151 | 0 | 0 | 0 | 48 | 494 | 0 | 2102144 | 2102717 | 0 | 4935 | 2097782 | 2102643 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097739 | 0 | 964 | 0 | 0 | 41111 | 96618 | 0 | 0 | 1966187 | 0 | 2097691 | 0 | 681667958 | 0 | 12075191983451801 | 12075203506811362 | 12075203507407357 | 12075191984464904 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f091615d500 | 0x7f090a637440 | 3331656 | 3171792 | 65536 | 416456 | 416456 | 13326592 | 12065171 | 0 | 0 | 0 | 48 | 397 | 0 | 2101376 | 2101869 | 0 | 4183 | 2097686 | 2101896 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097703 | 0 | 924 | 0 | 0 | 60141 | 112349 | 0 | 0 | 1966171 | 0 | 2097644 | 0 | 575579226 | 0 | 12075191984585167 | 12075203507468957 | 12075203507737594 | 12075191985265241 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f091615d400 | 0x7f090a637480 | 11898368 | 11741098 | 65536 | 1487295 | 1487295 | 47593440 | 45260087 | 0 | 0 | 0 | 48 | 884 | 0 | 4195408 | 4196418 | 0 | 1128 | 4195290 | 4196391 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195237 | 0 | 1818 | 0 | 0 | 0 | 55941 | 0 | 0 | 4063258 | 0 | 4194990 | 0 | 1022705558 | 0 | 12075191985374885 | 12075203507783674 | 12075203508767665 | 12075191986773334 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f091615d300 | 0x7f090a6374c0 | 6216728 | 6058507 | 65536 | 777090 | 777090 | 24866880 | 23673975 | 0 | 0 | 0 | 48 | 715 | 0 | 4198576 | 4199334 | 0 | 4230 | 4195104 | 4199365 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195169 | 0 | 1550 | 0 | 0 | 48234 | 100620 | 0 | 0 | 4063324 | 0 | 4195364 | 0 | 1246495890 | 0 | 12075191986884129 | 12075203508820785 | 12075203509352140 | 12075191987820800 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f091615da00 | 0x7f090a637500 | 3379912 | 3219697 | 65536 | 422488 | 422488 | 13519616 | 12224161 | 0 | 0 | 0 | 48 | 367 | 0 | 2101424 | 2101965 | 0 | 4230 | 2097735 | 2101961 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097656 | 0 | 828 | 0 | 0 | 60494 | 107723 | 0 | 0 | 1966172 | 0 | 2097678 | 0 | 579016701 | 0 | 12075191987903764 | 12075203509407180 | 12075203509677578 | 12075191988597313 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f091615d900 | 0x7f090a637540 | 9008776 | 8849978 | 65536 | 1126096 | 1126096 | 36035072 | 26838015 | 0 | 0 | 0 | 48 | 430 | 0 | 2099120 | 2099828 | 0 | 1974 | 2097854 | 2099758 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097608 | 0 | 828 | 0 | 0 | 0 | 59732 | 0 | 0 | 1966124 | 0 | 2097765 | 0 | 524902095 | 0 | 12075191988704633 | 12075203509726697 | 12075203510463491 | 12075191989859589 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f091615d800 | 0x7f090a637580 | 3888136 | 3732945 | 65536 | 486016 | 486016 | 15552512 | 14231538 | 0 | 0 | 0 | 48 | 473 | 0 | 2102144 | 2102616 | 0 | 4935 | 2097681 | 2102658 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097640 | 0 | 766 | 0 | 0 | 91042 | 141272 | 0 | 0 | 1966187 | 0 | 2097699 | 0 | 585818162 | 0 | 12075191989977448 | 12075203510526530 | 12075203510840607 | 12075191990711582 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f091615d700 | 0x7f090a6375c0 | 14156616 | 13987120 | 65536 | 1769576 | 1769576 | 56626432 | 54760373 | 0 | 0 | 0 | 48 | 628 | 0 | 4195504 | 4196498 | 0 | 1222 | 4195276 | 4196073 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195015 | 0 | 1370 | 0 | 0 | 374 | 57070 | 0 | 0 | 4063260 | 0 | 4195210 | 0 | 1017851703 | 0 | 12075191990815535 | 12075203510888287 | 12075203512058997 | 12075191992409968 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f091615d600 | 0x7f090a637600 | 7364376 | 7201957 | 65536 | 920546 | 920546 | 29457472 | 27633433 | 0 | 0 | 0 | 48 | 748 | 0 | 4199344 | 4200183 | 0 | 4982 | 4195201 | 4200143 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195179 | 0 | 1538 | 0 | 0 | 135087 | 188568 | 0 | 0 | 4063340 | 0 | 4195159 | 0 | 1060404094 | 0 | 12075191992523159 | 12075203512110996 | 12075203512721551 | 12075191993551540 