43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 880391 | 880396 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f2c10c04180 | 4194304 | 3146026 | 402749560 | 12075536711335293 | 12075536954971850 | 12075536955296328 | 12075536955407670 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 880391 | 880396 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f2c10c35100 | 512 | 21876 | 2775000 | 12075536969889464 | 12075536970192928 | 12075536970199328 | 12075536970212084 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f2d1c80b900 | 0x7f2c10c35140 | 65536 | 170518 | 21917192 | 12075536970267747 | 12075536970478846 | 12075536970609886 | 12075536970614381 |
| 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 | 6 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f2d1c80b800 | 0x7f2c10c35180 | 65536 | 158228 | 20238640 | 12075536970684111 | 12075536970852444 | 12075536971099003 | 12075536971170204 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f2d1c80b700 | 0x7f2c10c351c0 | 65536 | 164302 | 20903400 | 12075536971205680 | 12075536971398361 | 12075536971645720 | 12075536971715067 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f2d1c80b600 | 0x7f2c10c35200 | 65536 | 183696 | 23490592 | 12075536971743099 | 12075536971928279 | 12075536972063478 | 12075536972067712 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f2d1c80b500 | 0x7f2c10c35240 | 65536 | 180394 | 23078456 | 12075536972118126 | 12075536972300117 | 12075536972432596 | 12075536972436798 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f2d1c80b400 | 0x7f2c10c35280 | 131072 | 274318 | 35156120 | 12075536972515845 | 12075536972678995 | 12075536972811954 | 12075536972815792 |
| 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 | 16 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f2d1c80b300 | 0x7f2c10c352c0 | 131072 | 207470 | 26652424 | 12075536972866016 | 12075536973042193 | 12075536973296431 | 12075536973338865 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f2d1c80ba00 | 0x7f2c10c35300 | 65536 | 192140 | 24530152 | 12075536973368119 | 12075536973548110 | 12075536973795309 | 12075536973836810 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f2d1c80b900 | 0x7f2c10c35340 | 131072 | 240078 | 30908048 | 12075536973860935 | 12075536974056107 | 12075536974189227 | 12075536974193433 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f2d1c80b800 | 0x7f2c10c35380 | 131072 | 290578 | 37207176 | 12075536974243366 | 12075536974415945 | 12075536974551465 | 12075536974555415 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f2d1c80b700 | 0x7f2c10c353c0 | 131072 | 258686 | 33165296 | 12075536974619234 | 12075536974782983 | 12075536974912743 | 12075536974916867 |
| 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 | 26 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f2d1c80b600 | 0x7f2c10c35400 | 131072 | 205628 | 26294208 | 12075536974969064 | 12075536975148261 | 12075536975397060 | 12075536975466599 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f2d1c80b500 | 0x7f2c10c35440 | 65536 | 143418 | 18407800 | 12075536975496074 | 12075536975673539 | 12075536975924577 | 12075536975992075 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f2d1c80b400 | 0x7f2c10c35480 | 131072 | 265942 | 33999264 | 12075536976021941 | 12075536976211776 | 12075536976340255 | 12075536976344320 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f2d1c80b300 | 0x7f2c10c354c0 | 131072 | 220410 | 28267504 | 12075536976395405 | 12075536976558494 | 12075536976693533 | 12075536976697406 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f2d1c80ba00 | 0x7f2c10c35500 | 131072 | 222484 | 28395528 | 12075536976760063 | 12075536976925052 | 12075536977055611 | 12075536977059850 |
| 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 | 36 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f2d1c80b900 | 0x7f2c10c35540 | 131072 | 206300 | 26333480 | 12075536977110865 | 12075536977275290 | 12075536977525849 | 12075536977593992 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f2d1c80b800 | 0x7f2c10c35580 | 65536 | 153314 | 19579608 | 12075536977619259 | 12075536977802807 | 12075536978056566 | 12075536978126592 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f2d1c80b700 | 0x7f2c10c355c0 | 131072 | 221816 | 28482736 | 12075536978155346 | 12075536978340724 | 12075536978470644 | 12075536978474629 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f2d1c80b600 | 0x7f2c10c35600 | 131072 | 221960 | 28606360 | 12075536978523480 | 12075536978685843 | 12075536978819762 | 12075536978823748 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f2d1c80b500 | 0x7f2c10c35640 | 131072 | 224502 | 28681728 | 12075536978887426 | 12075536979055601 | 12075536979229520 | 12075536979233760 |
