43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_VMEM | SQ_INST_LEVEL_VMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 747934 | 747939 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fe2d6a04180 | 1048576 | 11096515 | 1420097720 | 12073197371357776 | 12073197611777712 | 12073197612102990 | 12073197612215562 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 747934 | 747939 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fe2d6a35100 | 4096 | 112341 | 14385376 | 12073197626636267 | 12073197626938001 | 12073197626944561 | 12073197626949650 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fe3e26d0900 | 0x7fe2d6a35140 | 524288 | 11212591 | 1435255616 | 12073197627020481 | 12073197627236559 | 12073197627374159 | 12073197627378076 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fe3e26d0800 | 0x7fe2d6a35180 | 524288 | 12581433 | 1610444712 | 12073197627448026 | 12073197627615278 | 12073197627867436 | 12073197627935912 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fe3e26d0700 | 0x7fe2d6a351c0 | 524288 | 14324548 | 1833492104 | 12073197627967661 | 12073197628156395 | 12073197628407914 | 12073197628477489 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fe3e26d0600 | 0x7fe2d6a35200 | 524288 | 11593738 | 1484028292 | 12073197628502375 | 12073197628685193 | 12073197628819912 | 12073197628823452 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fe3e26d0500 | 0x7fe2d6a35240 | 524288 | 12315750 | 1576298544 | 12073197628866191 | 12073197629048071 | 12073197629179750 | 12073197629183200 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fe3e26d0400 | 0x7fe2d6a35280 | 524288 | 13325288 | 1705650748 | 12073197629264140 | 12073197629436869 | 12073197629564869 | 12073197629568756 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fe3e26d0300 | 0x7fe2d6a352c0 | 524288 | 12835714 | 1642904220 | 12073197629620062 | 12073197629791108 | 12073197630043906 | 12073197630086659 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fe3e26d0a00 | 0x7fe2d6a35300 | 524288 | 14318433 | 1832735324 | 12073197630111124 | 12073197630292385 | 12073197630541344 | 12073197630608719 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fe3e26d0900 | 0x7fe2d6a35340 | 524288 | 12116124 | 1550835264 | 12073197630632803 | 12073197630817663 | 12073197630950622 | 12073197630954090 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fe3e26d0800 | 0x7fe2d6a35380 | 524288 | 12218697 | 1563963388 | 12073197631007700 | 12073197631180221 | 12073197631313341 | 12073197631317255 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fe3e26d0700 | 0x7fe2d6a353c0 | 524288 | 13446116 | 1721004468 | 12073197631378489 | 12073197631540700 | 12073197631667579 | 12073197631671053 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fe3e26d0600 | 0x7fe2d6a35400 | 524288 | 13451240 | 1721730948 | 12073197631718531 | 12073197631888858 | 12073197632141497 | 12073197632211757 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fe3e26d0500 | 0x7fe2d6a35440 | 524288 | 13645516 | 1746540580 | 12073197632237736 | 12073197632415255 | 12073197632668534 | 12073197632735490 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fe3e26d0400 | 0x7fe2d6a35480 | 524288 | 12672645 | 1622147800 | 12073197632762190 | 12073197632939893 | 12073197633069492 | 12073197633073128 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fe3e26d0300 | 0x7fe2d6a354c0 | 524288 | 11887780 | 1521699688 | 12073197633121447 | 12073197633291411 | 12073197633425171 | 12073197633428799 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fe3e26d0a00 | 0x7fe2d6a35500 | 524288 | 12791971 | 1637282252 | 12073197633489942 | 12073197633648210 | 12073197633777649 | 12073197633781264 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fe3e26d0900 | 0x7fe2d6a35540 | 524288 | 14345063 | 1836167812 | 12073197633829974 | 12073197633996848 | 12073197634251567 | 12073197634296431 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fe3e26d0800 | 0x7fe2d6a35580 | 524288 | 13701027 | 1753661912 | 12073197634319614 | 12073197634505326 | 12073197634756525 | 12073197634823300 