37 KiB
37 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_fillBufferAligned.kd | 0 | 0 | 0 | 143794 | 143794 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f24c3c04280 | 16025461758366 | 16025461787106 | 16025462025348 | 16025462096648 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 143794 | 143794 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f24c3c23f80 | 16025466923291 | 16025466939141 | 16025466947461 | 16025466967660 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f24caee9380 | 0x7f24c3c23fc0 | 16025466972220 | 16025467041542 | 16025467133862 | 16025467136077 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 8 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f24caee9200 | 0x7f24c3c24000 | 16025467157906 | 16025467168263 | 16025467348104 | 16025467350352 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f24caee9080 | 0x7f24c3c24040 | 16025467365521 | 16025467373864 | 16025467554665 | 16025467556767 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f24c8847f00 | 0x7f24c3c24080 | 16025467571497 | 16025467579785 | 16025467672106 | 16025467674255 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f24c8847d80 | 0x7f24c3c240c0 | 16025467690464 | 16025467698346 | 16025467789707 | 16025467791892 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f24c8847c00 | 0x7f24c3c24100 | 16025467821401 | 16025467832267 | 16025467923948 | 16025467926099 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 23 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f24c8847a80 | 0x7f24c3c24140 | 16025467946019 | 16025467955948 | 16025468136269 | 16025468138244 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f24c8847900 | 0x7f24c3c24180 | 16025468166994 | 16025468184750 | 16025468364271 | 16025468366599 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f24c8847780 | 0x7f24c3c241c0 | 16025468383149 | 16025468391471 | 16025468484272 | 16025468486377 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f24c8847600 | 0x7f24c3c24200 | 16025468505096 | 16025468544752 | 16025468637233 | 16025468639693 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f24caee9480 | 0x7f24c3c24240 | 16025468662743 | 16025468699313 | 16025468791794 | 16025468794160 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 38 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f24caee9300 | 0x7f24c3c24280 | 16025468812399 | 16025468821394 | 16025469000915 | 16025469003045 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f24caee9180 | 0x7f24c3c242c0 | 16025469018525 | 16025469027315 | 16025469208757 | 16025469210820 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f24caee9000 | 0x7f24c3c24300 | 16025469230840 | 16025469240917 | 16025469334197 | 16025469336298 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f24c8847e80 | 0x7f24c3c24340 | 16025469352037 | 16025469361718 | 16025469453558 | 16025469455745 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f24c8847d00 | 0x7f24c3c24380 | 16025469478275 | 16025469488599 | 16025469580439 | 16025469582572 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 53 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f24c8847b80 | 0x7f24c3c243c0 | 16025469600142 | 16025469620279 | 16025469800921 | 16025469803027 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f24c8847a00 | 0x7f24c3c24400 | 16025469820727 | 16025469830201 | 16025470011322 | 16025470013503 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f24c8847880 | 0x7f24c3c24440 | 16025470032962 | 16025470042522 | 16025470135323 | 16025470137590 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f24c8847700 | 0x7f24c3c24480 | 16025470154330 | 16025470163643 | 16025470255484 | 16025470257587 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f24caee9580 | 0x7f24c3c244c0 | 16025470278607 | 16025470289244 | 16025470380925 | 16025470383015 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 68 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f24caee9400 | 0x7f24c3c24500 | 16025470402434 | 16025470413085 | 16025470592446 | 16025470594430 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f24caee9280 | 0x7f24c3c24540 | 16025470612739 | 16025470636766 | 16025470815808 | 16025470818045 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f24caee9100 | 0x7f24c3c24580 | 16025470837584 | 16025470847968 | 16025470940449 | 16025470942752 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f24c8847f80 | 0x7f24c3c245c0 | 16025470958292 | 16025470968289 | 16025471059969 | 16025471062089 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f24c8847e00 | 0x7f24c3c24600 | 16025471082819 | 16025471093730 | 16025471185090 | 16025471187207 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 83 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f24c8847c80 | 0x7f24c3c24640 | 16025471206646 | 16025471217250 | 16025471397252 | 16025471399522 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f24c8847b00 | 0x7f24c3c24680 | 16025471416152 | 16025471424932 | 16025471606533 | 16025471608617 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f24c8847980 | 0x7f24c3c246c0 | 16025471626277 | 16025471634693 | 16025471726694 | 16025471728825 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f24c8847800 | 0x7f24c3c24700 | 16025471742304 | 16025471753414 | 16025471846055 | 16025471848072 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f24c8847680 | 0x7f24c3c24740 | 16025471869642 | 16025471878535 | 16025471970536 | 16025471972639 