40 KiB
40 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | SQ_INSTS_LDS | SQ_INST_LEVEL_LDS | SQ_ACCUM_PREV_HIRES | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 760307 | 760312 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f0a03a04180 | 0 | 0 | 0 | 12073373706548791 | 12073373951177370 | 12073373951501368 | 12073373951611411 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 760307 | 760312 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f0a03a35100 | 0 | 0 | 0 | 12073373965893753 | 12073373966201733 | 12073373966208773 | 12073373966219919 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f0b33d44900 | 0x7f0a03a35140 | 0 | 0 | 0 | 12073373966280211 | 12073373966497732 | 12073373966636931 | 12073373966640911 |
| 5 | 3 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 6 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f0b33d44800 | 0x7f0a03a35180 | 0 | 0 | 0 | 12073373966713276 | 12073373966885090 | 12073373967137248 | 12073373967206162 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f0b33d44700 | 0x7f0a03a351c0 | 0 | 0 | 0 | 12073373967241918 | 12073373967417727 | 12073373967670686 | 12073373967738150 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f0b33d44600 | 0x7f0a03a35200 | 0 | 0 | 0 | 12073373967767315 | 12073373967941084 | 12073373968082364 | 12073373968086508 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f0b33d44500 | 0x7f0a03a35240 | 0 | 0 | 0 | 12073373968131822 | 12073373968307643 | 12073373968449242 | 12073373968452879 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f0b33d44400 | 0x7f0a03a35280 | 0 | 0 | 0 | 12073373968531855 | 12073373968690841 | 12073373968820600 | 12073373968824229 |
| 10 | 8 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 16 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f0b33d44300 | 0x7f0a03a352c0 | 0 | 0 | 0 | 12073373968874532 | 12073373969045079 | 12073373969299318 | 12073373969342081 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f0b33d44a00 | 0x7f0a03a35300 | 0 | 0 | 0 | 12073373969369021 | 12073373969545556 | 12073373969836435 | 12073373969876925 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f0b33d44900 | 0x7f0a03a35340 | 0 | 0 | 0 | 12073373969901551 | 12073373970092754 | 12073373970225713 | 12073373970229590 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f0b33d44800 | 0x7f0a03a35380 | 0 | 0 | 0 | 12073373970283831 | 12073373970450672 | 12073373970589551 | 12073373970593236 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f0b33d44700 | 0x7f0a03a353c0 | 0 | 0 | 0 | 12073373970655572 | 12073373970815630 | 12073373970946189 | 12073373970949889 |
| 15 | 13 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 26 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f0b33d44600 | 0x7f0a03a35400 | 0 | 0 | 0 | 12073373970998369 | 12073373971172108 | 12073373971431947 | 12073373971500242 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f0b33d44500 | 0x7f0a03a35440 | 0 | 0 | 0 | 12073373971527162 | 12073373971700906 | 12073373971955304 | 12073373972023043 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f0b33d44400 | 0x7f0a03a35480 | 0 | 0 | 0 | 12073373972050665 | 12073373972226023 | 12073373972359622 | 12073373972363376 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f0b33d44300 | 0x7f0a03a354c0 | 0 | 0 | 0 | 12073373972415443 | 12073373972573701 | 12073373972711460 | 12073373972715370 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f0b33d44a00 | 0x7f0a03a35500 | 0 | 0 | 0 | 12073373972776193 | 12073373972939939 | 12073373973074179 | 12073373973078385 |
