41 KiB
41 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_SMEM | SQ_INST_LEVEL_SMEM | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBufferAligned.kd | 0 | 0 | 0 | 168845 | 168845 | 33554432 | 256 | 0 | 0 | 4 | 32 | 4160 | 0x0 | 0x7f758e804280 | 3670016 | 3090688 | 345969424 | 16685107292208 | 16679519771609 | 16685255521913 | 16685255636172 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 168845 | 168845 | 32768 | 256 | 0 | 0 | 12 | 24 | 13888 | 0x0 | 0x7f758e823f80 | 512 | 101656 | 11382912 | 16685260804240 | 16685255521913 | 16685260932125 | 16685260936516 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 5 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 14336 | 0x7f75917ec380 | 0x7f758e823fc0 | 65536 | 630202 | 70530368 | 16685260970545 | 16685260932125 | 16685261289563 | 16685261292034 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15040 | 0x7f75917ec200 | 0x7f758e824000 | 65536 | 675110 | 75685000 | 16685261327103 | 16685261289563 | 16685261689241 | 16685261691481 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 11 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 15488 | 0x7f75917ec080 | 0x7f758e824040 | 65536 | 665410 | 74699056 | 16685261723020 | 16685261689241 | 16685262077079 | 16685262090297 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 14 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 15936 | 0x7f758f14df00 | 0x7f758e824080 | 65536 | 664618 | 74477208 | 16685262110907 | 16685262077079 | 16685262385718 | 16685262388008 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 17 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 16384 | 0x7f758f14dd80 | 0x7f758e8240c0 | 65536 | 624184 | 69904368 | 16685262418907 | 16685262385718 | 16685262688756 | 16685262691098 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 20 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 17088 | 0x7f758f14dc00 | 0x7f758e824100 | 131072 | 666920 | 74756872 | 16685262734426 | 16685262688756 | 16685262989555 | 16685262991708 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 17792 | 0x7f758f14da80 | 0x7f758e824140 | 131072 | 711958 | 79732864 | 16685263022407 | 16685262989555 | 16685263382033 | 16685263384315 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 26 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 18496 | 0x7f758f14d900 | 0x7f758e824180 | 65536 | 666688 | 74741736 | 16685263416333 | 16685263382033 | 16685263770031 | 16685263772282 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 29 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19200 | 0x7f758f14d780 | 0x7f758e8241c0 | 131072 | 707084 | 79212912 | 16685263801621 | 16685263770031 | 16685264081389 | 16685264083581 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 32 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 19904 | 0x7f758f14d600 | 0x7f758e824200 | 131072 | 707806 | 79318328 | 16685264115050 | 16685264081389 | 16685264379788 | 16685264382061 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 35 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 20608 | 0x7f75917ec480 | 0x7f758e824240 | 131072 | 699356 | 78524232 | 16685264422210 | 16685264379788 | 16685264678666 | 16685264680952 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 21312 | 0x7f75917ec300 | 0x7f758e824280 | 131072 | 710124 | 79643184 | 16685264711630 | 16685264678666 | 16685265066504 | 16685265068719 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 41 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22016 | 0x7f75917ec180 | 0x7f758e8242c0 | 65536 | 667422 | 74750576 | 16685265100528 | 16685265066504 | 16685265451622 | 16685265453976 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 44 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 22720 | 0x7f75917ec000 | 0x7f758e824300 | 131072 | 705600 | 79052312 | 16685265485295 | 16685265451622 | 16685265750181 | 16685265752286 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 47 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 23424 | 0x7f758f14de80 | 0x7f758e824340 | 131072 | 701132 | 78485128 | 16685265785175 | 16685265750181 | 16685266053699 | 16685266055766 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 50 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 24128 | 0x7f758f14dd00 | 0x7f758e824380 | 131072 | 703390 | 78794440 | 16685266110354 | 16685266053699 | 16685266395138 | 16685266397535 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 24832 | 0x7f758f14db80 | 0x7f758e8243c0 | 131072 | 709234 | 79552968 | 16685266427924 | 16685266395138 | 16685266765696 | 16685266767142 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 56 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 25536 | 0x7f758f14da00 | 0x7f758e824400 | 65536 | 682568 | 76467104 | 16685266797821 | 16685266765696 | 16685267133214 | 16685267134920 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 59 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26240 | 0x7f758f14d880 | 0x7f758e824440 | 131072 | 709132 | 79296776 | 