39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 896557 | 896562 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f1e26a04180 | 12075850856331131 | 12075850856374194 | 12075850856696751 | 12075850856805743 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 896557 | 896562 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f1e26a35100 | 12075850872219850 | 12075850872330012 | 12075850872336412 | 12075850872341927 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f1f56b4e900 | 0x7f1e26a35140 | 12075850872399754 | 12075850872414332 | 12075850872546010 | 12075850872549482 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f1f56b4e800 | 0x7f1e26a35180 | 12075850872602281 | 12075850872614810 | 12075850872856728 | 12075850872954465 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f1f56b4e700 | 0x7f1e26a351c0 | 12075850872987466 | 12075850873000086 | 12075850873282004 | 12075850873382440 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f1f56b4e600 | 0x7f1e26a35200 | 12075850873416424 | 12075850873428883 | 12075850873554801 | 12075850873557977 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f1f56b4e500 | 0x7f1e26a35240 | 12075850873592461 | 12075850873606961 | 12075850873733040 | 12075850873736008 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f1f56b4e400 | 0x7f1e26a35280 | 12075850873796159 | 12075850873810959 | 12075850873934958 | 12075850873937382 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f1f56b4e300 | 0x7f1e26a352c0 | 12075850873973779 | 12075850873989518 | 12075850874234155 | 12075850874332496 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f1f56b4ea00 | 0x7f1e26a35300 | 12075850874377840 | 12075850874390634 | 12075850874637832 | 12075850874735485 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f1f56b4e900 | 0x7f1e26a35340 | 12075850874763717 | 12075850874775591 | 12075850874899750 | 12075850874902826 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f1f56b4e800 | 0x7f1e26a35380 | 12075850874936459 | 12075850874949189 | 12075850875074148 | 12075850875077370 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f1f56b4e700 | 0x7f1e26a353c0 | 12075850875126261 | 12075850875138147 | 12075850875262946 | 12075850875265941 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f1f56b4e600 | 0x7f1e26a35400 | 12075850875299153 | 12075850875316546 | 12075850875567424 | 12075850875640998 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f1f56b4e500 | 0x7f1e26a35440 | 12075850875670873 | 12075850875683103 | 12075850875963100 | 12075850876033417 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f1f56b4e400 | 0x7f1e26a35480 | 12075850876088099 | 12075850876101819 | 12075850876226778 | 12075850876229772 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f1f56b4e300 | 0x7f1e26a354c0 | 12075850876262012 | 12075850876276857 | 12075850876401816 | 12075850876404998 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f1f56b4ea00 | 0x7f1e26a35500 | 12075850876449811 | 12075850876465976 | 12075850876590935 | 12075850876593678 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f1f56b4e900 | 0x7f1e26a35540 | 12075850876626660 | 12075850876641974 | 12075850876888052 | 12075850876960390 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f1f56b4e800 | 0x7f1e26a35580 | 12075850876989434 | 12075850877001491 | 12075850877244689 | 12075850877316592 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f1f56b4e700 | 0x7f1e26a355c0 | 12075850877359061 | 12075850877373008 | 12075850877497007 | 12075850877499953 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f1f56b4e600 | 0x7f1e26a35600 | 12075850877532653 | 12075850877547406 | 12075850877673005 | 12075850877675850 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f1f56b4e500 | 0x7f1e26a35640 | 12075850877720032 | 12075850877732045 | 12075850877856843 | 12075850877859932 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f1f56b4e400 | 0x7f1e26a35680 | 12075850877894015 | 12075850877906283 | 12075850878157321 | 12075850878255587 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f1f56b4e300 | 0x7f1e26a356c0 | 12075850878284791 | 12075850878298120 | 12075850878543397 | 12075850878612610 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f1f56b4ea00 | 0x7f1e26a35700 | 12075850878643458 | 12075850878655396 | 12075850878779555 | 12075850878782486 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f1f56b4e900 | 0x7f1e26a35740 | 12075850878814536 | 12075850878826115 | 12075850878950914 | 12075850878953674 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f1f56b4e800 | 