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fe3e26d0700 | 0x7fe2d6a355c0 | 524288 | 11344749 | 1452085932 | 12073197634849719 | 12073197635039723 | 12073197635174923 | 12073197635178590 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fe3e26d0600 | 0x7fe2d6a35600 | 524288 | 12472074 | 1596436332 | 12073197635228893 | 12073197635393962 | 12073197635525801 | 12073197635529692 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fe3e26d0500 | 0x7fe2d6a35640 | 524288 | 12827671 | 1641925264 | 12073197635591146 | 12073197635751080 | 12073197635880840 | 12073197635884602 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fe3e26d0400 | 0x7fe2d6a35680 | 524288 | 13913086 | 1780876220 | 12073197635936548 | 12073197636104679 | 12073197636353317 | 12073197636423974 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fe3e26d0300 | 0x7fe2d6a356c0 | 524288 | 14010039 | 1793297200 | 12073197636447608 | 12073197636627396 | 12073197636881315 | 12073197636948919 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fe3e26d0a00 | 0x7fe2d6a35700 | 524288 | 11848617 | 1516595020 | 12073197636976050 | 12073197637157794 | 12073197637289953 | 12073197637293660 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fe3e26d0900 | 0x7fe2d6a35740 | 524288 | 12692558 | 1624629196 | 12073197637341729 | 12073197637512672 | 12073197637643711 | 12073197637647487 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fe3e26d0800 | 0x7fe2d6a35780 | 524288 | 13151693 | 1683305156 | 12073197637708170 | 12073197637868190 | 12073197637996670 | 12073197638005202 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fe3e26d0700 | 0x7fe2d6a357c0 | 524288 | 13984724 | 1790064352 | 12073197638049755 | 12073197638223709 | 12073197638478748 | 12073197638547029 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fe3e26d0600 | 0x7fe2d6a35800 | 524288 | 13980321 | 1789457572 | 12073197638570262 | 12073197638750906 | 12073197639004505 | 12073197639073136 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fe3e26d0500 | 0x7fe2d6a35840 | 524288 | 11951647 | 1529885940 | 12073197639100808 | 12073197639284184 | 12073197639416503 | 12073197639420081 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fe3e26d0400 | 0x7fe2d6a35880 | 524288 | 12177599 | 1558704956 | 12073197639468741 | 12073197639633462 | 12073197639766262 | 12073197639770041 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fe3e26d0300 | 0x7fe2d6a358c0 | 524288 | 13462484 | 1723263016 | 12073197639830594 | 12073197639988661 | 12073197640116020 | 12073197640120032 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fe3e26d0a00 | 0x7fe2d6a35900 | 524288 | 12512802 | 1601600008 | 12073197640174092 | 12073197640333779 | 12073197640630898 | 12073197640700089 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fe3e26d0900 | 0x7fe2d6a35940 | 524288 | 13533162 | 1732185628 | 12073197640725617 | 12073197640899696 | 12073197641151535 | 12073197641220386 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fe3e26d0800 | 0x7fe2d6a35980 | 524288 | 12488852 | 1598561888 | 12073197641243850 | 12073197641425294 | 12073197641555693 | 12073197641559045 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fe3e26d0700 | 0x7fe2d6a359c0 | 524288 | 11884379 | 1521182688 | 12073197641608658 | 12073197641781452 | 12073197641916492 | 12073197641920277 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fe3e26d0600 | 0x7fe2d6a35a00 | 524288 | 13400335 | 1715178208 | 12073197641982021 | 12073197642150891 | 12073197642278410 | 12073197642282460 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fe3e26d0500 | 0x7fe2d6a35a40 | 524288 | 14158642 | 1812279416 | 12073197642333314 | 12073197642505929 | 12073197642755688 | 12073197642823014 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fe3e26d0400 | 0x7fe2d6a35a80 | 524288 | 14115848 | 1806803256 | 12073197642848782 | 12073197643028167 | 12073197643284005 | 12073197643353209 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fe3e26d0300 | 0x7fe2d6a35ac0 | 524288 | 12176907 | 1558546172 | 12073197643381602 | 12073197643556324 | 12073197643688164 | 12073197643691949 