16685267165419 | 16685267133214 | 16685267404413 | 16685267406001 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 62 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 26944 | 0x7f758f14d700 | 0x7f758e824480 | 131072 | 706738 | 79150280 | 16685267436660 | 16685267404413 | 16685267675451 | 16685267677032 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 65 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 27648 | 0x7f75917ec580 | 0x7f758e8244c0 | 131072 | 677718 | 75967448 | 16685267715141 | 16685267675451 | 16685267946490 | 16685267948183 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 28608 | 0x7f75917ec400 | 0x7f758e824500 | 131072 | 701380 | 78602360 | 16685267980442 | 16685267946490 | 16685268308248 | 16685268309861 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 71 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 29312 | 0x7f75917ec280 | 0x7f758e824540 | 65536 | 663300 | 74412768 | 16685268340180 | 16685268308248 | 16685268674006 | 16685268675559 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 74 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 30016 | 0x7f75917ec100 | 0x7f758e824580 | 131072 | 686022 | 76784400 | 16685268707058 | 16685268674006 | 16685268944565 | 16685268946210 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 77 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 30976 | 0x7f758f14df80 | 0x7f758e8245c0 | 131072 | 686456 | 76847744 | 16685268975909 | 16685268944565 | 16685269213203 | 16685269214871 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 80 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 31680 | 0x7f758f14de00 | 0x7f758e824600 | 131072 | 697878 | 78060288 | 16685269252480 | 16685269213203 | 16685269483602 | 16685269485282 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 32640 | 0x7f758f14dc80 | 0x7f758e824640 | 131072 | 664134 | 74488888 | 16685269515521 | 16685269483602 | 16685269844400 | 16685269846000 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 86 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 33600 | 0x7f758f14db00 | 0x7f758e824680 | 65536 | 659588 | 73789248 | 16685269876609 | 16685269844400 | 16685270207278 | 16685270209138 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 89 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 34560 | 0x7f758f14d980 | 0x7f758e8246c0 | 131072 | 702486 | 78709152 | 16685270240667 | 16685270207278 | 16685270483597 | 16685270485359 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 92 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 35520 | 0x7f758f14d800 | 0x7f758e824700 | 131072 | 704206 | 78974304 | 16685270515818 | 16685270483597 | 16685270755436 | 16685270757070 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 95 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 36224 | 0x7f758f14d680 | 0x7f758e824740 | 131072 | 702728 | 78709496 | 16685270796069 | 16685270755436 | 16685271027434 | 16685271028951 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 37184 | 0x7f75917ec500 | 0x7f758e824780 | 131072 | 662308 | 74144592 | 16685271060050 | 16685271027434 | 16685271389513 | 16685271391029 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 101 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 38144 | 0x7f75917ec380 | 0x7f758e8247c0 | 65536 | 664832 | 74435200 | 16685271422658 | 16685271389513 | 16685271749511 | 16685271751207 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 104 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 39104 | 0x7f75917ec200 | 0x7f758e824800 | 131072 | 700778 | 78555856 | 16685271782906 | 16685271749511 | 16685272023109 | 16685272024598 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 107 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 40320 | 0x7f75917ec080 | 0x7f758e824840 | 131072 | 700816 | 78505160 | 16685272056107 | 16685272023109 | 16685272296068 | 16685272297659 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 110 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 41280 | 0x7f758f14df00 | 0x7f758e824880 | 131072 | 698478 | 78238512 | 16685272335867 | 16685272296068 | 16685272569667 | 16685272571260 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 42240 | 0x7f758f14dd80 | 0x7f758e8248c0 | 131072 | 707726 | 79264768 | 16685272601409 | 16685272569667 | 16685272932545 | 16685272934178 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 116 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 43200 | 0x7f758f14dc00 | 0x7f758e824900 | 65536 | 637122 | 71386736 | 16685272964757 | 16685272932545 | 16685273302143 | 16685273303735 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 119 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 44160 | 0x7f758f14da80 | 0x7f758e824940 | 131072 | 709962 | 79497968 | 16685273334754 | 16685273302143 | 16685273574942 | 16685273576406 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 122 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 45376 | 0x7f758f14d900 | 0x7f758e824980 | 131072 | 707774 | 79276376 | 