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 | 98949 | 98949 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f4fd1a04280 | 15261234311167 | 15261234340777 | 15261234576778 | 15261234681208 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 98949 | 98949 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f4fd1a23f80 | 15261239462877 | 15261239478560 | 15261239486720 | 15261239510036 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f4fd4ad9380 | 0x7f4fd1a23fc0 | 15261239511466 | 15261239563040 | 15261239655200 | 15261239657742 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f4fd4ad9200 | 0x7f4fd1a24000 | 15261239681132 | 15261239690721 | 15261239869921 | 15261239872407 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f4fd4ad9080 | 0x7f4fd1a24040 | 15261239887657 | 15261239895682 | 15261240075522 | 15261240078203 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f4fd2439f00 | 0x7f4fd1a24080 | 15261240092512 | 15261240100483 | 15261240193283 | 15261240195800 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f4fd2439d80 | 0x7f4fd1a240c0 | 15261240212370 | 15261240220483 | 15261240312163 | 15261240314517 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f4fd2439c00 | 0x7f4fd1a24100 | 15261240346446 | 15261240357284 | 15261240448964 | 15261240451264 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f4fd2439a80 | 0x7f4fd1a24140 | 15261240476143 | 15261240485764 | 15261240665285 | 15261240667589 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f4fd2439900 | 0x7f4fd1a24180 | 15261240691178 | 15261240701765 | 15261240881926 | 15261240884214 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f4fd2439780 | 0x7f4fd1a241c0 | 15261240901034 | 15261240909606 | 15261241002087 | 15261241004431 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f4fd2439600 | 0x7f4fd1a24200 | 15261241024941 | 15261241035207 | 15261241127367 | 15261241129688 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f4fd4ad9480 | 0x7f4fd1a24240 | 15261241153458 | 15261241178087 | 15261241270088 | 15261241272635 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f4fd4ad9300 | 0x7f4fd1a24280 | 15261241295894 | 15261241306248 | 15261241485769 | 15261241488270 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f4fd4ad9180 | 0x7f4fd1a242c0 | 15261241506540 | 15261241515209 | 15261241695690 | 15261241698135 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f4fd4ad9000 | 0x7f4fd1a24300 | 15261241716915 | 15261241728170 | 15261241821130 | 15261241823592 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f4fd2439e80 | 0x7f4fd1a24340 | 15261241843852 | 15261241853131 | 15261241944811 | 15261241947339 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f4fd2439d00 | 0x7f4fd1a24380 | 15261241969169 | 15261241979211 | 15261242070732 | 15261242073116 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f4fd2439b80 | 0x7f4fd1a243c0 | 15261242095106 | 15261242104812 | 15261242284813 | 15261242287421 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f4fd2439a00 | 0x7f4fd1a24400 | 15261242305291 | 15261242347853 | 15261242527214 | 15261242529986 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f4fd2439880 | 0x7f4fd1a24440 | 15261242545525 | 15261242554414 | 15261242646574 | 15261242649013 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f4fd2439700 | 0x7f4fd1a24480 | 15261242667233 | 15261242675854 | 15261242767855 | 15261242769670 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f4fd4ad9580 | 0x7f4fd1a244c0 | 15261242791540 | 15261242801455 | 15261242892655 | 15261242894397 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f4fd4ad9400 | 0x7f4fd1a24500 | 15261242910107 | 15261242917936 | 15261243096656 | 15261243098493 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f4fd4ad9280 | 0x7f4fd1a24540 | 15261243115422 | 15261243123216 | 15261243303217 | 15261243305068 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f4fd4ad9100 | 0x7f4fd1a24580 | 15261243319577 | 15261243327857 | 15261243420018 | 15261243421895 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f4fd2439f80 | 0x7f4fd1a245c0 | 15261243436395 | 15261243444178 | 15261243535218 | 15261243537082 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f4fd2439e00 | 0x7f4fd1a24600 | 15261243556862 | 15261243567378 | 15261243659539 | 15261243661379 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f4fd2439c80 | 0x7f4fd1a24640 | 15261243676579 | 15261243684979 | 15261243863860 | 15261243865525 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f4fd2439b00 | 0x7f4fd1a24680 | 15261243880524 | 15261243888340 | 15261244070101 | 15261244071890 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f4fd2439980 | 0x7f4fd1a246c0 | 15261244086589 | 15261244094421 | 15261244186901 | 15261244188787 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f4fd2439800 | 0x7f4fd1a24700 | 15261244203867 | 15261244211381 | 15261244304182 | 15261244306234 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f4fd2439680 | 0x7f4fd1a24740 | 15261244327344 | 15261244336982 | 15261244429142 | 15261244431071 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f4fd4ad9500 | 0x7f4fd1a24780 | 15261244446771 | 15261244454583 | 15261244634583 | 15261244636247 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f4fd4ad9380 | 0x7f4fd1a247c0 | 15261244651686 | 15261244660664 | 15261244842104 | 15261244843812 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f4fd4ad9200 | 0x7f4fd1a24800 | 15261244858501 | 15261244866424 | 15261244958745 | 15261244960429 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f4fd4ad9080 | 0x7f4fd1a24840 | 15261244977199 | 15261244985145 | 15261245077625 | 15261245079436 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f4fd2439f00 | 0x7f4fd1a24880 | 15261245099766 | 15261245110106 | 15261245201946 | 15261245203843 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f4fd2439d80 | 0x7f4fd1a248c0 | 15261245219243 | 15261245227066 | 15261245405467 | 15261245407119 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f4fd2439c00 | 0x7f4fd1a24900 | 15261245421688 | 15261245429947 | 15261245610268 | 15261245612074 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f4fd2439a80 | 0x7f4fd1a24940 | 15261245627143 | 15261245635868 | 15261245728348 | 15261245730171 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f4fd2439900 | 0x7f4fd1a24980 | 15261245744091 | 15261245751869 | 15261245844509 | 15261245846328 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f4fd2439780 | 0x7f4fd1a249c0 | 15261245867558 | 15261245878109 | 15261245970270 | 15261245971945 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f4fd2439600 | 0x7f4fd1a24a00 | 15261245986905 | 15261245995070 | 15261246174751 | 15261246176941 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f4fd4ad9480 | 0x7f4fd1a24a40 | 15261246191860 | 15261246200191 | 15261246381151 | 15261246383216 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f4fd4ad9300 | 0x7f4fd1a24a80 | 15261246397316 | 15261246404992 | 15261246497632 | 15261246499623 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f4fd4ad9180 | 0x7f4fd1a24ac0 | 15261246513083 | 15261246521312 | 15261246613153 | 15261246615100 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f4fd4ad9000 | 0x7f4fd1a24b00 | 15261246634990 | 15261246645473 | 15261246736833 | 15261246738768 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f4fd2439e80 | 0x7f4fd1a24b40 | 15261246755057 | 15261246763073 | 15261246943074 | 15261246944983 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f4fd2439d00 | 0x7f4fd1a24b80 | 15261246959232 | 15261246966754 | 15261247146275 | 15261247148328 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f4fd2439b80 | 0x7f4fd1a24bc0 | 15261247162338 | 15261247169955 | 15261247262756 | 15261247264685 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f4fd2439a00 | 0x7f4fd1a24c00 | 15261247278655 | 15261247286596 | 15261247379716 | 15261247381413 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f4fd2439880 | 0x7f4fd1a24c40 | 15261247400722 | 15261247411716 | 15261247503877 | 15261247505850 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f4fd2439700 | 0x7f4fd1a24c80 | 15261247520649 | 15261247528677 | 15261247707878 | 15261247709615 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f4fd4ad9580 | 0x7f4fd1a24cc0 | 15261247723355 | 15261247731238 | 15261247911559 | 15261247913450 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f4fd4ad9400 | 