| 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 | 46 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f2d1c80b400 | 0x7f2c10c35680 | 131072 | 178342 | 22940152 | 12075536979284464 | 12075536979449999 | 12075536979696237 | 12075536979763394 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f2d1c80b300 | 0x7f2c10c356c0 | 65536 | 147938 | 18831920 | 12075536979790695 | 12075536979969836 | 12075536980216234 | 12075536980284683 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f2d1c80ba00 | 0x7f2c10c35700 | 131072 | 248648 | 31660552 | 12075536980308607 | 12075536980493673 | 12075536980621992 | 12075536980626148 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f2d1c80b900 | 0x7f2c10c35740 | 131072 | 226958 | 29004024 | 12075536980677563 | 12075536980835591 | 12075536980966470 | 12075536980970568 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f2d1c80b800 | 0x7f2c10c35780 | 131072 | 252808 | 32427600 | 12075536981038965 | 12075536981203429 | 12075536981373668 | 12075536981377604 |
| 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 | 56 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f2d1c80b700 | 0x7f2c10c357c0 | 131072 | 200286 | 25681624 | 12075536981429611 | 12075536981603587 | 12075536981861026 | 12075536981928538 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f2d1c80b600 | 0x7f2c10c35800 | 65536 | 153410 | 19617272 | 12075536981952753 | 12075536982142464 | 12075536982395903 | 12075536982465536 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f2d1c80b500 | 0x7f2c10c35840 | 131072 | 227210 | 29216984 | 12075536982495101 | 12075536982671581 | 12075536982800861 | 12075536982804877 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f2d1c80b400 | 0x7f2c10c35880 | 131072 | 250458 | 32168904 | 12075536982857214 | 12075536983022939 | 12075536983155579 | 12075536983159796 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f2d1c80b300 | 0x7f2c10c358c0 | 131072 | 223722 | 28671024 | 12075536983224216 | 12075536983391098 | 12075536983519897 | 12075536983524264 |
| 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 | 66 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f2d1c80ba00 | 0x7f2c10c35900 | 131072 | 213632 | 27296200 | 12075536983572453 | 12075536983744536 | 12075536983993974 | 12075536984041084 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f2d1c80b900 | 0x7f2c10c35940 | 65536 | 159764 | 20390584 | 12075536984069737 | 12075536984254773 | 12075536984510452 | 12075536984578283 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f2d1c80b800 | 0x7f2c10c35980 | 131072 | 264280 | 33854144 | 12075536984604100 | 12075536984789170 | 12075536984922289 | 12075536984926410 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f2d1c80b700 | 0x7f2c10c359c0 | 131072 | 229254 | 29154192 | 12075536984982233 | 12075536985149808 | 12075536985282447 | 12075536985286549 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f2d1c80b600 | 0x7f2c10c35a00 | 131072 | 250094 | 32037384 | 12075536985349666 | 12075536985513486 | 12075536985644206 | 12075536985648431 |
| 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 | 76 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f2d1c80b500 | 0x7f2c10c35a40 | 131072 | 172426 | 22039776 | 12075536985698625 | 12075536985865164 | 12075536986126763 | 12075536986198273 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f2d1c80b400 | 0x7f2c10c35a80 | 65536 | 180522 | 23163312 | 12075536986226846 | 12075536986404041 | 12075536986652680 | 12075536986720834 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f2d1c80b300 | 0x7f2c10c35ac0 | 131072 | 228058 | 29017544 | 12075536986747895 | 12075536986923399 | 12075536987058118 | 12075536987062359 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f2d1c80ba00 | 0x7f2c10c35b00 | 131072 | 251600 | 32185168 | 12075536987112863 | 12075536987279397 | 12075536987412996 | 12075536987417168 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f2d1c80b900 | 0x7f2c10c35b40 | 131072 | 246260 | 31660376 | 12075536987480827 | 12075536987643715 | 12075536987779714 | 12075536987783860 |