16685273607015 | 16685273574942 | 16685273849500 | 16685273851067 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 125 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 46336 | 0x7f758f14d780 | 0x7f758e8249c0 | 131072 | 702658 | 78686928 | 16685273888766 | 16685273849500 | 16685274123739 | 16685274125428 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 47552 | 0x7f758f14d600 | 0x7f758e824a00 | 131072 | 707580 | 79284192 | 16685274157407 | 16685274123739 | 16685274490137 | 16685274491846 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 131 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 48512 | 0x7f75917ec480 | 0x7f758e824a40 | 65536 | 661000 | 74047760 | 16685274522915 | 16685274490137 | 16685274850775 | 16685274852344 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 134 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 49472 | 0x7f75917ec300 | 0x7f758e824a80 | 131072 | 671052 | 75236424 | 16685274882923 | 16685274850775 | 16685275121494 | 16685275123115 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 137 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 50688 | 0x7f75917ec180 | 0x7f758e824ac0 | 131072 | 661380 | 73998392 | 16685275154004 | 16685275121494 | 16685275395252 | 16685275396686 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 140 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 51648 | 0x7f75917ec000 | 0x7f758e824b00 | 131072 | 669868 | 75083752 | 16685275437155 | 16685275395252 | 16685275672691 | 16685275674267 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 52864 | 0x7f758f14de80 | 0x7f758e824b40 | 131072 | 754822 | 84564328 | 16685275704336 | 16685275672691 | 16685276032849 | 16685276034525 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 146 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 54080 | 0x7f758f14dd00 | 0x7f758e824b80 | 65536 | 676218 | 75821192 | 16685276064324 | 16685276032849 | 16685276389808 | 16685276391503 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 149 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 55296 | 0x7f758f14db80 | 0x7f758e824bc0 | 131072 | 698796 | 78337336 | 16685276422252 | 16685276389808 | 16685276662926 | 16685276664494 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 152 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 56768 | 0x7f758f14da00 | 0x7f758e824c00 | 131072 | 700498 | 78290432 | 16685276695273 | 16685276662926 | 16685276936045 | 16685276937655 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 155 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 57728 | 0x7f758f14d880 | 0x7f758e824c40 | 131072 | 699764 | 78509976 | 16685276975003 | 16685276936045 | 16685277209483 | 16685277211056 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 58944 | 0x7f758f14d700 | 0x7f758e824c80 | 131072 | 672602 | 75338120 | 16685277241575 | 16685277209483 | 16685277569642 | 16685277571084 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 161 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 60160 | 0x7f75917ec580 | 0x7f758e824cc0 | 65536 | 662652 | 74199152 | 16685277602483 | 16685277569642 | 16685277925640 | 16685277927342 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 164 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 61376 | 0x7f75917ec400 | 0x7f758e824d00 | 131072 | 695550 | 77878208 | 16685277957691 | 16685277925640 | 16685278201798 | 16685278203563 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 167 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 62848 | 0x7f75917ec280 | 0x7f758e824d40 | 131072 | 708592 | 79421000 | 16685278235442 | 16685278201798 | 16685278487717 | 16685278489203 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 170 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 63808 | 0x7f75917ec100 | 0x7f758e824d80 | 131072 | 704816 | 78977272 | 16685278528632 | 16685278487717 | 16685278767076 | 16685278768724 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 65024 | 0x7f758f14df80 | 0x7f758e824dc0 | 131072 | 686990 | 77022800 | 16685278799913 | 16685278767076 | 16685279126594 | 16685279128242 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 176 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 66240 | 0x7f758f14de00 | 0x7f758e824e00 | 65536 | 633302 | 70933088 | 16685279159141 | 16685279126594 | 16685279483872 | 16685279485480 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 179 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 67456 | 0x7f758f14dc80 | 0x7f758e824e40 | 131072 | 709458 | 79324840 | 16685279515719 | 16685279483872 | 16685279754271 | 16685279755781 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 182 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 68928 | 0x7f758f14db00 | 0x7f758e824e80 | 131072 | 702034 | 78637528 | 16685279787010 | 16685279754271 | 16685280034909 | 16685280036582 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 185 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 70144 | 0x7f758f14d980 | 0x7f758e824ec0 | 131072 | 673706 | 75481944 | 