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 | 105051 | 105051 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7fd7b5204280 | 15350964905154 | 15350964930274 | 15350965168355 | 15350965259645 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 105051 | 105051 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7fd7b5223f80 | 15350969971296 | 15350969986294 | 15350969999414 | 15350970017035 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7fd7b8146380 | 0x7fd7b5223fc0 | 15350970021885 | 15350970065654 | 15350970158295 | 15350970160642 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7fd7b8146200 | 0x7fd7b5224000 | 15350970182682 | 15350970192375 | 15350970370296 | 15350970372257 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7fd7b8146080 | 0x7fd7b5224040 | 15350970387027 | 15350970395256 | 15350970574616 | 15350970576582 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7fd7b59e7f00 | 0x7fd7b5224080 | 15350970590602 | 15350970598457 | 15350970692057 | 15350970694020 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7fd7b59e7d80 | 0x7fd7b52240c0 | 15350970708989 | 15350970717177 | 15350970809017 | 15350970811067 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7fd7b59e7c00 | 0x7fd7b5224100 | 15350970838046 | 15350970848218 | 15350970940058 | 15350970942084 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7fd7b59e7a80 | 0x7fd7b5224140 | 15350970962034 | 15350970972378 | 15350971151739 | 15350971153809 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7fd7b59e7900 | 0x7fd7b5224180 | 15350971171719 | 15350971188379 | 15350971370460 | 15350971372734 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7fd7b59e7780 | 0x7fd7b52241c0 | 15350971387254 | 15350971395580 | 15350971489500 | 15350971491471 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7fd7b59e7600 | 0x7fd7b5224200 | 15350971509611 | 15350971517820 | 15350971611581 | 15350971613669 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7fd7b8146480 | 0x7fd7b5224240 | 15350971632658 | 15350971642941 | 15350971736061 | 15350971738136 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7fd7b8146300 | 0x7fd7b5224280 | 15350971757085 | 15350971768221 | 15350971946942 | 15350971948831 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7fd7b8146180 | 0x7fd7b52242c0 | 15350971965770 | 15350971973822 | 15350972153343 | 15350972155416 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7fd7b8146000 | 0x7fd7b5224300 | 15350972170836 | 15350972179263 | 15350972272863 | 15350972274863 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7fd7b59e7e80 | 0x7fd7b5224340 | 15350972294753 | 15350972309344 | 15350972401824 | 15350972403810 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7fd7b59e7d00 | 0x7fd7b5224380 | 15350972424140 | 15350972434784 | 15350972528065 | 15350972530017 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7fd7b59e7b80 | 0x7fd7b52243c0 | 15350972546307 | 15350972554305 | 15350972732865 | 15350972734893 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7fd7b59e7a00 | 0x7fd7b5224400 | 15350972751242 | 15350972759585 | 15350972939746 | 15350972941678 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7fd7b59e7880 | 0x7fd7b5224440 | 15350972958158 | 15350972966146 | 15350973059587 | 15350973061505 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7fd7b59e7700 | 0x7fd7b5224480 | 15350973078795 | 15350973087267 | 15350973181347 | 15350973183292 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7fd7b8146580 | 0x7fd7b52244c0 | 15350973203562 | 15350973213667 | 15350973305508 | 15350973307520 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7fd7b8146400 | 0x7fd7b5224500 | 15350973323029 | 15350973331268 | 15350973509829 | 15350973511865 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7fd7b8146280 | 0x7fd7b5224540 | 15350973525115 | 15350973533349 | 15350973712869 | 15350973714910 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7fd7b8146100 | 0x7fd7b5224580 | 15350973729600 | 15350973737830 | 15350973830150 | 15350973831988 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7fd7b59e7f80 | 0x7fd7b52245c0 | 15350973848187 | 15350973877990 | 15350973969830 | 15350973971864 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7fd7b59e7e00 | 0x7fd7b5224600 | 15350973993114 | 15350974003591 | 15350974096871 | 15350974098861 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7fd7b59e7c80 | 0x7fd7b5224640 | 15350974121931 | 15350974132231 | 15350974313512 | 15350974315586 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7fd7b59e7b00 | 0x7fd7b5224680 | 15350974331196 | 15350974339912 | 15350974520233 | 15350974522252 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7fd7b59e7980 | 0x7fd7b52246c0 | 15350974535951 | 15350974543753 | 15350974636553 | 15350974637999 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7fd7b59e7800 | 0x7fd7b5224700 | 15350974656559 | 15350974664073 | 15350974758154 | 15350974759806 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7fd7b59e7680 | 0x7fd7b5224740 | 15350974780886 | 15350974790474 | 15350974883754 | 15350974885433 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7fd7b8146500 | 0x7fd7b5224780 | 15350974900913 | 15350974908874 | 15350975088875 | 15350975090619 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7fd7b8146380 | 0x7fd7b52247c0 | 15350975104228 | 15350975112875 | 15350975293676 | 15350975295214 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7fd7b8146200 | 0x7fd7b5224800 | 15350975310744 | 15350975318476 | 15350975411916 | 15350975413561 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7fd7b8146080 | 0x7fd7b5224840 | 15350975428531 | 15350975438157 | 15350975532077 | 15350975533658 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7fd7b59e7f00 | 0x7fd7b5224880 | 15350975553358 | 15350975564237 | 15350975657517 | 15350975659226 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7fd7b59e7d80 | 0x7fd7b52248c0 | 15350975674045 | 15350975681838 | 15350975860398 | 15350975861971 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7fd7b59e7c00 | 0x7fd7b5224900 | 15350975876311 | 15350975883918 | 15350976065359 | 15350976067046 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7fd7b59e7a80 | 0x7fd7b5224940 | 15350976081496 | 15350976089679 | 15350976183280 | 15350976184903 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7fd7b59e7900 | 0x7fd7b5224980 | 15350976199673 | 15350976207600 | 15350976302320 | 15350976304041 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7fd7b59e7780 | 0x7fd7b52249c0 | 15350976324640 | 15350976335120 | 15350976429361 | 15350976430888 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7fd7b59e7600 | 0x7fd7b5224a00 | 15350976445277 | 15350976453361 | 15350976633041 | 15350976634443 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7fd7b8146480 | 0x7fd7b5224a40 | 15350976649053 | 15350976657042 | 15350976838002 | 15350976839508 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7fd7b8146300 | 0x7fd7b5224a80 | 15350976853618 | 15350976861682 | 15350976954323 | 15350976955816 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7fd7b8146180 | 0x7fd7b5224ac0 | 15350976970555 | 15350976978803 | 15350977071763 | 15350977073283 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7fd7b8146000 | 0x7fd7b5224b00 | 15350977093453 | 15350977104083 | 15350977196084 | 15350977197630 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7fd7b59e7e80 | 0x7fd7b5224b40 | 15350977215160 | 15350977223764 | 15350977402485 | 15350977404195 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7fd7b59e7d00 | 0x7fd7b5224b80 | 15350977417855 | 15350977425365 | 15350977605525 | 15350977606941 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7fd7b59e7b80 | 0x7fd7b5224bc0 | 15350977620990 | 15350977629526 | 15350977723126 | 15350977724548 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7fd7b59e7a00 | 0x7fd7b5224c00 | 15350977738468 | 15350977746326 | 15350977841526 | 15350977843045 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7fd7b59e7880 | 0x7fd7b5224c40 | 15350977863115 | 15350977878327 | 15350977971767 | 15350977973272 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7fd7b59e7700 | 0x7fd7b5224c80 | 15350977987242 | 15350977995927 | 15350978174168 | 15350978175628 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7fd7b8146580 | 0x7fd7b5224cc0 | 15350978189377 | 15350978197208 | 15350978376569 | 15350978378103 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7fd7b8146400 | 