40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 748123 | 748128 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f14cf204180 | 0 | 0 | 0 | 12073198620537158 | 12073198863702901 | 12073198864028179 | 12073198864137881 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 748123 | 748128 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f14cf235100 | 0 | 0 | 0 | 12073198878460684 | 12073198878747260 | 12073198878753660 | 12073198878758598 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f15ff400900 | 0x7f14cf235140 | 0 | 0 | 0 | 12073198878825182 | 12073198879050299 | 12073198879181658 | 12073198879185611 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f15ff400800 | 0x7f14cf235180 | 0 | 0 | 0 | 12073198879253898 | 12073198879422457 | 12073198879673815 | 12073198879743237 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f15ff400700 | 0x7f14cf2351c0 | 0 | 0 | 0 | 12073198879778633 | 12073198879953974 | 12073198880211733 | 12073198880280476 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f15ff400600 | 0x7f14cf235200 | 0 | 0 | 0 | 12073198880309449 | 12073198880489971 | 12073198880627090 | 12073198880630526 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f15ff400500 | 0x7f14cf235240 | 0 | 0 | 0 | 12073198880680960 | 12073198880844689 | 12073198880979729 | 12073198880983221 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f15ff400400 | 0x7f14cf235280 | 0 | 0 | 0 | 12073198881061868 | 12073198881236207 | 12073198881373486 | 12073198881377043 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f15ff400300 | 0x7f14cf2352c0 | 0 | 0 | 0 | 12073198881430703 | 12073198881594125 | 12073198881885004 | 12073198881928378 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f15ff400a00 | 0x7f14cf235300 | 0 | 0 | 0 | 12073198881956830 | 12073198882140362 | 12073198882392201 | 12073198882462019 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f15ff400900 | 0x7f14cf235340 | 0 | 0 | 0 | 12073198882488438 | 12073198882671720 | 12073198882801639 | 12073198882805187 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f15ff400800 | 0x7f14cf235380 | 0 | 0 | 0 | 12073198882855560 | 12073198883034118 | 12073198883164837 | 12073198883168422 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f15ff400700 | 0x7f14cf2353c0 | 0 | 0 | 0 | 12073198883234544 | 12073198883400676 | 12073198883535555 | 12073198883539231 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f15ff400600 | 0x7f14cf235400 | 0 | 0 | 0 | 12073198883589204 | 12073198883754594 | 12073198884012672 | 12073198884081969 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f15ff400500 | 0x7f14cf235440 | 0 | 0 | 0 | 12073198884108659 | 12073198884293151 | 12073198884549630 | 12073198884617725 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f15ff400400 | 0x7f14cf235480 | 0 | 0 | 0 | 12073198884647951 | 12073198884830748 | 12073198884963707 | 12073198884967214 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f15ff400300 | 0x7f14cf2354c0 | 0 | 0 | 0 | 12073198885020232 | 12073198885190266 | 12073198885366105 | 12073198885369692 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f15ff400a00 | 0x7f14cf235500 | 0 | 0 | 0 | 12073198885436205 | 12073198885597944 | 12073198885728983 | 12073198885732666 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f15ff400900 | 0x7f14cf235540 | 0 | 0 | 0 | 12073198885782890 | 12073198885944822 | 12073198886202741 | 12073198886272790 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f15ff400800 | 0x7f14cf235580 | 0 | 0 | 0 | 12073198886299630 | 12073198886481939 | 12073198886739858 | 12073198886807383 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f15ff400700 | 0x7f14cf2355c0 | 0 | 0 | 0 | 12073198886833121 | 12073198887007697 | 12073198887142096 | 12073198887145812 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f15ff400600 | 0x7f14cf235600 | 0 | 0 | 0 | 12073198887190896 | 12073198887364975 | 12073198887498414 | 12073198887502074 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f15ff400500 | 0x7f14cf235640 | 0 | 0 | 0 | 12073198887565191 | 12073198887725133 | 12073198887852652 | 12073198887856222 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f15ff400400 | 0x7f14cf235680 | 0 | 0 | 0 | 12073198887907307 | 12073198888073931 | 12073198888328330 | 12073198888396095 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f15ff400300 | 0x7f14cf2356c0 | 0 | 0 | 0 | 12073198888422715 | 12073198888600008 | 12073198888853927 | 12073198888921752 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f15ff400a00 | 0x7f14cf235700 | 0 | 0 | 0 | 12073198888947890 | 12073198889131685 | 12073198889264805 | 12073198889268657 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f15ff400900 | 0x7f14cf235740 | 0 | 0 | 0 | 12073198889317958 | 12073198889478404 | 12073198889612323 | 12073198889615952 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f15ff400800 | 0x7f14cf235780 | 0 | 0 | 0 | 12073198889677897 | 12073198889837282 | 12073198889968001 | 12073198889971523 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f15ff400700 | 0x7f14cf2357c0 | 0 | 0 | 0 | 12073198890029530 | 12073198890194240 | 12073198890450878 | 12073198890495707 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f15ff400600 | 0x7f14cf235800 | 0 | 0 | 0 | 12073198890520002 | 12073198890704797 | 12073198890959676 | 12073198891028667 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f15ff400500 | 0x7f14cf235840 | 0 | 0 | 0 | 12073198891053172 | 12073198891231994 | 12073198891366714 | 12073198891370231 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f15ff400400 | 0x7f14cf235880 | 0 | 0 | 0 | 12073198891419393 | 12073198891587512 | 12073198891721912 | 12073198891725542 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f15ff400300 | 0x7f14cf2358c0 | 0 | 0 | 0 | 12073198891787316 | 12073198891945751 | 12073198892081910 | 12073198892085581 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f15ff400a00 | 0x7f14cf235900 | 0 | 0 | 0 | 12073198892135944 | 12073198892301269 | 12073198892598067 | 12073198892667402 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f15ff400900 | 0x7f14cf235940 | 0 | 0 | 0 | 12073198892694081 | 12073198892867506 | 12073198893125424 | 12073198893194611 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f15ff400800 | 0x7f14cf235980 | 0 | 0 | 0 | 12073198893221832 | 12073198893398383 | 12073198893532782 | 12073198893536426 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f15ff400700 | 0x7f14cf2359c0 | 0 | 0 | 0 | 12073198893586129 | 12073198893754381 | 12073198893891980 | 12073198893895664 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f15ff400600 | 0x7f14cf235a00 | 0 | 0 | 0 | 12073198893956557 | 12073198894120619 | 12073198894254538 | 12073198894258648 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f15ff400500 | 0x7f14cf235a40 | 0 | 0 | 0 | 12073198894307389 | 12073198894479817 | 12073198894738216 | 12073198894807037 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f15ff400400 | 0x7f14cf235a80 | 0 | 0 | 0 | 12073198894830631 | 12073198895005894 | 12073198895259653 | 12073198895330109 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f15ff400300 | 0x7f14cf235ac0 | 0 | 0 | 0 | 12073198895352992 | 12073198895535972 | 12073198895667171 | 12073198895670742 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f15ff400a00 | 0x7f14cf235b00 | 0 | 0 | 0 | 12073198895722027 | 12073198895882370 | 12073198896019329 | 12073198896023107 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f15ff400900 | 0x7f14cf235b40 | 0 | 0 | 0 | 12073198896085543 | 12073198896250848 | 12073198896385887 | 12073198896389518 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f15ff400800 | 0x7f14cf235b80 | 0 | 0 | 0 | 12073198896438519 | 12073198896605726 | 12073198896877725 | 12073198896945641 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f15ff400700 | 0x7f14cf235bc0 | 0 | 0 | 0 | 12073198896971639 | 12073198897153883 | 12073198897412122 | 12073198897482479 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f15ff400600 | 0x7f14cf235c00 | 0 | 0 | 0 | 12073198897508246 | 12073198897681080 | 12073198897813080 | 12073198897816720 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f15ff400500 | 0x7f14cf235c40 | 0 | 0 | 0 | 12073198897865360 | 12073198898039958 | 12073198898179958 | 12073198898184002 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f15ff400400 | 0x7f14cf235c80 | 