43 KiB
43 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 910940 | 910945 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7fbb29204180 | 4194304 | 3072326 | 393422784 | 12076131878204691 | 12076132121676698 | 12076132122000377 | 12076132122110910 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 910940 | 910945 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7fbb29235100 | 512 | 21876 | 2797384 | 12076132136823112 | 12076132137121587 | 12076132137127667 | 12076132137132998 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7fbc34dd9900 | 0x7fbb29235140 | 65536 | 180780 | 23110632 | 12076132137192027 | 12076132137407986 | 12076132137546225 | 12076132137550373 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7fbc34dd9800 | 0x7fbb29235180 | 65536 | 138384 | 17823328 | 12076132137616045 | 12076132137790704 | 12076132138041903 | 12076132138110684 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7fbc34dd9700 | 0x7fbb292351c0 | 65536 | 153584 | 19582720 | 12076132138143586 | 12076132138331342 | 12076132138589741 | 12076132138656970 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7fbc34dd9600 | 0x7fbb29235200 | 65536 | 152318 | 19473080 | 12076132138683890 | 12076132138861579 | 12076132139002219 | 12076132139006309 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7fbc34dd9500 | 0x7fbb29235240 | 65536 | 172994 | 22170000 | 12076132139057133 | 12076132139229418 | 12076132139370057 | 12076132139374393 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7fbc34dd9400 | 0x7fbb29235280 | 131072 | 233910 | 29939832 | 12076132139451496 | 12076132139618696 | 12076132139751975 | 12076132139755872 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7fbc34dd9300 | 0x7fbb292352c0 | 131072 | 200292 | 25575320 | 12076132139803631 | 12076132139978054 | 12076132140231493 | 12076132140274606 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7fbc34dd9a00 | 0x7fbb29235300 | 65536 | 151592 | 19355152 | 12076132140301215 | 12076132140482052 | 12076132140740131 | 12076132140782059 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7fbc34dd9900 | 0x7fbb29235340 | 131072 | 255818 | 32979328 | 12076132140805242 | 12076132140997250 | 12076132141129889 | 12076132141133873 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7fbc34dd9800 | 0x7fbb29235380 | 131072 | 230210 | 29437200 | 12076132141180049 | 12076132141359328 | 12076132141499327 | 12076132141503450 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7fbc34dd9700 | 0x7fbb292353c0 | 131072 | 222944 | 28551960 | 12076132141565756 | 12076132141726206 | 12076132141856286 | 12076132141860043 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7fbc34dd9600 | 0x7fbb29235400 | 131072 | 185606 | 23849872 | 12076132141911709 | 12076132142078045 | 12076132142339164 | 12076132142383085 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7fbc34dd9500 | 0x7fbb29235440 | 65536 | 180220 | 22985112 | 12076132142412189 | 12076132142594202 | 12076132142849881 | 12076132142890798 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7fbc34dd9400 | 0x7fbb29235480 | 131072 | 228436 | 29049760 | 12076132142917267 | 12076132143104440 | 12076132143235319 | 12076132143239216 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7fbc34dd9300 | 0x7fbb292354c0 | 131072 | 221800 | 28237176 | 12076132143290942 | 12076132143455798 | 12076132143593558 | 12076132143597411 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7fbc34dd9a00 | 0x7fbb29235500 | 131072 | 228972 | 29374800 | 12076132143657974 | 12076132143821717 | 12076132143950356 | 12076132143954054 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7fbc34dd9900 | 0x7fbb29235540 | 131072 | 182016 | 23384320 | 12076132144016240 | 12076132144179475 | 12076132144440434 | 12076132144506641 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7fbc34dd9800 | 0x7fbb29235580 | 65536 | 151292 | 19313408 | 12076132144530626 | 12076132144714673 | 12076132144971312 | 12076132145038479 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7fbc34dd9700 | 0x7fbb292355c0 | 