37 KiB
37 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 156034 | 156034 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fe2d8a04280 | 16343179251330 | 16343179280950 | 16343179518712 | 16343179625622 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 156034 | 156034 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fe2d8a23f80 | 16343184389807 | 16343184405785 | 16343184412985 | 16343184423136 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fe2dbae5380 | 0x7fe2d8a23fc0 | 16343184437766 | 16343184447706 | 16343184539866 | 16343184542333 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fe2dbae5200 | 0x7fe2d8a24000 | 16343184563613 | 16343184574106 | 16343184754428 | 16343184756889 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fe2dbae5080 | 0x7fe2d8a24040 | 16343184772738 | 16343184780988 | 16343184961629 | 16343184963744 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fe2d944df00 | 0x7fe2d8a24080 | 16343184977424 | 16343184985789 | 16343185078110 | 16343185080482 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fe2d944dd80 | 0x7fe2d8a240c0 | 16343185096781 | 16343185104830 | 16343185196831 | 16343185198859 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fe2d944dc00 | 0x7fe2d8a24100 | 16343185230958 | 16343185241471 | 16343185332832 | 16343185334926 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fe2d944da80 | 0x7fe2d8a24140 | 16343185358615 | 16343185371712 | 16343185551553 | 16343185553721 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fe2d944d900 | 0x7fe2d8a24180 | 16343185587140 | 16343185597794 | 16343185776515 | 16343185778806 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fe2d944d780 | 0x7fe2d8a241c0 | 16343185801606 | 16343185812035 | 16343185904196 | 16343185906513 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fe2d944d600 | 0x7fe2d8a24200 | 16343185926093 | 16343185936516 | 16343186028837 | 16343186031051 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fe2dbae5480 | 0x7fe2d8a24240 | 16343186059030 | 16343186068837 | 16343186160998 | 16343186163118 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fe2dbae5300 | 0x7fe2d8a24280 | 16343186186687 | 16343186198118 | 16343186378279 | 16343186380743 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fe2dbae5180 | 0x7fe2d8a242c0 | 16343186397152 | 16343186406439 | 16343186586921 | 16343186589218 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fe2dbae5000 | 0x7fe2d8a24300 | 16343186604238 | 16343186613001 | 16343186705162 | 16343186707256 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fe2d944de80 | 0x7fe2d8a24340 | 16343186723665 | 16343186733962 | 16343186825642 | 16343186827753 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fe2d944dd00 | 0x7fe2d8a24380 | 16343186849202 | 16343186859563 | 16343186951243 | 16343186953440 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fe2d944db80 | 0x7fe2d8a243c0 | 16343186978390 | 16343186988524 | 16343187168205 | 16343187170305 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fe2d944da00 | 0x7fe2d8a24400 | 16343187188125 | 16343187196845 | 16343187376366 | 16343187378371 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fe2d944d880 | 0x7fe2d8a24440 | 16343187393850 | 16343187402766 | 16343187495887 | 16343187498058 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fe2d944d700 | 0x7fe2d8a24480 | 16343187515908 | 16343187524687 | 16343187616688 | 16343187618855 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fe2dbae5580 | 0x7fe2d8a244c0 | 16343187639625 | 16343187650288 | 16343187741649 | 16343187743933 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fe2dbae5400 | 0x7fe2d8a24500 | 16343187760122 | 16343187792049 | 16343187972690 | 16343187975127 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fe2dbae5280 | 0x7fe2d8a24540 | 16343187990077 | 16343187999411 | 16343188181812 | 16343188184083 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fe2dbae5100 | 0x7fe2d8a24580 | 16343188205342 | 16343188214612 | 16343188306453 | 16343188308170 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fe2d944df80 | 0x7fe2d8a245c0 | 16343188323110 | 16343188331253 | 16343188422294 | 16343188423988 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fe2d944de00 | 0x7fe2d8a24600 | 16343188443547 | 16343188454614 | 16343188546295 | 16343188547855 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fe2d944dc80 | 0x7fe2d8a24640 | 16343188563144 | 16343188571255 | 16343188750776 | 16343188752460 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fe2d944db00 | 0x7fe2d8a24680 | 16343188766310 | 16343188774296 | 16343188954617 | 16343188956116 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fe2d944d980 | 0x7fe2d8a246c0 | 16343188969735 | 16343188977818 | 16343189070298 | 16343189071953 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fe2d944d800 | 0x7fe2d8a24700 | 16343189086313 | 16343189094298 | 16343189186139 | 16343189187831 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fe2d944d680 | 0x7fe2d8a24740 | 16343189208750 | 16343189218299 | 16343189310460 | 16343189312148 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fe2dbae5500 | 0x7fe2d8a24780 | 16343189326778 | 16343189334620 | 16343189513821 | 16343189515353 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fe2dbae5380 | 0x7fe2d8a247c0 | 16343189529823 | 16343189538142 | 16343189717663 | 16343189719289 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fe2dbae5200 | 0x7fe2d8a24800 | 16343189734168 | 16343189742143 | 16343189834784 | 16343189836276 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fe2dbae5080 | 0x7fe2d8a24840 | 16343189851116 | 16343189858944 | 16343189951584 | 16343189953214 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fe2d944df00 | 0x7fe2d8a24880 | 16343189972733 | 16343189983905 | 16343190075585 | 16343190081261 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fe2d944dd80 | 0x7fe2d8a248c0 | 16343190095640 | 16343190104386 | 16343190283747 | 16343190285506 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fe2d944dc00 | 0x7fe2d8a24900 | 16343190299176 | 16343190307267 | 16343190487908 | 16343190489432 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fe2d944da80 | 0x7fe2d8a24940 | 16343190504381 | 16343190512708 | 16343190605189 | 16343190606959 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fe2d944d900 | 0x7fe2d8a24980 | 16343190620849 | 16343190628869 | 16343190721670 | 16343190723457 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fe2d944d780 | 0x7fe2d8a249c0 | 16343190743146 | 16343190753990 | 16343190845991 | 16343190847874 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fe2d944d600 | 0x7fe2d8a24a00 | 16343190862684 | 16343190870951 | 16343191050632 | 16343191052319 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fe2dbae5480 | 0x7fe2d8a24a40 | 16343191066209 | 16343191074152 | 16343191255114 | 16343191256865 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fe2dbae5300 | 0x7fe2d8a24a80 | 16343191271395 | 16343191279114 | 16343191371435 | 16343191373242 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fe2dbae5180 | 0x7fe2d8a24ac0 | 16343191388052 | 16343191397195 | 16343191489355 | 16343191490970 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fe2dbae5000 | 0x7fe2d8a24b00 | 16343191510219 | 16343191521676 | 16343191612876 | 16343191614357 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fe2d944de80 | 0x7fe2d8a24b40 | 16343191630457 | 16343191638636 | 16343191817358 | 16343191818843 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fe2d944dd00 | 0x7fe2d8a24b80 | 16343191834442 | 16343191842158 | 16343192023119 | 16343192024778 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fe2d944db80 | 0x7fe2d8a24bc0 | 16343192039228 | 16343192047119 | 16343192140560 | 16343192142075 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fe2d944da00 | 0x7fe2d8a24c00 | 16343192156215 | 16343192164240 | 16343192257041 | 16343192258573 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fe2d944d880 | 0x7fe2d8a24c40 | 16343192278482 | 16343192289361 | 16343192381202 | 16343192382810 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fe2d944d700 | 0x7fe2d8a24c80 | 16343192397560 | 16343192405522 | 16343192584563 | 16343192586156 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fe2dbae5580 | 0x7fe2d8a24cc0 | 16343192601195 | 16343192609043 | 16343192790325 | 16343192791791 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fe2dbae5400 | 0x7fe2d8a24d00 | 16343192806811 | 16343192814485 | 16343192907285 | 16343192908819 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fe2dbae5280 | 0x7fe2d8a24d40 | 16343192924728 | 16343192932406 | 16343193029686 | 16343193031166 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fe2dbae5100 | 0x7fe2d8a24d80 | 16343193051305 | 16343193062006 | 16343193154007 | 16343193155593 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fe2d944df80 | 0x7fe2d8a24dc0 | 16343193172353 | 16343193181047 | 16343193361049 | 16343193362499 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fe2d944de00 | 0x7fe2d8a24e00 | 16343193376538 | 16343193384729 | 16343193562330 | 16343193563944 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fe2d944dc80 | 0x7fe2d8a24e40 | 16343193580714 | 16343193589050 | 16343193682171 | 16343193683712 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fe2d944db00 | 0x7fe2d8a24e80 | 16343193699671 | 16343193708091 | 16343193810492 | 16343193812079 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fe2d944d980 | 0x7fe2d8a24ec0 | 16343193832088 | 16343193842812 | 16343193934973 | 16343193936466 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fe2d944d800 | 0x7fe2d8a24f00 | 16343193951066 | 16343193958813 | 16343194139454 | 16343194141121 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fe2d944d680 | 0x7fe2d8a24f40 | 16343194157671 | 16343194166814 | 16343194346816 | 16343194348497 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fe2dbae5500 | 0x7fe2d8a24f80 | 16343194362177 | 16343194370016 | 16343194462976 | 16343194464644 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fe2dbae5380 | 0x7fe2d8a24fc0 | 16343194478974 | 16343194486977 | 16343194592417 | 16343194594001 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fe2dbae5200 | 0x7fe2d8a25000 | 16343194614161 | 16343194624738 | 16343194717218 | 16343194718939 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fe2dbae5080 | 0x7fe2d8a25040 | 16343194733008 | 16343194741058 | 16343194921700 | 16343194923434 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fe2d944df00 | 0x7fe2d8a25080 | 16343194937114 | 16343194945060 | 16343195126341 | 16343195128180 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fe2d944dd80 | 0x7fe2d8a250c0 | 16343195142049 | 16343195150181 | 16343195244102 | 16343195246117 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fe2d944dc00 | 0x7fe2d8a25100 | 16343195259447 | 16343195267302 | 16343195379463 | 16343195381104 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fe2d944da80 | 0x7fe2d8a25140 | 16343195416063 | 16343195425543 | 16343195517864 | 16343195519451 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fe2d944d900 | 0x7fe2d8a25180 | 16343195535511 | 16343195543144 | 16343195723145 | 16343195724856 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fe2d944d780 | 0x7fe2d8a251c0 | 16343195741306 | 16343195749705 | 16343195930507 | 16343195932242 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fe2d944d600 | 0x7fe2d8a25200 | 16343195946101 | 16343195954187 | 16343196047948 | 16343196049549 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fe2dbae5480 | 0x7fe2d8a25240 | 16343196064889 | 16343196074028 | 16343196192749 | 16343196194286 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fe2dbae5300 | 0x7fe2d8a25280 | 16343196214185 | 16343196224909 | 16343196316909 | 16343196318353 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fe2dbae5180 | 0x7fe2d8a252c0 | 16343196332843 | 16343196341070 | 16343196521231 | 16343196522839 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fe2dbae5000 | 0x7fe2d8a25300 | 16343196538048 | 16343196546031 | 16343196725072 | 16343196726604 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fe2d944de80 | 0x7fe2d8a25340 | 16343196741274 | 16343196749713 | 16343196843153 | 16343196844621 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fe2d944dd00 | 0x7fe2d8a25380 | 16343196859731 | 16343196867793 | 16343196991634 | 16343196993098 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fe2d944db80 | 0x7fe2d8a253c0 | 16343197012698 | 16343197023634 | 16343197116915 | 16343197118375 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fe2d944da00 | 0x7fe2d8a25400 | 16343197133115 | 16343197140915 | 16343197319317 | 16343197320891 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fe2d944d880 | 0x7fe2d8a25440 | 16343197335561 | 16343197343477 | 16343197523638 | 16343197525236 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fe2d944d700 | 0x7fe2d8a25480 | 16343197539266 | 16343197547478 | 16343197639959 | 16343197641554 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fe2dbae5580 | 0x7fe2d8a254c0 | 16343197655714 | 16343197663639 | 16343197792120 | 16343197793630 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fe2dbae5400 | 0x7fe2d8a25500 | 16343197813600 | 16343197824440 | 16343197916921 | 16343197918478 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fe2dbae5280 | 0x7fe2d8a25540 | 16343197934117 | 16343197943161 | 16343198121082 | 16343198122713 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fe2dbae5100 | 0x7fe2d8a25580 | 16343198138493 | 16343198146682 | 16343198325724 | 16343198327589 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fe2d944df80 | 0x7fe2d8a255c0 | 16343198342018 | 16343198349724 | 16343198443004 | 16343198444726 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fe2d944de00 | 0x7fe2d8a25600 | 16343198458786 | 16343198466685 | 16343198602366 | 16343198604103 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fe2d944dc80 | 0x7fe2d8a25640 | 16343198624332 | 16343198635326 | 16343198728606 | 16343198730400 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fe2d944db00 | 0x7fe2d8a25680 | 16343198745289 | 16343198753407 | 16343198932288 | 16343198934065 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fe2d944d980 | 0x7fe2d8a256c0 | 16343198947535 | 16343198956128 | 16343199135969 | 16343199137651 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fe2d944d800 | 0x7fe2d8a25700 | 16343199150761 | 16343199158690 | 16343199254050 | 16343199255758 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fe2d944d680 | 0x7fe2d8a25740 | 16343199270588 | 16343199278530 | 16343199420611 | 16343199422405 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fe2dbae5500 | 0x7fe2d8a25780 | 16343199442664 | 16343199452932 | 16343199546212 | 16343199547752 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fe2dbae5380 | 0x7fe2d8a257c0 | 16343199562221 | 16343199570052 | 16343199747654 | 16343199749437 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fe2dbae5200 | 0x7fe2d8a25800 | 16343199763937 | 16343199771814 | 16343199951335 | 16343199953053 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fe2dbae5080 | 0x7fe2d8a25840 | 16343199967493 | 16343199976135 | 16343200075496 | 16343200077370 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fe2d944df00 | 0x7fe2d8a25880 | 16343200091290 | 16343200099176 | 16343200253097 | 16343200254736 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fe2d944dd80 | 0x7fe2d8a258c0 | 16343200274136 | 16343200285257 | 16343200378058 | 16343200379783 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fe2d944dc00 | 0x7fe2d8a25900 | 16343200395443 | 16343200403498 | 16343200582220 | 16343200583759 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fe2d944da80 | 0x7fe2d8a25940 | 16343200598269 | 16343200606700 | 16343200787661 | 16343200789294 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fe2d944d900 | 0x7fe2d8a25980 | 16343200802984 | 16343200810861 | 16343200914542 | 16343200916142 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fe2d944d780 | 0x7fe2d8a259c0 | 16343200930921 | 16343200939342 | 16343201106703 | 16343201108147 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fe2d944d600 | 0x7fe2d8a25a00 | 16343201128177 | 16343201139024 | 16343201232784 | 16343201234245 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fe2dbae5480 | 0x7fe2d8a25a40 | 16343201248744 | 16343201256464 | 16343201435186 | 16343201436640 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fe2dbae5300 | 0x7fe2d8a25a80 | 16343201453660 | 16343201461266 | 16343201640307 | 16343201641896 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fe2dbae5180 | 0x7fe2d8a25ac0 | 16343201656555 | 16343201664467 | 16343201772788 | 16343201774403 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fe2dbae5000 | 0x7fe2d8a25b00 | 16343201789572 | 16343201797428 | 16343201976629 | 16343201978188 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fe2d944de80 | 0x7fe2d8a25b40 | 16343201999068 | 16343202009270 | 16343202109590 | 16343202111195 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fe2d944dd00 | 0x7fe2d8a25b80 | 16343202126925 | 16343202135831 | 16343202317272 | 16343202318761 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fe2d944db80 | 0x7fe2d8a25bc0 | 16343202332851 | 16343202340792 | 16343202524473 | 16343202526016 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fe2d944da00 | 0x7fe2d8a25c00 | 16343202540856 | 16343202549113 | 16343202669914 | 16343202671473 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fe2d944d880 | 0x7fe2d8a25c40 | 16343202685493 | 16343202693595 | 16343202897596 | 16343202916608 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fe2d944d700 | 0x7fe2d8a25c80 | 16343202931587 | 16343202942556 | 16343203051197 | 16343203052735 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fe2dbae5580 | 0x7fe2d8a25cc0 | 16343203067954 | 16343203076637 | 16343203259839 | 16343203261390 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fe2dbae5400 | 0x7fe2d8a25d00 | 16343203275750 | 16343203283999 | 16343203466400 | 16343203467976 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fe2dbae5280 | 0x7fe2d8a25d40 | 16343203483815 | 16343203491360 | 16343203623841 | 16343203625392 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fe2dbae5100 | 0x7fe2d8a25d80 | 16343203639212 | 16343203647201 | 16343203877763 | 16343203896376 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fe2d944df80 | 0x7fe2d8a25dc0 | 16343203912026 | 16343203922723 | 16343204047684 | 16343204049163 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fe2d944de00 | 0x7fe2d8a25e00 | 16343204063872 | 16343204071684 | 16343204262406 | 16343204263958 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fe2d944dc80 | 0x7fe2d8a25e40 | 16343204278608 | 16343204286726 | 16343204478247 | 16343204479703 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fe2d944db00 | 0x7fe2d8a25e80 | 16343204493263 | 16343204501447 | 16343204659208 | 16343204660649 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fe2d944d980 | 0x7fe2d8a25ec0 | 16343204675279 | 16343204683369 | 16343204964971 | 16343204982602 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fe2d944d800 | 0x7fe2d8a25f00 | 16343204997692 | 16343205008811 | 16343205155052 | 16343205156528 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fe2d944d680 | 0x7fe2d8a25f40 | 16343205172998 | 16343205180812 | 16343205390414 | 16343205408013 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fe2dbae5500 | 0x7fe2d8a25f80 | 16343205417223 | 16343205427534 | 16343205638735 | 16343205655917 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fe2dbae5380 | 0x7fe2d8a25fc0 | 16343205664287 | 16343205674576 | 16343205858257 | 16343205859833 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fe2dbae5200 | 0x7fe2d8a26000 | 16343205875473 | 16343205883377 | 16343206216499 | 16343206260844 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fe2dbae5080 | 0x7fe2d8a26040 | 16343206279054 | 16343206288980 | 16343206453141 | 16343206454770 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fe2d944df00 | 0x7fe2d8a26080 | 16343206470619 | 16343206478581 | 16343206709143 | 16343206747693 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fe2d944dd80 | 0x7fe2d8a260c0 | 16343206757993 | 16343206768503 | 16343206996985 | 16343207038087 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fe2d944dc00 | 0x7fe2d8a26100 | 16343207047577 | 16343207057465 | 16343207267387 | 16343207305871 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fe2d944da80 | 0x7fe2d8a26140 | 16343207317091 | 16343207326587 | 16343207709310 | 16343207747581 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fe2d944d900 | 0x7fe2d8a26180 | 16343207763311 | 16343207773950 | 16343207958592 | 16343207960066 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fe2d944d780 | 0x7fe2d8a261c0 | 16343207975326 | 16343207983072 | 16343208235714 | 16343208274349 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fe2d944d600 | 0x7fe2d8a26200 | 16343208284729 | 16343208294754 | 16343208540836 | 16343208582293 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fe2dbae5480 | 0x7fe2d8a26240 | 16343208593322 | 16343208603556 | 16343208839078 | 16343208856586 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fe2dbae5300 | 0x7fe2d8a26280 | 16343208867016 | 16343208877798 | 16343209327401 | 16343209344546 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fe2dbae5180 | 0x7fe2d8a262c0 | 16343209360175 | 16343209371402 | 16343209594603 | 16343209608820 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fe2dbae5000 | 0x7fe2d8a26300 | 16343209617790 | 16343209628204 | 16343209926606 | 16343209940412 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fe2d944de80 | 0x7fe2d8a26340 | 16343209952042 | 16343209961966 | 16343210258928 | 16343210302734 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fe2d944dd00 | 0x7fe2d8a26380 | 16343210312374 | 16343210322288 | 16343210616050 | 16343210658977 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fe2d944db80 | 0x7fe2d8a263c0 | 16343210669606 | 16343210680051 | 16343211233495 | 16343211274293 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fe2d944da00 | 0x7fe2d8a26400 | 16343211290323 | 16343211301335 | 16343211563097 | 16343211603836 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fe2d944d880 | 0x7fe2d8a26440 | 16343211613216 | 16343211623258 | 16343211973980 | 16343212014957 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fe2d944d700 | 0x7fe2d8a26480 | 16343212025217 | 16343212034781 | 16343212385023 | 16343212426418 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fe2dbae5580 | 0x7fe2d8a264c0 | 16343212435368 | 16343212445663 | 16343212790466 | 16343212831199 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fe2dbae5400 | 0x7fe2d8a26500 | 16343212842599 | 16343212853026 | 16343213509831 | 16343213548873 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fe2dbae5280 | 0x7fe2d8a26540 | 16343213566263 | 16343213575911 | 16343214019115 | 16343214033642 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fe2dbae5100 | 0x7fe2d8a26580 | 16343214043012 | 16343214052715 | 16343214513358 | 16343214555601 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fe2d944df80 | 0x7fe2d8a265c0 | 16343214565991 | 16343214575438 | 16343215032882 | 16343215074829 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fe2d944de00 | 0x7fe2d8a26600 | 16343215083819 | 16343215093842 | 16343215542645 | 16343215582108 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fe2d944dc80 | 0x7fe2d8a26640 | 16343215591568 | 16343215601366 | 16343216465852 | 16343216505568 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fe2d944db00 | 0x7fe2d8a26680 | 16343216522318 | 16343216532892 | 16343217382498 | 16343217421978 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fe2d944d980 | 0x7fe2d8a266c0 | 16343217432028 | 16343217442019 | 16343218322825 | 16343218371987 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fe2d944d800 | 0x7fe2d8a26700 | 16343218386676 | 16343218411146 | 16343219287152 | 16343219333026 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fe2d944d680 | 0x7fe2d8a26740 | 16343219343615 | 16343219360272 | 16343220215638 | 16343220261625 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fe2dbae5500 | 0x7fe2d8a26780 | 16343220271545 | 16343220280919 | 16343221975971 | 16343222041215 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fe2dbae5380 | 0x7fe2d8a267c0 | 16343222057985 | 16343222068931 | 16343223730543 | 16343223802237 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fe2dbae5200 | 0x7fe2d8a26800 | 16343223814246 | 16343223851024 | 16343225571516 | 16343225639416 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fe2dbae5080 | 0x7fe2d8a26840 | 16343225650016 | 16343225659837 | 16343227371369 | 16343227442167 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fe2d944df00 | 0x7fe2d8a26880 | 16343227454646 | 16343227473770 | 16343229142901 | 16343229207858 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 156034 | 156034 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fe2d944dd80 | 0x7fe2d8a268c0 | 16343229217868 | 16343229227702 | 16343232581966 | 16343232660111 |