0x7fd7b5224d00 | 15350978392563 | 15350978400249 | 15350978494809 | 15350978496490 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7fd7b8146280 | 0x7fd7b5224d40 | 15350978512090 | 15350978519769 | 15350978618330 | 15350978619937 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7fd7b8146100 | 0x7fd7b5224d80 | 15350978639177 | 15350978651130 | 15350978744730 | 15350978746364 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7fd7b59e7f80 | 0x7fd7b5224dc0 | 15350978763684 | 15350978772730 | 15350978952091 | 15350978953800 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7fd7b59e7e00 | 0x7fd7b5224e00 | 15350978968529 | 15350978976251 | 15350979155612 | 15350979157195 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7fd7b59e7c80 | 0x7fd7b5224e40 | 15350979172134 | 15350979179932 | 15350979274492 | 15350979276122 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7fd7b59e7b00 | 0x7fd7b5224e80 | 15350979290012 | 15350979298652 | 15350979402973 | 15350979404489 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7fd7b59e7980 | 0x7fd7b5224ec0 | 15350979424119 | 15350979435133 | 15350979527933 | 15350979529606 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7fd7b59e7800 | 0x7fd7b5224f00 | 15350979544796 | 15350979553214 | 15350979732734 | 15350979734191 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7fd7b59e7680 | 0x7fd7b5224f40 | 15350979749531 | 15350979757854 | 15350979937215 | 15350979938837 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7fd7b8146500 | 0x7fd7b5224f80 | 15350979953456 | 15350979962015 | 15350980055296 | 15350980056784 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7fd7b8146380 | 0x7fd7b5224fc0 | 15350980071104 | 15350980080416 | 15350980186816 | 15350980188371 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7fd7b8146200 | 0x7fd7b5225000 | 15350980209170 | 15350980219936 | 15350980314177 | 15350980315698 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7fd7b8146080 | 0x7fd7b5225040 | 15350980331408 | 15350980339777 | 15350980518658 | 15350980520153 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7fd7b59e7f00 | 0x7fd7b5225080 | 15350980534293 | 15350980542498 | 15350980721858 | 15350980723239 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7fd7b59e7d80 | 0x7fd7b52250c0 | 15350980736778 | 15350980746818 | 15350980841539 | 15350980842926 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7fd7b59e7c00 | 0x7fd7b5225100 | 15350980858445 | 15350980866499 | 15350980981699 | 15350980983213 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7fd7b59e7a80 | 0x7fd7b5225140 | 15350981019482 | 15350981029380 | 15350981123460 | 15350981125009 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7fd7b59e7900 | 0x7fd7b5225180 | 15350981139329 | 15350981147300 | 15350981326661 | 15350981328095 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7fd7b59e7780 | 0x7fd7b52251c0 | 15350981342634 | 15350981350501 | 15350981532262 | 15350981533930 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7fd7b59e7600 | 0x7fd7b5225200 | 15350981549469 | 15350981557062 | 15350981651942 | 15350981653437 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7fd7b8146480 | 0x7fd7b5225240 | 15350981672067 | 15350981680262 | 15350981800263 | 15350981801824 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7fd7b8146300 | 0x7fd7b5225280 | 15350981822843 | 15350981833543 | 15350981927623 | 15350981929091 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7fd7b8146180 | 0x7fd7b52252c0 | 15350981944250 | 15350981952583 | 15350982131944 | 15350982133646 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7fd7b8146000 | 0x7fd7b5225300 | 15350982147996 | 15350982156104 | 15350982335145 | 15350982336611 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7fd7b59e7e80 | 0x7fd7b5225340 | 15350982351771 | 15350982359305 | 15350982453866 | 15350982455288 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7fd7b59e7d00 | 0x7fd7b5225380 | 15350982470698 | 15350982478346 | 15350982604266 | 15350982605795 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7fd7b59e7b80 | 0x7fd7b52253c0 | 15350982625595 | 15350982636266 | 15350982730827 | 15350982732352 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7fd7b59e7a00 | 0x7fd7b5225400 | 