| 20 | 18 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 36 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f0b33d44900 | 0x7f0a03a35540 | 0 | 0 | 0 | 12073373973128698 | 12073373973306657 | 12073373973570496 | 12073373973637424 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f0b33d44800 | 0x7f0a03a35580 | 0 | 0 | 0 | 12073373973663502 | 12073373973845375 | 12073373974103293 | 12073373974173510 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f0b33d44700 | 0x7f0a03a355c0 | 0 | 0 | 0 | 12073373974201311 | 12073373974375932 | 12073373974505691 | 12073373974509524 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f0b33d44600 | 0x7f0a03a35600 | 0 | 0 | 0 | 12073373974563064 | 12073373974719770 | 12073373974861850 | 12073373974865726 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f0b33d44500 | 0x7f0a03a35640 | 0 | 0 | 0 | 12073373974927020 | 12073373975092888 | 12073373975226168 | 12073373975230274 |
| 25 | 23 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 46 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f0b33d44400 | 0x7f0a03a35680 | 0 | 0 | 0 | 12073373975273163 | 12073373975443287 | 12073373975698645 | 12073373975765468 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f0b33d44300 | 0x7f0a03a356c0 | 0 | 0 | 0 | 12073373975792579 | 12073373975963124 | 12073373976219443 | 12073373976287719 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f0b33d44a00 | 0x7f0a03a35700 | 0 | 0 | 0 | 12073373976315921 | 12073373976492561 | 12073373976623761 | 12073373976627751 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f0b33d44900 | 0x7f0a03a35740 | 0 | 0 | 0 | 12073373976677082 | 12073373976841360 | 12073373976974799 | 12073373976978683 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f0b33d44800 | 0x7f0a03a35780 | 0 | 0 | 0 | 12073373977045898 | 12073373977207438 | 12073373977337037 | 12073373977341166 |
| 30 | 28 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 56 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f0b33d44700 | 0x7f0a03a357c0 | 0 | 0 | 0 | 12073373977393203 | 12073373977549996 | 12073373977806155 | 12073373977848980 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f0b33d44600 | 0x7f0a03a35800 | 0 | 0 | 0 | 12073373977874888 | 12073373978052234 | 12073373978310792 | 12073373978379767 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f0b33d44500 | 0x7f0a03a35840 | 0 | 0 | 0 | 12073373978409091 | 12073373978581831 | 12073373978711590 | 12073373978715471 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f0b33d44400 | 0x7f0a03a35880 | 0 | 0 | 0 | 12073373978765744 | 12073373978921029 | 12073373979062149 | 12073373979066403 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f0b33d44300 | 0x7f0a03a358c0 | 0 | 0 | 0 | 12073373979128338 | 12073373979290467 | 12073373979466946 | 12073373979470734 |
| 35 | 33 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 66 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f0b33d44a00 | 0x7f0a03a35900 | 0 | 0 | 0 | 12073373979521969 | 12073373979678465 | 12073373979933664 | 12073373980005879 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f0b33d44900 | 0x7f0a03a35940 | 0 | 0 | 0 | 12073373980034071 | 12073373980207583 | 12073373980465821 | 12073373980534631 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f0b33d44800 | 0x7f0a03a35980 | 0 | 0 | 0 | 12073373980561501 | 12073373980731260 | 12073373980858780 | 12073373980862601 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f0b33d44700 | 0x7f0a03a359c0 | 0 | 0 | 0 | 12073373980910510 | 12073373981078298 | 12073373981216378 | 12073373981220506 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f0b33d44600 | 0x7f0a03a35a00 | 0 | 0 | 0 | 12073373981282321 | 12073373981442457 | 12073373981573176 | 12073373981576948 |
| 40 | 38 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 76 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f0b33d44500 | 0x7f0a03a35a40 | 0 | 0 | 0 | 12073373981626460 | 12073373981794775 | 12073373982057493 | 12073373982127842 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f0b33d44400 | 0x7f0a03a35a80 | 0 | 0 | 0 | 12073373982156726 | 12073373982334452 | 12073373982590771 | 12073373982659139 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f0b33d44300 | 0x7f0a03a35ac0 | 0 | 0 | 0 | 12073373982683955 | 12073373982856049 | 12073373982989969 | 12073373982993731 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f0b33d44a00 | 0x7f0a03a35b00 | 0 | 0 | 0 | 12073373983043454 | 12073373983206928 | 12073373983348847 | 12073373983352748 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f0b33d44900 | 0x7f0a03a35b40 | 0 | 0 | 0 | 12073373983413481 | 12073373983570766 | 12073373983709645 | 12073373983713489 |