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fe3e26d0a00 | 0x7fe2d6a35b00 | 524288 | 11804041 | 1510959772 | 12073197643741761 | 12073197643903523 | 12073197644037762 | 12073197644041809 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fe3e26d0900 | 0x7fe2d6a35b40 | 524288 | 12819279 | 1640778728 | 12073197644103403 | 12073197644265121 | 12073197644394400 | 12073197644398121 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fe3e26d0800 | 0x7fe2d6a35b80 | 524288 | 13620372 | 1743394680 | 12073197644449456 | 12073197644610559 | 12073197644870558 | 12073197644938986 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fe3e26d0700 | 0x7fe2d6a35bc0 | 524288 | 14233310 | 1821876844 | 12073197644963702 | 12073197645144637 | 12073197645396956 | 12073197645467528 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fe3e26d0600 | 0x7fe2d6a35c00 | 524288 | 12296472 | 1573979516 | 12073197645489969 | 12073197645671034 | 12073197645803034 | 12073197645806778 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fe3e26d0500 | 0x7fe2d6a35c40 | 524288 | 11563011 | 1480018488 | 12073197645857683 | 12073197646028953 | 12073197646165272 | 12073197646169121 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fe3e26d0400 | 0x7fe2d6a35c80 | 524288 | 12786714 | 1636780128 | 12073197646232189 | 12073197646391031 | 12073197646521431 | 12073197646525353 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fe3e26d0300 | 0x7fe2d6a35cc0 | 524288 | 12997975 | 1663683152 | 12073197646574485 | 12073197646739030 | 12073197646998548 | 12073197647068362 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fe3e26d0a00 | 0x7fe2d6a35d00 | 524288 | 13072767 | 1673256944 | 12073197647090744 | 12073197647270387 | 12073197647523346 | 12073197647591514 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fe3e26d0900 | 0x7fe2d6a35d40 | 524288 | 13240905 | 1694762312 | 12073197647613365 | 12073197647797105 | 12073197647925104 | 12073197647928881 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fe3e26d0800 | 0x7fe2d6a35d80 | 524288 | 10393391 | 1330363804 | 12073197647978083 | 12073197648144303 | 12073197648281422 | 12073197648285484 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fe3e26d0700 | 0x7fe2d6a35dc0 | 524288 | 12165310 | 1557232592 | 12073197648345946 | 12073197648504301 | 12073197648635661 | 12073197648639431 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fe3e26d0600 | 0x7fe2d6a35e00 | 524288 | 12200329 | 1561692460 | 12073197648688232 | 12073197648853580 | 12073197649112619 | 12073197649157544 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fe3e26d0500 | 0x7fe2d6a35e40 | 524288 | 13575928 | 1737708624 | 12073197649179846 | 12073197649367817 | 12073197649619016 | 12073197649661711 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fe3e26d0400 | 0x7fe2d6a35e80 | 524288 | 12991656 | 1662869032 | 12073197649689032 | 12073197649866695 | 12073197649995975 | 12073197649999739 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fe3e26d0300 | 0x7fe2d6a35ec0 | 524288 | 9347798 | 1196537280 | 12073197650049542 | 12073197650218854 | 12073197650357733 | 12073197650361531 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fe3e26d0a00 | 0x7fe2d6a35f00 | 524288 | 12902877 | 1651622616 | 12073197650424037 | 12073197650581732 | 12073197650711811 | 12073197650715629 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fe3e26d0900 | 0x7fe2d6a35f40 | 524288 | 13336615 | 1707105708 | 12073197650764530 | 12073197650928450 | 12073197651192449 | 12073197651263417 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fe3e26d0800 | 0x7fe2d6a35f80 | 524288 | 13332193 | 1706518352 | 12073197651286400 | 12073197651463808 | 12073197651718047 | 12073197651785708 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fe3e26d0700 | 0x7fe2d6a35fc0 | 524288 | 11936218 | 1527850504 | 12073197651811115 | 12073197651982045 | 12073197652115645 | 12073197652119678 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fe3e26d0600 | 0x7fe2d6a36000 | 524288 | 8022050 | 1026836612 | 12073197652169982 | 12073197652332444 | 12073197652471803 | 12073197652475720 