| 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 | 86 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f2d1c80b800 | 0x7f2c10c35b80 | 131072 | 199454 | 25468608 | 12075536987834494 | 12075536987992353 | 12075536988248992 | 12075536988317291 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f2d1c80b700 | 0x7f2c10c35bc0 | 65536 | 173646 | 22218496 | 12075536988344372 | 12075536988525150 | 12075536988779389 | 12075536988846966 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f2d1c80b600 | 0x7f2c10c35c00 | 131072 | 261880 | 33539200 | 12075536988872333 | 12075536989075387 | 12075536989203547 | 12075536989207786 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f2d1c80b500 | 0x7f2c10c35c40 | 131072 | 238258 | 30508520 | 12075536989260144 | 12075536989432505 | 12075536989566745 | 12075536989570851 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f2d1c80b400 | 0x7f2c10c35c80 | 131072 | 250992 | 32096128 | 12075536989632726 | 12075536989795543 | 12075536989929943 | 12075536989933946 |
| 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 | 96 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f2d1c80b300 | 0x7f2c10c35cc0 | 131072 | 198708 | 25573576 | 12075536989983598 | 12075536990162421 | 12075536990423700 | 12075536990493656 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f2d1c80ba00 | 0x7f2c10c35d00 | 65536 | 171384 | 22056456 | 12075536990521989 | 12075536990698739 | 12075536990958577 | 12075536991027127 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f2d1c80b900 | 0x7f2c10c35d40 | 131072 | 260506 | 33305720 | 12075536991054598 | 12075536991232656 | 12075536991363215 | 12075536991367310 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f2d1c80b800 | 0x7f2c10c35d80 | 131072 | 255382 | 32531968 | 12075536991416782 | 12075536991577934 | 12075536991722893 | 12075536991726798 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f2d1c80b700 | 0x7f2c10c35dc0 | 131072 | 230348 | 29224976 | 12075536991789885 | 12075536991951692 | 12075536992082731 | 12075536992087107 |
| 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 | 106 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f2d1c80b600 | 0x7f2c10c35e00 | 131072 | 280134 | 35942048 | 12075536992138713 | 12075536992300650 | 12075536992558889 | 12075536992625969 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f2d1c80b500 | 0x7f2c10c35e40 | 65536 | 172458 | 22056560 | 12075536992653800 | 12075536992828807 | 12075536993084006 | 12075536993151896 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f2d1c80b400 | 0x7f2c10c35e80 | 131072 | 254536 | 32525320 | 12075536993177083 | 12075536993367044 | 12075536993501764 | 12075536993506205 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f2d1c80b300 | 0x7f2c10c35ec0 | 131072 | 248750 | 31878120 | 12075536993555095 | 12075536993728962 | 12075536993871682 | 12075536993875912 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f2d1c80ba00 | 0x7f2c10c35f00 | 131072 | 251048 | 32126816 | 12075536993937957 | 12075536994101921 | 12075536994236000 | 12075536994240219 |
| 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 | 116 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f2d1c80b900 | 0x7f2c10c35f40 | 131072 | 255126 | 32983568 | 12075536994290542 | 12075536994453759 | 12075536994712317 | 12075536994779962 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f2d1c80b800 | 0x7f2c10c35f80 | 65536 | 166492 | 21361248 | 12075536994807082 | 12075536994984636 | 12075536995236154 | 12075536995304637 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f2d1c80b700 | 0x7f2c10c35fc0 | 131072 | 221292 | 28372544 | 12075536995332248 | 12075536995510713 | 12075536995646712 | 12075536995650860 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f2d1c80b600 | 0x7f2c10c36000 | 131072 | 268220 | 34214224 | 12075536995700372 | 12075536995869111 | 12075536996007030 | 12075536996011060 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f2d1c80b500 | 0x7f2c10c36040 | 131072 | 250202 | 32087368 | 12075536996074748 | 12075536996237109 | 12075536996375668 | 12075536996379785 |
