38 KiB
38 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 183436 | 183436 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f3f03604280 | 0 | 0 | 0 | 16924668595638 | 16923966494861 | 16924819033898 | 16924819145857 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 183436 | 183436 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f3f03623f80 | 0 | 0 | 0 | 16924824276904 | 16924819033898 | 16924824410041 | 16924824414810 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f3f0a76b380 | 0x7f3f03623fc0 | 0 | 0 | 0 | 16924824449859 | 16924824410041 | 16924824779800 | 16924824782369 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f3f0a76b200 | 0x7f3f03624000 | 0 | 0 | 0 | 16924824819178 | 16924824779800 | 16924825187958 | 16924825190257 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f3f0a76b080 | 0x7f3f03624040 | 0 | 0 | 0 | 16924825222506 | 16924825187958 | 16924825586197 | 16924825588415 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f3f080c9f00 | 0x7f3f03624080 | 0 | 0 | 0 | 16924825621644 | 16924825586197 | 16924825890036 | 16924825892286 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f3f080c9d80 | 0x7f3f036240c0 | 0 | 0 | 0 | 16924825925015 | 16924825890036 | 16924826205235 | 16924826207426 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f3f080c9c00 | 0x7f3f03624100 | 0 | 0 | 0 | 16924826252575 | 16924826205235 | 16924826514834 | 16924826517227 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f3f080c9a80 | 0x7f3f03624140 | 0 | 0 | 0 | 16924826549636 | 16924826514834 | 16924826908433 | 16924826910555 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f3f080c9900 | 0x7f3f03624180 | 0 | 0 | 0 | 16924826942955 | 16924826908433 | 16924827301392 | 16924827303544 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f3f080c9780 | 0x7f3f036241c0 | 0 | 0 | 0 | 16924827334513 | 16924827301392 | 16924827622671 | 16924827625014 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f3f080c9600 | 0x7f3f03624200 | 0 | 0 | 0 | 16924827658573 | 16924827622671 | 16924827931470 | 16924827933725 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f3f0a76b480 | 0x7f3f03624240 | 0 | 0 | 0 | 16924827975734 | 16924827931470 | 16924828237229 | 16924828239486 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f3f0a76b300 | 0x7f3f03624280 | 0 | 0 | 0 | 16924828272565 | 16924828237229 | 16924828627788 | 16924828630054 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f3f0a76b180 | 0x7f3f036242c0 | 0 | 0 | 0 | 16924828663593 | 16924828627788 | 16924829020907 | 16924829023213 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f3f0a76b000 | 0x7f3f03624300 | 0 | 0 | 0 | 16924829056372 | 16924829020907 | 16924829328106 | 16924829330444 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f3f080c9e80 | 0x7f3f03624340 | 0 | 0 | 0 | 16924829362533 | 16924829328106 | 16924829631625 | 16924829633905 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f3f080c9d00 | 0x7f3f03624380 | 0 | 0 | 0 | 16924829673003 | 16924829631625 | 16924829946824 | 16924829948985 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f3f080c9b80 | 0x7f3f036243c0 | 0 | 0 | 0 | 16924829982494 | 16924829946824 | 16924830359303 | 16924830361033 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f3f080c9a00 | 0x7f3f03624400 | 0 | 0 | 0 | 16924830394082 | 16924830359303 | 16924830727942 | 16924830729492 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f3f080c9880 | 0x7f3f03624440 | 0 | 0 | 0 | 16924830761181 | 16924830727942 | 16924831010981 | 16924831012654 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f3f080c9700 | 0x7f3f03624480 | 0 | 0 | 0 | 16924831045663 | 16924831010981 | 16924831288420 | 16924831290215 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f3f0a76b580 | 0x7f3f036244c0 | 0 | 0 | 0 | 16924831329904 | 16924831288420 | 16924831566499 | 16924831568057 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f3f0a76b400 | 0x7f3f03624500 | 0 | 0 | 0 | 16924831600306 | 16924831566499 | 16924831932258 | 16924831933886 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f3f0a76b280 | 0x7f3f03624540 | 0 | 0 | 0 | 16924831965945 | 16924831932258 | 16924832297697 | 16924832299376 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f3f0a76b100 | 0x7f3f03624580 | 0 | 0 | 0 | 16924832331785 | 16924832297697 | 16924832574976 | 16924832576797 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f3f080c9f80 | 0x7f3f036245c0 | 0 | 0 | 0 | 16924832608546 | 16924832574976 | 16924832850175 | 16924832851879 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f3f080c9e00 | 0x7f3f03624600 | 0 | 0 | 0 | 16924832890198 | 16924832850175 | 16924833127774 | 16924833129341 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f3f080c9c80 | 0x7f3f03624640 | 0 | 0 | 0 | 16924833162500 | 16924833127774 | 16924833494493 | 16924833496140 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f3f080c9b00 | 0x7f3f03624680 | 0 | 0 | 0 | 16924833527079 | 16924833494493 | 16924833856732 | 16924833858449 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f3f080c9980 | 0x7f3f036246c0 | 0 | 0 | 0 | 16924833889428 | 16924833856732 | 16924834140731 | 16924834142571 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f3f080c9800 | 0x7f3f03624700 | 0 | 0 | 0 | 16924834174900 | 16924834140731 | 16924834422971 | 16924834424592 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f3f080c9680 | 0x7f3f03624740 | 0 | 0 | 0 | 16924834462981 | 16924834422971 | 16924834701370 | 16924834703114 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f3f0a76b500 | 0x7f3f03624780 | 0 | 0 | 0 | 16924834735213 | 16924834701370 | 16924835061209 | 16924835062793 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f3f0a76b380 | 0x7f3f036247c0 | 0 | 0 | 0 | 16924835094673 | 16924835061209 | 16924835427128 | 16924835428883 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f3f0a76b200 | 0x7f3f03624800 | 0 | 0 | 0 | 16924835460762 | 16924835427128 | 16924835703607 | 16924835705134 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f3f0a76b080 | 0x7f3f03624840 | 0 | 0 | 0 | 16924835736663 | 16924835703607 | 16924835982326 | 16924835984106 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f3f080c9f00 | 0x7f3f03624880 | 0 | 0 | 0 | 16924836023385 | 16924835982326 | 16924836263285 | 16924836264988 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f3f080c9d80 | 0x7f3f036248c0 | 0 | 0 | 0 | 16924836297147 | 16924836263285 | 16924836625204 | 16924836626847 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f3f080c9c00 | 0x7f3f03624900 | 0 | 0 | 0 | 16924836658036 | 16924836625204 | 16924836989843 | 16924836991646 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f3f080c9a80 | 0x7f3f03624940 | 0 | 0 | 0 | 16924837023495 | 16924836989843 | 16924837266642 | 16924837268308 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f3f080c9900 | 0x7f3f03624980 | 0 | 0 | 0 | 16924837299707 | 16924837266642 | 16924837544241 | 16924837545780 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f3f080c9780 | 0x7f3f036249c0 | 0 | 0 | 0 | 16924837584399 | 16924837544241 | 16924837821200 | 16924837822832 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f3f080c9600 | 0x7f3f03624a00 | 0 | 0 | 0 | 16924837853951 | 16924837821200 | 16924838184079 | 16924838185721 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f3f0a76b480 | 0x7f3f03624a40 | 0 | 0 | 0 | 16924838217930 | 16924838184079 | 16924838548558 | 16924838550180 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f3f0a76b300 | 0x7f3f03624a80 | 0 | 0 | 0 | 16924838581789 | 16924838548558 | 16924838824877 | 16924838826742 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f3f0a76b180 | 0x7f3f03624ac0 | 0 | 0 | 0 | 16924838857831 | 16924838824877 | 16924839100556 | 16924839102164 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f3f0a76b000 | 