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fe3e26d0500 | 0x7fe2d6a36040 | 524288 | 11550985 | 1478503904 | 12073197652536623 | 12073197652690842 | 12073197652824922 | 12073197652828655 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fe3e26d0400 | 0x7fe2d6a36080 | 524288 | 12969609 | 1660133296 | 12073197652878318 | 12073197653049721 | 12073197653313719 | 12073197653364371 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fe3e26d0300 | 0x7fe2d6a360c0 | 524288 | 13411485 | 1716707536 | 12073197653387644 | 12073197653567638 | 12073197653822197 | 12073197653872886 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fe3e26d0a00 | 0x7fe2d6a36100 | 524288 | 12595176 | 1612181092 | 12073197653897842 | 12073197654071636 | 12073197654202835 | 12073197654206816 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fe3e26d0900 | 0x7fe2d6a36140 | 524288 | 6931932 | 887185468 | 12073197654256418 | 12073197654425714 | 12073197654570834 | 12073197654574710 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fe3e26d0800 | 0x7fe2d6a36180 | 524288 | 11884893 | 1521257192 | 12073197654635793 | 12073197654792752 | 12073197654925392 | 12073197654929038 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fe3e26d0700 | 0x7fe2d6a361c0 | 524288 | 11203591 | 1434023088 | 12073197654978310 | 12073197655143791 | 12073197655406510 | 12073197655457129 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fe3e26d0600 | 0x7fe2d6a36200 | 524288 | 13234978 | 1694116808 | 12073197655479501 | 12073197655656589 | 12073197655913227 | 12073197655961126 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fe3e26d0500 | 0x7fe2d6a36240 | 524288 | 11792877 | 1509496040 | 12073197655987655 | 12073197656166506 | 12073197656300426 | 12073197656304434 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fe3e26d0400 | 0x7fe2d6a36280 | 524288 | 5271026 | 674672700 | 12073197656353174 | 12073197656531464 | 12073197656681224 | 12073197656684891 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fe3e26d0300 | 0x7fe2d6a362c0 | 524288 | 10756148 | 1376694228 | 12073197656763717 | 12073197656920423 | 12073197657057702 | 12073197657061761 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fe3e26d0a00 | 0x7fe2d6a36300 | 524288 | 11533426 | 1476280508 | 12073197657112455 | 12073197657283461 | 12073197657550180 | 12073197657602035 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fe3e26d0900 | 0x7fe2d6a36340 | 524288 | 13971451 | 1788337004 | 12073197657625078 | 12073197657803459 | 12073197658055777 | 12073197658106692 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fe3e26d0800 | 0x7fe2d6a36380 | 524288 | 12249143 | 1567869692 | 12073197658131248 | 12073197658308096 | 12073197658439936 | 12073197658443799 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fe3e26d0700 | 0x7fe2d6a363c0 | 524288 | 4678335 | 598758164 | 12073197658492199 | 12073197658650975 | 12073197658808414 | 12073197658812193 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fe3e26d0600 | 0x7fe2d6a36400 | 524288 | 10574531 | 1353460772 | 12073197658873688 | 12073197659034653 | 12073197659172092 | 12073197659176150 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fe3e26d0500 | 0x7fe2d6a36440 | 524288 | 11132774 | 1424975556 | 12073197659225441 | 12073197659394971 | 12073197659656730 | 12073197659705934 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fe3e26d0400 | 0x7fe2d6a36480 | 524288 | 12652006 | 1619405216 | 12073197659728386 | 12073197659901849 | 12073197660159608 | 12073197660211313 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fe3e26d0300 | 0x7fe2d6a364c0 | 524288 | 11783419 | 1508269532 | 12073197660238403 | 12073197660411767 | 12073197660544886 | 12073197660548860 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fe3e26d0a00 | 0x7fe2d6a36500 | 524288 | 4143736 | 530302432 | 12073197660598122 | 12073197660765365 | 12073197660930804 | 12073197660934727 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fe3e26d0900 | 0x7fe2d6a36540 | 524288 | 12032592 | 1540087856 | 12073197660996081 | 12073197661160883 | 12073197661294803 | 12073197661298934 