41 KiB
41 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_fillBufferAligned.kd | 0 | 0 | 0 | 211527 | 211527 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f4688204280 | 3670016 | 3054154 | 341857152 | 17413315644610 | 17404579624633 | 17413463333343 | 17413463447223 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 211527 | 211527 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f4688223f80 | 512 | 96322 | 10800192 | 17413468616208 | 17413463333343 | 17413468744548 | 17413468748994 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f468b1cd380 | 0x7f4688223fc0 | 65536 | 621694 | 69634176 | 17413468781314 | 17413468744548 | 17413469103109 | 17413469105425 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f468b1cd200 | 0x7f4688224000 | 65536 | 643514 | 72164040 | 17413469140564 | 17413469103109 | 17413469501189 | 17413469503305 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f468b1cd080 | 0x7f4688224040 | 65536 | 636462 | 71343968 | 17413469536664 | 17413469501189 | 17413469891910 | 17413469894275 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f4688b2df00 | 0x7f4688224080 | 65536 | 629238 | 70473624 | 17413469926374 | 17413469891910 | 17413470203270 | 17413470205907 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f4688b2dd80 | 0x7f46882240c0 | 65536 | 599958 | 67221304 | 17413470237096 | 17413470203270 | 17413470509510 | 17413470511529 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f4688b2dc00 | 0x7f4688224100 | 131072 | 640130 | 71792960 | 17413470555557 | 17413470509510 | 17413470807591 | 17413470809741 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f4688b2da80 | 0x7f4688224140 | 131072 | 677124 | 75851384 | 17413470841170 | 17413470807591 | 17413471195911 | 17413471198001 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f4688b2d900 | 0x7f4688224180 | 65536 | 635248 | 71305040 | 17413471229740 | 17413471195911 | 17413471580072 | 17413471582150 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f4688b2d780 | 0x7f46882241c0 | 131072 | 678536 | 75950712 | 17413471612380 | 17413471580072 | 17413471889352 | 17413471891562 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f4688b2d600 | 0x7f4688224200 | 131072 | 677332 | 75923736 | 17413471922862 | 17413471889352 | 17413472187592 | 17413472189595 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f468b1cd480 | 0x7f4688224240 | 131072 | 675828 | 75653360 | 17413472229074 | 17413472187592 | 17413472498633 | 17413472500816 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f468b1cd300 | 0x7f4688224280 | 131072 | 695556 | 78063880 | 17413472533496 | 17413472498633 | 17413472885353 | 17413472887726 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f468b1cd180 | 0x7f46882242c0 | 65536 | 641160 | 71738440 | 17413472918585 | 17413472885353 | 17413473269194 | 17413473271376 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f468b1cd000 | 0x7f4688224300 | 131072 | 674386 | 75492320 | 17413473302925 | 17413473269194 | 17413473566794 | 17413473568838 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f4688b2de80 | 0x7f4688224340 | 131072 | 719064 | 80606264 | 17413473600928 | 17413473566794 | 17413473865514 | 17413473867451 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f4688b2dd00 | 0x7f4688224380 | 131072 | 671080 | 75150016 | 17413473906620 | 17413473865514 | 17413474161675 | 17413474164013 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f4688b2db80 | 0x7f46882243c0 | 131072 | 674090 | 75575568 | 17413474196162 | 17413474161675 | 17413474558315 | 17413474560633 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f4688b2da00 | 0x7f4688224400 | 65536 | 598762 | 67144976 | 17413474591742 | 17413474558315 | 17413474952235 | 17413474953842 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f4688b2d880 | 0x7f4688224440 | 131072 | 681814 | 76366904 | 17413474984912 | 17413474952235 | 17413475220716 | 17413475222265 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f4688b2d700 | 0x7f4688224480 | 131072 | 671874 | 75284312 | 17413475253725 | 17413475220716 | 17413475492236 | 17413475493798 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f468b1cd580 | 0x7f46882244c0 | 131072 | 636370 | 71132568 | 17413475532707 | 17413475492236 | 17413475766796 | 17413475768341 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f468b1cd400 | 0x7f4688224500 | 131072 | 671134 | 75181736 | 17413475801540 | 17413475766796 | 17413476122477 | 17413476124062 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f468b1cd280 | 0x7f4688224540 | 65536 | 637228 | 71386024 | 17413476155191 | 17413476122477 | 17413476478797 | 17413476480433 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f468b1cd100 | 0x7f4688224580 | 131072 | 648782 | 72667656 | 17413476512992 | 17413476478797 | 17413476752237 | 17413476753916 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f4688b2df80 | 0x7f46882245c0 | 131072 | 633632 | 71119808 | 17413476785985 | 17413476752237 | 17413477022798 | 17413477024339 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f4688b2de00 | 0x7f4688224600 | 131072 | 671120 | 75268432 | 17413477061778 | 17413477022798 | 17413477294478 | 17413477296021 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f4688b2dc80 | 0x7f4688224640 | 131072 | 628346 | 70386176 | 17413477327881 | 17413477294478 | 17413477654638 | 17413477656132 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f4688b2db00 | 0x7f4688224680 | 65536 | 622784 | 69767616 | 17413477686391 | 17413477654638 | 17413478019119 | 17413478020673 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f4688b2d980 | 0x7f46882246c0 | 131072 | 688582 | 77188672 | 17413478052652 | 17413478019119 | 17413478299919 | 17413478301695 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f4688b2d800 | 0x7f4688224700 | 131072 | 702372 | 78772392 | 17413478332484 | 17413478299919 | 17413478574160 | 17413478575648 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f4688b2d680 | 0x7f4688224740 | 131072 | 675656 | 75621680 | 17413478614557 | 17413478574160 | 17413478850480 | 17413478851881 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f468b1cd500 | 0x7f4688224780 | 131072 | 634606 | 71138768 | 17413478882710 | 17413478850480 | 17413479208080 | 17413479209661 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f468b1cd380 | 0x7f46882247c0 | 65536 | 634048 | 71012496 | 17413479240981 | 17413479208080 | 17413479564561 | 17413479566142 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f468b1cd200 | 0x7f4688224800 | 131072 | 671802 | 75177928 | 17413479597711 | 17413479564561 | 17413479833841 | 17413479835435 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f468b1cd080 | 0x7f4688224840 | 131072 | 678204 | 75984544 | 17413479867424 | 17413479833841 | 17413480104241 | 17413480105818 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f4688b2df00 | 0x7f4688224880 | 131072 | 673330 | 75327472 | 17413480143647 | 17413480104241 | 17413480376242 | 17413480377741 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f4688b2dd80 | 0x7f46882248c0 | 131072 | 715934 | 80209904 | 17413480409320 | 17413480376242 | 17413480740402 | 17413480741931 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f4688b2dc00 | 0x7f4688224900 | 65536 | 595772 | 66743584 | 17413480773041 | 17413480740402 | 17413481096402 | 17413481097932 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f4688b2da80 | 0x7f4688224940 | 131072 | 677044 | 75814800 | 17413481129091 | 17413481096402 | 17413481365203 | 17413481366725 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f4688b2d900 | 0x7f4688224980 | 131072 | 673146 | 75382656 | 17413481397994 | 17413481365203 | 17413481634643 | 17413481636228 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f4688b2d780 | 0x7f46882249c0 | 131072 | 670170 | 75026448 | 17413481674937 | 17413481634643 | 17413481907443 | 17413481909081 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f4688b2d600 | 0x7f4688224a00 | 131072 | 693382 | 77525920 | 17413481940420 | 17413481907443 | 17413482265364 | 17413482267031 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f468b1cd480 | 0x7f4688224a40 | 65536 | 627076 | 70288576 | 17413482299501 | 17413482265364 | 17413482626964 | 17413482628532 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f468b1cd300 | 0x7f4688224a80 | 131072 | 643632 | 72050528 | 17413482660141 | 17413482626964 | 17413482896404 | 17413482897975 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f468b1cd180 | 0x7f4688224ac0 | 131072 | 641432 | 71807368 | 17413482929354 | 17413482896404 | 17413483166805 | 17413483168338 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f468b1cd000 | 