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 | 901311 | 901316 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f8ba1604180 | 0 | 0 | 0 | 12075942327036344 | 12075942571037950 | 12075942571360189 | 12075942571463912 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 901311 | 901316 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f8ba1635100 | 0 | 0 | 0 | 12075942586056261 | 12075942586355119 | 12075942586361839 | 12075942586377678 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f8cad17c900 | 0x7f8ba1635140 | 0 | 0 | 0 | 12075942586430637 | 12075942586646478 | 12075942586779597 | 12075942586783532 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f8cad17c800 | 0x7f8ba1635180 | 0 | 0 | 0 | 12075942586848583 | 12075942587013836 | 12075942587261995 | 12075942587313227 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f8cad17c700 | 0x7f8ba16351c0 | 0 | 0 | 0 | 12075942587346699 | 12075942587530953 | 12075942587787272 | 12075942587833313 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f8cad17c600 | 0x7f8ba1635200 | 0 | 0 | 0 | 12075942587859883 | 12075942588052711 | 12075942588186790 | 12075942588190577 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f8cad17c500 | 0x7f8ba1635240 | 0 | 0 | 0 | 12075942588231564 | 12075942588424869 | 12075942588555589 | 12075942588558702 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f8cad17c400 | 0x7f8ba1635280 | 0 | 0 | 0 | 12075942588636646 | 12075942588802948 | 12075942588934787 | 12075942588938247 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f8cad17c300 | 0x7f8ba16352c0 | 0 | 0 | 0 | 12075942588985825 | 12075942589173346 | 12075942589432705 | 12075942589454366 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f8cad17ca00 | 0x7f8ba1635300 | 0 | 0 | 0 | 12075942589503047 | 12075942589665824 | 12075942589921342 | 12075942589968021 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f8cad17c900 | 0x7f8ba1635340 | 0 | 0 | 0 | 12075942589995662 | 12075942590194141 | 12075942590327741 | 12075942590331386 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f8cad17c800 | 0x7f8ba1635380 | 0 | 0 | 0 | 12075942590377532 | 12075942590570779 | 12075942590707099 | 12075942590710370 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f8cad17c700 | 0x7f8ba16353c0 | 0 | 0 | 0 | 12075942590769590 | 12075942590933498 | 12075942591061977 | 12075942591066142 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f8cad17c600 | 0x7f8ba1635400 | 0 | 0 | 0 | 12075942591114481 | 12075942591298136 | 12075942591547415 | 12075942591593802 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f8cad17c500 | 0x7f8ba1635440 | 0 | 0 | 0 | 12075942591620161 | 12075942591797174 | 12075942592049173 | 12075942592097428 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f8cad17c400 | 0x7f8ba1635480 | 0 | 0 | 0 | 12075942592120701 | 12075942592301011 | 12075942592432691 | 12075942592436248 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f8cad17c300 | 0x7f8ba16354c0 | 0 | 0 | 0 | 12075942592486060 | 12075942592663250 | 12075942592796209 | 12075942592799663 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f8cad17ca00 | 0x7f8ba1635500 | 0 | 0 | 0 | 12075942592862871 | 12075942593057968 | 12075942593188047 | 12075942593191772 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f8cad17c900 | 0x7f8ba1635540 | 0 | 0 | 0 | 12075942593239971 | 12075942593426446 | 12075942593679405 | 12075942593724281 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f8cad17c800 | 0x7f8ba1635580 | 0 | 0 | 0 | 12075942593750039 | 12075942593930124 | 12075942594184203 | 12075942594229420 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f8cad17c700 | 0x7f8ba16355c0 | 0 | 0 | 0 | 12075942594267321 | 12075942594441962 | 12075942594573801 | 12075942594577147 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f8cad17c600 | 0x7f8ba1635600 | 0 | 0 | 0 | 12075942594625136 | 12075942594810920 | 12075942594939239 | 12075942594942656 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f8cad17c500 | 0x7f8ba1635640 | 0 | 0 | 0 | 12075942595011694 | 12075942595183078 | 12075942595311078 | 12075942595314357 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f8cad17c400 | 0x7f8ba1635680 | 0 | 0 | 0 | 12075942595364370 | 12075942595541797 | 12075942595797795 | 12075942595842067 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f8cad17c300 | 0x7f8ba16356c0 | 0 | 0 | 0 | 12075942595869318 | 12075942596058914 | 12075942596312993 | 12075942596358818 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f8cad17ca00 | 0x7f8ba1635700 | 0 | 0 | 0 | 12075942596387411 | 12075942596554272 | 12075942596687711 | 12075942596690865 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f8cad17c900 | 0x7f8ba1635740 | 0 | 0 | 0 | 12075942596740076 | 12075942596914430 | 12075942597045950 | 12075942597049521 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f8cad17c800 | 0x7f8ba1635780 | 0 | 0 | 0 | 12075942597110254 | 12075942597280029 | 12075942597415548 | 12075942597419288 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f8cad17c700 | 0x7f8ba16357c0 | 0 | 0 | 0 | 12075942597467829 | 12075942597647067 | 12075942597903066 | 12075942597947660 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f8cad17c600 | 0x7f8ba1635800 | 0 | 0 | 0 | 12075942597972797 | 12075942598158905 | 12075942598412663 | 12075942598458229 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f8cad17c500 | 0x7f8ba1635840 | 0 | 0 | 0 | 12075942598484628 | 12075942598661462 | 12075942598793622 | 12075942598797039 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f8cad17c400 | 0x7f8ba1635880 | 0 | 0 | 0 | 12075942598845699 | 12075942599028660 | 12075942599163540 | 12075942599167267 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f8cad17c300 | 0x7f8ba16358c0 | 0 | 0 | 0 | 12075942599228821 | 12075942599397459 | 12075942599528498 | 12075942599531815 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f8cad17ca00 | 0x7f8ba1635900 | 0 | 0 | 0 | 12075942599583170 | 12075942599757137 | 12075942600013776 | 12075942600058614 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f8cad17c900 | 0x7f8ba1635940 | 0 | 0 | 0 | 12075942600085854 | 12075942600263055 | 12075942600512014 | 12075942600555387 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f8cad17c800 | 0x7f8ba1635980 | 0 | 0 | 0 | 12075942600583229 | 12075942600751853 | 12075942600886412 | 12075942600889888 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f8cad17c700 | 0x7f8ba16359c0 | 0 | 0 | 0 | 12075942600937036 | 12075942601128171 | 12075942601266090 | 12075942601269664 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f8cad17c600 | 0x7f8ba1635a00 | 0 | 0 | 0 | 12075942601330177 | 12075942601497609 | 12075942601629929 | 12075942601633280 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f8cad17c500 | 0x7f8ba1635a40 | 0 | 0 | 0 | 12075942601675198 | 12075942601863047 | 12075942602124326 | 12075942602169687 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f8cad17c400 | 0x7f8ba1635a80 | 0 | 0 | 0 | 12075942602195936 | 12075942602372485 | 12075942602624644 | 12075942602668374 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f8cad17c300 | 0x7f8ba1635ac0 | 0 | 0 | 0 | 12075942602694512 | 12075942602874243 | 12075942603005762 | 12075942603009227 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f8cad17ca00 | 0x7f8ba1635b00 | 0 | 0 | 0 | 12075942603060793 | 12075942603230721 | 12075942603362241 | 12075942603365720 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f8cad17c900 | 0x7f8ba1635b40 | 0 | 0 | 0 | 12075942603425681 | 12075942603591039 | 12075942603724479 | 12075942603727963 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f8cad17c800 | 0x7f8ba1635b80 | 0 | 0 | 0 | 12075942603775391 | 12075942603949758 | 12075942604212637 | 12075942604258439 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f8cad17c700 | 0x7f8ba1635bc0 | 0 | 0 | 0 | 12075942604284407 | 12075942604460635 | 12075942604716474 | 12075942604761293 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f8cad17c600 | 0x7f8ba1635c00 | 0 | 0 | 0 | 12075942604785869 | 12075942604961593 | 12075942605092153 | 12075942605095965 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f8cad17c500 | 0x7f8ba1635c40 | 0 | 0 | 0 | 12075942605145908 | 12075942605325271 | 12075942605457591 | 12075942605461094 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f8cad17c400 | 0x7f8ba1635c80 | 