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 98 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f24caee9500 | 0x7f24c3c24780 | 16025471986799 | 16025472011496 | 16025472191817 | 16025472194084 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f24caee9380 | 0x7f24c3c247c0 | 16025472207754 | 16025472233577 | 16025472413899 | 16025472415909 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f24caee9200 | 0x7f24c3c24800 | 16025472430559 | 16025472456779 | 16025472549100 | 16025472551246 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f24caee9080 | 0x7f24c3c24840 | 16025472564526 | 16025472583340 | 16025472675821 | 16025472677914 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f24c8847f00 | 0x7f24c3c24880 | 16025472698253 | 16025472708141 | 16025472799821 | 16025472801861 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 113 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f24c8847d80 | 0x7f24c3c248c0 | 16025472817501 | 16025472832142 | 16025473011823 | 16025473014006 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f24c8847c00 | 0x7f24c3c24900 | 16025473027856 | 16025473038223 | 16025473217264 | 16025473219332 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f24c8847a80 | 0x7f24c3c24940 | 16025473233431 | 16025473250864 | 16025473343185 | 16025473345189 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f24c8847900 | 0x7f24c3c24980 | 16025473360038 | 16025473376625 | 16025473469586 | 16025473471816 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f24c8847780 | 0x7f24c3c249c0 | 16025473491786 | 16025473502226 | 16025473594227 | 16025473596413 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 128 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f24c8847600 | 0x7f24c3c24a00 | 16025473610193 | 16025473627827 | 16025473806868 | 16025473808929 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f24caee9480 | 0x7f24c3c24a40 | 16025473822808 | 16025473840789 | 16025474021110 | 16025474023214 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f24caee9300 | 0x7f24c3c24a80 | 16025474036833 | 16025474054070 | 16025474146231 | 16025474148641 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f24caee9180 | 0x7f24c3c24ac0 | 16025474162061 | 16025474189431 | 16025474282872 | 16025474284938 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f24caee9000 | 0x7f24c3c24b00 | 16025474306597 | 16025474316792 | 16025474408312 | 16025474410495 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 143 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f24c8847e80 | 0x7f24c3c24b40 | 16025474425015 | 16025474441593 | 16025474620634 | 16025474622710 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f24c8847d00 | 0x7f24c3c24b80 | 16025474635910 | 16025474655034 | 16025474833755 | 16025474835886 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f24c8847b80 | 0x7f24c3c24bc0 | 16025474848995 | 16025474867356 | 16025474960956 | 16025474963183 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f24c8847a00 | 0x7f24c3c24c00 | 16025474978242 | 16025474987676 | 16025475080637 | 16025475082240 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f24c8847880 | 0x7f24c3c24c40 | 16025475105490 | 16025475115837 | 16025475207838 | 16025475209467 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 158 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f24c8847700 | 0x7f24c3c24c80 | 16025475224787 | 16025475232958 | 16025475411999 | 16025475413583 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f24caee9580 | 0x7f24c3c24cc0 | 16025475429252 | 16025475437600 | 16025475616001 | 16025475617508 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f24caee9400 | 0x7f24c3c24d00 | 16025475631118 | 16025475639041 | 16025475731362 | 16025475732976 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f24caee9280 | 0x7f24c3c24d40 | 16025475748605 | 16025475756642 | 16025475854082 | 16025475855533 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f24caee9100 | 0x7f24c3c24d80 | 16025475875342 | 16025475885923 | 16025475978403 | 16025475979900 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 173 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f24c8847f80 | 0x7f24c3c24dc0 | 16025475993170 | 16025476001603 | 16025476179365 | 16025476180986 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f24c8847e00 | 0x7f24c3c24e00 | 16025476195345 | 16025476203685 | 16025476384806 | 16025476386321 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f24c8847c80 | 0x7f24c3c24e40 | 16025476401541 | 16025476409446 | 16025476502567 | 16025476504178 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f24c8847b00 | 0x7f24c3c24e80 | 16025476518038 | 16025476525927 | 16025476628328 | 16025476629916 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f24c8847980 | 0x7f24c3c24ec0 | 16025476649425 | 16025476660488 | 16025476752969 | 16025476754473 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 188 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f24c8847800 | 0x7f24c3c24f00 | 16025476769562 | 16025476777609 | 16025476957290 | 16025476958968 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f24c8847680 | 0x7f24c3c24f40 | 16025476974788 | 16025476983210 | 16025477163211 | 16025477164834 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f24caee9500 | 0x7f24c3c24f80 | 16025477179163 | 16025477187052 | 16025477280012 | 16025477281581 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f24caee9380 | 