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fe3e26d0800 | 0x7fe2d6a36580 | 524288 | 10457763 | 1338586580 | 12073197661340982 | 12073197661511442 | 12073197661771440 | 12073197661820032 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fe3e26d0700 | 0x7fe2d6a365c0 | 524288 | 14157464 | 1812185552 | 12073197661844397 | 12073197662022799 | 12073197662275918 | 12073197662326844 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fe3e26d0600 | 0x7fe2d6a36600 | 524288 | 10614211 | 1358632916 | 12073197662354185 | 12073197662527917 | 12073197662667276 | 12073197662671284 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fe3e26d0500 | 0x7fe2d6a36640 | 524288 | 3551383 | 454646120 | 12073197662719403 | 12073197662883275 | 12073197663057034 | 12073197663061148 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fe3e26d0400 | 0x7fe2d6a36680 | 524288 | 10367386 | 1327015448 | 12073197663121811 | 12073197663278793 | 12073197663418953 | 12073197663422921 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fe3e26d0300 | 0x7fe2d6a366c0 | 524288 | 7844350 | 1004057236 | 12073197663470769 | 12073197663637832 | 12073197663900871 | 12073197663949779 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fe3e26d0a00 | 0x7fe2d6a36700 | 524288 | 13967361 | 1787819284 | 12073197663971430 | 12073197664159109 | 12073197664414788 | 12073197664466490 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fe3e26d0900 | 0x7fe2d6a36740 | 524288 | 11909891 | 1524460524 | 12073197664490454 | 12073197664668867 | 12073197664802626 | 12073197664806451 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fe3e26d0800 | 0x7fe2d6a36780 | 524288 | 3671462 | 469829376 | 12073197664856264 | 12073197665025185 | 12073197665207585 | 12073197665211975 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fe3e26d0700 | 0x7fe2d6a367c0 | 524288 | 11520716 | 1474624736 | 12073197665273178 | 12073197665429504 | 12073197665564863 | 12073197665568728 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fe3e26d0600 | 0x7fe2d6a36800 | 524288 | 4142426 | 530202344 | 12073197665616887 | 12073197665780382 | 12073197666078621 | 12073197666128197 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fe3e26d0500 | 0x7fe2d6a36840 | 524288 | 12518770 | 1602409940 | 12073197666151240 | 12073197666328379 | 12073197666584538 | 12073197666633436 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fe3e26d0400 | 0x7fe2d6a36880 | 524288 | 11471812 | 1468467188 | 12073197666655196 | 12073197666828377 | 12073197666963736 | 12073197666967697 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fe3e26d0300 | 0x7fe2d6a368c0 | 524288 | 3682298 | 471432724 | 12073197667022158 | 12073197667186295 | 12073197667378135 | 12073197667429265 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fe3e26d0a00 | 0x7fe2d6a36900 | 524288 | 12371030 | 1583466544 | 12073197667463088 | 12073197667624373 | 12073197667756213 | 12073197667759999 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fe3e26d0900 | 0x7fe2d6a36940 | 524288 | 2991858 | 382995184 | 12073197667807838 | 12073197667974932 | 12073197668259730 | 12073197668311514 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fe3e26d0800 | 0x7fe2d6a36980 | 524288 | 12919876 | 1653738804 | 12073197668328415 | 12073197668512209 | 12073197668770608 | 12073197668818807 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fe3e26d0700 | 0x7fe2d6a369c0 | 524288 | 11021326 | 1410703744 | 12073197668846107 | 12073197669021487 | 12073197669157966 | 12073197669162255 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fe3e26d0600 | 0x7fe2d6a36a00 | 524288 | 3839316 | 491431388 | 12073197669211246 | 12073197669377325 | 12073197669587404 | 12073197669636115 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fe3e26d0500 | 0x7fe2d6a36a40 | 524288 | 10897125 | 1394876964 | 12073197669672803 | 12073197669829643 | 12073197669965003 | 12073197669968723 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fe3e26d0400 | 0x7fe2d6a36a80 | 524288 | 2545104 | 325861632 | 12073197670015731 | 12073197670187562 | 12073197670495080 | 12073197670519697 