131072 | 217318 | 27682952 | 12076132145064959 | 12076132145246350 | 12076132145376430 | 12076132145380165 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7fbc34dd9600 | 0x7fbb29235600 | 131072 | 235506 | 30241400 | 12076132145428715 | 12076132145595149 | 12076132145735628 | 12076132145739232 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7fbc34dd9500 | 0x7fbb29235640 | 131072 | 261628 | 33424512 | 12076132145798462 | 12076132145957547 | 12076132146090186 | 12076132146094182 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7fbc34dd9400 | 0x7fbb29235680 | 131072 | 181114 | 23184528 | 12076132146145347 | 12076132146307145 | 12076132146569224 | 12076132146612334 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7fbc34dd9300 | 0x7fbb292356c0 | 65536 | 149790 | 19148952 | 12076132146637942 | 12076132146812743 | 12076132147106502 | 12076132147173457 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7fbc34dd9a00 | 0x7fbb29235700 | 131072 | 236670 | 30280568 | 12076132147199375 | 12076132147376261 | 12076132147505060 | 12076132147508690 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7fbc34dd9900 | 0x7fbb29235740 | 131072 | 224204 | 28710768 | 12076132147560146 | 12076132147725379 | 12076132147865538 | 12076132147869300 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7fbc34dd9800 | 0x7fbb29235780 | 131072 | 223734 | 28571344 | 12076132147927909 | 12076132148094017 | 12076132148226017 | 12076132148229720 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7fbc34dd9700 | 0x7fbb292357c0 | 131072 | 184856 | 23791536 | 12076132148278070 | 12076132148456096 | 12076132148710655 | 12076132148778190 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7fbc34dd9600 | 0x7fbb29235800 | 65536 | 177898 | 22852504 | 12076132148802775 | 12076132148981213 | 12076132149239932 | 12076132149307974 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7fbc34dd9500 | 0x7fbb29235840 | 131072 | 231578 | 29595048 | 12076132149331909 | 12076132149511451 | 12076132149640730 | 12076132149644379 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7fbc34dd9400 | 0x7fbb29235880 | 131072 | 226464 | 28911584 | 12076132149692879 | 12076132149854329 | 12076132149984249 | 12076132149988178 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7fbc34dd9300 | 0x7fbb292358c0 | 131072 | 232212 | 29717216 | 12076132150049061 | 12076132150211128 | 12076132150344247 | 12076132150348388 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7fbc34dd9a00 | 0x7fbb29235900 | 131072 | 211950 | 27194872 | 12076132150399403 | 12076132150562486 | 12076132150822485 | 12076132150865278 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7fbc34dd9900 | 0x7fbb29235940 | 65536 | 153500 | 19619816 | 12076132150891046 | 12076132151073204 | 12076132151328403 | 12076132151395834 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7fbc34dd9800 | 0x7fbb29235980 | 131072 | 255802 | 32754880 | 12076132151422013 | 12076132151602801 | 12076132151737041 | 12076132151740886 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7fbc34dd9700 | 0x7fbb292359c0 | 131072 | 230826 | 29522616 | 12076132151788454 | 12076132151955120 | 12076132152091759 | 12076132152096126 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7fbc34dd9600 | 0x7fbb29235a00 | 131072 | 220394 | 28291960 | 12076132152158321 | 12076132152320718 | 12076132152452878 | 12076132152456716 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7fbc34dd9500 | 0x7fbb29235a40 | 131072 | 175666 | 22497928 | 12076132152504214 | 12076132152670637 | 12076132152929355 | 12076132152996369 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7fbc34dd9400 | 0x7fbb29235a80 | 65536 | 143316 | 18384288 | 12076132153018740 | 12076132153209674 | 12076132153464393 | 12076132153532856 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7fbc34dd9300 | 0x7fbb29235ac0 | 131072 | 231258 | 29703992 | 12076132153559095 | 12076132153733672 | 12076132153861191 | 12076132153864983 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7fbc34dd9a00 | 0x7fbb29235b00 | 131072 | 