0x7f3f03624b00 | 0 | 0 | 0 | 16924839140752 | 16924839100556 | 16924839376236 | 16924839377975 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f3f080c9e80 | 0x7f3f03624b40 | 0 | 0 | 0 | 16924839409344 | 16924839376236 | 16924839739435 | 16924839741215 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f3f080c9d00 | 0x7f3f03624b80 | 0 | 0 | 0 | 16924839775134 | 16924839739435 | 16924840114473 | 16924840116203 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f3f080c9b80 | 0x7f3f03624bc0 | 0 | 0 | 0 | 16924840147293 | 16924840114473 | 16924840391433 | 16924840393055 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f3f080c9a00 | 0x7f3f03624c00 | 0 | 0 | 0 | 16924840424634 | 16924840391433 | 16924840667432 | 16924840669017 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f3f080c9880 | 0x7f3f03624c40 | 0 | 0 | 0 | 16924840707216 | 16924840667432 | 16924840943431 | 16924840945079 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f3f080c9700 | 0x7f3f03624c80 | 0 | 0 | 0 | 16924840975988 | 16924840943431 | 16924841307270 | 16924841308878 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f3f0a76b580 | 0x7f3f03624cc0 | 0 | 0 | 0 | 16924841341817 | 16924841307270 | 16924841672709 | 16924841674317 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f3f0a76b400 | 0x7f3f03624d00 | 0 | 0 | 0 | 16924841705566 | 16924841672709 | 16924841949188 | 16924841950829 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f3f0a76b280 | 0x7f3f03624d40 | 0 | 0 | 0 | 16924841982608 | 16924841949188 | 16924842241187 | 16924842243250 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f3f0a76b100 | 0x7f3f03624d80 | 0 | 0 | 0 | 16924842282609 | 16924842241187 | 16924842519106 | 16924842520782 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f3f080c9f80 | 0x7f3f03624dc0 | 0 | 0 | 0 | 16924842552771 | 16924842519106 | 16924842886305 | 16924842888031 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f3f080c9e00 | 0x7f3f03624e00 | 0 | 0 | 0 | 16924842919080 | 16924842886305 | 16924843253664 | 16924843255280 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f3f080c9c80 | 0x7f3f03624e40 | 0 | 0 | 0 | 16924843286319 | 16924843253664 | 16924843531263 | 16924843532692 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f3f080c9b00 | 0x7f3f03624e80 | 0 | 0 | 0 | 16924843564981 | 16924843531263 | 16924843814462 | 16924843816224 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f3f080c9980 | 0x7f3f03624ec0 | 0 | 0 | 0 | 16924843855422 | 16924843814462 | 16924844089981 | 16924844091605 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f3f080c9800 | 0x7f3f03624f00 | 0 | 0 | 0 | 16924844122835 | 16924844089981 | 16924844453340 | 16924844454885 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f3f080c9680 | 0x7f3f03624f40 | 0 | 0 | 0 | 16924844487014 | 16924844453340 | 16924844816379 | 16924844818054 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f3f0a76b500 | 0x7f3f03624f80 | 0 | 0 | 0 | 16924844849873 | 16924844816379 | 16924845093178 | 16924845094746 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f3f0a76b380 | 0x7f3f03624fc0 | 0 | 0 | 0 | 16924845126805 | 16924845093178 | 16924845385498 | 16924845387377 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f3f0a76b200 | 0x7f3f03625000 | 0 | 0 | 0 | 16924845425756 | 16924845385498 | 16924845668697 | 16924845670079 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f3f0a76b080 | 0x7f3f03625040 | 0 | 0 | 0 | 16924845702278 | 16924845668697 | 16924846039416 | 16924846040878 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f3f080c9f00 | 0x7f3f03625080 | 0 | 0 | 0 | 16924846072487 | 16924846039416 | 16924846410135 | 16924846411917 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f3f080c9d80 | 0x7f3f036250c0 | 0 | 0 | 0 | 16924846443356 | 16924846410135 | 16924846688694 | 16924846690368 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f3f080c9c00 | 0x7f3f03625100 | 0 | 0 | 0 | 16924846722497 | 16924846688694 | 16924846987413 | 16924846989029 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f3f080c9a80 | 0x7f3f03625140 | 0 | 0 | 0 | 16924847041028 | 16924846987413 | 16924847271572 | 16924847273781 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f3f080c9900 | 0x7f3f03625180 | 0 | 0 | 0 | 16924847304760 | 16924847271572 | 16924847644691 | 16924847646460 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f3f080c9780 | 0x7f3f036251c0 | 0 | 0 | 0 | 16924847677979 | 16924847644691 | 16924848012050 | 16924848013699 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f3f080c9600 | 0x7f3f03625200 | 0 | 0 | 0 | 16924848044728 | 16924848012050 | 16924848289809 | 16924848291441 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f3f0a76b480 | 0x7f3f03625240 | 0 | 0 | 0 | 16924848322460 | 16924848289809 | 16924848590768 | 16924848592382 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f3f0a76b300 | 0x7f3f03625280 | 0 | 0 | 0 | 16924848631781 | 16924848590768 | 16924848876207 | 16924848877893 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f3f0a76b180 | 0x7f3f036252c0 | 0 | 0 | 0 | 16924848908862 | 16924848876207 | 16924849243566 | 16924849245312 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f3f0a76b000 | 0x7f3f03625300 | 0 | 0 | 0 | 16924849277112 | 16924849243566 | 16924849604045 | 16924849605752 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f3f080c9e80 | 0x7f3f03625340 | 0 | 0 | 0 | 16924849636491 | 16924849604045 | 16924849885804 | 16924849887443 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f3f080c9d00 | 0x7f3f03625380 | 0 | 0 | 0 | 16924849918403 | 16924849885804 | 16924850193163 | 16924850195514 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f3f080c9b80 | 0x7f3f036253c0 | 0 | 0 | 0 | 16924850233693 | 16924850193163 | 16924850484842 | 16924850486466 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f3f080c9a00 | 0x7f3f03625400 | 0 | 0 | 0 | 16924850517795 | 16924850484842 | 16924850848041 | 16924850849825 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f3f080c9880 | 0x7f3f03625440 | 0 | 0 | 0 | 16924850881504 | 16924850848041 | 16924851213800 | 16924851215494 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f3f080c9700 | 0x7f3f03625480 | 0 | 0 | 0 | 16924851246743 | 16924851213800 | 16924851490759 | 16924851492256 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f3f0a76b580 | 0x7f3f036254c0 | 0 | 0 | 0 | 16924851523985 | 16924851490759 | 16924851807238 | 16924851808976 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f3f0a76b400 | 0x7f3f03625500 | 0 | 0 | 0 | 16924851847145 | 16924851807238 | 16924852096517 | 16924852098118 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f3f0a76b280 | 0x7f3f03625540 | 0 | 0 | 0 | 16924852129337 | 16924852096517 | 16924852456836 | 16924852458537 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f3f0a76b100 | 0x7f3f03625580 | 0 | 0 | 0 | 16924852489776 | 16924852456836 | 16924852817475 | 16924852819206 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f3f080c9f80 | 0x7f3f036255c0 | 0 | 0 | 0 | 16924852849675 | 16924852817475 | 16924853094914 | 16924853096518 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f3f080c9e00 | 0x7f3f03625600 | 0 | 0 | 0 | 16924853127377 | 16924853094914 | 16924853415233 | 16924853416939 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f3f080c9c80 | 0x7f3f03625640 | 0 | 0 | 0 | 16924853454268 | 16924853415233 | 16924853696513 | 16924853698240 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f3f080c9b00 | 0x7f3f03625680 | 0 | 0 | 0 | 16924853728839 | 16924853696513 | 16924854062431 | 16924854064089 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f3f080c9980 | 0x7f3f036256c0 | 0 | 0 | 0 | 16924854095948 | 16924854062431 | 16924854432190 | 16924854433748 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f3f080c9800 | 0x7f3f03625700 | 0 | 0 | 0 | 16924854465037 | 16924854432190 | 16924854712830 | 16924854714420 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f3f080c9680 | 0x7f3f03625740 | 0 | 0 | 0 | 16924854745209 | 16924854712830 | 16924855044189 | 16924855045640 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f3f0a76b500 | 0x7f3f03625780 | 0 | 0 | 0 | 16924855084729 | 16924855044189 | 16924855326588 | 16924855328342 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f3f0a76b380 | 0x7f3f036257c0 | 0 | 0 | 0 | 16924855359141 | 16924855326588 | 16924855689467 | 16924855691211 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f3f0a76b200 | 0x7f3f03625800 | 0 | 0 | 0 | 16924855723700 | 16924855689467 | 16924856058265 | 16924856060060 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f3f0a76b080 | 0x7f3f03625840 | 0 | 0 | 0 | 16924856090719 | 16924856058265 | 16924856345785 | 16924856347481 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f3f080c9f00 | 0x7f3f03625880 | 0 | 0 | 0 | 16924856379440 | 16924856345785 | 16924856689784 | 16924856691361 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f3f080c9d80 | 0x7f3f036258c0 | 0 | 0 | 0 | 16924856730560 | 16924856689784 | 16924856975383 | 16924856977072 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f3f080c9c00 | 0x7f3f03625900 | 0 | 0 | 0 | 16924857007612 | 16924856975383 | 16924857339222 | 16924857340932 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f3f080c9a80 | 0x7f3f03625940 | 0 | 0 | 0 | 16924857372591 | 16924857339222 | 16924857701781 | 16924857703511 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f3f080c9900 | 0x7f3f03625980 | 0 | 0 | 0 | 16924857734650 | 16924857701781 | 16924857990420 | 16924857992052 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f3f080c9780 | 0x7f3f036259c0 | 0 | 0 | 0 | 16924858024221 | 16924857990420 | 16924858361779 | 16924858363651 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f3f080c9600 | 0x7f3f03625a00 | 0 | 0 | 0 | 16924858402690 | 16924858361779 | 16924858643058 | 16924858644643 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f3f0a76b480 | 0x7f3f03625a40 | 0 | 0 | 0 | 16924858675552 | 16924858643058 | 16924859006417 | 16924859008122 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f3f0a76b300 | 0x7f3f03625a80 | 0 | 0 | 0 | 16924859039701 | 16924859006417 | 16924859371056 | 16924859372841 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f3f0a76b180 | 0x7f3f03625ac0 | 0 | 0 | 0 | 16924859404230 | 16924859371056 | 16924859667695 | 16924859669382 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f3f0a76b000 | 0x7f3f03625b00 | 0 | 0 | 0 | 16924859700911 | 16924859667695 | 16924860030094 | 16924860031792 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f3f080c9e80 | 0x7f3f03625b40 | 0 | 0 | 0 | 16924860070330 | 16924860030094 | 16924860314573 | 16924860316193 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f3f080c9d00 | 0x7f3f03625b80 | 0 | 0 | 0 | 16924860346992 | 16924860314573 | 16924860680812 | 16924860682492 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f3f080c9b80 | 0x7f3f03625bc0 | 0 | 0 | 0 | 16924860713361 | 16924860680812 | 16924861046250 | 16924861048041 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f3f080c9a00 | 0x7f3f03625c00 | 0 | 0 | 0 | 16924861078681 | 16924861046250 | 16924861356490 | 16924861358162 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f3f080c9880 | 0x7f3f03625c40 | 0 | 0 | 0 | 16924861389491 | 16924861356490 | 16924861745768 | 16924861766400 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f3f080c9700 | 0x7f3f03625c80 | 0 | 0 | 0 | 16924861785930 | 16924861745768 | 16924862046727 | 16924862048292 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f3f0a76b580 | 0x7f3f03625cc0 | 0 | 0 | 0 | 16924862087861 | 16924862046727 | 16924862425446 | 16924862427231 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f3f0a76b400 | 0x7f3f03625d00 | 0 | 0 | 0 | 16924862458930 | 16924862425446 | 16924862792965 | 16924862794670 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f3f0a76b280 | 0x7f3f03625d40 | 0 | 0 | 0 | 16924862824509 | 16924862792965 | 16924863110564 | 16924863112180 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f3f0a76b100 | 0x7f3f03625d80 | 0 | 0 | 0 | 16924863143009 | 16924863110564 | 16924863524483 | 16924863546117 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f3f080c9f80 | 0x7f3f03625dc0 | 0 | 0 | 0 | 16924863565317 | 16924863524483 | 16924863844162 | 16924863845968 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f3f080c9e00 | 0x7f3f03625e00 | 0 | 0 | 0 | 16924863876108 | 16924863844162 | 16924864217281 | 16924864218797 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f3f080c9c80 | 0x7f3f03625e40 | 0 | 0 | 0 | 16924864250116 | 16924864217281 | 16924864596800 | 16924864614726 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f3f080c9b00 | 0x7f3f03625e80 | 0 | 0 | 0 | 16924864628935 | 16924864596800 | 16924864952159 | 16924864953956 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f3f080c9980 | 0x7f3f03625ec0 | 0 | 0 | 0 | 16924864985245 | 16924864952159 | 16924865420477 | 16924865438111 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f3f080c9800 | 0x7f3f03625f00 | 0 | 0 | 0 | 16924865460860 | 16924865420477 | 16924865756476 | 16924865758132 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f3f080c9680 | 0x7f3f03625f40 | 0 | 0 | 0 | 16924865789381 | 16924865756476 | 16924866157755 | 16924866179769 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f3f0a76b500 | 0x7f3f03625f80 | 0 | 0 | 0 | 16924866191769 | 16924866157755 | 16924866569594 | 16924866611496 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f3f0a76b380 | 0x7f3f03625fc0 | 0 | 0 | 0 | 16924866623036 | 16924866569594 | 16924866969753 | 16924866971296 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f3f0a76b200 | 0x7f3f03626000 | 0 | 0 | 0 | 16924867003625 | 16924866969753 | 16924867486071 | 16924867528279 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f3f0a76b080 | 0x7f3f03626040 | 0 | 0 | 0 | 16924867547869 | 16924867486071 | 16924867871510 | 16924867873359 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f3f080c9f00 | 0x7f3f03626080 | 0 | 0 | 0 | 16924867904688 | 16924867871510 | 16924868291029 | 16924868332905 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f3f080c9d80 | 0x7f3f036260c0 | 0 | 0 | 0 | 16924868344485 | 16924868291029 | 16924868737427 | 16924868779562 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f3f080c9c00 | 0x7f3f03626100 | 0 | 0 | 0 | 16924868791182 | 16924868737427 | 16924869162386 | 16924869204129 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f3f080c9a80 | 0x7f3f03626140 | 0 | 0 | 0 | 16924869216449 | 16924869162386 | 16924869763024 | 16924869782892 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f3f080c9900 | 0x7f3f03626180 | 0 | 0 | 0 | 16924869803822 | 16924869763024 | 16924870138543 | 16924870140282 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f3f080c9780 | 0x7f3f036261c0 | 0 | 0 | 0 | 16924870171661 | 16924870138543 | 16924870577582 | 16924870624717 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f3f080c9600 | 0x7f3f03626200 | 0 | 0 | 0 | 16924870637047 | 16924870577582 | 16924871039980 | 16924871084094 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f3f0a76b480 | 0x7f3f03626240 | 0 | 0 | 0 | 16924871095613 | 16924871039980 | 16924871493259 | 16924871535060 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f3f0a76b300 | 0x7f3f03626280 | 0 | 0 | 0 | 16924871546920 | 16924871493259 | 16924872159657 | 16924872201630 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f3f0a76b180 | 0x7f3f036262c0 | 0 | 0 | 0 | 16924872220750 | 16924872159657 | 16924872607176 | 16924872649677 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f3f0a76b000 | 0x7f3f03626300 | 0 | 0 | 0 | 16924872661197 | 