0x7f24c3c24fc0 | 16025477295701 | 16025477303532 | 16025477408813 | 16025477410318 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f24caee9200 | 0x7f24c3c25000 | 16025477429758 | 16025477440973 | 16025477533774 | 16025477535375 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 203 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f24caee9080 | 0x7f24c3c25040 | 16025477550585 | 16025477558894 | 16025477737935 | 16025477739561 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f24c8847f00 | 0x7f24c3c25080 | 16025477755840 | 16025477764496 | 16025477944497 | 16025477946226 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f24c8847d80 | 0x7f24c3c250c0 | 16025477961156 | 16025477969617 | 16025478063058 | 16025478064604 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f24c8847c00 | 0x7f24c3c25100 | 16025478121402 | 16025478131698 | 16025478244499 | 16025478246059 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f24c8847a80 | 0x7f24c3c25140 | 16025478284169 | 16025478293619 | 16025478386100 | 16025478387696 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 218 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f24c8847900 | 0x7f24c3c25180 | 16025478402316 | 16025478410260 | 16025478590421 | 16025478591932 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f24c8847780 | 0x7f24c3c251c0 | 16025478605982 | 16025478613781 | 16025478794743 | 16025478796277 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f24c8847600 | 0x7f24c3c25200 | 16025478811107 | 16025478818903 | 16025478912344 | 16025478913915 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f24caee9480 | 0x7f24c3c25240 | 16025478928794 | 16025478937464 | 16025479055385 | 16025479056982 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f24caee9300 | 0x7f24c3c25280 | 16025479076751 | 16025479087545 | 16025479179705 | 16025479181269 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 233 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f24caee9180 | 0x7f24c3c252c0 | 16025479196338 | 16025479204666 | 16025479384507 | 16025479386014 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f24caee9000 | 0x7f24c3c25300 | 16025479400324 | 16025479408187 | 16025479587388 | 16025479588960 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f24c8847e80 | 0x7f24c3c25340 | 16025479603559 | 16025479611388 | 16025479705469 | 16025479706947 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f24c8847d00 | 0x7f24c3c25380 | 16025479721017 | 16025479729469 | 16025479853630 | 16025479855144 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f24c8847b80 | 0x7f24c3c253c0 | 16025479875293 | 16025479886110 | 16025479979071 | 16025479980581 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 248 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f24c8847a00 | 0x7f24c3c25400 | 16025479996261 | 16025480003871 | 16025480182272 | 16025480183917 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f24c8847880 | 0x7f24c3c25440 | 16025480197826 | 16025480206112 | 16025480386274 | 16025480387822 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f24c8847700 | 0x7f24c3c25480 | 16025480402142 | 16025480410114 | 16025480503395 | 16025480504969 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f24caee9580 | 0x7f24c3c254c0 | 16025480518219 | 16025480526275 | 16025480655236 | 16025480656706 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f24caee9400 | 0x7f24c3c25500 | 16025480677416 | 16025480687876 | 16025480780356 | 16025480781833 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 263 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f24caee9280 | 0x7f24c3c25540 | 16025480797083 | 16025480805477 | 16025480984838 | 16025480986389 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f24caee9100 | 0x7f24c3c25580 | 16025481001118 | 16025481009318 | 16025481188039 | 16025481189604 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f24c8847f80 | 0x7f24c3c255c0 | 16025481203634 | 16025481211879 | 16025481305800 | 16025481307422 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f24c8847e00 | 0x7f24c3c25600 | 16025481321601 | 16025481329640 | 16025481464841 | 16025481466448 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f24c8847c80 | 0x7f24c3c25640 | 16025481486558 | 16025481497321 | 16025481590282 | 16025481591905 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 278 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f24c8847b00 | 0x7f24c3c25680 | 16025481606225 | 16025481614442 | 16025481792843 | 16025481794441 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f24c8847980 | 0x7f24c3c256c0 | 16025481808620 | 16025481816844 | 16025481995725 | 16025481997266 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f24c8847800 | 0x7f24c3c25700 | 16025482011106 | 16025482019405 | 16025482114126 | 16025482115754 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f24c8847680 | 0x7f24c3c25740 | 16025482130983 | 16025482139246 | 16025482281007 | 16025482282720 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f24caee9500 | 0x7f24c3c25780 | 16025482302580 | 16025482313327 | 16025482406928 | 16025482408477 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 293 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f24caee9380 | 0x7f24c3c257c0 | 16025482423307 | 16025482431248 | 16025482610609 | 16025482612093 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f24caee9200 | 0x7f24c3c25800 | 16025482626442 | 16025482634609 | 16025482814450 | 16025482815988 