0 | 0 | 0 | 12073198898244665 | 12073198898404756 | 12073198898536116 | 12073198898539663 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f15ff400300 | 0x7f14cf235cc0 | 0 | 0 | 0 | 12073198898588203 | 12073198898759635 | 12073198899031313 | 12073198899100946 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f15ff400a00 | 0x7f14cf235d00 | 0 | 0 | 0 | 12073198899133727 | 12073198899308752 | 12073198899567470 | 12073198899635188 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f15ff400900 | 0x7f14cf235d40 | 0 | 0 | 0 | 12073198899662339 | 12073198899835469 | 12073198899965388 | 12073198899969019 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f15ff400800 | 0x7f14cf235d80 | 0 | 0 | 0 | 12073198900017779 | 12073198900188107 | 12073198900327786 | 12073198900331612 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f15ff400700 | 0x7f14cf235dc0 | 0 | 0 | 0 | 12073198900391353 | 12073198900552585 | 12073198900686024 | 12073198900689778 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f15ff400600 | 0x7f14cf235e00 | 0 | 0 | 0 | 12073198900738589 | 12073198900899623 | 12073198901170502 | 12073198901241714 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f15ff400500 | 0x7f14cf235e40 | 0 | 0 | 0 | 12073198901280075 | 12073198901441060 | 12073198901695939 | 12073198901763764 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f15ff400400 | 0x7f14cf235e80 | 0 | 0 | 0 | 12073198901793409 | 12073198901970818 | 12073198902105857 | 12073198902109887 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f15ff400300 | 0x7f14cf235ec0 | 0 | 0 | 0 | 12073198902158848 | 12073198902328256 | 12073198902465055 | 12073198902468603 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f15ff400a00 | 0x7f14cf235f00 | 0 | 0 | 0 | 12073198902529907 | 12073198902687774 | 12073198902821213 | 12073198902824865 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f15ff400900 | 0x7f14cf235f40 | 0 | 0 | 0 | 12073198902873796 | 12073198903047292 | 12073198903312891 | 12073198903383313 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f15ff400800 | 0x7f14cf235f80 | 0 | 0 | 0 | 12073198903407909 | 12073198903584889 | 12073198903843928 | 12073198903911735 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f15ff400700 | 0x7f14cf235fc0 | 0 | 0 | 0 | 12073198903938254 | 12073198904113686 | 12073198904250006 | 12073198904253860 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f15ff400600 | 0x7f14cf236000 | 0 | 0 | 0 | 12073198904305296 | 12073198904464244 | 12073198904603764 | 12073198904607367 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f15ff400500 | 0x7f14cf236040 | 0 | 0 | 0 | 12073198904668341 | 12073198904825203 | 12073198904958962 | 12073198904962697 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f15ff400400 | 0x7f14cf236080 | 0 | 0 | 0 | 12073198905014784 | 12073198905186641 | 12073198905458479 | 12073198905531084 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f15ff400300 | 0x7f14cf2360c0 | 0 | 0 | 0 | 12073198905553726 | 12073198905730798 | 12073198905989996 | 12073198906077800 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f15ff400a00 | 0x7f14cf236100 | 0 | 0 | 0 | 12073198906101824 | 12073198906285835 | 12073198906420394 | 12073198906424233 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f15ff400900 | 0x7f14cf236140 | 0 | 0 | 0 | 12073198906474186 | 12073198906644553 | 12073198906788712 | 12073198906792427 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f15ff400800 | 0x7f14cf236180 | 0 | 0 | 0 | 12073198906854172 | 12073198907011591 | 12073198907146950 | 12073198907150843 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f15ff400700 | 0x7f14cf2361c0 | 0 | 0 | 0 | 12073198907200355 | 12073198907368869 | 12073198907630468 | 12073198907681048 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f15ff400600 | 0x7f14cf236200 | 0 | 0 | 0 | 12073198907708119 | 12073198907878146 | 12073198908170785 | 12073198908223496 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f15ff400500 | 0x7f14cf236240 | 0 | 0 | 0 | 12073198908246339 | 12073198908426784 | 12073198908561503 | 12073198908565261 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f15ff400400 | 0x7f14cf236280 | 0 | 0 | 