0x7f4688224b00 | 131072 | 635002 | 71035432 | 17413483207277 | 17413483166805 | 17413483444725 | 17413483446221 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f4688b2de80 | 0x7f4688224b40 | 131072 | 674652 | 75571584 | 17413483477090 | 17413483444725 | 17413483803125 | 17413483804651 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f4688b2dd00 | 0x7f4688224b80 | 65536 | 628022 | 70441480 | 17413483836561 | 17413483803125 | 17413484161046 | 17413484162552 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f4688b2db80 | 0x7f4688224bc0 | 131072 | 675660 | 75748880 | 17413484193671 | 17413484161046 | 17413484433686 | 17413484435175 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f4688b2da00 | 0x7f4688224c00 | 131072 | 670106 | 75030952 | 17413484467314 | 17413484433686 | 17413484705686 | 17413484707258 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f4688b2d880 | 0x7f4688224c40 | 131072 | 692330 | 77465888 | 17413484747897 | 17413484705686 | 17413484978167 | 17413484979701 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f4688b2d700 | 0x7f4688224c80 | 131072 | 662996 | 74212592 | 17413485010180 | 17413484978167 | 17413485338327 | 17413485339872 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f468b1cd580 | 0x7f4688224cc0 | 65536 | 642072 | 71870336 | 17413485370621 | 17413485338327 | 17413485694648 | 17413485696212 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f468b1cd400 | 0x7f4688224d00 | 131072 | 673130 | 75378256 | 17413485727761 | 17413485694648 | 17413485966488 | 17413485968055 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f468b1cd280 | 0x7f4688224d40 | 131072 | 675338 | 75582216 | 17413485999824 | 17413485966488 | 17413486255608 | 17413486257338 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f468b1cd100 | 0x7f4688224d80 | 131072 | 674430 | 75712832 | 17413486296507 | 17413486255608 | 17413486528088 | 17413486529681 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f4688b2df80 | 0x7f4688224dc0 | 131072 | 644106 | 72262936 | 17413486561460 | 17413486528088 | 17413486888089 | 17413486889711 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f4688b2de00 | 0x7f4688224e00 | 65536 | 597672 | 66970024 | 17413486921570 | 17413486888089 | 17413487242649 | 17413487244012 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f4688b2dc80 | 0x7f4688224e40 | 131072 | 694356 | 77892936 | 17413487276031 | 17413487242649 | 17413487513530 | 17413487515115 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f4688b2db00 | 0x7f4688224e80 | 131072 | 669890 | 75064160 | 17413487546844 | 17413487513530 | 17413487791450 | 17413487793057 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f4688b2d980 | 0x7f4688224ec0 | 131072 | 686412 | 76904088 | 17413487831106 | 17413487791450 | 17413488063770 | 17413488065250 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f4688b2d800 | 0x7f4688224f00 | 131072 | 700512 | 78451672 | 17413488097059 | 17413488063770 | 17413488424571 | 17413488426101 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f4688b2d680 | 0x7f4688224f40 | 65536 | 644730 | 72174024 | 17413488457630 | 17413488424571 | 17413488783451 | 17413488785051 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f468b1cd500 | 0x7f4688224f80 | 131072 | 636230 | 71255616 | 17413488816841 | 17413488783451 | 17413489058011 | 17413489059634 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f468b1cd380 | 0x7f4688224fc0 | 131072 | 639840 | 71704272 | 17413489091353 | 17413489058011 | 17413489342812 | 17413489344297 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f468b1cd200 | 0x7f4688225000 | 131072 | 669866 | 75160312 | 17413489382476 | 17413489342812 | 17413489614332 | 17413489615920 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f468b1cd080 | 0x7f4688225040 | 131072 | 711212 | 79729128 | 17413489647389 | 17413489614332 | 17413489971772 | 17413489973410 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f4688b2df00 | 0x7f4688225080 | 65536 | 641306 | 71791856 | 17413490005200 | 17413489971772 | 17413490337853 | 17413490339491 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f4688b2dd80 | 0x7f46882250c0 | 131072 | 673870 | 75492480 | 17413490371060 | 17413490337853 | 17413490612573 | 17413490614084 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f4688b2dc00 | 0x7f4688225100 | 131072 | 