16924872607176 | 16924873125734 | 16924873167932 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f3f080c9e80 | 0x7f3f03626340 | 0 | 0 | 0 | 16924873179031 | 16924873125734 | 16924873643813 | 16924873685846 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f3f080c9d00 | 0x7f3f03626380 | 0 | 0 | 0 | 16924873697676 | 16924873643813 | 16924874152771 | 16924874197111 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f3f080c9b80 | 0x7f3f036263c0 | 0 | 0 | 0 | 16924874209731 | 16924874152771 | 16924874928449 | 16924874946499 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f3f080c9a00 | 0x7f3f03626400 | 0 | 0 | 0 | 16924874968828 | 16924874928449 | 16924875381567 | 16924875423015 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f3f080c9880 | 0x7f3f03626440 | 0 | 0 | 0 | 16924875434694 | 16924875381567 | 16924875944766 | 16924875988008 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f3f080c9700 | 0x7f3f03626480 | 0 | 0 | 0 | 16924876000178 | 16924875944766 | 16924876507484 | 16924876550111 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f3f0a76b580 | 0x7f3f036264c0 | 0 | 0 | 0 | 16924876561621 | 16924876507484 | 16924877067962 | 16924877109835 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f3f0a76b400 | 0x7f3f03626500 | 0 | 0 | 0 | 16924877121964 | 16924877067962 | 16924877940440 | 16924877982359 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f3f0a76b280 | 0x7f3f03626540 | 0 | 0 | 0 | 16924878002138 | 16924877940440 | 16924878608118 | 16924878652529 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f3f0a76b100 | 0x7f3f03626580 | 0 | 0 | 0 | 16924878664509 | 16924878608118 | 16924879290516 | 16924879334249 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f3f080c9f80 | 0x7f3f036265c0 | 0 | 0 | 0 | 16924879345818 | 16924879290516 | 16924879969554 | 16924880011609 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f3f080c9e00 | 0x7f3f03626600 | 0 | 0 | 0 | 16924880023988 | 16924879969554 | 16924880632592 | 16924880675189 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f3f080c9c80 | 0x7f3f03626640 | 0 | 0 | 0 | 16924880686719 | 16924880632302 | 16924881715338 | 16924881761967 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f3f080c9b00 | 0x7f3f03626680 | 0 | 0 | 0 | 16924881781156 | 16924881715338 | 16924882787333 | 16924882855104 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f3f080c9980 | 0x7f3f036266c0 | 0 | 0 | 0 | 16924882867854 | 16924882787333 | 16924883933729 | 16924884000570 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f3f080c9800 | 0x7f3f03626700 | 0 | 0 | 0 | 16924884012800 | 16924883933729 | 16924885063965 | 16924885130557 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f3f080c9680 | 0x7f3f03626740 | 0 | 0 | 0 | 16924885142646 | 16924885063965 | 16924886177881 | 16924886247803 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f3f0a76b500 | 0x7f3f03626780 | 0 | 0 | 0 | 16924886260563 | 16924886177881 | 16924888140434 | 16924888207645 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f3f0a76b380 | 0x7f3f036267c0 | 0 | 0 | 0 | 16924888227464 | 16924888140434 | 16924890060107 | 16924890135547 |
| 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 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f3f0a76b200 | 0x7f3f03626800 | 0 | 0 | 0 | 16924890148117 | 16924890060107 | 16924892058020 | 16924892128498 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f3f0a76b080 | 0x7f3f03626840 | 0 | 0 | 0 | 16924892139548 | 16924892058020 | 16924894034333 | 16924894110769 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f3f080c9f00 | 0x7f3f03626880 | 0 | 0 | 0 | 16924894123519 | 16924894034333 | 16924895974166 | 16924896044162 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 183436 | 183436 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f3f080c9d80 | 0x7f3f036268c0 | 0 | 0 | 0 | 16924896056132 | 16924895974166 | 16924899589833 | 16924899665964 |