0 | 12073198908614232 | 12073198908783582 | 12073198908933661 | 12073198908937303 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f15ff400300 | 0x7f14cf2362c0 | 0 | 0 | 0 | 12073198909028542 | 12073198909189819 | 12073198909321019 | 12073198909324672 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f15ff400a00 | 0x7f14cf236300 | 0 | 0 | 0 | 12073198909377240 | 12073198909542298 | 12073198909806616 | 12073198909830843 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f15ff400900 | 0x7f14cf236340 | 0 | 0 | 0 | 12073198909882549 | 12073198910051255 | 12073198910310134 | 12073198910361930 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f15ff400800 | 0x7f14cf236380 | 0 | 0 | 0 | 12073198910387407 | 12073198910572052 | 12073198910708691 | 12073198910712571 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f15ff400700 | 0x7f14cf2363c0 | 0 | 0 | 0 | 12073198910764879 | 12073198910922130 | 12073198911079569 | 12073198911083551 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f15ff400600 | 0x7f14cf236400 | 0 | 0 | 0 | 12073198911144133 | 12073198911302448 | 12073198911441968 | 12073198911445704 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f15ff400500 | 0x7f14cf236440 | 0 | 0 | 0 | 12073198911492871 | 12073198911662126 | 12073198911931565 | 12073198911981860 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f15ff400400 | 0x7f14cf236480 | 0 | 0 | 0 | 12073198912014400 | 12073198912191244 | 12073198912453162 | 12073198912504551 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f15ff400300 | 0x7f14cf2364c0 | 0 | 0 | 0 | 12073198912529858 | 12073198912703721 | 12073198912842440 | 12073198912846286 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f15ff400a00 | 0x7f14cf236500 | 0 | 0 | 0 | 12073198912893574 | 12073198913066919 | 12073198913233318 | 12073198913237283 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f15ff400900 | 0x7f14cf236540 | 0 | 0 | 0 | 12073198913298346 | 12073198913459557 | 12073198913590916 | 12073198913594616 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f15ff400800 | 0x7f14cf236580 | 0 | 0 | 0 | 12073198913642756 | 12073198913817635 | 12073198914081474 | 12073198914133979 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f15ff400700 | 0x7f14cf2365c0 | 0 | 0 | 0 | 12073198914161480 | 12073198914337632 | 12073198914591871 | 12073198914639608 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f15ff400600 | 0x7f14cf236600 | 0 | 0 | 0 | 12073198914663212 | 12073198914841630 | 12073198914976669 | 12073198914980632 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f15ff400500 | 0x7f14cf236640 | 0 | 0 | 0 | 12073198915029603 | 12073198915207068 | 12073198915380187 | 12073198915384131 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f15ff400400 | 0x7f14cf236680 | 0 | 0 | 0 | 12073198915443852 | 12073198915602426 | 12073198915740345 | 12073198915744371 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f15ff400300 | 0x7f14cf2366c0 | 0 | 0 | 0 | 12073198915791899 | 12073198915958264 | 12073198916218102 | 12073198916250361 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f15ff400a00 | 0x7f14cf236700 | 0 | 0 | 0 | 12073198916290926 | 12073198916450901 | 12073198916709780 | 12073198916736003 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f15ff400900 | 0x7f14cf236740 | 0 | 0 | 0 | 12073198916780556 | 12073198916939059 | 12073198917079058 | 12073198917082908 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f15ff400800 | 0x7f14cf236780 | 0 | 0 | 0 | 12073198917132330 | 12073198917293937 | 12073198917476816 | 12073198917480677 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f15ff400700 | 0x7f14cf2367c0 | 0 | 0 | 0 | 12073198917541921 | 12073198917701295 | 12073198917836334 | 12073198917840155 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f15ff400600 | 0x7f14cf236800 | 0 | 0 | 0 | 12073198917887062 | 12073198918067053 | 12073198918334251 | 12073198918366152 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f15ff400500 | 0x7f14cf236840 | 0 | 0 | 0 | 12073198918403251 | 12073198918565450 | 12073198918822569 | 12073198918848479 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f15ff400400 | 0x7f14cf236880 | 0 | 0 | 0 | 