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 | 167556 | 167556 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f5678404280 | 16649012672586 | 16649012699076 | 16649012939874 | 16649013055803 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 167556 | 167556 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f5678423f80 | 16649017699376 | 16649017715526 | 16649017729126 | 16649017746554 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f567b46b380 | 0x7f5678423fc0 | 16649017751024 | 16649017795366 | 16649017887685 | 16649017890059 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f567b46b200 | 0x7f5678424000 | 16649017912079 | 16649017921445 | 16649018101284 | 16649018103802 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f567b46b080 | 0x7f5678424040 | 16649018118882 | 16649018127524 | 16649018307203 | 16649018309325 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f5678e0bf00 | 0x7f5678424080 | 16649018322845 | 16649018331043 | 16649018424162 | 16649018426231 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f5678e0bd80 | 0x7f56784240c0 | 16649018442731 | 16649018450882 | 16649018543041 | 16649018544957 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f5678e0bc00 | 0x7f5678424100 | 16649018571846 | 16649018582401 | 16649018674561 | 16649018676723 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f5678e0ba80 | 0x7f5678424140 | 16649018698312 | 16649018713601 | 16649018892960 | 16649018895175 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f5678e0b900 | 0x7f5678424180 | 16649018911955 | 16649018920639 | 16649019099998 | 16649019102158 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f5678e0b780 | 0x7f56784241c0 | 16649019119708 | 16649019127838 | 16649019222078 | 16649019224144 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f5678e0b600 | 0x7f5678424200 | 16649019240104 | 16649019248478 | 16649019341277 | 16649019343280 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f567b46b480 | 0x7f5678424240 | 16649019362750 | 16649019373437 | 16649019466396 | 16649019468436 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f567b46b300 | 0x7f5678424280 | 16649019493125 | 16649019503676 | 16649019682555 | 16649019684549 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f567b46b180 | 0x7f56784242c0 | 16649019705548 | 16649019715355 | 16649019895354 | 16649019897312 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f567b46b000 | 0x7f5678424300 | 16649019916061 | 16649019926074 | 16649020019673 | 16649020021767 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f5678e0be80 | 0x7f5678424340 | 16649020044957 | 16649020069753 | 16649020163352 | 16649020165542 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f5678e0bd00 | 0x7f5678424380 | 16649020188152 | 16649020198712 | 16649020292472 | 16649020294468 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f5678e0bb80 | 0x7f56784243c0 | 16649020312687 | 16649020321591 | 16649020501270 | 16649020503231 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f5678e0ba00 | 0x7f5678424400 | 16649020519860 | 16649020533910 | 16649020713909 | 16649020716044 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f5678e0b880 | 0x7f5678424440 | 16649020731813 | 16649020740789 | 16649020835029 | 16649020837080 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f5678e0b700 | 0x7f5678424480 | 16649020856799 | 16649020867028 | 16649020960468 | 16649020962485 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f567b46b580 | 0x7f56784244c0 | 16649020984515 | 16649020995188 | 16649021087507 | 16649021089461 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f567b46b400 | 0x7f5678424500 | 16649021109810 | 16649021126067 | 16649021305426 | 16649021307604 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f567b46b280 | 0x7f5678424540 | 16649021321533 | 16649021331026 | 16649021511825 | 16649021513837 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f567b46b100 | 0x7f5678424580 | 16649021532066 | 16649021540785 | 16649021633104 | 16649021635073 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f5678e0bf80 | 0x7f56784245c0 | 16649021655772 | 16649021665744 | 16649021757903 | 16649021759948 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f5678e0be00 | 0x7f5678424600 | 16649021781968 | 16649021792623 | 16649021886383 | 16649021888344 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f5678e0bc80 | 0x7f5678424640 | 16649021906034 | 16649021932942 | 16649022112621 | 16649022114806 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f5678e0bb00 | 0x7f5678424680 | 16649022131996 | 16649022141421 | 16649022322380 | 16649022323999 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f5678e0b980 | 0x7f56784246c0 | 16649022343069 | 16649022351020 | 16649022444779 | 16649022446265 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f5678e0b800 | 0x7f5678424700 | 16649022461935 | 16649022470379 | 16649022564139 | 16649022565741 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f5678e0b680 | 0x7f5678424740 | 16649022587080 | 16649022596619 | 16649022690218 | 16649022691677 