0x7f4fd1a24d00 | 15261247927390 | 15261247934759 | 15261248028039 | 15261248029787 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f4fd4ad9280 | 0x7f4fd1a24d40 | 15261248045437 | 15261248053159 | 15261248149960 | 15261248151685 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f4fd4ad9100 | 0x7f4fd1a24d80 | 15261248171074 | 15261248181960 | 15261248274440 | 15261248276092 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f4fd2439f80 | 0x7f4fd1a24dc0 | 15261248292711 | 15261248301480 | 15261248481801 | 15261248483507 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f4fd2439e00 | 0x7f4fd1a24e00 | 15261248498346 | 15261248506281 | 15261248684682 | 15261248686542 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f4fd2439c80 | 0x7f4fd1a24e40 | 15261248699902 | 15261248708202 | 15261248801483 | 15261248803559 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f4fd2439b00 | 0x7f4fd1a24e80 | 15261248818009 | 15261248825643 | 15261248927243 | 15261248928906 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f4fd2439980 | 0x7f4fd1a24ec0 | 15261248948906 | 15261248959563 | 15261249051724 | 15261249053494 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f4fd2439800 | 0x7f4fd1a24f00 | 15261249067733 | 15261249075404 | 15261249255245 | 15261249256999 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f4fd2439680 | 0x7f4fd1a24f40 | 15261249271818 | 15261249279885 | 15261249461486 | 15261249463444 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f4fd4ad9500 | 0x7f4fd1a24f80 | 15261249477684 | 15261249485646 | 15261249579246 | 15261249581001 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f4fd4ad9380 | 0x7f4fd1a24fc0 | 15261249596321 | 15261249604046 | 15261249709487 | 15261249711268 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f4fd4ad9200 | 0x7f4fd1a25000 | 15261249731458 | 15261249741967 | 15261249834767 | 15261249836815 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f4fd4ad9080 | 0x7f4fd1a25040 | 15261249850755 | 15261249858768 | 15261250038448 | 15261250040160 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f4fd2439f00 | 0x7f4fd1a25080 | 15261250054980 | 15261250062608 | 15261250243409 | 15261250245466 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f4fd2439d80 | 0x7f4fd1a250c0 | 15261250260065 | 15261250267889 | 15261250361330 | 15261250363303 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f4fd2439c00 | 0x7f4fd1a25100 | 15261250377123 | 15261250385010 | 15261250496370 | 15261250498300 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f4fd2439a80 | 0x7f4fd1a25140 | 15261250532029 | 15261250541651 | 15261250634611 | 15261250636467 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f4fd2439900 | 0x7f4fd1a25180 | 15261250651056 | 15261250659091 | 15261250838772 | 15261250840572 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f4fd2439780 | 0x7f4fd1a251c0 | 15261250854671 | 15261250862452 | 15261251041813 | 15261251043807 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f4fd2439600 | 0x7f4fd1a25200 | 15261251057587 | 15261251065333 | 15261251158454 | 15261251160104 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f4fd4ad9480 | 0x7f4fd1a25240 | 15261251174314 | 15261251182614 | 15261251300534 | 15261251302311 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f4fd4ad9300 | 0x7f4fd1a25280 | 15261251321901 | 15261251332534 | 15261251424855 | 15261251426558 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f4fd4ad9180 | 0x7f4fd1a252c0 | 15261251440898 | 15261251448695 | 15261251628216 | 15261251629883 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f4fd4ad9000 | 0x7f4fd1a25300 | 15261251646433 | 15261251653976 | 15261251835417 | 15261251837019 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f4fd2439e80 | 0x7f4fd1a25340 | 15261251854578 | 15261251862297 | 15261251955897 | 15261251957986 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f4fd2439d00 | 0x7f4fd1a25380 | 15261251974145 | 15261251981817 | 15261252105818 | 15261252107502 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f4fd2439b80 | 0x7f4fd1a253c0 | 15261252127932 | 15261252138778 | 15261252231258 | 15261252233039 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f4fd2439a00 | 0x7f4fd1a25400 | 