| 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 | 126 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f2d1c80b400 | 0x7f2c10c36080 | 131072 | 211022 | 26904904 | 12075536996428375 | 12075536996595187 | 12075536996859346 | 12075536996907606 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f2d1c80b300 | 0x7f2c10c360c0 | 65536 | 140918 | 18115616 | 12075536996932943 | 12075536997122544 | 12075536997373583 | 12075536997424286 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f2d1c80ba00 | 0x7f2c10c36100 | 131072 | 254662 | 32703848 | 12075536997453320 | 12075536997628782 | 12075536997762221 | 12075536997766362 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f2d1c80b900 | 0x7f2c10c36140 | 131072 | 204098 | 26171944 | 12075536997815473 | 12075536997979180 | 12075536998125579 | 12075536998129848 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f2d1c80b800 | 0x7f2c10c36180 | 131072 | 269088 | 34532096 | 12075536998192815 | 12075536998357258 | 12075536998488457 | 12075536998492662 |
| 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 | 136 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f2d1c80b700 | 0x7f2c10c361c0 | 131072 | 200184 | 25681192 | 12075536998541953 | 12075536998704616 | 12075536998963175 | 12075536999018499 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f2d1c80b600 | 0x7f2c10c36200 | 65536 | 184808 | 23638792 | 12075536999046471 | 12075536999226053 | 12075536999482372 | 12075536999532144 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f2d1c80b500 | 0x7f2c10c36240 | 131072 | 225624 | 28900752 | 12075536999559264 | 12075536999734371 | 12075536999866370 | 12075536999870532 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f2d1c80b400 | 0x7f2c10c36280 | 131072 | 195044 | 25098640 | 12075536999918772 | 12075537000093569 | 12075537000244128 | 12075537000248565 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f2d1c80b300 | 0x7f2c10c362c0 | 131072 | 250714 | 31998616 | 12075537000329666 | 12075537000492286 | 12075537000624766 | 12075537000629132 |
| 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 | 146 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f2d1c80ba00 | 0x7f2c10c36300 | 131072 | 218248 | 27951416 | 12075537000679245 | 12075537000846685 | 12075537001105563 | 12075537001155040 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f2d1c80b900 | 0x7f2c10c36340 | 65536 | 146340 | 18656592 | 12075537001179906 | 12075537001360282 | 12075537001612121 | 12075537001661942 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f2d1c80b800 | 0x7f2c10c36380 | 131072 | 252370 | 32327824 | 12075537001687139 | 12075537001862839 | 12075537001992599 | 12075537001996664 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f2d1c80b700 | 0x7f2c10c363c0 | 131072 | 244520 | 31469640 | 12075537002047508 | 12075537002220437 | 12075537002377876 | 12075537002382210 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f2d1c80b600 | 0x7f2c10c36400 | 131072 | 259636 | 33354944 | 12075537002445298 | 12075537002609715 | 12075537002741715 | 12075537002745776 |
| 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 | 156 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f2d1c80b500 | 0x7f2c10c36440 | 131072 | 198430 | 25362152 | 12075537002796811 | 12075537002960273 | 12075537003223792 | 12075537003274919 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f2d1c80b400 | 0x7f2c10c36480 | 65536 | 191016 | 24307368 | 12075537003303673 | 12075537003479151 | 12075537003734189 | 12075537003782332 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f2d1c80b300 | 0x7f2c10c364c0 | 131072 | 221848 | 28397552 | 12075537003809533 | 12075537003983788 | 12075537004117867 | 12075537004122525 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f2d1c80ba00 | 0x7f2c10c36500 | 131072 | 223480 | 28591664 | 12075537004172057 | 12075537004347146 | 12075537004513545 | 12075537004517609 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f2d1c80b900 | 0x7f2c10c36540 | 131072 | 228954 | 29206488 | 12075537004579404 | 12075537004739624 | 12075537004876583 | 12075537004880734 |