0 | 0 | 0 | 12075942605521306 | 12075942605686390 | 12075942605816629 | 12075942605820041 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f8cad17c300 | 0x7f8ba1635cc0 | 0 | 0 | 0 | 12075942605869733 | 12075942606053428 | 12075942606322867 | 12075942606368140 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f8cad17ca00 | 0x7f8ba1635d00 | 0 | 0 | 0 | 12075942606396122 | 12075942606566866 | 12075942606826225 | 12075942606869091 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f8cad17c900 | 0x7f8ba1635d40 | 0 | 0 | 0 | 12075942606894167 | 12075942607075663 | 12075942607203023 | 12075942607206538 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f8cad17c800 | 0x7f8ba1635d80 | 0 | 0 | 0 | 12075942607255388 | 12075942607430702 | 12075942607572301 | 12075942607575604 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f8cad17c700 | 0x7f8ba1635dc0 | 0 | 0 | 0 | 12075942607636477 | 12075942607800940 | 12075942607933739 | 12075942607937045 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f8cad17c600 | 0x7f8ba1635e00 | 0 | 0 | 0 | 12075942607976970 | 12075942608171178 | 12075942608436617 | 12075942608481527 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f8cad17c500 | 0x7f8ba1635e40 | 0 | 0 | 0 | 12075942608507375 | 12075942608687816 | 12075942608939495 | 12075942608983480 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f8cad17c400 | 0x7f8ba1635e80 | 0 | 0 | 0 | 12075942609016051 | 12075942609186534 | 12075942609317253 | 12075942609320607 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f8cad17c300 | 0x7f8ba1635ec0 | 0 | 0 | 0 | 12075942609372904 | 12075942609545892 | 12075942609687331 | 12075942609690754 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f8cad17ca00 | 0x7f8ba1635f00 | 0 | 0 | 0 | 12075942609749434 | 12075942609915650 | 12075942610044130 | 12075942610047808 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f8cad17c900 | 0x7f8ba1635f40 | 0 | 0 | 0 | 12075942610098222 | 12075942610272609 | 12075942610534847 | 12075942610579206 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f8cad17c800 | 0x7f8ba1635f80 | 0 | 0 | 0 | 12075942610604553 | 12075942610777726 | 12075942611029405 | 12075942611073855 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f8cad17c700 | 0x7f8ba1635fc0 | 0 | 0 | 0 | 12075942611101055 | 12075942611271004 | 12075942611403483 | 12075942611406844 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f8cad17c600 | 0x7f8ba1636000 | 0 | 0 | 0 | 12075942611457077 | 12075942611628442 | 12075942611767642 | 12075942611771181 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f8cad17c500 | 0x7f8ba1636040 | 0 | 0 | 0 | 12075942611835530 | 12075942612003801 | 12075942612136600 | 12075942612140317 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f8cad17c400 | 0x7f8ba1636080 | 0 | 0 | 0 | 12075942612188106 | 12075942612380919 | 12075942612649878 | 12075942612694417 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f8cad17c300 | 0x7f8ba16360c0 | 0 | 0 | 0 | 12075942612724062 | 12075942612886197 | 12075942613139955 | 12075942613186120 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f8cad17ca00 | 0x7f8ba1636100 | 0 | 0 | 0 | 12075942613220675 | 12075942613391314 | 12075942613519794 | 12075942613523548 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f8cad17c900 | 0x7f8ba1636140 | 0 | 0 | 0 | 12075942613571396 | 12075942613754033 | 12075942613897552 | 12075942613900999 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f8cad17c800 | 0x7f8ba1636180 | 0 | 0 | 0 | 12075942613962273 | 12075942614134191 | 12075942614263790 | 12075942614267721 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f8cad17c700 | 0x7f8ba16361c0 | 0 | 0 | 0 | 12075942614315850 | 12075942614490509 | 12075942614757228 | 12075942614801933 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f8cad17c600 | 0x7f8ba1636200 | 0 | 0 | 0 | 12075942614828934 | 12075942614997547 | 12075942615246986 | 12075942615293387 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f8cad17c500 | 0x7f8ba1636240 | 0 | 0 | 0 | 12075942615317942 | 12075942615495305 | 12075942615630504 | 12075942615633890 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f8cad17c400 | 0x7f8ba1636280 | 0 | 0 | 