| 45 | 43 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 86 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f0b33d44800 | 0x7f0a03a35b80 | 0 | 0 | 0 | 12073373983764103 | 12073373983917644 | 12073373984183083 | 12073373984252210 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f0b33d44700 | 0x7f0a03a35bc0 | 0 | 0 | 0 | 12073373984279440 | 12073373984452201 | 12073373984707400 | 12073373984747921 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f0b33d44600 | 0x7f0a03a35c00 | 0 | 0 | 0 | 12073373984776053 | 12073373984945319 | 12073373985080678 | 12073373985084587 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f0b33d44500 | 0x7f0a03a35c40 | 0 | 0 | 0 | 12073373985133417 | 12073373985303877 | 12073373985448036 | 12073373985451889 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f0b33d44400 | 0x7f0a03a35c80 | 0 | 0 | 0 | 12073373985511751 | 12073373985667555 | 12073373985798755 | 12073373985802561 |
| 50 | 48 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 96 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f0b33d44300 | 0x7f0a03a35cc0 | 0 | 0 | 0 | 12073373985849969 | 12073373986022754 | 12073373986294912 | 12073373986364666 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f0b33d44a00 | 0x7f0a03a35d00 | 0 | 0 | 0 | 12073373986393700 | 12073373986564991 | 12073373986820030 | 12073373986887197 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f0b33d44900 | 0x7f0a03a35d40 | 0 | 0 | 0 | 12073373986914688 | 12073373987091868 | 12073373987224508 | 12073373987228351 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f0b33d44800 | 0x7f0a03a35d80 | 0 | 0 | 0 | 12073373987277863 | 12073373987439226 | 12073373987581786 | 12073373987585595 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f0b33d44700 | 0x7f0a03a35dc0 | 0 | 0 | 0 | 12073373987646127 | 12073373987804985 | 12073373987939864 | 12073373987943840 |
| 55 | 53 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 106 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f0b33d44600 | 0x7f0a03a35e00 | 0 | 0 | 0 | 12073373987992621 | 12073373988165303 | 12073373988425141 | 12073373988493131 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f0b33d44500 | 0x7f0a03a35e40 | 0 | 0 | 0 | 12073373988522165 | 12073373988690260 | 12073373988943699 | 12073373989019650 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f0b33d44400 | 0x7f0a03a35e80 | 0 | 0 | 0 | 12073373989053272 | 12073373989223857 | 12073373989352337 | 12073373989356155 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f0b33d44300 | 0x7f0a03a35ec0 | 0 | 0 | 0 | 12073373989405727 | 12073373989562576 | 12073373989698415 | 12073373989702378 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f0b33d44a00 | 0x7f0a03a35f00 | 0 | 0 | 0 | 12073373989765265 | 12073373989926734 | 12073373990056973 | 12073373990061165 |
| 60 | 58 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 116 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f0b33d44900 | 0x7f0a03a35f40 | 0 | 0 | 0 | 12073373990110477 | 12073373990278092 | 12073373990546731 | 12073373990613582 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f0b33d44800 | 0x7f0a03a35f80 | 0 | 0 | 0 | 12073373990639480 | 12073373990810089 | 12073373991065128 | 12073373991132186 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f0b33d44700 | 0x7f0a03a35fc0 | 0 | 0 | 0 | 12073373991161891 | 12073373991333127 | 12073373991465126 | 12073373991469032 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f0b33d44600 | 0x7f0a03a36000 | 0 | 0 | 0 | 12073373991518564 | 12073373991676965 | 12073373991819044 | 12073373991822979 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f0b33d44500 | 0x7f0a03a36040 | 0 | 0 | 0 | 12073373991884674 | 12073373992047363 | 12073373992178243 | 12073373992182648 |