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f567b46b500 | 0x7f5678424780 | 16649022706486 | 16649022714538 | 16649022894857 | 16649022896430 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f567b46b380 | 0x7f56784247c0 | 16649022911049 | 16649022919817 | 16649023100456 | 16649023102193 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f567b46b200 | 0x7f5678424800 | 16649023116662 | 16649023124936 | 16649023218375 | 16649023219939 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f567b46b080 | 0x7f5678424840 | 16649023233398 | 16649023242535 | 16649023335974 | 16649023337435 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f5678e0bf00 | 0x7f5678424880 | 16649023357034 | 16649023368134 | 16649023462534 | 16649023464091 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f5678e0bd80 | 0x7f56784248c0 | 16649023478880 | 16649023487174 | 16649023667653 | 16649023669154 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f5678e0bc00 | 0x7f5678424900 | 16649023684823 | 16649023692452 | 16649023873251 | 16649023874767 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f5678e0ba80 | 0x7f5678424940 | 16649023892196 | 16649023900931 | 16649023994851 | 16649023996412 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f5678e0b900 | 0x7f5678424980 | 16649024010822 | 16649024019171 | 16649024113410 | 16649024114928 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f5678e0b780 | 0x7f56784249c0 | 16649024136068 | 16649024146530 | 16649024241089 | 16649024242584 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f5678e0b600 | 0x7f5678424a00 | 16649024258024 | 16649024266369 | 16649024446208 | 16649024447797 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f567b46b480 | 0x7f5678424a40 | 16649024462477 | 16649024471328 | 16649024650687 | 16649024652260 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f567b46b300 | 0x7f5678424a80 | 16649024665740 | 16649024674207 | 16649024766526 | 16649024768076 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f567b46b180 | 0x7f5678424ac0 | 16649024783426 | 16649024792606 | 16649024885886 | 16649024887362 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f567b46b000 | 0x7f5678424b00 | 16649024908791 | 16649024919325 | 16649025011165 | 16649025012688 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f5678e0be80 | 0x7f5678424b40 | 16649025029857 | 16649025037725 | 16649025216764 | 16649025218311 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f5678e0bd00 | 0x7f5678424b80 | 16649025232870 | 16649025241084 | 16649025421723 | 16649025423164 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f5678e0bb80 | 0x7f5678424bc0 | 16649025437323 | 16649025446362 | 16649025541082 | 16649025542590 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f5678e0ba00 | 0x7f5678424c00 | 16649025557109 | 16649025566042 | 16649025661241 | 16649025662796 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f5678e0b880 | 0x7f5678424c40 | 16649025683745 | 16649025694521 | 16649025788121 | 16649025789571 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f5678e0b700 | 0x7f5678424c80 | 16649025804881 | 16649025813080 | 16649025993079 | 16649025994544 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f567b46b580 | 0x7f5678424cc0 | 16649026008794 | 16649026017399 | 16649026198038 | 16649026199647 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f567b46b400 | 0x7f5678424d00 | 16649026216507 | 16649026224598 | 16649026318678 | 16649026320343 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f567b46b280 | 0x7f5678424d40 | 16649026335563 | 16649026343637 | 16649026442997 | 16649026444649 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f567b46b100 | 0x7f5678424d80 | 16649026465568 | 16649026476117 | 16649026570036 | 16649026571685 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f5678e0bf80 | 0x7f5678424dc0 | 16649026589304 | 16649026598676 | 16649026779635 | 16649026781328 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f5678e0be00 | 0x7f5678424e00 | 16649026796897 | 16649026804915 | 16649026985234 | 16649026986971 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f5678e0bc80 | 0x7f5678424e40 | 16649027001710 | 16649027009714 | 16649027104753 | 16649027106437 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f5678e0bb00 | 0x7f5678424e80 | 16649027122346 | 16649027130193 | 16649027235632 | 16649027237292 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f5678e0b980 | 0x7f5678424ec0 | 16649027259432 | 16649027270032 | 16649027362832 | 16649027364298 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f5678e0b800 | 0x7f5678424f00 | 16649027379308 | 16649027387312 | 16649027567470 | 16649027568891 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f5678e0b680 | 0x7f5678424f40 | 16649027584491 | 16649027594510 | 16649027775309 | 16649027776854 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f567b46b500 | 0x7f5678424f80 | 16649027790264 | 16649027799309 | 16649027893069 | 16649027894510 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f567b46b380 | 0x7f5678424fc0 | 16649027910660 | 