15350982747852 | 15350982755627 | 15350982935788 | 15350982937337 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7fd7b59e7880 | 0x7fd7b5225440 | 15350982952137 | 15350982960108 | 15350983141228 | 15350983142693 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7fd7b59e7700 | 0x7fd7b5225480 | 15350983156122 | 15350983163948 | 15350983257869 | 15350983259310 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7fd7b8146580 | 0x7fd7b52254c0 | 15350983274550 | 15350983283949 | 15350983414829 | 15350983416246 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7fd7b8146400 | 0x7fd7b5225500 | 15350983437256 | 15350983447630 | 15350983540750 | 15350983542323 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7fd7b8146280 | 0x7fd7b5225540 | 15350983557453 | 15350983566510 | 15350983746351 | 15350983747829 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7fd7b8146100 | 0x7fd7b5225580 | 15350983762208 | 15350983773711 | 15350983953072 | 15350983954634 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7fd7b59e7f80 | 0x7fd7b52255c0 | 15350983969664 | 15350983979472 | 15350984074992 | 15350984076411 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7fd7b59e7e00 | 0x7fd7b5225600 | 15350984091691 | 15350984101072 | 15350984240273 | 15350984241677 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7fd7b59e7c80 | 0x7fd7b5225640 | 15350984263127 | 15350984274033 | 15350984368433 | 15350984369894 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7fd7b59e7b00 | 0x7fd7b5225680 | 15350984385874 | 15350984394194 | 15350984573714 | 15350984575180 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7fd7b59e7980 | 0x7fd7b52256c0 | 15350984589449 | 15350984598354 | 15350984777875 | 15350984779255 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7fd7b59e7800 | 0x7fd7b5225700 | 15350984793175 | 15350984802355 | 15350984898676 | 15350984900092 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7fd7b59e7680 | 0x7fd7b5225740 | 15350984916302 | 15350984926196 | 15350985071316 | 15350985072748 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7fd7b8146500 | 0x7fd7b5225780 | 15350985093808 | 15350985104596 | 15350985199637 | 15350985201055 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7fd7b8146380 | 0x7fd7b52257c0 | 15350985217235 | 15350985226357 | 15350985406998 | 15350985408471 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7fd7b8146200 | 0x7fd7b5225800 | 15350985422510 | 15350985432118 | 15350985612599 | 15350985614016 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7fd7b8146080 | 0x7fd7b5225840 | 15350985629015 | 15350985636919 | 15350985736759 | 15350985738273 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7fd7b59e7f00 | 0x7fd7b5225880 | 15350985752293 | 15350985760119 | 15350985915160 | 15350985916759 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7fd7b59e7d80 | 0x7fd7b52258c0 | 15350985940098 | 15350985950680 | 15350986045560 | 15350986047106 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7fd7b59e7c00 | 0x7fd7b5225900 | 15350986062535 | 15350986071640 | 15350986250201 | 15350986251891 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7fd7b59e7a80 | 0x7fd7b5225940 | 15350986267291 | 15350986275161 | 15350986456762 | 15350986458176 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7fd7b59e7900 | 0x7fd7b5225980 | 15350986472166 | 15350986480122 | 15350986587643 | 15350986589053 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7fd7b59e7780 | 0x7fd7b52259c0 | 15350986607433 | 15350986615323 | 15350986786363 | 15350986787889 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7fd7b59e7600 | 0x7fd7b5225a00 | 15350986808888 | 15350986819324 | 15350986915164 | 15350986916676 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7fd7b8146480 | 0x7fd7b5225a40 | 15350986933435 | 15350986941244 | 15350987120445 | 15350987121931 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7fd7b8146300 | 0x7fd7b5225a80 | 15350987137121 | 15350987145725 | 15350987325566 | 15350987327096 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7fd7b8146180 | 0x7fd7b5225ac0 | 15350987341896 | 15350987350206 | 15350987460446 | 15350987461933 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7fd7b8146000 | 0x7fd7b5225b00 | 15350987476043 | 15350987484126 | 15350987665407 | 15350987666889 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7fd7b59e7e80 | 0x7fd7b5225b40 | 15350987689278 | 15350987699327 | 15350987799648 | 15350987801105 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7fd7b59e7d00 | 0x7fd7b5225b80 | 15350987816965 | 15350987825408 | 15350988010688 | 15350988012221 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7fd7b59e7b80 | 0x7fd7b5225bc0 | 15350988026160 | 15350988034529 | 15350988217249 | 15350988218686 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7fd7b59e7a00 | 0x7fd7b5225c00 | 15350988233106 | 15350988242689 | 15350988365410 | 15350988366892 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7fd7b59e7880 | 0x7fd7b5225c40 | 15350988381712 | 15350988391170 | 15350988597891 | 15350988619747 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7fd7b59e7700 | 0x7fd7b5225c80 | 15350988633866 | 15350988644611 | 15350988756132 | 15350988757673 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7fd7b8146580 | 0x7fd7b5225cc0 | 15350988774333 | 15350988782532 | 15350988966532 | 15350988968009 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7fd7b8146400 | 0x7fd7b5225d00 | 15350988984708 | 15350988992773 | 15350989178693 | 15350989180154 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7fd7b8146280 | 0x7fd7b5225d40 | 15350989196283 | 15350989205733 | 15350989339974 | 15350989341440 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7fd7b8146100 | 0x7fd7b5225d80 | 15350989357200 | 15350989365094 | 15350989597415 | 15350989617264 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7fd7b59e7f80 | 0x7fd7b5225dc0 | 15350989632223 | 15350989642855 | 15350989769256 | 15350989770810 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7fd7b59e7e00 | 0x7fd7b5225e00 | 15350989786980 | 15350989795976 | 15350989987337 | 15350989988915 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7fd7b59e7c80 | 0x7fd7b5225e40 | 15350990003825 | 15350990012937 | 15350990205898 | 15350990207430 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7fd7b59e7b00 | 0x7fd7b5225e80 | 15350990221780 | 15350990229418 | 15350990389738 | 15350990391376 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7fd7b59e7980 | 0x7fd7b5225ec0 | 15350990406005 | 15350990414058 | 15350990696940 | 15350990742958 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7fd7b59e7800 | 0x7fd7b5225f00 | 15350990757947 | 15350990768940 | 15350990919020 | 15350990920494 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7fd7b59e7680 | 0x7fd7b5225f40 | 15350990936183 | 15350990943981 | 15350991152141 | 15350991195767 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7fd7b8146500 | 0x7fd7b5225f80 | 15350991205637 | 15350991216142 | 15350991424943 | 15350991468601 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7fd7b8146380 | 0x7fd7b5225fc0 | 15350991478071 | 15350991488463 | 15350991674224 | 15350991675636 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7fd7b8146200 | 0x7fd7b5226000 | 15350991691886 | 15350991699984 | 15350992034545 | 15350992074847 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7fd7b8146080 | 0x7fd7b5226040 | 15350992091016 | 15350992101585 | 15350992269266 | 15350992270712 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7fd7b59e7f00 | 0x7fd7b5226080 | 15350992285872 | 15350992294066 | 15350992521907 | 15350992562046 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7fd7b59e7d80 | 0x7fd7b52260c0 | 15350992569255 | 15350992579987 | 15350992809908 | 15350992850529 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7fd7b59e7c00 | 0x7fd7b5226100 | 15350992858519 | 15350992868629 | 15350993079989 | 15350993096723 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7fd7b59e7a80 | 0x7fd7b5226140 | 15350993105463 | 15350993114710 | 15350993500311 | 15350993517973 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7fd7b59e7900 | 0x7fd7b5226180 | 15350993533213 | 15350993543991 | 15350993730712 | 15350993732248 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7fd7b59e7780 | 0x7fd7b52261c0 | 15350993748388 | 15350993756312 | 15350994007033 | 15350994022772 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7fd7b59e7600 | 0x7fd7b5226200 | 15350994033911 | 15350994044313 | 15350994292474 | 15350994334554 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7fd7b8146480 | 0x7fd7b5226240 | 15350994343414 | 15350994353595 | 15350994590556 | 15350994635688 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7fd7b8146300 | 0x7fd7b5226280 | 15350994644477 | 15350994654876 | 15350995107198 | 15350995148236 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7fd7b8146180 | 0x7fd7b52262c0 | 15350995163435 | 15350995174238 | 15350995399839 | 15350995439869 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7fd7b8146000 | 0x7fd7b5226300 | 15350995447979 | 15350995458399 | 15350995756800 | 15350995796851 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7fd7b59e7e80 | 0x7fd7b5226340 | 15350995808901 | 15350995818721 | 15350996117762 | 15350996161352 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7fd7b59e7d00 | 0x7fd7b5226380 | 15350996170372 | 15350996180482 | 15350996476963 | 15350996520054 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7fd7b59e7b80 | 0x7fd7b52263c0 | 15350996529284 | 15350996539364 | 15350997097286 | 15350997137220 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7fd7b59e7a00 | 0x7fd7b5226400 | 15350997153250 | 15350997163526 | 15350997427207 | 15350997443253 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7fd7b59e7880 | 0x7fd7b5226440 | 15350997451863 | 15350997462247 | 15350997812969 | 15350997829334 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7fd7b59e7700 | 0x7fd7b5226480 | 15350997837604 | 15350997848489 | 15350998198731 | 15350998251794 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7fd7b8146580 | 0x7fd7b52264c0 | 15350998261374 | 15350998271371 | 15350998618412 | 15350998665495 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7fd7b8146400 | 0x7fd7b5226500 | 15350998673835 | 15350998684013 | 15350999345295 | 15350999390078 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7fd7b8146280 | 0x7fd7b5226540 | 15350999407178 | 15350999416976 | 15350999864817 | 15350999909546 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7fd7b8146100 | 0x7fd7b5226580 | 15350999919206 | 15350999929138 | 15351000392660 | 15351000437694 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7fd7b59e7f80 | 0x7fd7b52265c0 | 15351000449283 | 15351000465140 | 15351000927222 | 15351000971801 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7fd7b59e7e00 | 0x7fd7b5226600 | 15351000979801 | 15351000990582 | 15351001442104 | 15351001487189 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7fd7b59e7c80 | 0x7fd7b5226640 | 15351001496259 | 15351001506104 | 15351002373948 | 15351002423678 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7fd7b59e7b00 | 0x7fd7b5226680 | 15351002439967 | 15351002450588 | 15351003305152 | 15351003348106 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7fd7b59e7980 | 0x7fd7b52266c0 | 15351003357416 | 15351003367232 | 15351004252356 | 15351004298725 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7fd7b59e7800 | 0x7fd7b5226700 | 15351004309844 | 15351004325316 | 15351005205159 | 15351005249963 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7fd7b59e7680 | 0x7fd7b5226740 | 15351005259172 | 15351005275720 | 15351006135723 | 15351006183151 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7fd7b8146500 | 0x7fd7b5226780 | 15351006192521 | 15351006203244 | 15351007902771 | 15351007976010 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7fd7b8146380 | 0x7fd7b52267c0 | 15351007992230 | 15351008002771 | 15351009668218 | 15351009737709 |
| 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 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7fd7b8146200 | 0x7fd7b5226800 | 15351009747169 | 15351009757338 | 15351011481985 | 15351011554137 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7fd7b8146080 | 0x7fd7b5226840 | 15351011563357 | 15351011573506 | 15351013288873 | 15351013357656 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7fd7b59e7f00 | 0x7fd7b5226880 | 15351013366965 | 15351013377033 | 15351015051920 | 15351015122895 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 105051 | 105051 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7fd7b59e7d80 | 0x7fd7b52268c0 | 15351015131575 | 15351015191441 | 15351018548895 | 15351018627604 |