0 | 12075942615684423 | 12075942615856743 | 12075942616006342 | 12075942616010249 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f8cad17c300 | 0x7f8ba16362c0 | 0 | 0 | 0 | 12075942616096099 | 12075942616265061 | 12075942616399620 | 12075942616403079 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f8cad17ca00 | 0x7f8ba1636300 | 0 | 0 | 0 | 12075942616445438 | 12075942616626499 | 12075942616895138 | 12075942616939095 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f8cad17c900 | 0x7f8ba1636340 | 0 | 0 | 0 | 12075942616967929 | 12075942617141537 | 12075942617393216 | 12075942617439355 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f8cad17c800 | 0x7f8ba1636380 | 0 | 0 | 0 | 12075942617470483 | 12075942617645535 | 12075942617778174 | 12075942617781641 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f8cad17c700 | 0x7f8ba16363c0 | 0 | 0 | 0 | 12075942617829159 | 12075942618011933 | 12075942618170172 | 12075942618173680 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f8cad17c600 | 0x7f8ba1636400 | 0 | 0 | 0 | 12075942618237007 | 12075942618404891 | 12075942618533851 | 12075942618537155 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f8cad17c500 | 0x7f8ba1636440 | 0 | 0 | 0 | 12075942618588220 | 12075942618756090 | 12075942619021368 | 12075942619066609 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f8cad17c400 | 0x7f8ba1636480 | 0 | 0 | 0 | 12075942619094461 | 12075942619263287 | 12075942619517686 | 12075942619561409 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f8cad17c300 | 0x7f8ba16364c0 | 0 | 0 | 0 | 12075942619586505 | 12075942619758325 | 12075942619891764 | 12075942619895309 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f8cad17ca00 | 0x7f8ba1636500 | 0 | 0 | 0 | 12075942619941675 | 12075942620136883 | 12075942620302962 | 12075942620306584 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f8cad17c900 | 0x7f8ba1636540 | 0 | 0 | 0 | 12075942620368639 | 12075942620537361 | 12075942620673841 | 12075942620677313 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f8cad17c800 | 0x7f8ba1636580 | 0 | 0 | 0 | 12075942620725061 | 12075942620897840 | 12075942621162799 | 12075942621208850 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f8cad17c700 | 0x7f8ba16365c0 | 0 | 0 | 0 | 12075942621238055 | 12075942621404077 | 12075942621696076 | 12075942621715061 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f8cad17c600 | 0x7f8ba1636600 | 0 | 0 | 0 | 12075942621770905 | 12075942621937195 | 12075942622073034 | 12075942622077004 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f8cad17c500 | 0x7f8ba1636640 | 0 | 0 | 0 | 12075942622127538 | 12075942622312393 | 12075942622486472 | 12075942622489821 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f8cad17c400 | 0x7f8ba1636680 | 0 | 0 | 0 | 12075942622553249 | 12075942622720231 | 12075942622855271 | 12075942622858646 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f8cad17c300 | 0x7f8ba16366c0 | 0 | 0 | 0 | 12075942622906395 | 12075942623096550 | 12075942623356708 | 12075942623402237 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f8cad17ca00 | 0x7f8ba1636700 | 0 | 0 | 0 | 12075942623428826 | 12075942623597187 | 12075942623849666 | 12075942623893690 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f8cad17c900 | 0x7f8ba1636740 | 0 | 0 | 0 | 12075942623918797 | 12075942624098145 | 12075942624231904 | 12075942624235595 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f8cad17c800 | 0x7f8ba1636780 | 0 | 0 | 0 | 12075942624285268 | 12075942624458303 | 12075942624640862 | 12075942624644375 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f8cad17c700 | 0x7f8ba16367c0 | 0 | 0 | 0 | 12075942624704677 | 12075942624869661 | 12075942625005661 | 12075942625009504 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f8cad17c600 | 0x7f8ba1636800 | 0 | 0 | 0 | 12075942625056140 | 12075942625235100 | 12075942625502459 | 12075942625540070 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f8cad17c500 | 0x7f8ba1636840 | 0 | 0 | 0 | 12075942625572360 | 12075942625733337 | 12075942625981496 | 12075942626017106 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f8cad17c400 | 0x7f8ba1636880 | 0 | 0 | 0 | 