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f091615d500 | 0x7f090a637640 | 3935752 | 3773993 | 65536 | 491968 | 491968 | 15742976 | 14220876 | 0 | 0 | 0 | 48 | 372 | 0 | 2102192 | 2102723 | 0 | 4982 | 2097741 | 2102690 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097650 | 0 | 784 | 0 | 0 | 97888 | 148943 | 0 | 0 | 1966185 | 0 | 2097791 | 0 | 569696319 | 0 | 12075191993663057 | 12075203512769391 | 12075203513087948 | 12075191994394196 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f091615d400 | 0x7f090a637680 | 10689624 | 10530387 | 65536 | 1336202 | 1336202 | 42758464 | 30503269 | 0 | 0 | 0 | 48 | 584 | 0 | 2099984 | 2100673 | 0 | 2820 | 2097853 | 2100693 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097792 | 0 | 1160 | 0 | 0 | 0 | 56358 | 0 | 0 | 1966142 | 0 | 2097816 | 0 | 527836759 | 0 | 12075191994505272 | 12075203513142347 | 12075203514020420 | 12075191995797474 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f091615d300 | 0x7f090a6376c0 | 5027976 | 4861538 | 65536 | 628496 | 628496 | 20111872 | 18183259 | 0 | 0 | 0 | 48 | 371 | 0 | 2103680 | 2104107 | 0 | 6439 | 2097668 | 2104212 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097670 | 0 | 762 | 0 | 0 | 42798 | 92257 | 0 | 0 | 1966219 | 0 | 2097690 | 0 | 580867978 | 0 | 12075191995917467 | 12075203514085219 | 12075203514494496 | 12075191996745345 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f091615da00 | 0x7f090a637700 | 18655704 | 18498086 | 65536 | 2331962 | 2331962 | 74622784 | 65770882 | 0 | 0 | 0 | 48 | 509 | 0 | 4195312 | 4196122 | 0 | 1034 | 4195088 | 4196245 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194909 | 0 | 1166 | 0 | 0 | 980 | 56712 | 0 | 0 | 4063241 | 0 | 4195049 | 0 | 1036836008 | 0 | 12075191996853827 | 12075203514543775 | 12075203516093042 | 12075191998824158 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f091615d900 | 0x7f090a637740 | 9617480 | 9445047 | 65536 | 1202184 | 1202184 | 38469888 | 37153286 | 0 | 0 | 0 | 48 | 655 | 0 | 4196368 | 4196870 | 0 | 2068 | 4194802 | 4197010 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194953 | 0 | 1210 | 0 | 0 | 2659 | 57371 | 0 | 0 | 4063278 | 0 | 4194932 | 0 | 1013736155 | 0 | 12075191998933421 | 12075203516187441 | 12075203516981674 | 12075192000144923 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f091615d800 | 0x7f090a637780 | 5126920 | 4962082 | 65536 | 640864 | 640864 | 20507648 | 19109542 | 0 | 0 | 0 | 48 | 579 | 0 | 2099264 | 2099780 | 0 | 2115 | 2097665 | 2099960 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097782 | 0 | 1170 | 0 | 0 | 0 | 56870 | 0 | 0 | 1966127 | 0 | 2097788 | 0 | 512821860 | 0 | 12075192000257762 | 12075203517071913 | 12075203517485350 | 12075192001083868 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f091615d700 | 0x7f090a6377c0 | 14056024 | 13899949 | 65536 | 1757002 | 1757002 | 56224064 | 37594919 | 0 | 0 | 0 | 48 | 627 | 0 | 2099984 | 2100554 | 0 | 2820 | 2097734 | 2100695 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097726 | 0 | 1028 | 0 | 0 | 0 | 56422 | 0 | 0 | 1966142 | 0 | 2097799 | 0 | 535890273 | 0 | 12075192001195936 | 12075203517575665 | 12075203518733736 | 12075192002763679 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f091615d600 | 0x7f090a637800 | 9590320 | 9423681 | 65536 | 1198789 | 1198789 | 38361248 | 29073371 | 0 | 0 | 0 | 48 | 591 | 0 | 2100752 | 2101417 | 0 | 3572 | 2097845 | 2101419 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097832 | 0 | 1208 | 0 | 0 | 0 | 56474 | 0 | 0 | 1966158 | 0 | 2097792 | 0 | 530496474 | 0 | 12075192002884283 | 12075203518843334 | 12075203519628448 | 12075192004092769 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f091615d500 | 0x7f090a637840 | 36670728 | 36509422 | 65536 | 4583840 | 4583840 | 146682880 | 89627783 | 0 | 0 | 0 | 48 | 912 | 0 | 4195312 | 4196316 | 0 | 1034 | 4195282 | 4196267 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195136 | 0 | 1620 | 0 | 0 | 0 | 56895 | 0 | 0 | 4063256 | 0 | 4194983 | 0 | 1177734379 | 0 | 12075192004200690 | 12075203519725568 | 12075203522775465 | 12075192007663956 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f091615d400 | 0x7f090a637880 | 18581768 | 18425231 | 65536 | 2322720 | 2322720 | 74327040 | 64032745 | 0 | 0 | 0 | 48 | 620 | 0 | 4196368 | 4197098 | 0 | 2068 | 4195030 | 4197012 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194872 | 0 | 1048 | 0 | 0 | 4871 | 62137 | 0 | 0 | 4063263 | 0 | 4195008 | 0 | 1041729261 | 0 | 12075192007773580 | 12075203522866505 | 12075203524406173 | 12075192009736197 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f091615d300 | 0x7f090a6378c0 | 9628680 | 9461310 | 65536 | 1203584 | 1203584 | 38514688 | 31038258 | 0 | 0 | 0 | 48 | 574 | 0 | 2099264 | 2099912 | 0 | 2115 | 2097797 | 2099972 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097602 | 0 | 810 | 0 | 0 | 0 | 56316 | 0 | 0 | 1966127 | 0 | 2097759 | 0 | 522689986 | 0 | 12075192009844298 | 12075203524504252 | 12075203525293047 | 12075192011057462 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f091615da00 | 0x7f090a637900 | 27543832 | 27381115 | 65536 | 3442978 | 3442978 | 110175296 | 38204149 | 0 | 0 | 0 | 48 | 563 | 0 | 2099984 | 2100694 | 0 | 2820 | 2097874 | 2100680 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097792 | 0 | 1160 | 0 | 0 | 0 | 55896 | 0 | 0 | 1966127 | 0 | 2097861 | 0 | 610143227 | 0 | 12075192011151397 | 12075203525389046 | 12075203527669669 | 12075192013841666 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f091615d900 | 0x7f090a637940 | 18577928 | 18414667 | 65536 | 2322240 | 2322240 | 74311680 | 40022332 | 0 | 0 | 0 | 48 | 753 | 0 | 2100752 | 2101612 | 0 | 3572 | 2098040 | 2101409 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097878 | 0 | 1300 | 0 | 0 | 0 | 56579 | 0 | 0 | 1966158 | 0 | 2097861 | 0 | 565823809 | 0 | 12075192013964835 | 12075203527775108 | 12075203529309497 | 12075192015921682 |
| 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 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f091615d800 | 0x7f090a637980 | 72689032 | 72533020 | 65536 | 9086128 | 9086128 | 290756096 | 92777607 | 0 | 0 | 0 | 48 | 739 | 0 | 4195312 | 4196058 | 0 | 1034 | 4195024 | 4196198 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4195024 | 0 | 1396 | 0 | 0 | 0 | 56282 | 0 | 0 | 4063241 | 0 | 4195168 | 0 | 1197265293 | 0 | 12075192016034361 | 12075203529399736 | 12075203535453612 | 12075192022500868 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f091615d700 | 0x7f090a6379c0 | 36579720 | 36419588 | 65536 | 4572464 | 4572464 | 146318848 | 75912969 | 0 | 0 | 0 | 48 | 743 | 0 | 4196368 | 4197113 | 0 | 2068 | 4195045 | 4197155 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4194965 | 0 | 1234 | 0 | 0 | 9042 | 65685 | 0 | 0 | 4063278 | 0 | 4194981 | 0 | 1283068177 | 0 | 12075192022612716 | 12075203535544811 | 12075203538585909 | 12075192026073828 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f091615d600 | 0x7f090a637a00 | 18628936 | 18462910 | 65536 | 2328616 | 2328616 | 74515712 | 37830513 | 0 | 0 | 0 | 48 | 648 | 0 | 2099264 | 2099923 | 0 | 2115 | 2097808 | 2100020 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097802 | 0 | 1210 | 0 | 0 | 0 | 56867 | 0 | 0 | 1966127 | 0 | 2097811 | 0 | 565931812 | 0 | 12075192026157925 | 12075203538678068 | 12075203540215977 | 12075192028107548 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 864972 | 864977 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f091615d500 | 0x7f090a637a40 | 54488472 | 54333242 | 65536 | 6811058 | 6811058 | 217953856 | 53816505 | 0 | 0 | 0 | 48 | 626 | 0 | 2099984 | 2100653 | 0 | 2820 | 2097833 | 2100579 | 0 | 0 | 31 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2097632 | 0 | 840 | 0 | 0 | 0 | 56697 | 0 | 0 | 1966142 | 0 | 2097793 | 0 | 619265404 | 0 | 12075192028218153 | 12075203540308936 | 12075203544835143 | 12075192033157031 |