0x7f1e26a35780 | 12075850878995422 | 12075850879007553 | 12075850879132352 | 12075850879135112 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f1f56b4e700 | 0x7f1e26a357c0 | 12075850879168343 | 12075850879185792 | 12075850879437469 | 12075850879535476 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f1f56b4e600 | 0x7f1e26a35800 | 12075850879563548 | 12075850879575228 | 12075850879819226 | 12075850879917956 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f1f56b4e500 | 0x7f1e26a35840 | 12075850879944916 | 12075850879957785 | 12075850880082744 | 12075850880085928 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f1f56b4e400 | 0x7f1e26a35880 | 12075850880119401 | 12075850880131063 | 12075850880256662 | 12075850880259862 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f1f56b4e300 | 0x7f1e26a358c0 | 12075850880301259 | 12075850880316982 | 12075850880441461 | 12075850880444285 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f1f56b4ea00 | 0x7f1e26a35900 | 12075850880477927 | 12075850880492340 | 12075850880737618 | 12075850880815785 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f1f56b4e900 | 0x7f1e26a35940 | 12075850880841873 | 12075850880857937 | 12075850881102255 | 12075850881184470 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f1f56b4e800 | 0x7f1e26a35980 | 12075850881214807 | 12075850881227374 | 12075850881352173 | 12075850881355037 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f1f56b4e700 | 0x7f1e26a359c0 | 12075850881388239 | 12075850881400012 | 12075850881526091 | 12075850881529321 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f1f56b4e600 | 0x7f1e26a35a00 | 12075850881571359 | 12075850881583210 | 12075850881707529 | 12075850881709997 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f1f56b4e500 | 0x7f1e26a35a40 | 12075850881742417 | 12075850881756489 | 12075850882010247 | 12075850882043036 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f1f56b4e400 | 0x7f1e26a35a80 | 12075850882075797 | 12075850882090086 | 12075850882333284 | 12075850882362990 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f1f56b4e300 | 0x7f1e26a35ac0 | 12075850882391123 | 12075850882406243 | 12075850882531682 | 12075850882534499 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f1f56b4ea00 | 0x7f1e26a35b00 | 12075850882569174 | 12075850882583042 | 12075850882709281 | 12075850882712179 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f1f56b4e900 | 0x7f1e26a35b40 | 12075850882756642 | 12075850882770720 | 12075850882896319 | 12075850882899527 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f1f56b4e800 | 0x7f1e26a35b80 | 12075850882931777 | 12075850882946078 | 12075850883203836 | 12075850883233248 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f1f56b4e700 | 0x7f1e26a35bc0 | 12075850883265508 | 12075850883279035 | 12075850883523993 | 12075850883547903 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f1f56b4e600 | 0x7f1e26a35c00 | 12075850883574843 | 12075850883588953 | 12075850883712952 | 12075850883715574 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f1f56b4e500 | 0x7f1e26a35c40 | 12075850883748004 | 12075850883761431 | 12075850883888150 | 12075850883890710 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f1f56b4e400 | 0x7f1e26a35c80 | 12075850883933399 | 12075850883946390 | 12075850884070868 | 12075850884073439 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f1f56b4e300 | 0x7f1e26a35cc0 | 12075850884108905 | 12075850884123828 | 12075850884379666 | 12075850884400758 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f1f56b4ea00 | 0x7f1e26a35d00 | 12075850884430042 | 12075850884444145 | 12075850884690383 | 12075850884717616 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f1f56b4e900 | 0x7f1e26a35d40 | 12075850884748464 | 12075850884763022 | 12075850884887821 | 12075850884890798 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f1f56b4e800 | 0x7f1e26a35d80 | 12075850884924631 | 12075850884938061 | 12075850885065420 | 12075850885068048 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f1f56b4e700 | 0x7f1e26a35dc0 | 12075850885111959 | 12075850885126059 | 12075850885251498 | 12075850885254324 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f1f56b4e600 | 0x7f1e26a35e00 | 12075850885286383 | 12075850885300298 | 12075850885556455 | 12075850885577134 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f1f56b4e500 | 0x7f1e26a35e40 | 12075850885613020 | 12075850885627815 | 12075850885908932 | 12075850885932444 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f1f56b4e400 | 0x7f1e26a35e80 | 12075850885961719 | 12075850885975652 | 12075850886101251 | 12075850886104193 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f1f56b4e300 | 0x7f1e26a35ec0 | 12075850886140120 | 12075850886153250 | 12075850886281249 | 12075850886283777 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f1f56b4ea00 | 0x7f1e26a35f00 | 12075850886329853 | 12075850886345408 | 12075850886470687 | 12075850886473169 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f1f56b4e900 | 0x7f1e26a35f40 | 12075850886505850 | 12075850886519647 | 12075850886774045 | 12075850886797892 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f1f56b4e800 | 0x7f1e26a35f80 | 12075850886826055 | 12075850886839644 | 12075850887088602 | 12075850887116515 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f1f56b4e700 | 0x7f1e26a35fc0 | 12075850887145448 | 12075850887159481 | 12075850887284440 | 12075850887287072 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f1f56b4e600 | 0x7f1e26a36000 | 12075850887318450 | 12075850887332280 | 12075850887468438 | 12075850887471314 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f1f56b4e500 | 0x7f1e26a36040 | 12075850887514184 | 12075850887528118 | 12075850887652597 | 12075850887655196 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f1f56b4e400 | 0x7f1e26a36080 | 12075850887688878 | 12075850887702996 | 12075850887961554 | 12075850887984608 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f1f56b4e300 | 0x7f1e26a360c0 | 12075850888020404 | 12075850888034193 | 12075850888280271 | 12075850888310013 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f1f56b4ea00 | 0x7f1e26a36100 | 12075850888341812 | 12075850888356111 | 12075850888481229 | 12075850888483966 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f1f56b4e900 | 0x7f1e26a36140 | 12075850888516546 | 12075850888530029 | 12075850888671948 | 12075850888674590 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f1f56b4e800 | 0x7f1e26a36180 | 12075850888716198 | 12075850888730667 | 12075850888856266 | 12075850888858873 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f1f56b4e700 | 0x7f1e26a361c0 | 12075850888892405 | 12075850888904746 | 12075850889155624 | 12075850889183616 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f1f56b4e600 | 0x7f1e26a36200 | 12075850889212119 | 12075850889224903 | 12075850889469861 | 12075850889498662 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f1f56b4e500 | 0x7f1e26a36240 | 12075850889525572 | 12075850889539940 | 12075850889665379 | 12075850889667956 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f1f56b4e400 | 0x7f1e26a36280 | 12075850889701278 | 12075850889715299 | 12075850889864577 | 12075850889867147 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f1f56b4e300 | 0x7f1e26a362c0 | 12075850889929522 | 12075850889942497 | 12075850890067935 | 12075850890071126 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f1f56b4ea00 | 0x7f1e26a36300 | 12075850890105590 | 12075850890120095 | 12075850890384573 | 12075850890409164 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f1f56b4e900 | 0x7f1e26a36340 | 12075850890437797 | 12075850890451612 | 12075850890698330 | 12075850890721354 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f1f56b4e800 | 0x7f1e26a36380 | 12075850890749216 | 12075850890762969 | 12075850890888408 | 12075850890891250 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f1f56b4e700 | 0x7f1e26a363c0 | 12075850890922608 | 12075850890936248 | 12075850891092566 | 12075850891095890 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f1f56b4e600 | 0x7f1e26a36400 | 12075850891138179 | 12075850891151926 | 12075850891276565 | 12075850891279121 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f1f56b4e500 | 0x7f1e26a36440 | 12075850891312002 | 12075850891324884 | 12075850891581362 | 12075850891608783 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f1f56b4e400 | 0x7f1e26a36480 | 12075850891638238 | 12075850891651921 | 12075850891898479 | 12075850891921835 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f1f56b4e300 | 0x7f1e26a364c0 | 12075850891952522 | 12075850891966319 | 12075850892091438 | 12075850892094115 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f1f56b4ea00 | 0x7f1e26a36500 | 12075850892128529 | 12075850892142317 | 12075850892306956 | 12075850892309616 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f1f56b4e900 | 0x7f1e26a36540 | 12075850892352375 | 12075850892365675 | 12075850892491594 | 12075850892494239 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f1f56b4e800 | 0x7f1e26a36580 | 