16649027918669 | 16649028025548 | 16649028027146 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f567b46b200 | 0x7f5678425000 | 16649028048955 | 16649028059788 | 16649028153547 | 16649028155031 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f567b46b080 | 0x7f5678425040 | 16649028171081 | 16649028179147 | 16649028359146 | 16649028360734 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f5678e0bf00 | 0x7f5678425080 | 16649028376994 | 16649028386346 | 16649028567465 | 16649028569057 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f5678e0bd80 | 0x7f56784250c0 | 16649028583887 | 16649028592745 | 16649028688104 | 16649028689563 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f5678e0bc00 | 0x7f5678425100 | 16649028704683 | 16649028713064 | 16649028829383 | 16649028830808 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f5678e0ba80 | 0x7f5678425140 | 16649028864837 | 16649028874343 | 16649028967943 | 16649028969434 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f5678e0b900 | 0x7f5678425180 | 16649028986143 | 16649028994022 | 16649029174821 | 16649029176327 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f5678e0b780 | 0x7f56784251c0 | 16649029193146 | 16649029201861 | 16649029381700 | 16649029383250 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f5678e0b600 | 0x7f5678425200 | 16649029398309 | 16649029406660 | 16649029502660 | 16649029504096 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f567b46b480 | 0x7f5678425240 | 16649029518405 | 16649029527299 | 16649029648579 | 16649029650111 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f567b46b300 | 0x7f5678425280 | 16649029671570 | 16649029682339 | 16649029776258 | 16649029777726 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f567b46b180 | 0x7f56784252c0 | 16649029794306 | 16649029802658 | 16649029982497 | 16649029983959 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f567b46b000 | 0x7f5678425300 | 16649029999999 | 16649030007937 | 16649030187456 | 16649030188982 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f5678e0be80 | 0x7f5678425340 | 16649030206232 | 16649030214656 | 16649030309375 | 16649030310838 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f5678e0bd00 | 0x7f5678425380 | 16649030325548 | 16649030333855 | 16649030460094 | 16649030461693 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f5678e0bb80 | 0x7f56784253c0 | 16649030482312 | 16649030492734 | 16649030586813 | 16649030588259 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f5678e0ba00 | 0x7f5678425400 | 16649030604528 | 16649030613213 | 16649030794012 | 16649030795642 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f5678e0b880 | 0x7f5678425440 | 16649030810741 | 16649030818652 | 16649031000091 | 16649031001575 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f5678e0b700 | 0x7f5678425480 | 16649031015034 | 16649031022971 | 16649031117210 | 16649031118671 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f567b46b580 | 0x7f56784254c0 | 16649031132940 | 16649031141210 | 16649031272090 | 16649031273676 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f567b46b400 | 0x7f5678425500 | 16649031295385 | 16649031305529 | 16649031398809 | 16649031400251 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f567b46b280 | 0x7f5678425540 | 16649031417411 | 16649031426169 | 16649031605688 | 16649031607014 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f567b46b100 | 0x7f5678425580 | 16649031621954 | 16649031629848 | 16649031810647 | 16649031812097 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f5678e0bf80 | 0x7f56784255c0 | 16649031825917 | 16649031834006 | 16649031930166 | 16649031931763 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f5678e0be00 | 0x7f5678425600 | 16649031946183 | 16649031954326 | 16649032093365 | 16649032094888 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f5678e0bc80 | 0x7f5678425640 | 16649032115977 | 16649032126965 | 16649032222164 | 16649032223694 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f5678e0bb00 | 0x7f5678425680 | 16649032239183 | 16649032247124 | 16649032426003 | 16649032427527 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f5678e0b980 | 0x7f56784256c0 | 16649032442726 | 16649032452563 | 16649032631602 | 16649032633030 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f5678e0b800 | 0x7f5678425700 | 16649032646879 | 16649032655922 | 16649032754161 | 16649032755726 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f5678e0b680 | 0x7f5678425740 | 16649032770755 | 16649032780081 | 16649032924880 | 16649032926420 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f567b46b500 | 0x7f5678425780 | 16649032945949 | 16649032956880 | 16649033051760 | 16649033053325 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f567b46b380 | 0x7f56784257c0 | 16649033069995 | 16649033078159 | 16649033261038 | 16649033262558 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f567b46b200 | 0x7f5678425800 | 16649033278268 | 16649033286958 | 16649033469677 | 16649033471141 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f567b46b080 | 0x7f5678425840 | 16649033485551 | 16649033494957 | 16649033595116 | 16649033596617 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f5678e0bf00 | 0x7f5678425880 | 16649033611317 | 16649033619436 | 16649033774795 | 16649033776311 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f5678e0bd80 | 0x7f56784258c0 | 16649033797340 | 16649033807915 | 16649033902795 | 16649033904347 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f5678e0bc00 | 0x7f5678425900 | 16649033919456 | 16649033927435 | 16649034107274 | 16649034108990 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f5678e0ba80 | 0x7f5678425940 | 16649034124989 | 16649034133033 | 16649034314472 | 16649034316023 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f5678e0b900 | 0x7f5678425980 | 16649034330402 | 16649034337992 | 16649034445512 | 16649034446978 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f5678e0b780 | 0x7f56784259c0 | 16649034461398 | 16649034469991 | 16649034641191 | 16649034642842 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f5678e0b600 | 0x7f5678425a00 | 16649034664191 | 16649034674790 | 16649034769670 | 16649034771327 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f567b46b480 | 0x7f5678425a40 | 16649034786647 | 16649034794630 | 16649034974629 | 16649034976170 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f567b46b300 | 0x7f5678425a80 | 16649034990510 | 16649034999109 | 16649035179427 | 16649035180923 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f567b46b180 | 0x7f5678425ac0 | 16649035195483 | 16649035203587 | 16649035313187 | 16649035314729 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f567b46b000 | 0x7f5678425b00 | 16649035329658 | 16649035339427 | 16649035520546 | 16649035522112 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f5678e0be80 | 0x7f5678425b40 | 16649035543411 | 16649035552865 | 16649035653985 | 16649035655607 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f5678e0bd00 | 0x7f5678425b80 | 16649035671317 | 16649035679425 | 16649035864544 | 16649035866050 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f5678e0bb80 | 0x7f5678425bc0 | 16649035880120 | 16649035888063 | 16649036070302 | 16649036071953 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f5678e0ba00 | 0x7f5678425c00 | 16649036086083 | 16649036094782 | 16649036217022 | 16649036218498 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f5678e0b880 | 0x7f5678425c40 | 16649036232558 | 16649036240701 | 16649036447260 | 16649036466680 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f5678e0b700 | 0x7f5678425c80 | 16649036481799 | 16649036492540 | 16649036602459 | 16649036603975 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f567b46b580 | 0x7f5678425cc0 | 16649036619715 | 16649036628859 | 16649036811098 | 16649036812538 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f567b46b400 | 0x7f5678425d00 | 16649036829028 | 16649036836698 | 16649037024857 | 16649037026521 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f567b46b280 | 0x7f5678425d40 | 16649037043360 | 16649037051577 | 16649037185976 | 16649037187555 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f567b46b100 | 0x7f5678425d80 | 16649037203825 | 16649037212216 | 16649037444535 | 16649037458516 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f5678e0bf80 | 0x7f5678425dc0 | 16649037474366 | 16649037485014 | 16649037611574 | 16649037613091 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f5678e0be00 | 0x7f5678425e00 | 16649037629061 | 16649037637494 | 16649037829013 | 16649037830574 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f5678e0bc80 | 0x7f5678425e40 | 16649037845383 | 16649037853812 | 16649038047091 | 16649038048766 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f5678e0bb00 | 0x7f5678425e80 | 16649038063186 | 16649038071731 | 16649038231570 | 16649038233190 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f5678e0b980 | 0x7f5678425ec0 | 16649038249489 | 16649038258130 | 16649038541808 | 16649038560649 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f5678e0b800 | 0x7f5678425f00 | 16649038577568 | 16649038588048 | 16649038737327 | 16649038738833 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f5678e0b680 | 0x7f5678425f40 | 16649038755882 | 16649038764047 | 16649038971726 | 16649039009744 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f567b46b500 | 0x7f5678425f80 | 16649039018083 | 16649039028366 | 16649039236525 | 16649039277574 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f567b46b380 | 0x7f5678425fc0 | 16649039289854 | 16649039299724 | 16649039485643 | 16649039487157 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f567b46b200 | 0x7f5678426000 | 16649039503397 | 16649039511723 | 16649039846281 | 16649039884194 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f567b46b080 | 0x7f5678426040 | 16649039900813 | 16649039911241 | 16649040079560 | 16649040081017 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f5678e0bf00 | 0x7f5678426080 | 16649040096107 | 16649040104520 | 16649040333158 | 16649040371227 