673650 | 75408536 | 17413490646333 | 17413490612573 | 17413490905533 | 17413490907266 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f4688b2da80 | 0x7f4688225140 | 131072 | 675406 | 75641952 | 17413490956145 | 17413490905533 | 17413491181694 | 17413491183129 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f4688b2d900 | 0x7f4688225180 | 131072 | 673550 | 75571544 | 17413491215168 | 17413491181694 | 17413491541214 | 17413491542810 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f4688b2d780 | 0x7f46882251c0 | 65536 | 649482 | 72681168 | 17413491574629 | 17413491541214 | 17413491906015 | 17413491907410 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f4688b2d600 | 0x7f4688225200 | 131072 | 677866 | 75854536 | 17413491938639 | 17413491906015 | 17413492177535 | 17413492179103 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f468b1cd480 | 0x7f4688225240 | 131072 | 673228 | 75448512 | 17413492210892 | 17413492177535 | 17413492471455 | 17413492473115 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f468b1cd300 | 0x7f4688225280 | 131072 | 671074 | 75165616 | 17413492511544 | 17413492471455 | 17413492747455 | 17413492748978 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f468b1cd180 | 0x7f46882252c0 | 131072 | 673358 | 75307088 | 17413492780237 | 17413492747455 | 17413493101856 | 17413493103429 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f468b1cd000 | 0x7f4688225300 | 65536 | 643618 | 72121992 | 17413493134688 | 17413493101856 | 17413493457216 | 17413493458710 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f4688b2de80 | 0x7f4688225340 | 131072 | 671562 | 75201416 | 17413493489799 | 17413493457216 | 17413493727137 | 17413493728633 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f4688b2dd00 | 0x7f4688225380 | 131072 | 686378 | 76796440 | 17413493759902 | 17413493727137 | 17413494028737 | 17413494030285 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f4688b2db80 | 0x7f46882253c0 | 131072 | 669892 | 74967720 | 17413494068534 | 17413494028737 | 17413494313857 | 17413494315407 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f4688b2da00 | 0x7f4688225400 | 131072 | 630746 | 70669960 | 17413494347177 | 17413494313857 | 17413494677698 | 17413494679198 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f4688b2d880 | 0x7f4688225440 | 65536 | 671088 | 75186776 | 17413494711617 | 17413494677698 | 17413495034818 | 17413495036218 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f4688b2d700 | 0x7f4688225480 | 131072 | 642614 | 71914968 | 17413495067338 | 17413495034818 | 17413495306018 | 17413495307401 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f468b1cd580 | 0x7f46882254c0 | 131072 | 636816 | 71338536 | 17413495338291 | 17413495306018 | 17413495611779 | 17413495613203 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f468b1cd400 | 0x7f4688225500 | 131072 | 625094 | 70109264 | 17413495652102 | 17413495611779 | 17413495888419 | 17413495889916 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f468b1cd280 | 0x7f4688225540 | 131072 | 679288 | 76104736 | 17413495923205 | 17413495888419 | 17413496244099 | 17413496245667 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f468b1cd100 | 0x7f4688225580 | 65536 | 686358 | 76961304 | 17413496277496 | 17413496244099 | 17413496600740 | 17413496602287 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f4688b2df80 | 0x7f46882255c0 | 131072 | 676500 | 75716296 | 17413496633477 | 17413496600740 | 17413496872260 | 17413496873850 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f4688b2de00 | 0x7f4688225600 | 131072 | 669748 | 75081784 | 17413496904950 | 17413496872260 | 17413497185380 | 17413497187092 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f4688b2dc80 | 0x7f4688225640 | 131072 | 670242 | 75050920 | 17413497224991 | 17413497185380 | 17413497454501 | 17413497455895 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f4688b2db00 | 0x7f4688225680 | 131072 | 676994 | 75803264 | 17413497486424 | 17413497454501 | 17413497817061 | 17413497818496 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f4688b2d980 | 0x7f46882256c0 | 65536 | 641910 | 72022832 | 17413497849715 | 17413497817061 | 17413498174022 | 17413498175696 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f4688b2d800 | 0x7f4688225700 | 131072 | 674958 | 75586328 | 