15261252247889 | 15261252255739 | 15261252434139 | 15261252435945 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f4fd2439880 | 0x7f4fd1a25440 | 15261252452084 | 15261252459740 | 15261252640220 | 15261252642050 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f4fd2439700 | 0x7f4fd1a25480 | 15261252656929 | 15261252664860 | 15261252758781 | 15261252760487 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f4fd4ad9580 | 0x7f4fd1a254c0 | 15261252776207 | 15261252784541 | 15261252913342 | 15261252915183 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f4fd4ad9400 | 0x7f4fd1a25500 | 15261252935333 | 15261252945662 | 15261253038142 | 15261253039830 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f4fd4ad9280 | 0x7f4fd1a25540 | 15261253055980 | 15261253065182 | 15261253242623 | 15261253244406 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f4fd4ad9100 | 0x7f4fd1a25580 | 15261253258145 | 15261253266143 | 15261253445184 | 15261253446761 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f4fd2439f80 | 0x7f4fd1a255c0 | 15261253460491 | 15261253468704 | 15261253561985 | 15261253563708 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f4fd2439e00 | 0x7f4fd1a25600 | 15261253577988 | 15261253585825 | 15261253721985 | 15261253723725 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f4fd2439c80 | 0x7f4fd1a25640 | 15261253743904 | 15261253754785 | 15261253847426 | 15261253849162 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f4fd2439b00 | 0x7f4fd1a25680 | 15261253864731 | 15261253872706 | 15261254050467 | 15261254052237 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f4fd2439980 | 0x7f4fd1a256c0 | 15261254067236 | 15261254075427 | 15261254254308 | 15261254256412 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f4fd2439800 | 0x7f4fd1a25700 | 15261254271722 | 15261254279748 | 15261254374308 | 15261254376309 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f4fd2439680 | 0x7f4fd1a25740 | 15261254390829 | 15261254398948 | 15261254541029 | 15261254542975 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f4fd4ad9500 | 0x7f4fd1a25780 | 15261254563055 | 15261254573509 | 15261254666790 | 15261254668743 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f4fd4ad9380 | 0x7f4fd1a257c0 | 15261254683682 | 15261254691590 | 15261254871111 | 15261254873068 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f4fd4ad9200 | 0x7f4fd1a25800 | 15261254887237 | 15261254895271 | 15261255075272 | 15261255077123 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f4fd4ad9080 | 0x7f4fd1a25840 | 15261255090073 | 15261255098472 | 15261255197832 | 15261255199670 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f4fd2439f00 | 0x7f4fd1a25880 | 15261255213440 | 15261255221192 | 15261255374313 | 15261255376286 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f4fd2439d80 | 0x7f4fd1a258c0 | 15261255397376 | 15261255408073 | 15261255500874 | 15261255502603 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f4fd2439c00 | 0x7f4fd1a25900 | 15261255518213 | 15261255525994 | 15261255704394 | 15261255706269 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f4fd2439a80 | 0x7f4fd1a25940 | 15261255721028 | 15261255728715 | 15261255908395 | 15261255910454 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f4fd2439900 | 0x7f4fd1a25980 | 15261255924783 | 15261255932556 | 15261256036716 | 15261256038641 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f4fd2439780 | 0x7f4fd1a259c0 | 15261256053200 | 15261256061676 | 15261256229037 | 15261256230856 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f4fd2439600 | 0x7f4fd1a25a00 | 15261256250966 | 15261256261517 | 15261256355277 | 15261256357233 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f4fd4ad9480 | 0x7f4fd1a25a40 | 15261256373203 | 15261256381038 | 15261256560078 | 15261256561809 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f4fd4ad9300 | 0x7f4fd1a25a80 | 15261256576298 | 15261256584719 | 15261256765999 | 15261256767744 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f4fd4ad9180 | 0x7f4fd1a25ac0 | 15261256781704 | 15261256789679 | 15261256897840 | 15261256899521 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f4fd4ad9000 | 0x7f4fd1a25b00 | 15261256913011 | 15261256921040 | 15261257099921 | 15261257101676 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f4fd2439e80 | 0x7f4fd1a25b40 | 15261257122606 | 15261257132241 | 15261257232402 | 15261257234133 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f4fd2439d00 | 0x7f4fd1a25b80 | 15261257249143 | 15261257257202 | 15261257439922 | 15261257441698 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f4fd2439b80 | 0x7f4fd1a25bc0 | 15261257455788 | 15261257463763 | 15261257646323 | 15261257648113 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f4fd2439a00 | 0x7f4fd1a25c00 | 15261257661663 | 15261257670004 | 15261257791284 | 15261257793060 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f4fd2439880 | 0x7f4fd1a25c40 | 15261257809320 | 15261257816884 | 15261258021045 | 15261258040954 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f4fd2439700 | 0x7f4fd1a25c80 | 15261258056594 | 15261258066965 | 15261258175446 | 15261258177691 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f4fd4ad9580 | 0x7f4fd1a25cc0 | 15261258192551 | 15261258201686 | 15261258386167 | 15261258388246 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f4fd4ad9400 | 0x7f4fd1a25d00 | 15261258402486 | 15261258410327 | 15261258593208 | 15261258595211 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f4fd4ad9280 | 0x7f4fd1a25d40 | 15261258609871 | 15261258617528 | 15261258749849 | 15261258751838 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f4fd4ad9100 | 0x7f4fd1a25d80 | 15261258766237 | 15261258774169 | 15261259004570 | 15261259047441 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f4fd2439f80 | 0x7f4fd1a25dc0 | 15261259063311 | 15261259073850 | 15261259198491 | 15261259200387 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f4fd2439e00 | 0x7f4fd1a25e00 | 15261259215487 | 15261259223451 | 15261259414172 | 15261259416032 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f4fd2439c80 | 0x7f4fd1a25e40 | 15261259430652 | 15261259438812 | 15261259630493 | 15261259632307 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f4fd2439b00 | 0x7f4fd1a25e80 | 15261259649387 | 15261259656733 | 15261259814653 | 15261259816463 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f4fd2439980 | 0x7f4fd1a25ec0 | 15261259831523 | 15261259839294 | 15261260120095 | 15261260143355 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f4fd2439800 | 0x7f4fd1a25f00 | 15261260161695 | 15261260171935 | 15261260318336 | 15261260320181 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f4fd2439680 | 0x7f4fd1a25f40 | 15261260337171 | 15261260344576 | 15261260553857 | 15261260568275 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f4fd4ad9500 | 0x7f4fd1a25f80 | 15261260578675 | 15261260589057 | 15261260798338 | 15261260813110 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f4fd4ad9380 | 0x7f4fd1a25fc0 | 15261260821360 | 15261260832258 | 15261261015619 | 15261261017345 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f4fd4ad9200 | 0x7f4fd1a26000 | 15261261032185 | 15261261040099 | 15261261372581 | 15261261386786 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f4fd4ad9080 | 0x7f4fd1a26040 | 15261261402656 | 15261261412741 | 15261261577542 | 15261261579212 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f4fd2439f00 | 0x7f4fd1a26080 | 15261261594821 | 15261261602342 | 15261261833703 | 15261261848086 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f4fd2439d80 | 0x7f4fd1a260c0 | 15261261856595 | 15261261867143 | 15261262097704 | 15261262118079 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f4fd2439c00 | 0x7f4fd1a26100 | 15261262128059 | 15261262137864 | 15261262346985 | 15261262361204 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f4fd2439a80 | 0x7f4fd1a26140 | 15261262372743 | 15261262382185 | 15261262764907 | 15261262779024 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f4fd2439900 | 0x7f4fd1a26180 | 15261262797243 | 15261262807787 | 15261262991308 | 15261262992999 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f4fd2439780 | 0x7f4fd1a261c0 | 15261263009218 | 15261263017388 | 15261263269549 | 15261263287022 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f4fd2439600 | 0x7f4fd1a26200 | 15261263295682 | 15261263305710 | 15261263551951 | 15261263572465 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f4fd4ad9480 | 0x7f4fd1a26240 | 15261263583095 | 15261263593551 | 15261263828592 | 15261263849069 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f4fd4ad9300 | 0x7f4fd1a26280 | 15261263859099 | 15261263869072 | 15261264318834 | 15261264333228 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f4fd4ad9180 | 0x7f4fd1a262c0 | 15261264350607 | 15261264361074 | 15261264583795 | 15261264598351 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f4fd4ad9000 | 0x7f4fd1a26300 | 15261264609621 | 15261264619796 | 15261264918357 | 15261264932264 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f4fd2439e80 | 0x7f4fd1a26340 | 15261264942153 | 15261264951157 | 15261265249559 | 15261265266316 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f4fd2439d00 | 0x7f4fd1a26380 | 15261265277425 | 15261265288119 | 15261265581880 | 15261265596438 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f4fd2439b80 | 0x7f4fd1a263c0 | 15261265605888 | 15261265615960 | 15261266170203 | 15261266215314 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f4fd2439a00 | 0x7f4fd1a26400 | 15261266232623 | 15261266242683 | 15261266504444 | 15261266522387 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f4fd2439880 | 0x7f4fd1a26440 | 15261266531706 | 15261266541404 | 15261266892286 | 15261266933657 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f4fd2439700 | 0x7f4fd1a26480 | 15261266945117 | 15261266964126 | 15261267314208 | 15261267355897 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f4fd4ad9580 | 0x7f4fd1a264c0 | 15261267367067 | 15261267377408 | 15261267722050 | 15261267763708 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f4fd4ad9400 | 0x7f4fd1a26500 | 15261267772438 | 15261267782050 | 15261268439173 | 15261268480861 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f4fd4ad9280 | 0x7f4fd1a26540 | 15261268498511 | 15261268507974 | 15261268951656 | 15261268993009 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f4fd4ad9100 | 0x7f4fd1a26580 | 15261269002159 | 15261269011976 | 15261269472778 | 15261269514307 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f4fd2439f80 | 0x7f4fd1a265c0 | 15261269527137 | 15261269537258 | 15261269995020 | 15261270011136 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f4fd2439e00 | 0x7f4fd1a26600 | 15261270021485 | 15261270031181 | 15261270479823 | 15261270525574 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f4fd2439c80 | 0x7f4fd1a26640 | 15261270534803 | 15261270544943 | 15261271410547 | 15261271456112 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f4fd2439b00 | 0x7f4fd1a26680 | 15261271473742 | 15261271484147 | 15261272334071 | 15261272376880 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f4fd2439980 | 0x7f4fd1a266c0 | 15261272387070 | 15261272397271 | 15261273278396 | 15261273321958 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f4fd2439800 | 0x7f4fd1a26700 | 15261273331658 | 15261273341916 | 15261274217600 | 15261274266976 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f4fd2439680 | 0x7f4fd1a26740 | 15261274279776 | 15261274304160 | 15261275159844 | 15261275206404 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f4fd4ad9500 | 0x7f4fd1a26780 | 15261275215904 | 15261275280965 | 15261276975693 | 15261277049501 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f4fd4ad9380 | 0x7f4fd1a267c0 | 15261277105440 | 15261277119373 | 15261278780501 | 15261278852099 |
| 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 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f4fd4ad9200 | 0x7f4fd1a26800 | 15261278872009 | 15261278883221 | 15261280604509 | 15261280672987 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f4fd4ad9080 | 0x7f4fd1a26840 | 15261280691766 | 15261280702110 | 15261282414118 | 15261282484945 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f4fd2439f00 | 0x7f4fd1a26880 | 15261282498924 | 15261282510118 | 15261284180366 | 15261284249044 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 98949 | 98949 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f4fd2439d80 | 0x7f4fd1a268c0 | 15261284264933 | 15261284275886 | 15261287629502 | 15261287707693 |