| 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 | 166 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f2d1c80b800 | 0x7f2c10c36580 | 131072 | 184554 | 23530040 | 12075537004930316 | 12075537005125542 | 12075537005391780 | 12075537005439101 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f2d1c80b700 | 0x7f2c10c365c0 | 65536 | 145146 | 18629376 | 12075537005467805 | 12075537005643459 | 12075537005897858 | 12075537005947266 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f2d1c80b600 | 0x7f2c10c36600 | 131072 | 226870 | 29103064 | 12075537005974106 | 12075537006157696 | 12075537006294016 | 12075537006298519 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f2d1c80b500 | 0x7f2c10c36640 | 131072 | 257012 | 32779312 | 12075537006342400 | 12075537006516894 | 12075537006690493 | 12075537006694645 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f2d1c80b400 | 0x7f2c10c36680 | 131072 | 223440 | 28660088 | 12075537006757071 | 12075537006919292 | 12075537007051452 | 12075537007055696 |
| 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 | 176 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f2d1c80b300 | 0x7f2c10c366c0 | 131072 | 187168 | 23937928 | 12075537007108354 | 12075537007270650 | 12075537007528089 | 12075537007576263 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f2d1c80ba00 | 0x7f2c10c36700 | 65536 | 146430 | 18711544 | 12075537007604315 | 12075537007777688 | 12075537008071766 | 12075537008121036 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f2d1c80b900 | 0x7f2c10c36740 | 131072 | 252492 | 32487072 | 12075537008146723 | 12075537008332725 | 12075537008469844 | 12075537008474262 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f2d1c80b800 | 0x7f2c10c36780 | 131072 | 225934 | 29104400 | 12075537008524415 | 12075537008685843 | 12075537008868242 | 12075537008872472 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f2d1c80b700 | 0x7f2c10c367c0 | 131072 | 231490 | 29412912 | 12075537008934477 | 12075537009111921 | 12075537009250160 | 12075537009254292 |
| 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 | 186 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f2d1c80b600 | 0x7f2c10c36800 | 131072 | 227088 | 29030392 | 12075537009303954 | 12075537009465359 | 12075537009731917 | 12075537009779879 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f2d1c80b500 | 0x7f2c10c36840 | 65536 | 174782 | 22318784 | 12075537009805767 | 12075537009982156 | 12075537010238955 | 12075537010290277 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f2d1c80b400 | 0x7f2c10c36880 | 131072 | 206450 | 26374744 | 12075537010317728 | 12075537010492393 | 12075537010627753 | 12075537010631982 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f2d1c80b300 | 0x7f2c10c368c0 | 131072 | 253782 | 32477176 | 12075537010682155 | 12075537010844231 | 12075537011036550 | 12075537011085575 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f2d1c80ba00 | 0x7f2c10c36900 | 131072 | 238900 | 30649704 | 12075537011122564 | 12075537011283589 | 12075537011418948 | 12075537011422992 |
| 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 | 196 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f2d1c80b900 | 0x7f2c10c36940 | 131072 | 259420 | 33351912 | 12075537011471322 | 12075537011639107 | 12075537011953665 | 12075537011976571 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f2d1c80b800 | 0x7f2c10c36980 | 65536 | 149710 | 19190920 | 12075537012031162 | 12075537012193504 | 12075537012450463 | 12075537012501216 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f2d1c80b700 | 0x7f2c10c369c0 | 131072 | 264718 | 33698064 | 12075537012525531 | 12075537012703261 | 12075537012840381 | 12075537012844604 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f2d1c80b600 | 0x7f2c10c36a00 | 131072 | 221420 | 28319536 | 12075537012893425 | 12075537013071260 | 12075537013282138 | 12075537013330998 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f2d1c80b500 | 0x7f2c10c36a40 | 131072 | 253290 | 32477936 | 12075537013373477 | 12075537013537337 | 12075537013676376 | 12075537013680448 |