12075942626050198 | 12075942626218135 | 12075942626351895 | 12075942626355515 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f8cad17c300 | 0x7f8ba16368c0 | 0 | 0 | 0 | 12075942626400799 | 12075942626577814 | 12075942626769813 | 12075942626787839 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f8cad17ca00 | 0x7f8ba1636900 | 0 | 0 | 0 | 12075942626851036 | 12075942627021812 | 12075942627160851 | 12075942627164449 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f8cad17c900 | 0x7f8ba1636940 | 0 | 0 | 0 | 12075942627209392 | 12075942627390610 | 12075942627673489 | 12075942627696187 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f8cad17c800 | 0x7f8ba1636980 | 0 | 0 | 0 | 12075942627734047 | 12075942627895407 | 12075942628150286 | 12075942628186198 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f8cad17c700 | 0x7f8ba16369c0 | 0 | 0 | 0 | 12075942628218668 | 12075942628388365 | 12075942628519405 | 12075942628523174 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f8cad17c600 | 0x7f8ba1636a00 | 0 | 0 | 0 | 12075942628571944 | 12075942628748044 | 12075942628957803 | 12075942628979913 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f8cad17c500 | 0x7f8ba1636a40 | 0 | 0 | 0 | 12075942629043992 | 12075942629210761 | 12075942629353001 | 12075942629356793 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f8cad17c400 | 0x7f8ba1636a80 | 0 | 0 | 0 | 12075942629403530 | 12075942629584360 | 12075942629891398 | 12075942629914509 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f8cad17c300 | 0x7f8ba1636ac0 | 0 | 0 | 0 | 12075942629959453 | 12075942630134117 | 12075942630393956 | 12075942630418186 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f8cad17ca00 | 0x7f8ba1636b00 | 0 | 0 | 0 | 12075942630466756 | 12075942630633315 | 12075942630768674 | 12075942630772414 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f8cad17c900 | 0x7f8ba1636b40 | 0 | 0 | 0 | 12075942630818900 | 12075942631005153 | 12075942631233632 | 12075942631258728 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f8cad17c800 | 0x7f8ba1636b80 | 0 | 0 | 0 | 12075942631314101 | 12075942631481631 | 12075942631619710 | 12075942631623375 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f8cad17c700 | 0x7f8ba1636bc0 | 0 | 0 | 0 | 12075942631671465 | 12075942631851709 | 12075942632181468 | 12075942632218351 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f8cad17c600 | 0x7f8ba1636c00 | 0 | 0 | 0 | 12075942632252875 | 12075942632421787 | 12075942632677945 | 12075942632699756 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f8cad17c500 | 0x7f8ba1636c40 | 0 | 0 | 0 | 12075942632744429 | 12075942632908664 | 12075942633050424 | 12075942633054365 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f8cad17c400 | 0x7f8ba1636c80 | 0 | 0 | 0 | 12075942633100911 | 12075942633281303 | 12075942633525942 | 12075942633547882 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f8cad17c300 | 0x7f8ba1636cc0 | 0 | 0 | 0 | 12075942633602213 | 12075942633768980 | 12075942633909300 | 12075942633912930 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f8cad17ca00 | 0x7f8ba1636d00 | 0 | 0 | 0 | 12075942633960158 | 12075942634153792 | 12075942634530271 | 12075942634569991 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f8cad17c900 | 0x7f8ba1636d40 | 0 | 0 | 0 | 12075942634597913 | 12075942634763869 | 12075942635028827 | 12075942635051647 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f8cad17c800 | 0x7f8ba1636d80 | 0 | 0 | 0 | 12075942635102681 | 12075942635268666 | 12075942635407866 | 12075942635411505 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f8cad17c700 | 0x7f8ba1636dc0 | 0 | 0 | 0 | 12075942635460416 | 12075942635634425 | 12075942635944983 | 12075942635966767 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f8cad17c600 | 0x7f8ba1636e00 | 0 | 0 | 0 | 12075942636032640 | 12075942636204182 | 12075942636341942 | 12075942636345621 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f8cad17c500 | 0x7f8ba1636e40 | 0 | 0 | 0 | 12075942636391436 | 12075942636577141 | 12075942637024499 | 12075942637047305 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f8cad17c400 | 0x7f8ba1636e80 | 0 | 0 | 0 | 12075942637096286 | 12075942637263858 | 12075942637529137 | 12075942637550561 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f8cad17c300 | 0x7f8ba1636ec0 | 0 | 0 | 0 | 12075942637598470 | 12075942637762255 | 12075942637900495 | 12075942637904348 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f8cad17ca00 | 0x7f8ba1636f00 | 0 | 0 | 0 | 12075942637950484 | 12075942638142894 | 12075942638457132 | 12075942638493824 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f8cad17c900 | 0x7f8ba1636f40 | 0 | 0 | 0 | 12075942638537826 | 12075942638703851 | 12075942638856331 | 12075942638859944 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f8cad17c800 | 0x7f8ba1636f80 | 0 | 0 | 0 | 12075942638906952 | 12075942639091850 | 12075942639609767 | 12075942639644893 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f8cad17c700 | 0x7f8ba1636fc0 | 0 | 0 | 0 | 12075942639680359 | 12075942639846886 | 12075942640143845 | 12075942640166282 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f8cad17c600 | 0x7f8ba1637000 | 0 | 0 | 0 | 12075942640215043 | 12075942640384004 | 12075942640539683 | 12075942640543172 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f8cad17c500 | 0x7f8ba1637040 | 0 | 0 | 0 | 12075942640591162 | 12075942640765762 | 12075942641153121 | 12075942641175748 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f8cad17c400 | 0x7f8ba1637080 | 0 | 0 | 0 | 12075942641238164 | 12075942641407039 | 12075942641583359 | 12075942641586922 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f8cad17c300 | 0x7f8ba16370c0 | 0 | 0 | 0 | 12075942641634050 | 12075942641818398 | 12075942642440955 | 12075942642476886 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f8cad17ca00 | 0x7f8ba1637100 | 0 | 0 | 0 | 12075942642510799 | 12075942642678234 | 12075942643007672 | 12075942643029964 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f8cad17c900 | 0x7f8ba1637140 | 0 | 0 | 0 | 12075942643079486 | 12075942643242231 | 12075942643421591 | 12075942643425098 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f8cad17c800 | 0x7f8ba1637180 | 0 | 0 | 0 | 12075942643473719 | 12075942643656150 | 12075942644133588 | 12075942644156778 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f8cad17c700 | 0x7f8ba16371c0 | 0 | 0 | 0 | 12075942644218383 | 12075942644388146 | 12075942644589426 | 12075942644611022 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f8cad17c600 | 0x7f8ba1637200 | 0 | 0 | 0 | 12075942644662959 | 12075942644829744 | 12075942645539501 | 12075942645580304 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f8cad17c500 | 0x7f8ba1637240 | 0 | 0 | 0 | 12075942645604989 | 12075942645781900 | 12075942646154699 | 12075942646202690 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f8cad17c400 | 0x7f8ba1637280 | 0 | 0 | 0 | 12075942646230452 | 12075942646397418 | 12075942646600457 | 12075942646645203 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f8cad17c300 | 0x7f8ba16372c0 | 0 | 0 | 0 | 12075942646679246 | 12075942646845736 | 12075942647371813 | 12075942647417688 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f8cad17ca00 | 0x7f8ba1637300 | 0 | 0 | 0 | 12075942647455809 | 12075942647628132 | 12075942647851651 | 12075942647896388 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f8cad17c900 | 0x7f8ba1637340 | 0 | 0 | 0 | 12075942647930111 | 12075942648100450 | 12075942648900607 | 12075942648945428 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f8cad17c800 | 0x7f8ba1637380 | 0 | 0 | 0 | 12075942648973880 | 12075942649142366 | 12075942649564444 | 12075942649610193 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f8cad17c700 | 0x7f8ba16373c0 | 0 | 0 | 0 | 12075942649637033 | 12075942649815003 | 12075942650041882 | 12075942650087961 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f8cad17c600 | 0x7f8ba1637400 | 0 | 0 | 0 | 12075942650114811 | 12075942650285561 | 12075942650883478 | 12075942650927822 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f8cad17c500 | 0x7f8ba1637440 | 0 | 0 | 0 | 12075942650965622 | 12075942651140917 | 12075942651410516 | 12075942651456434 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f8cad17c400 | 0x7f8ba1637480 | 0 | 0 | 0 | 12075942651483795 | 