252346 | 32407520 | 12076132153913022 | 12076132154081350 | 12076132154261349 | 12076132154265457 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7fbc34dd9900 | 0x7fbb29235b40 | 131072 | 258922 | 32945264 | 12076132154369872 | 12076132154601668 | 12076132154730467 | 12076132154734639 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7fbc34dd9800 | 0x7fbb29235b80 | 131072 | 186270 | 23737888 | 12076132154777309 | 12076132154977186 | 12076132155247585 | 12076132155317092 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7fbc34dd9700 | 0x7fbb29235bc0 | 65536 | 148530 | 19040576 | 12076132155378366 | 12076132155597023 | 12076132155854622 | 12076132155922357 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7fbc34dd9600 | 0x7fbb29235c00 | 131072 | 229132 | 29237856 | 12076132155982769 | 12076132156206780 | 12076132156343420 | 12076132156347497 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7fbc34dd9500 | 0x7fbb29235c40 | 131072 | 233500 | 29967168 | 12076132156407078 | 12076132156578139 | 12076132156758298 | 12076132156762127 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7fbc34dd9400 | 0x7fbb29235c80 | 131072 | 218404 | 27972480 | 12076132156827238 | 12076132156992857 | 12076132157121816 | 12076132157126274 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7fbc34dd9300 | 0x7fbb29235cc0 | 131072 | 184988 | 23616288 | 12076132157180765 | 12076132157343575 | 12076132157610774 | 12076132157678681 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7fbc34dd9a00 | 0x7fbb29235d00 | 65536 | 178590 | 22757232 | 12076132157733523 | 12076132157948533 | 12076132158206771 | 12076132158277003 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7fbc34dd9900 | 0x7fbb29235d40 | 131072 | 225476 | 28997168 | 12076132158339158 | 12076132158556370 | 12076132158692529 | 12076132158696492 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7fbc34dd9800 | 0x7fbb29235d80 | 131072 | 266322 | 34042592 | 12076132158754620 | 12076132158922928 | 12076132159066287 | 12076132159070688 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7fbc34dd9700 | 0x7fbb29235dc0 | 131072 | 231458 | 29540304 | 12076132159134637 | 12076132159300046 | 12076132159438126 | 12076132159442048 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7fbc34dd9600 | 0x7fbb29235e00 | 131072 | 226016 | 29015240 | 12076132159500867 | 12076132159663085 | 12076132159919244 | 12076132159986229 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7fbc34dd9500 | 0x7fbb29235e40 | 65536 | 151176 | 19325360 | 12076132160019231 | 12076132160200842 | 12076132160459241 | 12076132160527555 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7fbc34dd9400 | 0x7fbb29235e80 | 131072 | 226174 | 28851368 | 12076132160558974 | 12076132160739400 | 12076132160875399 | 12076132160879349 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7fbc34dd9300 | 0x7fbb29235ec0 | 131072 | 226608 | 28932968 | 12076132160929502 | 12076132161105158 | 12076132161247718 | 12076132161251811 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7fbc34dd9a00 | 0x7fbb29235f00 | 131072 | 225846 | 28963816 | 12076132161312314 | 12076132161473157 | 12076132161605796 | 12076132161609676 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7fbc34dd9900 | 0x7fbb29235f40 | 131072 | 226430 | 28936736 | 12076132161658768 | 12076132161821955 | 12076132162083074 | 12076132162152365 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7fbc34dd9800 | 0x7fbb29235f80 | 65536 | 182420 | 23265304 | 12076132162179575 | 12076132162355713 | 12076132162614271 | 12076132162682751 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7fbc34dd9700 | 0x7fbb29235fc0 | 131072 | 232802 | 29672888 | 12076132162707517 | 12076132162882750 | 12076132163014910 | 12076132163018915 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7fbc34dd9600 | 0x7fbb29236000 | 131072 | 224140 | 28838760 | 12076132163067626 | 12076132163236349 | 12076132163374908 | 12076132163378744 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7fbc34dd9500 | 0x7fbb29236040 | 131072 | 231464 | 29483880 | 12076132163441871 | 12076132163598747 | 12076132163731546 | 12076132163735567 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7fbc34dd9400 | 0x7fbb29236080 | 131072 | 210590 | 27042120 | 12076132163783136 | 12076132163954905 | 12076132164224184 | 12076132164291811 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7fbc34dd9300 | 0x7fbb292360c0 | 65536 | 143426 | 18291648 | 12076132164313020 | 12076132164477143 | 12076132164732182 | 12076132164800045 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7fbc34dd9a00 | 0x7fbb29236100 | 131072 | 258048 | 32943888 | 12076132164820554 | 12076132164978421 | 12076132165118900 | 12076132165123216 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7fbc34dd9900 | 0x7fbb29236140 | 131072 | 182820 | 23409928 | 12076132165169131 | 12076132165316819 | 12076132165461298 | 12076132165465402 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7fbc34dd9800 | 0x7fbb29236180 | 131072 | 225708 | 29047440 | 12076132165525213 | 12076132165658738 | 12076132165788657 | 12076132165792610 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7fbc34dd9700 | 0x7fbb292361c0 | 131072 | 184202 | 23579920 | 12076132165837904 | 12076132165981456 | 12076132166253135 | 12076132166305253 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7fbc34dd9600 | 0x7fbb29236200 | 65536 | 170004 | 21644608 | 12076132166326823 | 12076132166488494 | 12076132166754093 | 12076132166803038 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7fbc34dd9500 | 0x7fbb29236240 | 131072 | 224256 | 28589520 | 12076132166825880 | 12076132166981131 | 12076132167115531 | 12076132167120057 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7fbc34dd9400 | 0x7fbb29236280 | 131072 | 180804 | 23248048 | 12076132167168527 | 12076132167316010 | 12076132167465449 | 12076132167469376 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7fbc34dd9300 | 0x7fbb292362c0 | 131072 | 227118 | 29082792 | 12076132167542132 | 12076132167679528 | 12076132167812808 | 12076132167816712 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7fbc34dd9a00 | 0x7fbb29236300 | 131072 | 183726 | 23451376 | 12076132167862357 | 12076132168011527 | 12076132168280486 | 12076132168329705 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7fbc34dd9900 | 0x7fbb29236340 | 65536 | 151324 | 19332432 | 12076132168351386 | 12076132168509925 | 12076132168768483 | 12076132168819245 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7fbc34dd9800 | 0x7fbb29236380 | 131072 | 211268 | 27202024 | 12076132168839843 | 12076132168998402 | 12076132169135362 | 12076132169139640 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7fbc34dd9700 | 0x7fbb292363c0 | 131072 | 222170 | 28443448 | 12076132169185706 | 12076132169332001 | 12076132169488960 | 12076132169493067 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7fbc34dd9600 | 0x7fbb29236400 | 131072 | 226976 | 29075136 | 12076132169552598 | 12076132169683359 | 12076132169816799 | 12076132169820646 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7fbc34dd9500 | 0x7fbb29236440 | 131072 | 176688 | 22588632 | 12076132169866030 | 12076132170021278 | 12076132170289596 | 12076132170341484 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7fbc34dd9400 | 0x7fbb29236480 | 65536 | 178048 | 22782032 | 12076132170361822 | 12076132170520155 | 12076132170818394 | 12076132170866600 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7fbc34dd9300 | 0x7fbb292364c0 | 131072 | 226634 | 29113320 | 12076132170888230 | 12076132171052153 | 12076132171193592 | 12076132171197605 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7fbc34dd9a00 | 0x7fbb29236500 | 131072 | 227960 | 29136856 | 12076132171242829 | 12076132171398231 | 12076132171563671 | 12076132171567513 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7fbc34dd9900 | 0x7fbb29236540 | 131072 | 245820 | 31434312 | 12076132171626422 | 12076132171763510 | 12076132171891509 | 12076132171895723 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7fbc34dd9800 | 0x7fbb29236580 | 131072 | 186708 | 