| 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 | 206 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f2d1c80b400 | 0x7f2c10c36a80 | 131072 | 250690 | 31838624 | 12075537013729198 | 12075537013898135 | 12075537014206613 | 12075537014258151 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f2d1c80b300 | 0x7f2c10c36ac0 | 65536 | 160668 | 20600952 | 12075537014283438 | 12075537014462612 | 12075537014717331 | 12075537014765234 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f2d1c80ba00 | 0x7f2c10c36b00 | 131072 | 219126 | 28278632 | 12075537014793186 | 12075537014967569 | 12075537015103889 | 12075537015108271 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f2d1c80b900 | 0x7f2c10c36b40 | 131072 | 231306 | 29457008 | 12075537015158985 | 12075537015324688 | 12075537015552846 | 12075537015600826 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f2d1c80b800 | 0x7f2c10c36b80 | 131072 | 225628 | 28690976 | 12075537015639799 | 12075537015801805 | 12075537015941804 | 12075537015945878 |
| 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 | 216 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f2d1c80b700 | 0x7f2c10c36bc0 | 131072 | 267092 | 34174648 | 12075537015995630 | 12075537016175243 | 12075537016534121 | 12075537016583763 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f2d1c80b600 | 0x7f2c10c36c00 | 65536 | 144680 | 18399128 | 12075537016608229 | 12075537016788680 | 12075537017045158 | 12075537017095474 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f2d1c80b500 | 0x7f2c10c36c40 | 131072 | 243890 | 31286120 | 12075537017124258 | 12075537017307877 | 12075537017451236 | 12075537017455383 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f2d1c80b400 | 0x7f2c10c36c80 | 131072 | 222364 | 28842304 | 12075537017506809 | 12075537017670414 | 12075537017915533 | 12075537017966914 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f2d1c80b300 | 0x7f2c10c36cc0 | 131072 | 226284 | 28967992 | 12075537018008671 | 12075537018167691 | 12075537018305610 | 12075537018309410 |
| 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 | 226 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f2d1c80ba00 | 0x7f2c10c36d00 | 131072 | 258484 | 33045224 | 12075537018353612 | 12075537018528169 | 12075537018906407 | 12075537018953607 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f2d1c80b900 | 0x7f2c10c36d40 | 65536 | 161792 | 20686528 | 12075537018979566 | 12075537019164326 | 12075537019426405 | 12075537019477321 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f2d1c80b800 | 0x7f2c10c36d80 | 131072 | 227064 | 28998616 | 12075537019504581 | 12075537019680644 | 12075537019821923 | 12075537019825278 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f2d1c80b700 | 0x7f2c10c36dc0 | 131072 | 223004 | 28740832 | 12075537019875341 | 12075537020043042 | 12075537020323361 | 12075537020371863 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f2d1c80b600 | 0x7f2c10c36e00 | 131072 | 225976 | 29001624 | 12075537020408562 | 12075537020580320 | 12075537020716320 | 12075537020719810 |
| 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 | 236 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f2d1c80b500 | 0x7f2c10c36e40 | 131072 | 224448 | 28811176 | 12075537020772107 | 12075537020929119 | 12075537021354557 | 12075537021402509 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f2d1c80b400 | 0x7f2c10c36e80 | 65536 | 149812 | 19111224 | 12075537021429920 | 12075537021614716 | 12075537021874555 | 12075537021922916 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f2d1c80b300 | 0x7f2c10c36ec0 | 131072 | 220050 | 28243480 | 12075537021948554 | 12075537022133753 | 12075537022274233 | 12075537022278166 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f2d1c80ba00 | 0x7f2c10c36f00 | 131072 | 239138 | 30532384 | 12075537022328981 | 12075537022491992 | 12075537022835990 | 12075537022883782 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f2d1c80b900 | 0x7f2c10c36f40 | 131072 | 257800 | 33078776 | 12075537022924327 | 12075537023093909 | 12075537023246549 | 12075537023250092 |