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f5678e0bd80 | 0x7f56784260c0 | 16649040379917 | 16649040390118 | 16649040619557 | 16649040637118 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f5678e0bc00 | 0x7f5678426100 | 16649040645738 | 16649040655557 | 16649040866755 | 16649040880490 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f5678e0ba80 | 0x7f5678426140 | 16649040890470 | 16649040900035 | 16649041285473 | 16649041298716 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f5678e0b900 | 0x7f5678426180 | 16649041316095 | 16649041326433 | 16649041512832 | 16649041514288 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f5678e0b780 | 0x7f56784261c0 | 16649041530008 | 16649041537792 | 16649041787070 | 16649041799949 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f5678e0b600 | 0x7f5678426200 | 16649041808578 | 16649041819390 | 16649042067229 | 16649042085449 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f567b46b480 | 0x7f5678426240 | 16649042099358 | 16649042109308 | 16649042346267 | 16649042362260 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f567b46b300 | 0x7f5678426280 | 16649042370699 | 16649042380987 | 16649042833944 | 16649042849963 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f567b46b180 | 0x7f56784262c0 | 16649042866753 | 16649042877144 | 16649043101943 | 16649043117934 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f567b46b000 | 0x7f5678426300 | 16649043126394 | 16649043136343 | 16649043434261 | 16649043450023 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f5678e0be80 | 0x7f5678426340 | 16649043462082 | 16649043471701 | 16649043769299 | 16649043785311 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f5678e0bd00 | 0x7f5678426380 | 16649043795051 | 16649043805139 | 16649044101457 | 16649044117460 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f5678e0bb80 | 0x7f56784263c0 | 16649044125950 | 16649044136177 | 16649044693774 | 16649044706840 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f5678e0ba00 | 0x7f5678426400 | 16649044723450 | 16649044733774 | 16649044997452 | 16649045015490 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f5678e0b880 | 0x7f5678426440 | 16649045024339 | 16649045034732 | 16649045385290 | 16649045400397 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f5678e0b700 | 0x7f5678426480 | 16649045408826 | 16649045419210 | 16649045769608 | 16649045782984 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f567b46b580 | 0x7f56784264c0 | 16649045795513 | 16649045805767 | 16649046153765 | 16649046197980 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f567b46b400 | 0x7f5678426500 | 16649046207129 | 16649046216645 | 16649046876961 | 16649046894026 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f567b46b280 | 0x7f5678426540 | 16649046911406 | 16649046920481 | 16649047366879 | 16649047381040 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f567b46b100 | 0x7f5678426580 | 16649047393779 | 16649047403998 | 16649047867836 | 16649047881493 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f5678e0bf80 | 0x7f56784265c0 | 16649047891892 | 16649047902876 | 16649048364953 | 16649048378336 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f5678e0be00 | 0x7f5678426600 | 16649048387566 | 16649048397593 | 16649048849910 | 16649048863529 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f5678e0bc80 | 0x7f5678426640 | 16649048875069 | 16649048885590 | 16649049755025 | 16649049768769 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f5678e0bb00 | 0x7f5678426680 | 16649049785918 | 16649049796305 | 16649050649740 | 16649050692308 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f5678e0b980 | 0x7f56784266c0 | 16649050701707 | 16649050712460 | 16649051597895 | 16649051639845 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f5678e0b800 | 0x7f5678426700 | 16649051650885 | 16649051661094 | 16649052540929 | 16649052579034 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f5678e0b680 | 0x7f5678426740 | 16649052590173 | 16649052610049 | 16649053469084 | 16649053509382 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f567b46b500 | 0x7f5678426780 | 16649053518512 | 16649053528444 | 16649055226194 | 16649055277462 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f567b46b380 | 0x7f56784267c0 | 16649055298171 | 16649055308914 | 16649056974024 | 16649057019593 |
| 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 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f567b46b200 | 0x7f5678426800 | 16649057030822 | 16649057046504 | 16649058771614 | 16649058817322 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f567b46b080 | 0x7f5678426840 | 16649058826312 | 16649058836574 | 16649060551604 | 16649060595152 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f5678e0bf00 | 0x7f5678426880 | 16649060605111 | 16649060615444 | 16649062288394 | 16649062357842 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 167556 | 167556 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f5678e0bd80 | 0x7f56784268c0 | 16649062368342 | 16649062379754 | 16649065737655 | 16649065813095 |