16685280075681 | 16685280034909 | 16685280305148 | 16685280306823 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 71616 | 0x7f758f14d800 | 0x7f758e824f00 | 131072 | 706184 | 79121312 | 16685280337422 | 16685280305148 | 16685280664666 | 16685280666151 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 191 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 72832 | 0x7f758f14d680 | 0x7f758e824f40 | 65536 | 661918 | 74057952 | 16685280696460 | 16685280664666 | 16685281021784 | 16685281023329 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 194 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 74048 | 0x7f75917ec500 | 0x7f758e824f80 | 131072 | 661766 | 74146424 | 16685281053178 | 16685281021784 | 16685281298903 | 16685281300350 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 197 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 75776 | 0x7f75917ec380 | 0x7f758e824fc0 | 131072 | 680940 | 76211568 | 16685281331199 | 16685281298903 | 16685281584341 | 16685281585970 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 200 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 76992 | 0x7f75917ec200 | 0x7f758e825000 | 131072 | 701734 | 78679616 | 16685281624219 | 16685281584341 | 16685281857780 | 16685281859541 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 78464 | 0x7f75917ec080 | 0x7f758e825040 | 131072 | 705480 | 79031688 | 16685281890250 | 16685281857780 | 16685282217938 | 16685282219519 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 206 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 79936 | 0x7f758f14df00 | 0x7f758e825080 | 65536 | 667956 | 74882880 | 16685282252258 | 16685282217938 | 16685282579057 | 16685282580887 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 209 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 81408 | 0x7f758f14dd80 | 0x7f758e8250c0 | 131072 | 714954 | 80113312 | 16685282610706 | 16685282579057 | 16685282851855 | 16685282853538 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 212 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 83136 | 0x7f758f14dc00 | 0x7f758e825100 | 131072 | 724758 | 81052624 | 16685282884057 | 16685282851855 | 16685283142734 | 16685283144279 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 215 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 84352 | 0x7f758f14da80 | 0x7f758e825140 | 131072 | 709028 | 79514888 | 16685283192887 | 16685283142734 | 16685283416492 | 16685283418170 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 85824 | 0x7f758f14d900 | 0x7f758e825180 | 131072 | 704226 | 78955560 | 16685283450359 | 16685283416492 | 16685283779210 | 16685283781008 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 221 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 87296 | 0x7f758f14d780 | 0x7f758e8251c0 | 65536 | 668836 | 74911000 | 16685283811067 | 16685283779210 | 16685284142569 | 16685284144256 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 224 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 88768 | 0x7f758f14d600 | 0x7f758e825200 | 131072 | 696098 | 77985336 | 16685284173895 | 16685284142569 | 16685284416807 | 16685284418456 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 227 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 90752 | 0x7f75917ec480 | 0x7f758e825240 | 131072 | 714118 | 79942648 | 16685284450285 | 16685284416807 | 16685284718566 | 16685284720216 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 230 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 91968 | 0x7f75917ec300 | 0x7f758e825280 | 131072 | 712258 | 79888536 | 16685284757635 | 16685284718566 | 16685284990884 | 16685284992457 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 93440 | 0x7f75917ec180 | 0x7f758e8252c0 | 131072 | 700302 | 78440056 | 16685285023316 | 16685284990884 | 16685285353923 | 16685285355485 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 236 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 94912 | 0x7f75917ec000 | 0x7f758e825300 | 65536 | 672218 | 75111528 | 16685285386104 | 16685285353923 | 16685285710881 | 16685285712434 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 239 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 96384 | 0x7f758f14de80 | 0x7f758e825340 | 131072 | 709816 | 79532000 | 16685285742313 | 16685285710881 | 16685285988799 | 16685285990434 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 242 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 98368 | 0x7f758f14dd00 | 0x7f758e825380 | 131072 | 699140 | 78312032 | 16685286020173 | 16685285988799 | 16685286304958 | 16685286306804 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 245 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 99584 | 0x7f758f14db80 | 0x7f758e8253c0 | 131072 | 706044 | 79057064 | 16685286343783 | 16685286304958 | 16685286587996 | 16685286589484 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 101312 | 0x7f758f14da00 | 0x7f758e825400 | 131072 | 670326 | 75157888 | 16685286619073 | 16685286587996 | 16685286951195 | 