17413498207435 | 17413498174022 | 17413498455622 | 17413498457219 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f4688b2d680 | 0x7f4688225740 | 131072 | 668454 | 74859464 | 17413498488208 | 17413498455622 | 17413498774982 | 17413498776541 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f468b1cd500 | 0x7f4688225780 | 131072 | 676524 | 75746400 | 17413498814050 | 17413498774982 | 17413499047303 | 17413499048734 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f468b1cd380 | 0x7f46882257c0 | 131072 | 669782 | 75149336 | 17413499079423 | 17413499047303 | 17413499406503 | 17413499408084 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f468b1cd200 | 0x7f4688225800 | 65536 | 641412 | 71904112 | 17413499439343 | 17413499406503 | 17413499762183 | 17413499763695 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f468b1cd080 | 0x7f4688225840 | 131072 | 631604 | 70687064 | 17413499795904 | 17413499762183 | 17413500038984 | 17413500040548 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f4688b2df00 | 0x7f4688225880 | 131072 | 639760 | 71654416 | 17413500071887 | 17413500038984 | 17413500369544 | 17413500371029 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f4688b2dd80 | 0x7f46882258c0 | 131072 | 994480 | 111539568 | 17413500409808 | 17413500369544 | 17413500654344 | 17413500655932 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f4688b2dc00 | 0x7f4688225900 | 131072 | 642988 | 71927976 | 17413500686361 | 17413500654344 | 17413501011465 | 17413501012963 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f4688b2da80 | 0x7f4688225940 | 65536 | 637410 | 71311424 | 17413501044422 | 17413501011465 | 17413501367145 | 17413501368783 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f4688b2d900 | 0x7f4688225980 | 131072 | 672946 | 75422032 | 17413501399762 | 17413501367145 | 17413501648905 | 17413501650426 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f4688b2d780 | 0x7f46882259c0 | 131072 | 676182 | 75732528 | 17413501681055 | 17413501648905 | 17413501994826 | 17413501996377 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f4688b2d600 | 0x7f4688225a00 | 131072 | 997232 | 111752000 | 17413502035826 | 17413501994826 | 17413502273386 | 17413502274920 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f468b1cd480 | 0x7f4688225a40 | 131072 | 677166 | 75762984 | 17413502307739 | 17413502273386 | 17413502631307 | 17413502633020 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f468b1cd300 | 0x7f4688225a80 | 65536 | 673950 | 75455160 | 17413502664589 | 17413502631307 | 17413502988587 | 17413502990161 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f468b1cd180 | 0x7f4688225ac0 | 131072 | 628788 | 70400288 | 17413503021400 | 17413502988587 | 17413503274987 | 17413503276363 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f468b1cd000 | 0x7f4688225b00 | 131072 | 631928 | 70732800 | 17413503307513 | 17413503274987 | 17413503636748 | 17413503638184 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f4688b2de80 | 0x7f4688225b40 | 131072 | 948218 | 106276496 | 17413503677053 | 17413503636748 | 17413503919788 | 17413503921267 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f4688b2dd00 | 0x7f4688225b80 | 131072 | 675002 | 75553000 | 17413503952736 | 17413503919788 | 17413504277068 | 17413504278637 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f4688b2db80 | 0x7f4688225bc0 | 65536 | 642646 | 71903768 | 17413504309896 | 17413504277068 | 17413504634829 | 17413504636358 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f4688b2da00 | 0x7f4688225c00 | 131072 | 661620 | 74167408 | 17413504666797 | 17413504634829 | 17413504932909 | 17413504934580 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f4688b2d880 | 0x7f4688225c40 | 131072 | 636756 | 71231600 | 17413504965609 | 17413504932909 | 17413505315470 | 17413505338309 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f4688b2d700 | 0x7f4688225c80 | 131072 | 998564 | 111633768 | 17413505357019 | 17413505315470 | 17413505614190 | 17413505615752 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f468b1cd580 | 0x7f4688225cc0 | 131072 | 630966 | 70768776 | 17413505646691 | 17413505614190 | 17413505973710 | 17413505975193 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f468b1cd400 | 0x7f4688225d00 | 65536 | 661098 | 74069616 | 17413506007432 | 