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f24caee9080 | 0x7f24c3c25840 | 16025482830058 | 16025482838451 | 16025482937491 | 16025482939055 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f24c8847f00 | 0x7f24c3c25880 | 16025482952965 | 16025482961171 | 16025483114453 | 16025483115992 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f24c8847d80 | 0x7f24c3c258c0 | 16025483135781 | 16025483146773 | 16025483239573 | 16025483241209 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 308 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f24c8847c00 | 0x7f24c3c25900 | 16025483254968 | 16025483263414 | 16025483442295 | 16025483443904 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f24c8847a80 | 0x7f24c3c25940 | 16025483458244 | 16025483466775 | 16025483646936 | 16025483648560 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f24c8847900 | 0x7f24c3c25980 | 16025483662839 | 16025483670616 | 16025483776537 | 16025483777957 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f24c8847780 | 0x7f24c3c259c0 | 16025483791857 | 16025483800217 | 16025483967578 | 16025483969143 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f24c8847600 | 0x7f24c3c25a00 | 16025483989962 | 16025484000539 | 16025484094459 | 16025484096060 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 323 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f24caee9480 | 0x7f24c3c25a40 | 16025484110629 | 16025484118939 | 16025484298621 | 16025484300225 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f24caee9300 | 0x7f24c3c25a80 | 16025484314865 | 16025484322941 | 16025484504862 | 16025484506331 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f24caee9180 | 0x7f24c3c25ac0 | 16025484519840 | 16025484527902 | 16025484636703 | 16025484638218 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f24caee9000 | 0x7f24c3c25b00 | 16025484652607 | 16025484660863 | 16025484839584 | 16025484841213 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f24c8847e80 | 0x7f24c3c25b40 | 16025484861973 | 16025484872065 | 16025484971745 | 16025484973370 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 338 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f24c8847d00 | 0x7f24c3c25b80 | 16025484988130 | 16025484996066 | 16025485178307 | 16025485179836 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f24c8847b80 | 0x7f24c3c25bc0 | 16025485193285 | 16025485201507 | 16025485384548 | 16025485386071 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f24c8847a00 | 0x7f24c3c25c00 | 16025485402351 | 16025485410148 | 16025485531429 | 16025485533038 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f24c8847880 | 0x7f24c3c25c40 | 16025485546598 | 16025485554789 | 16025485759431 | 16025485775553 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f24c8847700 | 0x7f24c3c25c80 | 16025485790782 | 16025485801351 | 16025485909512 | 16025485911130 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 353 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f24caee9580 | 0x7f24c3c25cc0 | 16025485925709 | 16025485934472 | 16025486116393 | 16025486118215 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f24caee9400 | 0x7f24c3c25d00 | 16025486133865 | 16025486141993 | 16025486326475 | 16025486327970 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f24caee9280 | 0x7f24c3c25d40 | 16025486342720 | 16025486350315 | 16025486483276 | 16025486484907 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f24caee9100 | 0x7f24c3c25d80 | 16025486498716 | 16025486506636 | 16025486737198 | 16025486751941 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f24c8847f80 | 0x7f24c3c25dc0 | 16025486766841 | 16025486778158 | 16025486903279 | 16025486904797 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 368 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f24c8847e00 | 0x7f24c3c25e00 | 16025486919457 | 16025486927599 | 16025487119120 | 16025487120663 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f24c8847c80 | 0x7f24c3c25e40 | 16025487134252 | 16025487142320 | 16025487336242 | 16025487337988 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f24c8847b00 | 0x7f24c3c25e80 | 16025487352808 | 16025487360562 | 16025487518963 | 16025487520434 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f24c8847980 | 0x7f24c3c25ec0 | 16025487534744 | 16025487542803 | 16025487823925 | 16025487838207 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f24c8847800 | 0x7f24c3c25f00 | 16025487853356 | 16025487864245 | 16025488010646 | 16025488012263 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 383 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f24c8847680 | 0x7f24c3c25f40 | 16025488028133 | 16025488035766 | 16025488244408 | 16025488258317 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f24caee9500 | 0x7f24c3c25f80 | 16025488266057 | 16025488276568 | 16025488488570 | 16025488502782 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f24caee9380 | 0x7f24c3c25fc0 | 16025488510642 | 16025488521370 | 16025488704731 | 16025488706298 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f24caee9200 | 0x7f24c3c26000 | 16025488721037 | 16025488728891 | 16025489061534 | 16025489072039 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f24caee9080 | 0x7f24c3c26040 | 16025489087619 | 16025489098014 | 16025489262495 | 16025489264005 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 398 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f24c8847f00 | 0x7f24c3c26080 | 