| 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 | 246 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f2d1c80b800 | 0x7f2c10c36f80 | 131072 | 225676 | 28742768 | 12075537023300266 | 12075537023469428 | 12075537023988305 | 12075537024037416 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f2d1c80b700 | 0x7f2c10c36fc0 | 65536 | 172820 | 22189856 | 12075537024067622 | 12075537024245904 | 12075537024542383 | 12075537024587398 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f2d1c80b600 | 0x7f2c10c37000 | 131072 | 225186 | 28899896 | 12075537024614949 | 12075537024790062 | 12075537024945741 | 12075537024949230 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f2d1c80b500 | 0x7f2c10c37040 | 131072 | 259172 | 32802704 | 12075537025008851 | 12075537025189580 | 12075537025575818 | 12075537025624014 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f2d1c80b400 | 0x7f2c10c37080 | 131072 | 227554 | 29137040 | 12075537025662446 | 12075537025823977 | 12075537026000297 | 12075537026006876 |
| 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 | 256 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f2d1c80b300 | 0x7f2c10c370c0 | 131072 | 249334 | 31999824 | 12075537026053202 | 12075537026225096 | 12075537026836933 | 12075537026859240 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f2d1c80ba00 | 0x7f2c10c37100 | 65536 | 175068 | 22537088 | 12075537026892642 | 12075537027071172 | 12075537027398531 | 12075537027418249 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f2d1c80b900 | 0x7f2c10c37140 | 131072 | 254162 | 32712504 | 12075537027462521 | 12075537027622050 | 12075537027801249 | 12075537027804476 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f2d1c80b800 | 0x7f2c10c37180 | 131072 | 262848 | 33700064 | 12075537027856824 | 12075537028026368 | 12075537028482846 | 12075537028504818 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f2d1c80b700 | 0x7f2c10c371c0 | 131072 | 261076 | 33285144 | 12075537028567995 | 12075537028735805 | 12075537028935004 | 12075537028960865 |
| 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 | 266 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f2d1c80b600 | 0x7f2c10c37200 | 131072 | 244904 | 31297256 | 12075537029009175 | 12075537029171963 | 12075537029877400 | 12075537029902215 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f2d1c80b500 | 0x7f2c10c37240 | 65536 | 177168 | 22575896 | 12075537029945305 | 12075537030116439 | 12075537030490517 | 12075537030514353 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f2d1c80b400 | 0x7f2c10c37280 | 131072 | 266292 | 34030984 | 12075537030558124 | 12075537030724916 | 12075537030927955 | 12075537030947848 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f2d1c80b300 | 0x7f2c10c372c0 | 131072 | 226260 | 28834504 | 12075537030993002 | 12075537031157394 | 12075537031683952 | 12075537031704334 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f2d1c80ba00 | 0x7f2c10c37300 | 131072 | 242718 | 30858184 | 12075537031761360 | 12075537031920591 | 12075537032145550 | 12075537032168046 |
| 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 | 276 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f2d1c80b900 | 0x7f2c10c37340 | 131072 | 253594 | 32431232 | 12075537032211427 | 12075537032371149 | 12075537033171785 | 12075537033192861 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f2d1c80b800 | 0x7f2c10c37380 | 65536 | 169114 | 21598040 | 12075537033237083 | 12075537033399464 | 12075537033820743 | 12075537033841536 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f2d1c80b700 | 0x7f2c10c373c0 | 131072 | 231138 | 29319768 | 12075537033891920 | 12075537034077221 | 12075537034305220 | 12075537034328130 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f2d1c80b600 | 0x7f2c10c37400 | 131072 | 267110 | 34044240 | 12075537034374787 | 12075537034536099 | 12075537035134337 | 12075537035157852 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f2d1c80b500 | 0x7f2c10c37440 | 131072 | 254602 | 32578576 | 12075537035220258 | 12075537035381696 | 12075537035651455 | 12075537035672759 |
| 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 | 286 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f2d1c80b400 | 0x7f2c10c37480 | 131072 | 259926 | 33184696 | 12075537035719666 | 12075537035879614 | 12075537036867449 | 12075537036908235 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f2d1c80b300 | 0x7f2c10c374c0 | 65536 | 143158 | 18318096 | 12075537036932470 | 12075537037119448 | 12075537037636246 | 12075537037676744 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f2d1c80ba00 | 0x7f2c10c37500 | 131072 | 229118 | 29114992 | 12075537037703333 | 12075537037880085 | 12075537038153044 | 12075537038197421 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f2d1c80b900 | 0x7f2c10c37540 | 131072 | 216516 | 27733648 | 12075537038221777 | 12075537038404723 | 12075537039143279 | 12075537039184105 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f2d1c80b800 | 0x7f2c10c37580 | 131072 | 230364 | 29260456 | 12075537039223198 | 12075537039387438 | 12075537039703917 | 12075537039745148 |