17413505973710 | 17413506342671 | 17413506344233 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f468b1cd280 | 0x7f4688225d40 | 131072 | 632428 | 70763968 | 17413506375882 | 17413506342671 | 17413506663791 | 17413506665435 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f468b1cd100 | 0x7f4688225d80 | 131072 | 631878 | 70742224 | 17413506697514 | 17413506663791 | 17413507074032 | 17413507097764 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f4688b2df80 | 0x7f4688225dc0 | 131072 | 934310 | 104710968 | 17413507116453 | 17413507074032 | 17413507394512 | 17413507396036 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f4688b2de00 | 0x7f4688225e00 | 131072 | 680886 | 76236168 | 17413507426895 | 17413507394512 | 17413507760272 | 17413507761636 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f4688b2dc80 | 0x7f4688225e40 | 65536 | 634812 | 71138368 | 17413507792885 | 17413507760272 | 17413508129553 | 17413508150686 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f4688b2db00 | 0x7f4688225e80 | 131072 | 633030 | 70982336 | 17413508161796 | 17413508129553 | 17413508474833 | 17413508476318 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f4688b2d980 | 0x7f4688225ec0 | 131072 | 647724 | 72481624 | 17413508507047 | 17413508474833 | 17413508935954 | 17413508955045 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f4688b2d800 | 0x7f4688225f00 | 131072 | 1006220 | 112658664 | 17413508976235 | 17413508935954 | 17413509266514 | 17413509268077 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f4688b2d680 | 0x7f4688225f40 | 131072 | 932384 | 104523752 | 17413509298256 | 17413509266514 | 17413509651314 | 17413509668197 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f468b1cd500 | 0x7f4688225f80 | 65536 | 631214 | 70563568 | 17413509684506 | 17413509651314 | 17413510043955 | 17413510060277 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f468b1cd380 | 0x7f4688225fc0 | 131072 | 639594 | 71629640 | 17413510083796 | 17413510043955 | 17413510421395 | 17413510422957 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f468b1cd200 | 0x7f4688226000 | 131072 | 638232 | 71529640 | 17413510454706 | 17413510421395 | 17413510932596 | 17413510953073 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f468b1cd080 | 0x7f4688226040 | 131072 | 999436 | 112039952 | 17413510973783 | 17413510932596 | 17413511280756 | 17413511282135 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f4688b2df00 | 0x7f4688226080 | 131072 | 1009032 | 113082904 | 17413511312904 | 17413511280756 | 17413511688277 | 17413511706373 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f4688b2dd80 | 0x7f46882260c0 | 65536 | 640342 | 71664104 | 17413511721623 | 17413511688277 | 17413512101717 | 17413512118493 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f4688b2dc00 | 0x7f4688226100 | 131072 | 636568 | 71320800 | 17413512135042 | 17413512101717 | 17413512494358 | 17413512510492 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f4688b2da80 | 0x7f4688226140 | 131072 | 683380 | 76529240 | 17413512527492 | 17413512494358 | 17413513059478 | 17413513075858 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f4688b2d900 | 0x7f4688226180 | 131072 | 1039348 | 116303216 | 17413513099067 | 17413513059478 | 17413513436119 | 17413513437738 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f4688b2d780 | 0x7f46882261c0 | 131072 | 937292 | 104882984 | 17413513468387 | 17413513436119 | 17413513871799 | 17413513888476 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f4688b2d600 | 0x7f4688226200 | 65536 | 639342 | 71705416 | 17413513906676 | 17413513871799 | 17413514301880 | 17413514318615 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f468b1cd480 | 0x7f4688226240 | 131072 | 627678 | 70284000 | 17413514335525 | 17413514301880 | 17413514722040 | 17413514742714 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f468b1cd300 | 0x7f4688226280 | 131072 | 995194 | 111520056 | 17413514755034 | 17413514722040 | 17413515357241 | 17413515376458 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f468b1cd180 | 0x7f46882262c0 | 131072 | 1010354 | 113217368 | 17413515398027 | 17413515357241 | 17413515763961 | 17413515780047 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f468b1cd000 | 0x7f4688226300 | 131072 | 938840 | 105129272 | 17413515797057 | 