12073198918891348 | 12073198919052967 | 12073198919193767 | 12073198919197808 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f15ff400300 | 0x7f14cf2368c0 | 0 | 0 | 0 | 12073198919252459 | 12073198919409285 | 12073198919601284 | 12073198919627226 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f15ff400a00 | 0x7f14cf236900 | 0 | 0 | 0 | 12073198919682298 | 12073198919841443 | 12073198919979042 | 12073198919982716 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f15ff400900 | 0x7f14cf236940 | 0 | 0 | 0 | 12073198920031226 | 12073198920203201 | 12073198920487200 | 12073198920516929 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f15ff400800 | 0x7f14cf236980 | 0 | 0 | 0 | 12073198920558947 | 12073198920715839 | 12073198920976477 | 12073198921005126 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f15ff400700 | 0x7f14cf2369c0 | 0 | 0 | 0 | 12073198921047334 | 12073198921205436 | 12073198921345275 | 12073198921349025 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f15ff400600 | 0x7f14cf236a00 | 0 | 0 | 0 | 12073198921396984 | 12073198921563034 | 12073198921773113 | 12073198921794062 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f15ff400500 | 0x7f14cf236a40 | 0 | 0 | 0 | 12073198921849665 | 12073198922007832 | 12073198922147831 | 12073198922152087 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f15ff400400 | 0x7f14cf236a80 | 0 | 0 | 0 | 12073198922200617 | 12073198922372790 | 12073198922710868 | 12073198922737024 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f15ff400300 | 0x7f14cf236ac0 | 0 | 0 | 0 | 12073198922780324 | 12073198922935507 | 12073198923196785 | 12073198923223357 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f15ff400a00 | 0x7f14cf236b00 | 0 | 0 | 0 | 12073198923265556 | 12073198923423344 | 12073198923557744 | 12073198923561726 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f15ff400900 | 0x7f14cf236b40 | 0 | 0 | 0 | 12073198923611409 | 12073198923777582 | 12073198924005741 | 12073198924032361 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f15ff400800 | 0x7f14cf236b80 | 0 | 0 | 0 | 12073198924091981 | 12073198924253260 | 12073198924394539 | 12073198924398341 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f15ff400700 | 0x7f14cf236bc0 | 0 | 0 | 0 | 12073198924446550 | 12073198924609258 | 12073198924967016 | 12073198924992785 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f15ff400600 | 0x7f14cf236c00 | 0 | 0 | 0 | 12073198925037839 | 12073198925198215 | 12073198925462374 | 12073198925487404 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f15ff400500 | 0x7f14cf236c40 | 0 | 0 | 0 | 12073198925532538 | 12073198925686852 | 12073198925828452 | 12073198925832295 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f15ff400400 | 0x7f14cf236c80 | 0 | 0 | 0 | 12073198925880595 | 12073198926051170 | 12073198926296289 | 12073198926326083 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f15ff400300 | 0x7f14cf236cc0 | 0 | 0 | 0 | 12073198926379121 | 12073198926538966 | 12073198926676086 | 12073198926683387 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f15ff400a00 | 0x7f14cf236d00 | 0 | 0 | 0 | 12073198926728240 | 12073198926892884 | 12073198927271282 | 12073198927299622 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f15ff400900 | 0x7f14cf236d40 | 0 | 0 | 0 | 12073198927342131 | 12073198927505201 | 12073198927771440 | 12073198927795182 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f15ff400800 | 0x7f14cf236d80 | 0 | 0 | 0 | 12073198927839535 | 12073198927994639 | 12073198928132398 | 12073198928136146 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f15ff400700 | 0x7f14cf236dc0 | 0 | 0 | 0 | 12073198928183694 | 12073198928349197 | 12073198928630156 | 12073198928654860 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f15ff400600 | 0x7f14cf236e00 | 0 | 0 | 0 | 12073198928710523 | 12073198928869995 | 12073198929005194 | 12073198929008647 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f15ff400500 | 0x7f14cf236e40 | 0 | 0 | 0 | 12073198929057037 | 12073198929229353 | 12073198929653511 | 12073198929679844 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f15ff400400 | 0x7f14cf236e80 | 0 | 0 | 0 | 12073198929722123 | 12073198929879110 | 12073198930143269 | 12073198930171468 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f15ff400300 | 0x7f14cf236ec0 | 0 | 0 | 0 | 12073198930214117 | 12073198930375108 | 12073198930516707 | 12073198930520206 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f15ff400a00 | 0x7f14cf236f00 | 0 | 0 | 0 | 12073198930572813 | 12073198930730786 | 12073198931046305 | 12073198931071560 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f15ff400900 | 0x7f14cf236f40 | 0 | 0 | 0 | 12073198931130890 | 12073198931289984 | 12073198931442623 | 12073198931445986 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f15ff400800 | 0x7f14cf236f80 | 0 | 0 | 0 | 12073198931493634 | 12073198931670782 | 12073198932189180 | 12073198932214774 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f15ff400700 | 0x7f14cf236fc0 | 0 | 0 | 0 | 12073198932262713 | 12073198932421339 | 12073198932722297 | 12073198932745931 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f15ff400600 | 0x7f14cf237000 | 0 | 0 | 0 | 12073198932790895 | 12073198932949496 | 12073198933104695 | 12073198933108204 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f15ff400500 | 0x7f14cf237040 | 0 | 0 | 0 | 12073198933159580 | 12073198933319414 | 12073198933705493 | 12073198933730270 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f15ff400400 | 0x7f14cf237080 | 0 | 0 | 0 | 12073198933790192 | 12073198933949652 | 12073198934125491 | 12073198934129332 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f15ff400300 | 0x7f14cf2370c0 | 0 | 0 | 0 | 12073198934177902 | 12073198934349010 | 12073198934959247 | 12073198934984270 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f15ff400a00 | 0x7f14cf237100 | 0 | 0 | 0 | 12073198935035956 | 12073198935193806 | 12073198935522604 | 12073198935547537 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f15ff400900 | 0x7f14cf237140 | 0 | 0 | 0 | 12073198935595696 | 12073198935754603 | 12073198935933483 | 12073198935936800 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f15ff400800 | 0x7f14cf237180 | 0 | 0 | 0 | 12073198935984419 | 12073198936163402 | 12073198936619400 | 12073198936645998 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f15ff400700 | 0x7f14cf2371c0 | 0 | 0 | 0 | 12073198936700630 | 12073198936861478 | 12073198937061638 | 12073198937090644 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f15ff400600 | 0x7f14cf237200 | 0 | 0 | 0 | 12073198937122754 | 12073198937295716 | 12073198938000033 | 12073198938027264 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f15ff400500 | 0x7f14cf237240 | 0 | 0 | 0 | 12073198938069673 | 12073198938227552 | 12073198938601151 | 12073198938626548 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f15ff400400 | 0x7f14cf237280 | 0 | 0 | 0 | 12073198938669748 | 12073198938827550 | 12073198939030589 | 12073198939056457 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f15ff400300 | 0x7f14cf2372c0 | 0 | 0 | 0 | 12073198939100909 | 12073198939258428 | 12073198939785465 | 12073198939812031 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f15ff400a00 | 0x7f14cf237300 | 0 | 0 | 0 | 12073198939867263 | 12073198940033464 | 12073198940257463 | 12073198940282244 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f15ff400900 | 0x7f14cf237340 | 0 | 0 | 0 | 12073198940326577 | 12073198940484182 | 12073198941285298 | 12073198941311627 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f15ff400800 | 0x7f14cf237380 | 0 | 0 | 0 | 12073198941354427 | 12073198941513777 | 12073198941932335 | 12073198941959932 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f15ff400700 | 0x7f14cf2373c0 | 0 | 0 | 0 | 12073198942010716 | 12073198942168014 | 12073198942393933 | 12073198942422471 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f15ff400600 | 0x7f14cf237400 | 0 | 0 | 0 | 12073198942467515 | 12073198942622412 | 12073198943219530 | 12073198943271138 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f15ff400500 | 0x7f14cf237440 | 0 | 0 | 0 | 12073198943315200 | 12073198943472968 | 12073198943742727 | 12073198943790543 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f15ff400400 | 0x7f14cf237480 | 0 | 0 | 0 | 12073198943816221 | 