| 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 | 296 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f2d1c80b700 | 0x7f2c10c375c0 | 131072 | 225384 | 28860872 | 12075537039774823 | 12075537039955916 | 12075537041129511 | 12075537041170517 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f2d1c80b600 | 0x7f2c10c37600 | 65536 | 165242 | 21197992 | 12075537041200372 | 12075537041383110 | 12075537041993987 | 12075537042035284 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f2d1c80b500 | 0x7f2c10c37640 | 131072 | 224946 | 28578096 | 12075537042053247 | 12075537042241666 | 12075537042562945 | 12075537042604482 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f2d1c80b400 | 0x7f2c10c37680 | 131072 | 226596 | 29036792 | 12075537042629598 | 12075537042811744 | 12075537043690780 | 12075537043731797 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f2d1c80b300 | 0x7f2c10c376c0 | 131072 | 236754 | 30133160 | 12075537043768956 | 12075537043946299 | 12075537044358617 | 12075537044399908 |
| 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 | 306 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f2d1c80ba00 | 0x7f2c10c37700 | 131072 | 255316 | 32719808 | 12075537044425466 | 12075537044607416 | 12075537046157809 | 12075537046201947 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f2d1c80b900 | 0x7f2c10c37740 | 65536 | 147422 | 18763088 | 12075537046232705 | 12075537046414928 | 12075537047213164 | 12075537047255054 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f2d1c80b800 | 0x7f2c10c37780 | 131072 | 224018 | 28819360 | 12075537047288757 | 12075537047455403 | 12075537047870602 | 12075537047911174 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f2d1c80b700 | 0x7f2c10c377c0 | 131072 | 226866 | 29084264 | 12075537047942402 | 12075537048123560 | 12075537049283555 | 12075537049324270 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f2d1c80b600 | 0x7f2c10c37800 | 131072 | 251686 | 32104776 | 12075537049371007 | 12075537049539714 | 12075537050325951 | 12075537050370003 |
| 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 | 316 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f2d1c80b500 | 0x7f2c10c37840 | 131072 | 222236 | 28520088 | 12075537050401662 | 12075537050581150 | 12075537053635376 | 12075537053679985 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f2d1c80b400 | 0x7f2c10c37880 | 65536 | 169170 | 21656352 | 12075537053712215 | 12075537053887375 | 12075537055431689 | 12075537055500268 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f2d1c80b300 | 0x7f2c10c378c0 | 131072 | 243294 | 31297776 | 12075537055523992 | 12075537055718407 | 12075537056508804 | 12075537056552523 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f2d1c80ba00 | 0x7f2c10c37900 | 131072 | 250048 | 31923504 | 12075537056585324 | 12075537056771203 | 12075537059053593 | 12075537059121267 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f2d1c80b900 | 0x7f2c10c37940 | 131072 | 229312 | 29166584 | 12075537059168926 | 12075537059335512 | 12075537060871985 | 12075537060914771 |
| 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 | 326 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f2d1c80b800 | 0x7f2c10c37980 | 131072 | 228394 | 29238160 | 12075537060949014 | 12075537061125104 | 12075537067182998 | 12075537067253140 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f2d1c80b700 | 0x7f2c10c379c0 | 65536 | 142298 | 18192384 | 12075537067286993 | 12075537067464116 | 12075537070511623 | 12075537070584491 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f2d1c80b600 | 0x7f2c10c37a00 | 131072 | 226856 | 28990616 | 12075537070613856 | 12075537070799622 | 12075537072339615 | 12075537072410004 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 880391 | 880396 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f2d1c80b500 | 0x7f2c10c37a40 | 131072 | 265582 | 33806928 | 12075537072442765 | 12075537072626334 | 12075537077154794 | 12075537077225233 |