16685286952702 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 251 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 102784 | 0x7f758f14d880 | 0x7f758e825440 | 65536 | 669770 | 75006104 | 16685286983291 | 16685286951195 | 16685287308953 | 16685287310700 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 254 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 104256 | 0x7f758f14d700 | 0x7f758e825480 | 131072 | 669778 | 74909232 | 16685287340239 | 16685287308953 | 16685287586871 | 16685287588521 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 257 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 106240 | 0x7f75917ec580 | 0x7f758e8254c0 | 131072 | 679824 | 76100512 | 16685287618590 | 16685287586871 | 16685287896150 | 16685287897731 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 260 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 107712 | 0x7f75917ec400 | 0x7f758e825500 | 131072 | 662212 | 74229136 | 16685287935550 | 16685287896150 | 16685288167669 | 16685288169282 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 109440 | 0x7f75917ec280 | 0x7f758e825540 | 131072 | 700700 | 78568184 | 16685288199361 | 16685288167669 | 16685288534227 | 16685288535880 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 266 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 111168 | 0x7f75917ec100 | 0x7f758e825580 | 65536 | 663312 | 74336728 | 16685288566379 | 16685288534227 | 16685288890065 | 16685288891858 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 269 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 112896 | 0x7f758f14df80 | 0x7f758e8255c0 | 131072 | 704356 | 78917672 | 16685288922287 | 16685288890065 | 16685289163824 | 16685289165369 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 272 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 115136 | 0x7f758f14de00 | 0x7f758e825600 | 131072 | 700018 | 78444304 | 16685289195118 | 16685289163824 | 16685289482062 | 16685289483488 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 275 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 116608 | 0x7f758f14dc80 | 0x7f758e825640 | 131072 | 708320 | 79363880 | 16685289520737 | 16685289482062 | 16685289756461 | 16685289757999 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 118336 | 0x7f758f14db00 | 0x7f758e825680 | 131072 | 704274 | 78812336 | 16685289787648 | 16685289756461 | 16685290124779 | 16685290126667 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 281 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 16 | 24 | 120064 | 0x7f758f14d980 | 0x7f758e8256c0 | 65536 | 659564 | 74028752 | 16685290157576 | 16685290124779 | 16685290490217 | 16685290491795 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 284 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 121792 | 0x7f758f14d800 | 0x7f758e825700 | 131072 | 703792 | 78824544 | 16685290521294 | 16685290490217 | 16685290772135 | 16685290773616 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 287 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 124032 | 0x7f758f14d680 | 0x7f758e825740 | 131072 | 701936 | 78473736 | 16685290803585 | 16685290772135 | 16685291095014 | 16685291096625 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 290 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 125504 | 0x7f75917ec500 | 0x7f758e825780 | 131072 | 706782 | 79254496 | 16685291133764 | 16685291095014 | 16685291368132 | 16685291369616 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 127488 | 0x7f75917ec380 | 0x7f758e8257c0 | 131072 | 704270 | 78905672 | 16685291400235 | 16685291368132 | 16685291728291 | 16685291729854 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 296 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 129216 | 0x7f75917ec200 | 0x7f758e825800 | 65536 | 670988 | 75081368 | 16685291760293 | 16685291728291 | 16685292085249 | 16685292086812 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 299 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 130944 | 0x7f75917ec080 | 0x7f758e825840 | 131072 | 677464 | 75862736 | 16685292116971 | 16685292085249 | 16685292366687 | 16685292368123 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 302 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 133440 | 0x7f758f14df00 | 0x7f758e825880 | 131072 | 671992 | 75299560 | 16685292397962 | 16685292366687 | 16685292703806 | 16685292705461 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 305 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 134912 | 0x7f758f14dd80 | 0x7f758e8258c0 | 131072 | 1042600 | 116590680 | 16685292743190 | 16685292703806 | 16685292984604 | 16685292986212 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 136896 | 0x7f758f14dc00 | 0x7f758e825900 | 131072 | 664960 | 74464016 | 16685293015911 | 16685292984604 | 16685293342363 | 16685293344050 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 311 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 138880 | 0x7f758f14da80 | 0x7f758e825940 | 65536 | 660582 | 73875408 | 16685293373639 | 