12073198943990406 | 12073198944975682 | 12073198945047118 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f15ff400300 | 0x7f14cf2374c0 | 0 | 0 | 0 | 12073198945078887 | 12073198945251680 | 12073198945769438 | 12073198945837276 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f15ff400a00 | 0x7f14cf237500 | 0 | 0 | 0 | 12073198945864176 | 12073198946041277 | 12073198946314076 | 12073198946384453 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f15ff400900 | 0x7f14cf237540 | 0 | 0 | 0 | 12073198946408177 | 12073198946587354 | 12073198947325911 | 12073198947395472 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f15ff400800 | 0x7f14cf237580 | 0 | 0 | 0 | 12073198947440345 | 12073198947600630 | 12073198947917268 | 12073198947985308 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f15ff400700 | 0x7f14cf2375c0 | 0 | 0 | 0 | 12073198948019261 | 12073198948197107 | 12073198949369262 | 12073198949440391 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f15ff400600 | 0x7f14cf237600 | 0 | 0 | 0 | 12073198949469305 | 12073198949652300 | 12073198950262698 | 12073198950332769 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f15ff400500 | 0x7f14cf237640 | 0 | 0 | 0 | 12073198950362725 | 12073198950540616 | 12073198950859655 | 12073198950901706 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f15ff400400 | 0x7f14cf237680 | 0 | 0 | 0 | 12073198950928376 | 12073198951116934 | 12073198951995010 | 12073198952066541 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f15ff400300 | 0x7f14cf2376c0 | 0 | 0 | 0 | 12073198952100825 | 12073198952264609 | 12073198952698047 | 12073198952765810 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f15ff400a00 | 0x7f14cf237700 | 0 | 0 | 0 | 12073198952796818 | 12073198952972285 | 12073198954520438 | 12073198954591322 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f15ff400900 | 0x7f14cf237740 | 0 | 0 | 0 | 12073198954622540 | 12073198954792437 | 12073198955587794 | 12073198955658645 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f15ff400800 | 0x7f14cf237780 | 0 | 0 | 0 | 12073198955686707 | 12073198955865712 | 12073198956280910 | 12073198956350371 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f15ff400700 | 0x7f14cf2377c0 | 0 | 0 | 0 | 12073198956381559 | 12073198956558029 | 12073198957716584 | 12073198957786108 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f15ff400600 | 0x7f14cf237800 | 0 | 0 | 0 | 12073198957832234 | 12073198957991623 | 12073198958778019 | 12073198958849494 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f15ff400500 | 0x7f14cf237840 | 0 | 0 | 0 | 12073198958872617 | 12073198959055938 | 12073198962104884 | 12073198962175093 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f15ff400400 | 0x7f14cf237880 | 0 | 0 | 0 | 12073198962208225 | 12073198962391923 | 12073198963934636 | 12073198964012377 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f15ff400300 | 0x7f14cf2378c0 | 0 | 0 | 0 | 12073198964029529 | 12073198964221035 | 12073198965010631 | 12073198965079530 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f15ff400a00 | 0x7f14cf237900 | 0 | 0 | 0 | 12073198965111449 | 12073198965288710 | 12073198967570139 | 12073198967639677 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f15ff400900 | 0x7f14cf237940 | 0 | 0 | 0 | 12073198967684010 | 12073198967844858 | 12073198969380051 | 12073198969450542 |
| 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 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f15ff400800 | 0x7f14cf237980 | 0 | 0 | 0 | 12073198969483253 | 12073198969657810 | 12073198975714102 | 12073198975784150 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f15ff400700 | 0x7f14cf2379c0 | 0 | 0 | 0 | 12073198975815358 | 12073198975992181 | 12073198979033927 | 12073198979107455 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f15ff400600 | 0x7f14cf237a00 | 0 | 0 | 0 | 12073198979135848 | 12073198979311686 | 12073198980851039 | 12073198980920875 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 748123 | 748128 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f15ff400500 | 0x7f14cf237a40 | 0 | 0 | 0 | 12073198980946092 | 12073198981133758 | 12073198985660937 | 12073198985735170 |