12075850892526389 | 12075850892540394 | 12075850892800391 | 12075850892823811 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f1f56b4e700 | 0x7f1e26a365c0 | 12075850892851974 | 12075850892865031 | 12075850893110309 | 12075850893137434 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f1f56b4e600 | 0x7f1e26a36600 | 12075850893165476 | 12075850893179748 | 12075850893304547 | 12075850893307360 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f1f56b4e500 | 0x7f1e26a36640 | 12075850893339410 | 12075850893351746 | 12075850893523905 | 12075850893526487 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f1f56b4e400 | 0x7f1e26a36680 | 12075850893570749 | 12075850893584384 | 12075850893710143 | 12075850893712834 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f1f56b4e300 | 0x7f1e26a366c0 | 12075850893744963 | 12075850893759103 | 12075850894010621 | 12075850894038910 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f1f56b4ea00 | 0x7f1e26a36700 | 12075850894067743 | 12075850894081660 | 12075850894329818 | 12075850894353184 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f1f56b4e900 | 0x7f1e26a36740 | 12075850894384141 | 12075850894397657 | 12075850894523736 | 12075850894526596 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f1f56b4e800 | 0x7f1e26a36780 | 12075850894558555 | 12075850894571416 | 12075850894753334 | 12075850894756403 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f1f56b4e700 | 0x7f1e26a367c0 | 12075850894797850 | 12075850894810934 | 12075850894937492 | 12075850894940154 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f1f56b4e600 | 0x7f1e26a36800 | 12075850894972054 | 12075850894985812 | 12075850895248690 | 12075850895276409 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f1f56b4e500 | 0x7f1e26a36840 | 12075850895305604 | 12075850895319889 | 12075850895565487 | 12075850895588790 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f1f56b4e400 | 0x7f1e26a36880 | 12075850895620128 | 12075850895633806 | 12075850895759245 | 12075850895762102 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f1f56b4e300 | 0x7f1e26a368c0 | 12075850895795214 | 12075850895809005 | 12075850895999883 | 12075850896008400 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f1f56b4ea00 | 0x7f1e26a36900 | 12075850896045258 | 12075850896059083 | 12075850896185481 | 12075850896188334 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f1f56b4e900 | 0x7f1e26a36940 | 12075850896219803 | 12075850896235241 | 12075850896518118 | 12075850896542062 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f1f56b4e800 | 0x7f1e26a36980 | 12075850896568932 | 12075850896582118 | 12075850896828036 | 12075850896851657 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f1f56b4e700 | 0x7f1e26a369c0 | 12075850896877695 | 12075850896891395 | 12075850897019234 | 12075850897022454 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f1f56b4e600 | 0x7f1e26a36a00 | 12075850897058582 | 12075850897071714 | 12075850897280352 | 12075850897308456 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f1f56b4e500 | 0x7f1e26a36a40 | 12075850897347979 | 12075850897361311 | 12075850897490590 | 12075850897493640 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f1f56b4e400 | 0x7f1e26a36a80 | 12075850897527022 | 12075850897539549 | 12075850897876186 | 12075850897900396 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f1f56b4e300 | 0x7f1e26a36ac0 | 12075850897928678 | 12075850897943066 | 12075850898192664 | 12075850898218307 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f1f56b4ea00 | 0x7f1e26a36b00 | 12075850898245547 | 12075850898259543 | 12075850898387702 | 12075850898390547 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f1f56b4e900 | 0x7f1e26a36b40 | 12075850898423117 | 12075850898436502 | 12075850898664179 | 12075850898684112 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f1f56b4e800 | 0x7f1e26a36b80 | 12075850898721843 | 12075850898734899 | 12075850898862418 | 12075850898865049 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f1f56b4e700 | 0x7f1e26a36bc0 | 12075850898897689 | 12075850898912017 | 12075850899240654 | 12075850899268929 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f1f56b4e600 | 0x7f1e26a36c00 | 12075850899298104 | 12075850899312014 | 12075850899560812 | 12075850899584055 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f1f56b4e500 | 0x7f1e26a36c40 | 12075850899615093 | 12075850899629131 | 12075850899758090 | 12075850899760884 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f1f56b4e400 | 0x7f1e26a36c80 | 12075850899791561 | 