16685293342363 | 16685293701721 | 16685293703188 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 314 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 140864 | 0x7f758f14d900 | 0x7f758e825980 | 131072 | 702244 | 78741656 | 16685293732897 | 16685293701721 | 16685293986199 | 16685293987639 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 317 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 143616 | 0x7f758f14d780 | 0x7f758e8259c0 | 131072 | 702142 | 78606344 | 16685294017228 | 16685293986199 | 16685294343318 | 16685294345087 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 320 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 145344 | 0x7f758f14d600 | 0x7f758e825a00 | 131072 | 1048174 | 117541856 | 16685294382696 | 16685294343318 | 16685294625396 | 16685294626878 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 147584 | 0x7f75917ec480 | 0x7f758e825a40 | 131072 | 705432 | 78963136 | 16685294656827 | 16685294625396 | 16685294985874 | 16685294987496 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 326 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 149568 | 0x7f75917ec300 | 0x7f758e825a80 | 65536 | 662536 | 74102520 | 16685295018225 | 16685294985874 | 16685295341553 | 16685295343284 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 329 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 151552 | 0x7f75917ec180 | 0x7f758e825ac0 | 131072 | 665364 | 74455432 | 16685295373003 | 16685295341553 | 16685295631791 | 16685295633394 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 332 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 154304 | 0x7f75917ec000 | 0x7f758e825b00 | 131072 | 704980 | 78945672 | 16685295663003 | 16685295631791 | 16685295997069 | 16685295998532 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 335 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 156288 | 0x7f758f14de80 | 0x7f758e825b40 | 131072 | 1001348 | 112110888 | 16685296036221 | 16685295997069 | 16685296280268 | 16685296281893 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 158784 | 0x7f758f14dd00 | 0x7f758e825b80 | 131072 | 701350 | 78620408 | 16685296311462 | 16685296280268 | 16685296642026 | 16685296643691 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 341 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 161024 | 0x7f758f14db80 | 0x7f758e825bc0 | 65536 | 666294 | 74561784 | 16685296672900 | 16685296642026 | 16685297001864 | 16685297003689 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 344 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 163264 | 0x7f758f14da00 | 0x7f758e825c00 | 131072 | 658382 | 73758272 | 16685297033398 | 16685297001864 | 16685297302183 | 16685297303609 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 347 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 166528 | 0x7f758f14d880 | 0x7f758e825c40 | 131072 | 665724 | 74566632 | 16685297333118 | 16685297302183 | 16685297692581 | 16685297712625 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 350 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 168512 | 0x7f758f14d700 | 0x7f758e825c80 | 131072 | 1046382 | 117154512 | 16685297731135 | 16685297692581 | 16685297989539 | 16685297991086 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 171264 | 0x7f75917ec580 | 0x7f758e825cc0 | 131072 | 666648 | 74589920 | 16685298021005 | 16685297989539 | 16685298361057 | 16685298362734 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 356 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 173760 | 0x7f75917ec400 | 0x7f758e825d00 | 65536 | 669520 | 74975592 | 16685298393893 | 16685298361057 | 16685298723936 | 16685298725492 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 359 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 176256 | 0x7f75917ec280 | 0x7f758e825d40 | 131072 | 679062 | 76009536 | 16685298755701 | 16685298723936 | 16685299042014 | 16685299043721 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 362 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 179776 | 0x7f75917ec100 | 0x7f758e825d80 | 131072 | 707362 | 79251616 | 16685299073690 | 16685299042014 | 16685299453692 | 16685299497876 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 365 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 182272 | 0x7f758f14df80 | 0x7f758e825dc0 | 131072 | 1002434 | 112165616 | 16685299516225 | 16685299453692 | 16685299799450 | 16685299801036 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 185536 | 0x7f758f14de00 | 0x7f758e825e00 | 131072 | 708390 | 79444936 | 16685299830895 | 16685299799450 | 16685300170488 | 16685300214692 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 371 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 188544 | 0x7f758f14dc80 | 0x7f758e825e40 | 65536 | 667578 | 74849072 | 16685300224482 | 16685300170488 | 16685300576886 | 16685300618049 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 374 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 191552 | 0x7f758f14db00 | 0x7f758e825e80 | 131072 | 