17413515763961 | 17413516243642 | 17413516260635 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f4688b2de80 | 0x7f4688226340 | 65536 | 633026 | 70913224 | 17413516276494 | 17413516243642 | 17413516726202 | 17413516742402 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f4688b2dd00 | 0x7f4688226380 | 131072 | 937894 | 104929072 | 17413516760282 | 17413516726202 | 17413517205403 | 17413517221650 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f4688b2db80 | 0x7f46882263c0 | 131072 | 995188 | 111637792 | 17413517238409 | 17413517205403 | 17413517939324 | 17413517956390 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f4688b2da00 | 0x7f4688226400 | 131072 | 979648 | 109675832 | 17413517979840 | 17413517939324 | 17413518402044 | 17413518423778 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f4688b2d880 | 0x7f4688226440 | 131072 | 997810 | 111629944 | 17413518434538 | 17413518402044 | 17413518937565 | 17413518958054 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f4688b2d700 | 0x7f4688226480 | 65536 | 639652 | 71707992 | 17413518970534 | 17413518937565 | 17413519470846 | 17413519490660 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f468b1cd580 | 0x7f46882264c0 | 131072 | 1017586 | 113958960 | 17413519503010 | 17413519470846 | 17413520002846 | 17413520019286 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f468b1cd400 | 0x7f4688226500 | 131072 | 1023174 | 114849032 | 17413520036326 | 17413520002846 | 17413520840287 | 17413520857205 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f468b1cd280 | 0x7f4688226540 | 131072 | 1033356 | 115609416 | 17413520881174 | 17413520840287 | 17413521465408 | 17413521480938 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f468b1cd100 | 0x7f4688226580 | 131072 | 1013040 | 113391560 | 17413521498188 | 17413521465408 | 17413522106208 | 17413522127571 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f4688b2df80 | 0x7f46882265c0 | 65536 | 643498 | 72024184 | 17413522140231 | 17413522106208 | 17413522757249 | 17413522773824 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f4688b2de00 | 0x7f4688226600 | 131072 | 994844 | 111407168 | 17413522789804 | 17413522757249 | 17413523389570 | 17413523406398 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f4688b2dc80 | 0x7f4688226640 | 131072 | 1002104 | 112115152 | 17413523421978 | 17413523389570 | 17413524442051 | 17413524458951 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f4688b2db00 | 0x7f4688226680 | 131072 | 1007140 | 112924024 | 17413524482520 | 17413524442051 | 17413525475012 | 17413525495634 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f4688b2d980 | 0x7f46882266c0 | 131072 | 993940 | 111115600 | 17413525506823 | 17413525474615 | 17413526542935 | 17413526586465 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f4688b2d800 | 0x7f4688226700 | 65536 | 659588 | 73904944 | 17413526598205 | 17413526542935 | 17413527635415 | 17413527703086 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f4688b2d680 | 0x7f4688226740 | 131072 | 999884 | 111938024 | 17413527714176 | 17413527635415 | 17413528742615 | 17413528808057 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f468b1cd500 | 0x7f4688226780 | 131072 | 994604 | 111310240 | 17413528820287 | 17413528742615 | 17413530682296 | 17413530753366 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f468b1cd380 | 0x7f46882267c0 | 131072 | 1054984 | 118218008 | 17413530773466 | 17413530682296 | 17413532602617 | 17413532669706 |
| 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 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f468b1cd200 | 0x7f4688226800 | 131072 | 982786 | 110310024 | 17413532681386 | 17413532602617 | 17413534578617 | 17413534654945 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f468b1cd080 | 0x7f4688226840 | 65536 | 642648 | 71894608 | 17413534666554 | 17413534578617 | 17413536556858 | 17413536628063 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f4688b2df00 | 0x7f4688226880 | 131072 | 1029776 | 115238616 | 17413536640143 | 17413536556858 | 17413538488699 | 17413538559253 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 211527 | 211527 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f4688b2dd80 | 0x7f46882268c0 | 131072 | 1022756 | 114292336 | 17413538571642 | 17413538488699 | 17413542111420 | 17413542184158 |