12075850899804969 | 12075850900049447 | 12075850900074727 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f1f56b4e300 | 0x7f1e26a36cc0 | 12075850900112637 | 12075850900127527 | 12075850900256165 | 12075850900259430 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f1f56b4ea00 | 0x7f1e26a36d00 | 12075850900292482 | 12075850900306565 | 12075850900681282 | 12075850900708324 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f1f56b4e900 | 0x7f1e26a36d40 | 12075850900737198 | 12075850900749921 | 12075850901002559 | 12075850901030734 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f1f56b4e800 | 0x7f1e26a36d80 | 12075850901057824 | 12075850901072638 | 12075850901203037 | 12075850901206059 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f1f56b4e700 | 0x7f1e26a36dc0 | 12075850901238019 | 12075850901251357 | 12075850901528954 | 12075850901551752 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f1f56b4e600 | 0x7f1e26a36e00 | 12075850901592147 | 12075850901605273 | 12075850901741912 | 12075850901744610 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f1f56b4e500 | 0x7f1e26a36e40 | 12075850901777040 | 12075850901790872 | 12075850902214068 | 12075850902240712 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f1f56b4e400 | 0x7f1e26a36e80 | 12075850902268634 | 12075850902282388 | 12075850902537105 | 12075850902564294 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f1f56b4e300 | 0x7f1e26a36ec0 | 12075850902590733 | 12075850902605105 | 12075850902741583 | 12075850902744499 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f1f56b4ea00 | 0x7f1e26a36f00 | 12075850902776628 | 12075850902789903 | 12075850903103020 | 12075850903132540 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f1f56b4e900 | 0x7f1e26a36f40 | 12075850903170530 | 12075850903183660 | 12075850903335978 | 12075850903339264 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f1f56b4e800 | 0x7f1e26a36f80 | 12075850903371634 | 12075850903386058 | 12075850903902853 | 12075850903926465 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f1f56b4e700 | 0x7f1e26a36fc0 | 12075850903955940 | 12075850903970053 | 12075850904266850 | 12075850904299308 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f1f56b4e600 | 0x7f1e26a37000 | 12075850904331428 | 12075850904345089 | 12075850904498528 | 12075850904501694 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f1f56b4e500 | 0x7f1e26a37040 | 12075850904533022 | 12075850904546047 | 12075850904930684 | 12075850904954646 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f1f56b4e400 | 0x7f1e26a37080 | 12075850904991965 | 12075850905005563 | 12075850905180922 | 12075850905184163 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f1f56b4e300 | 0x7f1e26a370c0 | 12075850905217374 | 12075850905230841 | 12075850905840596 | 12075850905868334 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f1f56b4ea00 | 0x7f1e26a37100 | 12075850905895054 | 12075850905908115 | 12075850906233873 | 12075850906266504 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f1f56b4e900 | 0x7f1e26a37140 | 12075850906294526 | 12075850906307632 | 12075850906485870 | 12075850906489138 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f1f56b4e800 | 0x7f1e26a37180 | 12075850906521748 | 12075850906534670 | 12075850906989386 | 12075850907021487 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f1f56b4e700 | 0x7f1e26a371c0 | 12075850907068915 | 12075850907081705 | 12075850907280583 | 12075850907309202 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f1f56b4e600 | 0x7f1e26a37200 | 12075850907339318 | 12075850907352743 | 12075850908056096 | 12075850908084533 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f1f56b4e500 | 0x7f1e26a37240 | 12075850908116652 | 12075850908130016 | 12075850908502813 | 12075850908529920 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f1f56b4e400 | 0x7f1e26a37280 | 12075850908560597 | 12075850908573852 | 12075850908776730 | 12075850908803429 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f1f56b4e300 | 0x7f1e26a372c0 | 12075850908831060 | 12075850908843610 | 12075850909369365 | 12075850909401410 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f1f56b4ea00 | 0x7f1e26a37300 | 12075850909439972 | 12075850909452884 | 12075850909676082 | 12075850909702991 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f1f56b4e900 | 0x7f1e26a37340 | 12075850909733056 | 12075850909746802 | 12075850910544234 | 12075850910573168 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f1f56b4e800 | 0x7f1e26a37380 | 12075850910607732 | 12075850910621354 | 12075850911039750 | 12075850911068959 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f1f56b4e700 | 0x7f1e26a373c0 | 12075850911104976 | 12075850911119429 | 12075850911345027 | 12075850911369377 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f1f56b4e600 | 0x7f1e26a37400 | 12075850911402389 | 12075850911415267 | 12075850912011902 | 12075850912041006 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f1f56b4e500 | 0x7f1e26a37440 | 12075850912081281 | 12075850912094621 | 12075850912363738 | 12075850912391447 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f1f56b4e400 | 0x7f1e26a37480 | 12075850912423146 | 12075850912434458 | 12075850913418129 | 12075850913446578 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f1f56b4e300 | 0x7f1e26a374c0 | 12075850913476734 | 12075850913490448 | 12075850914022764 | 12075850914051332 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f1f56b4ea00 | 0x7f1e26a37500 | 12075850914086347 | 12075850914099723 | 12075850914371241 | 12075850914398697 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f1f56b4e900 | 0x7f1e26a37540 | 12075850914428453 | 12075850914441480 | 12075850915178434 | 12075850915207931 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f1f56b4e800 | 0x7f1e26a37580 | 12075850915249498 | 12075850915262753 | 12075850915577470 | 12075850915604578 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f1f56b4e700 | 0x7f1e26a375c0 | 12075850915634193 | 12075850915646909 | 12075850916817939 | 12075850916847508 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f1f56b4e600 | 0x7f1e26a37600 | 12075850916880129 | 12075850916893778 | 12075850917503373 | 12075850917538132 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f1f56b4e500 | 0x7f1e26a37640 | 12075850917571293 | 12075850917584972 | 12075850917904169 | 12075850917933016 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f1f56b4e400 | 0x7f1e26a37680 | 12075850917962460 | 12075850917976009 | 12075850918852641 | 12075850918885175 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f1f56b4e300 | 0x7f1e26a376c0 | 12075850918926702 | 12075850918939795 | 12075850919371952 | 12075850919405572 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f1f56b4ea00 | 0x7f1e26a37700 | 12075850919435849 | 12075850919449070 | 12075850920997859 | 12075850921071418 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f1f56b4e900 | 0x7f1e26a37740 | 12075850921104089 | 12075850921118658 | 12075850921912412 | 12075850921985166 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f1f56b4e800 | 0x7f1e26a37780 | 12075850922030801 | 12075850922044891 | 12075850922458328 | 12075850922531592 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f1f56b4e700 | 0x7f1e26a377c0 | 12075850922562409 | 12075850922576408 | 12075850923734799 | 12075850923808385 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f1f56b4e600 | 0x7f1e26a37800 | 12075850923851395 | 12075850923865838 | 12075850924650473 | 12075850924725389 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f1f56b4e500 | 0x7f1e26a37840 | 12075850924759082 | 12075850924773352 | 12075850927823890 | 12075850927896893 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f1f56b4e400 | 0x7f1e26a37880 | 12075850927931187 | 12075850927944849 | 12075850929485318 | 12075850929561206 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f1f56b4e300 | 0x7f1e26a378c0 | 12075850929593747 | 12075850929608197 | 12075850930396511 | 12075850930468903 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f1f56b4ea00 | 0x7f1e26a37900 | 12075850930503898 | 12075850930517470 | 12075850932798894 | 12075850932871628 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f1f56b4e900 | 0x7f1e26a37940 | 12075850932913827 | 12075850932927213 | 12075850934462082 | 12075850934538176 |
| 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 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f1f56b4e800 | 0x7f1e26a37980 | 12075850934566338 | 12075850934581761 | 12075850940635637 | 12075850940708222 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f1f56b4e700 | 0x7f1e26a379c0 | 12075850940741394 | 12075850940754517 | 12075850943794495 | 12075850943867684 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f1f56b4e600 | 0x7f1e26a37a00 | 12075850943900685 | 12075850943915614 | 12075850945454963 | 12075850945530144 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 896557 | 896562 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f1f56b4e500 | 0x7f1e26a37a40 | 12075850945560240 | 12075850945574002 | 12075850950100689 | 12075850950173914 |