16025489278605 | 16025489286495 | 16025489518497 | 16025489532869 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f24c8847d80 | 0x7f24c3c260c0 | 16025489541359 | 16025489551777 | 16025489780579 | 16025489791403 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f24c8847c00 | 0x7f24c3c26100 | 16025489799953 | 16025489810339 | 16025490020100 | 16025490031998 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f24c8847a80 | 0x7f24c3c26140 | 16025490044108 | 16025490053540 | 16025490436583 | 16025490448389 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f24c8847900 | 0x7f24c3c26180 | 16025490467678 | 16025490478503 | 16025490662345 | 16025490663934 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 413 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f24c8847780 | 0x7f24c3c261c0 | 16025490679464 | 16025490687305 | 16025490938987 | 16025490950528 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f24c8847600 | 0x7f24c3c26200 | 16025490961218 | 16025490977867 | 16025491225548 | 16025491237121 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f24caee9480 | 0x7f24c3c26240 | 16025491246001 | 16025491254989 | 16025491490190 | 16025491501126 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f24caee9300 | 0x7f24c3c26280 | 16025491510595 | 16025491520911 | 16025491970834 | 16025491981955 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f24caee9180 | 0x7f24c3c262c0 | 16025491998065 | 16025492009074 | 16025492231475 | 16025492243009 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 428 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f24caee9000 | 0x7f24c3c26300 | 16025492253209 | 16025492267476 | 16025492565878 | 16025492577462 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f24c8847e80 | 0x7f24c3c26340 | 16025492590401 | 16025492600118 | 16025492899000 | 16025492915054 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f24c8847d00 | 0x7f24c3c26380 | 16025492923754 | 16025492934520 | 16025493228602 | 16025493242647 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f24c8847b80 | 0x7f24c3c263c0 | 16025493252827 | 16025493263163 | 16025493816926 | 16025493827794 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f24c8847a00 | 0x7f24c3c26400 | 16025493844214 | 16025493854847 | 16025494116928 | 16025494131967 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 443 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f24c8847880 | 0x7f24c3c26440 | 16025494140807 | 16025494151169 | 16025494502691 | 16025494518259 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f24c8847700 | 0x7f24c3c26480 | 16025494526448 | 16025494537251 | 16025494887014 | 16025494901150 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f24caee9580 | 0x7f24c3c264c0 | 16025494911390 | 16025494921574 | 16025495266536 | 16025495280342 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f24caee9400 | 0x7f24c3c26500 | 16025495292531 | 16025495302697 | 16025495959501 | 16025495974286 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f24caee9280 | 0x7f24c3c26540 | 16025495990226 | 16025496000301 | 16025496443824 | 16025496459415 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 458 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f24caee9100 | 0x7f24c3c26580 | 16025496467515 | 16025496477585 | 16025496939028 | 16025496953084 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f24c8847f80 | 0x7f24c3c265c0 | 16025496962124 | 16025496972468 | 16025497430391 | 16025497446343 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f24c8847e00 | 0x7f24c3c26600 | 16025497455433 | 16025497466072 | 16025497913435 | 16025497924353 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f24c8847c80 | 0x7f24c3c26640 | 16025497932362 | 16025497941755 | 16025498807041 | 16025498822643 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f24c8847b00 | 0x7f24c3c26680 | 16025498840282 | 16025498850721 | 16025499700967 | 16025499716683 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 473 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f24c8847980 | 0x7f24c3c266c0 | 16025499725473 | 16025499736167 | 16025500617773 | 16025500633702 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f24c8847800 | 0x7f24c3c26700 | 16025500643382 | 16025500654574 | 16025501530900 | 16025501544742 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f24c8847680 | 0x7f24c3c26740 | 16025501553622 | 16025501564020 | 16025502420026 | 16025502436812 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f24caee9500 | 0x7f24c3c26780 | 16025502445912 | 16025502455866 | 16025504150438 | 16025504189744 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f24caee9380 | 0x7f24c3c267c0 | 16025504206123 | 16025504216518 | 16025505877170 | 16025505915985 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 488 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f24caee9200 | 0x7f24c3c26800 | 16025505926685 | 16025505953650 | 16025507675742 | 16025507716135 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f24caee9080 | 0x7f24c3c26840 | 16025507725295 | 16025507735582 | 16025509447434 | 16025509486686 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f24c8847f00 | 0x7f24c3c26880 | 16025509496946 | 16025509506475 | 16025511176246 | 16025511216718 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 143794 | 143794 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f24c8847d80 | 0x7f24c3c268c0 | 16025511226037 | 16025511236567 | 16025514590990 | 16025514635231 |