23931248 | 12076132171938692 | 12076132172095028 | 12076132172362707 | 12076132172411281 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7fbc34dd9700 | 0x7fbb292365c0 | 65536 | 177492 | 22753896 | 12076132172432079 | 12076132172589906 | 12076132172847825 | 12076132172896242 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7fbc34dd9600 | 0x7fbb29236600 | 131072 | 225044 | 28598888 | 12076132172917762 | 12076132173080784 | 12076132173219023 | 12076132173223119 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7fbc34dd9500 | 0x7fbb29236640 | 131072 | 224008 | 28763552 | 12076132173269716 | 12076132173414702 | 12076132173587981 | 12076132173591955 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7fbc34dd9400 | 0x7fbb29236680 | 131072 | 236174 | 30164496 | 12076132173652397 | 12076132173783501 | 12076132173922860 | 12076132173926717 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7fbc34dd9300 | 0x7fbb292366c0 | 131072 | 181892 | 23305664 | 12076132173973764 | 12076132174126219 | 12076132174389098 | 12076132174438328 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7fbc34dd9a00 | 0x7fbb29236700 | 65536 | 153442 | 19676784 | 12076132174460259 | 12076132174613097 | 12076132174909895 | 12076132174957022 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7fbc34dd9900 | 0x7fbb29236740 | 131072 | 217592 | 28165576 | 12076132174977339 | 12076132175149894 | 12076132175290854 | 12076132175294810 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7fbc34dd9800 | 0x7fbb29236780 | 131072 | 223826 | 28602168 | 12076132175340865 | 12076132175491973 | 12076132175674532 | 12076132175678422 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7fbc34dd9700 | 0x7fbb292367c0 | 131072 | 219612 | 28094352 | 12076132175738975 | 12076132175871651 | 12076132176009730 | 12076132176013916 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7fbc34dd9600 | 0x7fbb29236800 | 131072 | 226218 | 28832352 | 12076132176059411 | 12076132176204290 | 12076132176468288 | 12076132176493658 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7fbc34dd9500 | 0x7fbb29236840 | 65536 | 142250 | 18274424 | 12076132176533672 | 12076132176666367 | 12076132176925566 | 12076132176948823 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7fbc34dd9400 | 0x7fbb29236880 | 131072 | 224456 | 28711280 | 12076132176989459 | 12076132177129245 | 12076132177263325 | 12076132177267746 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7fbc34dd9300 | 0x7fbb292368c0 | 131072 | 211970 | 27237592 | 12076132177313090 | 12076132177459324 | 12076132177650683 | 12076132177675394 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7fbc34dd9a00 | 0x7fbb29236900 | 131072 | 223584 | 28690448 | 12076132177727591 | 12076132177860282 | 12076132177995161 | 12076132177999376 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7fbc34dd9900 | 0x7fbb29236940 | 131072 | 226720 | 29113688 | 12076132178046123 | 12076132178198520 | 12076132178514039 | 12076132178542225 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7fbc34dd9800 | 0x7fbb29236980 | 65536 | 147694 | 18903112 | 12076132178578262 | 12076132178728278 | 12076132178992117 | 12076132179021105 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7fbc34dd9700 | 0x7fbb292369c0 | 131072 | 229494 | 29408024 | 12076132179061800 | 12076132179194356 | 12076132179333075 | 12076132179337202 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7fbc34dd9600 | 0x7fbb29236a00 | 131072 | 224936 | 28867616 | 12076132179381444 | 12076132179525714 | 12076132179735314 | 12076132179757333 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7fbc34dd9500 | 0x7fbb29236a40 | 131072 | 226640 | 28922912 | 12076132179810522 | 12076132179943473 | 12076132180080432 | 12076132180084611 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7fbc34dd9400 | 0x7fbb29236a80 | 131072 | 226316 | 28797280 | 12076132180130627 | 12076132180277391 | 12076132180583630 | 12076132180607944 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7fbc34dd9300 | 0x7fbb29236ac0 | 65536 | 148350 | 18974968 | 12076132180646886 | 12076132180777069 | 12076132181034668 | 12076132181062799 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7fbc34dd9a00 | 0x7fbb29236b00 | 131072 | 222238 | 28529088 | 12076132181103926 | 12076132181246987 | 12076132181389386 | 12076132181393504 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7fbc34dd9900 | 0x7fbb29236b40 | 131072 | 225690 | 28934832 | 12076132181436874 | 12076132181587625 | 12076132181815944 | 12076132181841025 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7fbc34dd9800 | 0x7fbb29236b80 | 131072 | 224228 | 28716112 | 12076132181895346 | 12076132182032903 | 12076132182172262 | 12076132182176619 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7fbc34dd9700 | 0x7fbb29236bc0 | 131072 | 221308 | 28436128 | 12076132182221673 | 12076132182371942 | 12076132182701380 | 12076132182727443 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7fbc34dd9600 | 0x7fbb29236c00 | 65536 | 177914 | 22802400 | 12076132182767307 | 12076132182897379 | 12076132183156418 | 12076132183184332 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7fbc34dd9500 | 0x7fbb29236c40 | 131072 | 226896 | 29075080 | 12076132183223485 | 12076132183356737 | 12076132183497056 | 12076132183501020 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7fbc34dd9400 | 0x7fbb29236c80 | 131072 | 219358 | 27929184 | 12076132183545183 | 12076132183692256 | 12076132183937054 | 12076132183958430 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7fbc34dd9300 | 0x7fbb29236cc0 | 131072 | 230208 | 29346040 | 12076132184020516 | 12076132184155453 | 12076132184291773 | 12076132184295797 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7fbc34dd9a00 | 0x7fbb29236d00 | 131072 | 221338 | 28674760 | 12076132184340911 | 12076132184493224 | 12076132184868743 | 12076132184896594 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7fbc34dd9900 | 0x7fbb29236d40 | 65536 | 150994 | 19321856 | 12076132184934474 | 12076132185079941 | 12076132185346340 | 12076132185371296 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7fbc34dd9800 | 0x7fbb29236d80 | 131072 | 226750 | 29068584 | 12076132185416130 | 12076132185549219 | 12076132185683619 | 12076132185687073 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7fbc34dd9700 | 0x7fbb29236dc0 | 131072 | 230710 | 29501328 | 12076132185732377 | 12076132185876098 | 12076132186156897 | 12076132186185720 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7fbc34dd9600 | 0x7fbb29236e00 | 131072 | 225486 | 28935832 | 12076132186235813 | 12076132186370656 | 12076132186515615 | 12076132186519129 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7fbc34dd9500 | 0x7fbb29236e40 | 131072 | 224506 | 28668560 | 12076132186564003 | 12076132186708095 | 12076132187154653 | 12076132187179577 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7fbc34dd9400 | 0x7fbb29236e80 | 65536 | 176660 | 22647528 | 12076132187220172 | 12076132187352732 | 12076132187621531 | 12076132187645012 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7fbc34dd9300 | 0x7fbb29236ec0 | 131072 | 223374 | 28481128 | 12076132187683824 | 12076132187811931 | 12076132187953050 | 12076132187956491 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7fbc34dd9a00 | 0x7fbb29236f00 | 131072 | 245052 | 31145848 | 12076132188007726 | 12076132188162329 | 12076132188476568 | 12076132188504159 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7fbc34dd9900 | 0x7fbb29236f40 | 131072 | 222480 | 28476904 | 12076132188555454 | 12076132188686967 | 12076132188838487 | 12076132188841906 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7fbc34dd9800 | 0x7fbb29236f80 | 131072 | 245500 | 31307152 | 12076132188887130 | 12076132189040246 | 12076132189557204 | 12076132189581150 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7fbc34dd9700 | 0x7fbb29236fc0 | 65536 | 146142 | 18747960 | 12076132189621345 | 12076132189757683 | 12076132190055602 | 12076132190081169 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7fbc34dd9600 | 0x7fbb29237000 | 131072 | 227130 | 28957304 | 