667872 | 74843968 | 16685300628578 | 16685300576886 | 16685300946004 | 16685300947558 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 377 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 195840 | 0x7f758f14d980 | 0x7f758e825ec0 | 131072 | 672974 | 75360680 | 16685300977167 | 16685300946004 | 16685301409042 | 16685301427932 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 380 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 198592 | 0x7f758f14d800 | 0x7f758e825f00 | 131072 | 1037170 | 116268576 | 16685301448331 | 16685301409042 | 16685301740881 | 16685301742331 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 202368 | 0x7f758f14d680 | 0x7f758e825f40 | 131072 | 1001800 | 112099744 | 16685301772210 | 16685301740881 | 16685302131119 | 16685302149138 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 386 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 205888 | 0x7f75917ec500 | 0x7f758e825f80 | 65536 | 653208 | 73177312 | 16685302161878 | 16685302131119 | 16685302533677 | 16685302550585 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 389 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 209408 | 0x7f75917ec380 | 0x7f758e825fc0 | 131072 | 669022 | 74992024 | 16685302564854 | 16685302533677 | 16685302906315 | 16685302907843 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 392 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 214464 | 0x7f75917ec200 | 0x7f758e826000 | 131072 | 665578 | 74511776 | 16685302938022 | 16685302906315 | 16685303420872 | 16685303437125 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 395 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 217728 | 0x7f75917ec080 | 0x7f758e826040 | 131072 | 1048954 | 117435048 | 16685303460494 | 16685303420872 | 16685303779270 | 16685303780964 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 222016 | 0x7f758f14df00 | 0x7f758e826080 | 131072 | 1030902 | 115550512 | 16685303810643 | 16685303779270 | 16685304190788 | 16685304207240 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 401 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 226048 | 0x7f758f14dd80 | 0x7f758e8260c0 | 65536 | 670566 | 75093592 | 16685304224039 | 16685304190788 | 16685304604386 | 16685304621546 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 404 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 230080 | 0x7f758f14dc00 | 0x7f758e826100 | 131072 | 666380 | 74643112 | 16685304635645 | 16685304604386 | 16685305000704 | 16685305018943 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 407 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 235904 | 0x7f758f14da80 | 0x7f758e826140 | 131072 | 662956 | 74382272 | 16685305032112 | 16685305000704 | 16685305573021 | 16685305589814 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 410 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 239424 | 0x7f758f14d900 | 0x7f758e826180 | 131072 | 1037400 | 116249872 | 16685305612373 | 16685305573021 | 16685305943899 | 16685305945332 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 244224 | 0x7f758f14d780 | 0x7f758e8261c0 | 131072 | 992268 | 111141936 | 16685305975511 | 16685305943899 | 16685306386937 | 16685306414076 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 416 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 248768 | 0x7f758f14d600 | 0x7f758e826200 | 65536 | 667314 | 74716664 | 16685306425376 | 16685306386937 | 16685306837815 | 16685306880801 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 419 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 253312 | 0x7f75917ec480 | 0x7f758e826240 | 131072 | 667056 | 74640128 | 16685306891191 | 16685306837815 | 16685307287093 | 16685307329196 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 422 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 255552 | 0x7f75917ec300 | 0x7f758e826280 | 131072 | 1042462 | 116829272 | 16685307339536 | 16685307287093 | 16685307949009 | 16685307992244 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 425 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 259840 | 0x7f75917ec180 | 0x7f758e8262c0 | 131072 | 1037820 | 116276888 | 16685308010913 | 16685307949009 | 16685308386927 | 16685308428390 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 265664 | 0x7f75917ec000 | 0x7f758e826300 | 131072 | 988712 | 110695824 | 16685308439089 | 16685308386927 | 16685308897325 | 16685308938553 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 431 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 271232 | 0x7f758f14de80 | 0x7f758e826340 | 65536 | 662868 | 74315072 | 16685308949092 | 16685308897325 | 16685309402602 | 16685309444736 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 434 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 273216 | 0x7f758f14dd00 | 0x7f758e826380 | 131072 | 1015826 | 113815496 | 16685309454566 | 16685309402602 | 16685309909320 | 16685309926050 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 437 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 275712 | 