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fe3e26d0300 | 0x7fe2d6a36ac0 | 524288 | 12690051 | 1624254676 | 12073197670567035 | 12073197670725479 | 12073197670982278 | 12073197671030105 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fe3e26d0a00 | 0x7fe2d6a36b00 | 524288 | 10378914 | 1328452764 | 12073197671056474 | 12073197671230597 | 12073197671370116 | 12073197671373924 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fe3e26d0900 | 0x7fe2d6a36b40 | 524288 | 3428999 | 438934728 | 12073197671422525 | 12073197671588355 | 12073197671816034 | 12073197671863364 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fe3e26d0800 | 0x7fe2d6a36b80 | 524288 | 12100457 | 1548866284 | 12073197671899110 | 12073197672072353 | 12073197672206592 | 12073197672210649 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fe3e26d0700 | 0x7fe2d6a36bc0 | 524288 | 2463340 | 315323160 | 12073197672258508 | 12073197672426271 | 12073197672756990 | 12073197672805294 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fe3e26d0600 | 0x7fe2d6a36c00 | 524288 | 13245281 | 1695362952 | 12073197672830120 | 12073197673001949 | 12073197673261467 | 12073197673310262 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fe3e26d0500 | 0x7fe2d6a36c40 | 524288 | 9880791 | 1264794616 | 12073197673333756 | 12073197673510586 | 12073197673651226 | 12073197673655173 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fe3e26d0400 | 0x7fe2d6a36c80 | 524288 | 3293632 | 421549668 | 12073197673703413 | 12073197673865625 | 12073197674109784 | 12073197674158438 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fe3e26d0300 | 0x7fe2d6a36cc0 | 524288 | 10373304 | 1327810884 | 12073197674196980 | 12073197674357622 | 12073197674496182 | 12073197674499943 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fe3e26d0a00 | 0x7fe2d6a36d00 | 524288 | 2378085 | 304371452 | 12073197674548523 | 12073197674712365 | 12073197675088204 | 12073197675141344 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fe3e26d0900 | 0x7fe2d6a36d40 | 524288 | 13496109 | 1727457908 | 12073197675166551 | 12073197675349322 | 12073197675605641 | 12073197675653757 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fe3e26d0800 | 0x7fe2d6a36d80 | 524288 | 10266134 | 1314120260 | 12073197675684624 | 12073197675850280 | 12073197675988679 | 12073197675992095 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fe3e26d0700 | 0x7fe2d6a36dc0 | 524288 | 3408086 | 436092548 | 12073197676041838 | 12073197676211398 | 12073197676491237 | 12073197676542278 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fe3e26d0600 | 0x7fe2d6a36e00 | 524288 | 8102750 | 1037084076 | 12073197676576972 | 12073197676734436 | 12073197676877795 | 12073197676881247 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fe3e26d0500 | 0x7fe2d6a36e40 | 524288 | 2339960 | 299488572 | 12073197676932673 | 12073197677106274 | 12073197677553472 | 12073197677605032 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fe3e26d0400 | 0x7fe2d6a36e80 | 524288 | 10359981 | 1326045744 | 12073197677629768 | 12073197677803871 | 12073197678062590 | 12073197678114339 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fe3e26d0300 | 0x7fe2d6a36ec0 | 524288 | 7621467 | 975457860 | 12073197678135959 | 12073197678312189 | 12073197678451709 | 12073197678455382 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fe3e26d0a00 | 0x7fe2d6a36f00 | 524288 | 3565873 | 456484576 | 12073197678505886 | 12073197678671388 | 12073197678986426 | 12073197679036001 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fe3e26d0900 | 0x7fe2d6a36f40 | 524288 | 3645007 | 466492132 | 12073197679073190 | 12073197679232505 | 12073197679385305 | 12073197679388887 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fe3e26d0800 | 0x7fe2d6a36f80 | 524288 | 2301978 | 294625348 | 12073197679437667 | 12073197679596184 | 12073197680112982 | 12073197680161723 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fe3e26d0700 | 0x7fe2d6a36fc0 | 524288 | 7395001 | 946541752 | 12073197680188523 | 12073197680368661 | 12073197680666579 | 12073197680714780 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fe3e26d0600 | 0x7fe2d6a37000 | 524288 | 3161457 | 404864724 | 12073197680743874 | 12073197680923698 | 12073197681077618 | 12073197681081261 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fe3e26d0500 | 0x7fe2d6a37040 | 524288 | 3457590 | 442582692 | 12073197681131535 | 12073197681308817 | 12073197681694095 | 12073197681744694 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fe3e26d0400 | 0x7fe2d6a37080 | 524288 | 3294455 | 421789008 | 12073197681783126 | 12073197681938734 | 12073197682116013 | 12073197682119691 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fe3e26d0300 | 0x7fe2d6a370c0 | 524288 | 2347137 | 300384252 | 12073197682169614 | 12073197682330413 | 12073197682942090 | 12073197682990319 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fe3e26d0a00 | 0x7fe2d6a37100 | 524288 | 4545867 | 581974052 | 12073197683020294 | 12073197683201929 | 12073197683532648 | 12073197683580645 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fe3e26d0900 | 0x7fe2d6a37140 | 524288 | 3498074 | 447771416 | 12073197683617554 | 12073197683775527 | 12073197683992006 | 12073197684040380 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fe3e26d0800 | 0x7fe2d6a37180 | 524288 | 4124863 | 527896624 | 12073197684070145 | 12073197684241285 | 12073197684696803 | 12073197684743957 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fe3e26d0700 | 0x7fe2d6a371c0 | 524288 | 3126000 | 400073584 | 12073197684782298 | 12073197684942402 | 12073197685142401 | 12073197685193232 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fe3e26d0600 | 0x7fe2d6a37200 | 524288 | 2312993 | 296011860 | 12073197685211325 | 12073197685397920 | 12073197686100477 | 12073197686150731 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fe3e26d0500 | 0x7fe2d6a37240 | 524288 | 3452856 | 441988248 | 12073197686178953 | 12073197686359196 | 12073197686730074 | 12073197686777756 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fe3e26d0400 | 0x7fe2d6a37280 | 524288 | 3270536 | 418628344 | 12073197686804235 | 12073197686980473 | 12073197687184472 | 12073197687234475 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fe3e26d0300 | 0x7fe2d6a372c0 | 524288 | 4439374 | 568318752 | 12073197687269339 | 12073197687432951 | 12073197687958709 | 12073197688011909 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fe3e26d0a00 | 0x7fe2d6a37300 | 524288 | 3080398 | 394488868 | 12073197688054859 | 12073197688216788 | 12073197688439667 | 12073197688489176 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fe3e26d0900 | 0x7fe2d6a37340 | 524288 | 2299975 | 294406804 | 12073197688511628 | 12073197688686706 | 12073197689486063 | 12073197689540329 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fe3e26d0800 | 0x7fe2d6a37380 | 524288 | 3610588 | 462159828 | 12073197689567029 | 12073197689756302 | 12073197690199820 | 12073197690251420 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fe3e26d0700 | 0x7fe2d6a373c0 | 524288 | 3084018 | 394788628 | 12073197690281426 | 12073197690459179 | 12073197690685898 | 12073197690735400 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fe3e26d0600 | 0x7fe2d6a37400 | 524288 | 4473781 | 572551664 | 12073197690760737 | 12073197690932617 | 12073197691530534 | 12073197691582203 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fe3e26d0500 | 0x7fe2d6a37440 | 524288 | 3330284 | 426363324 | 12073197691617639 | 12073197691785413 | 12073197692054692 | 12073197692107359 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fe3e26d0400 | 0x7fe2d6a37480 | 524288 | 2308010 | 295577972 | 12073197692131394 | 12073197692306851 | 12073197693291327 | 12073197693360848 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fe3e26d0300 | 0x7fe2d6a374c0 | 524288 | 3385103 | 433167952 | 12073197693383500 | 12073197693563966 | 12073197694078364 | 12073197694147910 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fe3e26d0a00 | 0x7fe2d6a37500 | 524288 | 3389797 | 433777264 | 12073197694175101 | 12073197694345242 | 12073197694618361 | 12073197694686231 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fe3e26d0900 | 0x7fe2d6a37540 | 524288 | 2216719 | 283842224 | 12073197694710165 | 12073197694881720 | 12073197695619797 | 12073197695691068 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fe3e26d0800 | 0x7fe2d6a37580 | 524288 | 3293416 | 421458796 | 12073197695730351 | 12073197695890356 | 12073197696234195 | 12073197696305610 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fe3e26d0700 | 0x7fe2d6a375c0 | 524288 | 2301628 | 294581048 | 12073197696331438 | 12073197696515313 | 12073197697685389 | 12073197697755243 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fe3e26d0600 | 0x7fe2d6a37600 | 524288 | 3186553 | 407818188 | 12073197697785049 | 12073197697962987 | 12073197698571625 | 12073197698641109 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fe3e26d0500 | 0x7fe2d6a37640 | 524288 | 3310741 | 423678428 | 12073197698666506 | 12073197698846824 | 12073197699165062 | 12073197699237257 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fe3e26d0400 | 0x7fe2d6a37680 | 524288 | 2195876 | 281128880 | 12073197699262724 | 12073197699442501 | 12073197700321058 | 12073197700391291 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fe3e26d0300 | 0x7fe2d6a376c0 | 524288 | 3318811 | 424826160 | 12073197700430684 | 12073197700587936 | 12073197701023775 | 12073197701093306 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fe3e26d0a00 | 0x7fe2d6a37700 | 524288 | 2326784 | 297870612 | 12073197701122430 | 12073197701298173 | 12073197702845687 | 12073197702915602 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fe3e26d0900 | 0x7fe2d6a37740 | 524288 | 2288410 | 292937460 | 12073197702945337 | 12073197703127606 | 12073197703921683 | 12073197703992863 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fe3e26d0800 | 0x7fe2d6a37780 | 524288 | 2168592 | 277575340 | 12073197704016427 | 12073197704195921 | 12073197704610960 | 12073197704681643 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fe3e26d0700 | 0x7fe2d6a377c0 | 524288 | 2293896 | 293619428 | 12073197704702402 | 12073197704886319 | 12073197706045034 | 12073197706115187 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fe3e26d0600 | 0x7fe2d6a37800 | 524288 | 2232716 | 285951260 | 12073197706155782 | 12073197706316393 | 12073197707102469 | 12073197707171930 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fe3e26d0500 | 0x7fe2d6a37840 | 524288 | 2643405 | 338245572 | 12073197707202046 | 12073197707378308 | 12073197710427095 | 12073197710497169 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fe3e26d0400 | 0x7fe2d6a37880 | 524288 | 2316310 | 296555712 | 12073197710526283 | 12073197710704054 | 12073197712244528 | 12073197712314536 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fe3e26d0300 | 0x7fe2d6a378c0 | 524288 | 2310855 | 295775876 | 12073197712346926 | 12073197712526767 | 12073197713317643 | 12073197713387269 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fe3e26d0a00 | 0x7fe2d6a37900 | 524288 | 2517194 | 322272800 | 12073197713409500 | 12073197713591722 | 12073197715874113 | 12073197715943990 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fe3e26d0900 | 0x7fe2d6a37940 | 524288 | 2442373 | 312733256 | 12073197715986899 | 12073197716154432 | 12073197717690265 | 12073197717761527 |
| 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 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fe3e26d0800 | 0x7fe2d6a37980 | 524288 | 2864238 | 366523960 | 12073197717790982 | 12073197717967864 | 12073197724021599 | 12073197724095135 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fe3e26d0700 | 0x7fe2d6a379c0 | 524288 | 3032822 | 388230616 | 12073197724120011 | 12073197724299518 | 12073197727340945 | 12073197727411527 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fe3e26d0600 | 0x7fe2d6a37a00 | 524288 | 2257775 | 289061972 | 12073197727441994 | 12073197727622384 | 12073197729161097 | 12073197729230998 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 747934 | 747939 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fe3e26d0500 | 0x7fe2d6a37a40 | 524288 | 2582737 | 330543664 | 12073197729260974 | 12073197729436616 | 12073197733964277 | 12073197734034153 |