12076132190120863 | 12076132190254642 | 12076132190409201 | 12076132190412876 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7fbc34dd9500 | 0x7fbb29237040 | 131072 | 225940 | 29043824 | 12076132190456076 | 12076132190611760 | 12076132190998159 | 12076132191024543 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7fbc34dd9400 | 0x7fbb29237080 | 131072 | 226346 | 28913480 | 12076132191080737 | 12076132191216718 | 12076132191392717 | 12076132191396143 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7fbc34dd9300 | 0x7fbb292370c0 | 131072 | 225458 | 28608064 | 12076132191438913 | 12076132191587277 | 12076132192198634 | 12076132192223341 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7fbc34dd9a00 | 0x7fbb29237100 | 65536 | 145598 | 18541152 | 12076132192265809 | 12076132192400074 | 12076132192725672 | 12076132192748486 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7fbc34dd9900 | 0x7fbb29237140 | 131072 | 225354 | 28847376 | 12076132192788571 | 12076132192922152 | 12076132193099751 | 12076132193103246 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7fbc34dd9800 | 0x7fbb29237180 | 131072 | 223830 | 28731040 | 12076132193150253 | 12076132193306150 | 12076132193761988 | 12076132193787327 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7fbc34dd9700 | 0x7fbb292371c0 | 131072 | 232864 | 29723208 | 12076132193839204 | 12076132193972228 | 12076132194171427 | 12076132194198942 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7fbc34dd9600 | 0x7fbb29237200 | 131072 | 196174 | 25113536 | 12076132194238606 | 12076132194373986 | 12076132195076384 | 12076132195102481 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7fbc34dd9500 | 0x7fbb29237240 | 65536 | 151016 | 19262656 | 12076132195139169 | 12076132195291423 | 12076132195663901 | 12076132195688270 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7fbc34dd9400 | 0x7fbb29237280 | 131072 | 228110 | 29144592 | 12076132195727503 | 12076132195857661 | 12076132196061500 | 12076132196086670 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7fbc34dd9300 | 0x7fbb292372c0 | 131072 | 234894 | 29928304 | 12076132196131494 | 12076132196263579 | 12076132196806457 | 12076132196831474 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7fbc34dd9a00 | 0x7fbb29237300 | 131072 | 247212 | 31647160 | 12076132196884904 | 12076132197024376 | 12076132197248216 | 12076132197276211 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7fbc34dd9900 | 0x7fbb29237340 | 131072 | 227100 | 28955456 | 12076132197312969 | 12076132197453015 | 12076132198251092 | 12076132198277742 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7fbc34dd9800 | 0x7fbb29237380 | 65536 | 169566 | 21656968 | 12076132198311986 | 12076132198455251 | 12076132198877009 | 12076132198898706 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7fbc34dd9700 | 0x7fbb292373c0 | 131072 | 235532 | 30065712 | 12076132198945453 | 12076132199086129 | 12076132199312688 | 12076132199340758 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7fbc34dd9600 | 0x7fbb29237400 | 131072 | 260146 | 33722696 | 12076132199386934 | 12076132199519407 | 12076132200115245 | 12076132200164589 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7fbc34dd9500 | 0x7fbb29237440 | 131072 | 223174 | 28746800 | 12076132200202990 | 12076132200342924 | 12076132200613163 | 12076132200662093 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7fbc34dd9400 | 0x7fbb29237480 | 131072 | 224968 | 28850672 | 12076132200689414 | 12076132200842922 | 12076132201827078 | 12076132201877863 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7fbc34dd9300 | 0x7fbb292374c0 | 65536 | 153944 | 19505248 | 12076132201900976 | 12076132202056198 | 12076132202571236 | 12076132202621455 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7fbc34dd9a00 | 0x7fbb29237500 | 131072 | 257798 | 32990584 | 12076132202645209 | 12076132202798915 | 12076132203069954 | 12076132203119080 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7fbc34dd9900 | 0x7fbb29237540 | 131072 | 241354 | 30796160 | 12076132203140650 | 12076132203295873 | 12076132204033950 | 12076132204101886 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7fbc34dd9800 | 0x7fbb29237580 | 131072 | 214738 | 27592672 | 12076132204140708 | 12076132204281949 | 12076132204599068 | 12076132204665584 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7fbc34dd9700 | 0x7fbb292375c0 | 131072 | 226632 | 29110096 | 12076132204685200 | 12076132204839227 | 12076132206009303 | 12076132206090953 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7fbc34dd9600 | 0x7fbb29237600 | 65536 | 173128 | 22127296 | 12076132206115238 | 12076132206280982 | 12076132206890100 | 12076132206956401 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7fbc34dd9500 | 0x7fbb29237640 | 131072 | 228632 | 29351016 | 12076132206977771 | 12076132207150099 | 12076132207471057 | 12076132207537391 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7fbc34dd9400 | 0x7fbb29237680 | 131072 | 222962 | 28767560 | 12076132207557548 | 12076132207712017 | 12076132208589933 | 12076132208656551 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7fbc34dd9300 | 0x7fbb292376c0 | 131072 | 222358 | 28626376 | 12076132208691546 | 12076132208843532 | 12076132209276171 | 12076132209347605 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7fbc34dd9a00 | 0x7fbb29237700 | 131072 | 225516 | 28718792 | 12076132209370027 | 12076132209529610 | 12076132211076324 | 12076132211144485 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7fbc34dd9900 | 0x7fbb29237740 | 65536 | 151060 | 19385952 | 12076132211170052 | 12076132211325123 | 12076132212120160 | 12076132212190428 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7fbc34dd9800 | 0x7fbb29237780 | 131072 | 261682 | 33189960 | 12076132212215796 | 12076132212374879 | 12076132212788958 | 12076132212855394 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7fbc34dd9700 | 0x7fbb292377c0 | 131072 | 229702 | 29371856 | 12076132212876283 | 12076132213039517 | 12076132214197752 | 12076132214267689 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7fbc34dd9600 | 0x7fbb29237800 | 131072 | 225632 | 28854696 | 12076132214308034 | 12076132214442551 | 12076132215228309 | 12076132215298244 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7fbc34dd9500 | 0x7fbb29237840 | 131072 | 208964 | 26532968 | 12076132215327999 | 12076132215480788 | 12076132218530376 | 12076132218599199 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7fbc34dd9400 | 0x7fbb29237880 | 65536 | 177958 | 22696128 | 12076132218623123 | 12076132218782695 | 12076132220323330 | 12076132220393784 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7fbc34dd9300 | 0x7fbb292378c0 | 131072 | 230336 | 29395192 | 12076132220419281 | 12076132220582849 | 12076132221372126 | 12076132221440349 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7fbc34dd9a00 | 0x7fbb29237900 | 131072 | 228164 | 29178208 | 12076132221467550 | 12076132221629405 | 12076132223909716 | 12076132223977945 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7fbc34dd9900 | 0x7fbb29237940 | 131072 | 234990 | 29918400 | 12076132224021556 | 12076132224170515 | 12076132225706510 | 12076132225774514 |
| 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 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7fbc34dd9800 | 0x7fbb29237980 | 131072 | 265282 | 33822616 | 12076132225805000 | 12076132225959949 | 12076132232012566 | 12076132232085593 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7fbc34dd9700 | 0x7fbb292379c0 | 65536 | 177346 | 22940192 | 12076132232110399 | 12076132232274485 | 12076132235315114 | 12076132235386026 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7fbc34dd9600 | 0x7fbb29237a00 | 131072 | 220226 | 28148608 | 12076132235410692 | 12076132235570313 | 12076132237109507 | 12076132237178077 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 910940 | 910945 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7fbc34dd9500 | 0x7fbb29237a40 | 131072 | 250242 | 31984168 | 12076132237206470 | 12076132237361186 | 12076132241888049 | 12076132241956417 |