0x7f758f14db80 | 0x7f758e8263c0 | 131072 | 1037342 | 116296240 | 16685309940009 | 16685309909320 | 16685310654436 | 16685310698764 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 440 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 280768 | 0x7f758f14da00 | 0x7f758e826400 | 131072 | 1003100 | 112284296 | 16685310716864 | 16685310654436 | 16685311140513 | 16685311184678 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 287616 | 0x7f758f14d880 | 0x7f758e826440 | 131072 | 1038570 | 116480040 | 16685311194838 | 16685311140513 | 16685311703711 | 16685311745849 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 446 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 294208 | 0x7f758f14d700 | 0x7f758e826480 | 65536 | 670934 | 75199440 | 16685311755859 | 16685311703711 | 16685312263548 | 16685312304971 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 449 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 296960 | 0x7f75917ec580 | 0x7f758e8264c0 | 131072 | 1045098 | 117170576 | 16685312315391 | 16685312263548 | 16685312825305 | 16685312866452 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 452 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 299968 | 0x7f75917ec400 | 0x7f758e826500 | 131072 | 1086360 | 121623440 | 16685312877172 | 16685312825305 | 16685313691701 | 16685313733554 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 455 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 302720 | 0x7f75917ec280 | 0x7f758e826540 | 131072 | 1044512 | 116836008 | 16685313751943 | 16685313691701 | 16685314345617 | 16685314390692 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 305472 | 0x7f75917ec100 | 0x7f758e826580 | 131072 | 1040906 | 116327896 | 16685314401361 | 16685314345617 | 16685315023534 | 16685315067789 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 461 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 308224 | 0x7f758f14df80 | 0x7f758e8265c0 | 65536 | 697662 | 78237064 | 16685315078099 | 16685315023534 | 16685315696651 | 16685315738377 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 464 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 310976 | 0x7f758f14de00 | 0x7f758e826600 | 131072 | 1036902 | 116083272 | 16685315748667 | 16685315696651 | 16685316354567 | 16685316395885 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 467 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 313216 | 0x7f758f14dc80 | 0x7f758e826640 | 131072 | 1038926 | 116373768 | 16685316405785 | 16685316354567 | 16685317446882 | 16685317491019 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 470 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 315968 | 0x7f758f14db00 | 0x7f758e826680 | 131072 | 1038924 | 116251216 | 16685317509938 | 16685317446909 | 16685318526904 | 16685318578773 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 318720 | 0x7f758f14d980 | 0x7f758e8266c0 | 131072 | 1029040 | 115517808 | 16685318589762 | 16685318526904 | 16685319648497 | 16685319715205 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 476 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 321472 | 0x7f758f14d800 | 0x7f758e826700 | 65536 | 663068 | 74233352 | 16685319725365 | 16685319648497 | 16685320788332 | 16685320854467 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 479 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 324224 | 0x7f758f14d680 | 0x7f758e826740 | 131072 | 1046210 | 117163952 | 16685320864537 | 16685320788332 | 16685321892646 | 16685321955961 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 482 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 326464 | 0x7f75917ec500 | 0x7f758e826780 | 131072 | 1044126 | 116811304 | 16685321966510 | 16685321892646 | 16685323842396 | 16685323909426 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 485 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 329216 | 0x7f75917ec380 | 0x7f758e8267c0 | 131072 | 1043980 | 116783592 | 16685323927515 | 16685323842396 | 16685325760467 | 16685325831362 |
| 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 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 331968 | 0x7f75917ec200 | 0x7f758e826800 | 131072 | 1037862 | 115993488 | 16685325842122 | 16685325760467 | 16685327739337 | 16685327810026 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 491 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 12 | 24 | 334720 | 0x7f75917ec080 | 0x7f758e826840 | 65536 | 668948 | 74941856 | 16685327821406 | 16685327739337 | 16685329719967 | 16685329784841 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 494 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 337472 | 0x7f758f14df00 | 0x7f758e826880 | 131072 | 1038516 | 116490320 | 16685329795630 | 16685329719967 | 16685331650678 | 16685331721976 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 497 | 168845 | 168845 | 4194304 | 256 | 0 | 0 | 8 | 24 | 0 | 0x7f758f14dd80 | 0x7f758e8268c0 | 131072 | 1043422 | 117086000 | 16685331732436 | 16685331650678 | 16685335266500 | 16685335341486 |