12075942651650515 | 12075942652637070 | 12075942652682503 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f8cad17c300 | 0x7f8ba16374c0 | 0 | 0 | 0 | 12075942652716917 | 12075942652888429 | 12075942653402507 | 12075942653447484 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f8cad17ca00 | 0x7f8ba1637500 | 0 | 0 | 0 | 12075942653480205 | 12075942653648746 | 12075942653921545 | 12075942653940391 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f8cad17c900 | 0x7f8ba1637540 | 0 | 0 | 0 | 12075942653997196 | 12075942654171943 | 12075942654910180 | 12075942654956098 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f8cad17c800 | 0x7f8ba1637580 | 0 | 0 | 0 | 12075942655006211 | 12075942655173219 | 12075942655490978 | 12075942655537188 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f8cad17c700 | 0x7f8ba16375c0 | 0 | 0 | 0 | 12075942655563377 | 12075942655737537 | 12075942656908411 | 12075942656954803 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f8cad17c600 | 0x7f8ba1637600 | 0 | 0 | 0 | 12075942656985460 | 12075942657172250 | 12075942657783288 | 12075942657828116 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f8cad17c500 | 0x7f8ba1637640 | 0 | 0 | 0 | 12075942657860576 | 12075942658036247 | 12075942658356885 | 12075942658403515 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f8cad17c400 | 0x7f8ba1637680 | 0 | 0 | 0 | 12075942658436627 | 12075942658605684 | 12075942659484560 | 12075942659530540 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f8cad17c300 | 0x7f8ba16376c0 | 0 | 0 | 0 | 12075942659575934 | 12075942659741839 | 12075942660153997 | 12075942660200495 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f8cad17ca00 | 0x7f8ba1637700 | 0 | 0 | 0 | 12075942660230140 | 12075942660394156 | 12075942661943589 | 12075942661989640 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f8cad17c900 | 0x7f8ba1637740 | 0 | 0 | 0 | 12075942662020527 | 12075942662189188 | 12075942662985185 | 12075942663031947 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f8cad17c800 | 0x7f8ba1637780 | 0 | 0 | 0 | 12075942663064217 | 12075942663231904 | 12075942663647262 | 12075942663692524 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f8cad17c700 | 0x7f8ba16377c0 | 0 | 0 | 0 | 12075942663725806 | 12075942663891901 | 12075942665051096 | 12075942665097435 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f8cad17c600 | 0x7f8ba1637800 | 0 | 0 | 0 | 12075942665142760 | 12075942665313335 | 12075942666098931 | 12075942666144461 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f8cad17c500 | 0x7f8ba1637840 | 0 | 0 | 0 | 12075942666178565 | 12075942666345490 | 12075942669397317 | 12075942669443643 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f8cad17c400 | 0x7f8ba1637880 | 0 | 0 | 0 | 12075942669475031 | 12075942669645316 | 12075942671188989 | 12075942671235262 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f8cad17c300 | 0x7f8ba16378c0 | 0 | 0 | 0 | 12075942671269526 | 12075942671438428 | 12075942672228344 | 12075942672274363 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f8cad17ca00 | 0x7f8ba1637900 | 0 | 0 | 0 | 12075942672308807 | 12075942672476823 | 12075942674759053 | 12075942674804786 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f8cad17c900 | 0x7f8ba1637940 | 0 | 0 | 0 | 12075942674847535 | 12075942675013452 | 12075942676549125 | 12075942676595995 |
| 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 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f8cad17c800 | 0x7f8ba1637980 | 0 | 0 | 0 | 12075942676629688 | 12075942676800164 | 12075942682854698 | 12075942682901904 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f8cad17c700 | 0x7f8ba16379c0 | 0 | 0 | 0 | 12075942682936198 | 12075942683115656 | 12075942686156763 | 12075942686204051 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f8cad17c600 | 0x7f8ba1637a00 | 0 | 0 | 0 | 12075942686233836 | 12075942686396762 | 12075942687935475 | 12075942687982366 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 901311 | 901316 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f8cad17c500 | 0x7f8ba1637a40 | 0 | 0 | 0 | 12075942688024494 | 12075942688190674 | 12075942692717534 | 12075942692765686 |