| 65 | 63 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 126 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f0b33d44400 | 0x7f0a03a36080 | 0 | 0 | 0 | 12073373992232160 | 12073373992391202 | 12073373992666560 | 12073373992715528 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f0b33d44300 | 0x7f0a03a360c0 | 0 | 0 | 0 | 12073373992741456 | 12073373992910239 | 12073373993167038 | 12073373993216339 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f0b33d44a00 | 0x7f0a03a36100 | 0 | 0 | 0 | 12073373993244461 | 12073373993414716 | 12073373993552156 | 12073373993556070 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f0b33d44900 | 0x7f0a03a36140 | 0 | 0 | 0 | 12073373993605001 | 12073373993771515 | 12073373993915194 | 12073373993919014 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f0b33d44800 | 0x7f0a03a36180 | 0 | 0 | 0 | 12073373993981280 | 12073373994143353 | 12073373994278072 | 12073373994282099 |
| 70 | 68 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 136 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f0b33d44700 | 0x7f0a03a361c0 | 0 | 0 | 0 | 12073373994331741 | 12073373994493591 | 12073373994762390 | 12073373994785024 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f0b33d44600 | 0x7f0a03a36200 | 0 | 0 | 0 | 12073373994828064 | 12073373994981429 | 12073373995238867 | 12073373995287147 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f0b33d44500 | 0x7f0a03a36240 | 0 | 0 | 0 | 12073373995314878 | 12073373995485426 | 12073373995624305 | 12073373995628201 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f0b33d44400 | 0x7f0a03a36280 | 0 | 0 | 0 | 12073373995677162 | 12073373995835184 | 12073373995986063 | 12073373995990013 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f0b33d44300 | 0x7f0a03a362c0 | 0 | 0 | 0 | 12073373996067928 | 12073373996223982 | 12073373996355022 | 12073373996359079 |
| 75 | 73 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 146 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f0b33d44a00 | 0x7f0a03a36300 | 0 | 0 | 0 | 12073373996408922 | 12073373996564141 | 12073373996834219 | 12073373996882001 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f0b33d44900 | 0x7f0a03a36340 | 0 | 0 | 0 | 12073373996908781 | 12073373997084298 | 12073373997338377 | 12073373997387661 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f0b33d44800 | 0x7f0a03a36380 | 0 | 0 | 0 | 12073373997413949 | 12073373997591175 | 12073373997723815 | 12073373997727592 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f0b33d44700 | 0x7f0a03a363c0 | 0 | 0 | 0 | 12073373997776483 | 12073373997931814 | 12073373998089413 | 12073373998093713 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f0b33d44600 | 0x7f0a03a36400 | 0 | 0 | 0 | 12073373998154866 | 12073373998315332 | 12073373998450531 | 12073373998454413 |
| 80 | 78 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 156 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f0b33d44500 | 0x7f0a03a36440 | 0 | 0 | 0 | 12073373998502813 | 12073373998663650 | 12073373998931809 | 12073373998983306 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f0b33d44400 | 0x7f0a03a36480 | 0 | 0 | 0 | 12073373999016357 | 12073373999187167 | 12073373999450046 | 12073373999498774 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f0b33d44300 | 0x7f0a03a364c0 | 0 | 0 | 0 | 12073373999525083 | 12073373999694845 | 12073373999831164 | 12073373999834718 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f0b33d44a00 | 0x7f0a03a36500 | 0 | 0 | 0 | 12073373999883970 | 12073374000048123 | 12073374000215482 | 12073374000219854 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f0b33d44900 | 0x7f0a03a36540 | 0 | 0 | 0 | 12073374000282039 | 12073374000440601 | 12073374000575960 | 12073374000579943 |
| 85 | 83 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 166 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f0b33d44800 | 0x7f0a03a36580 | 0 | 0 | 0 | 12073374000629585 | 12073374000788759 | 12073374001059318 | 12073374001108696 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f0b33d44700 | 0x7f0a03a365c0 | 0 | 0 | 0 | 12073374001137910 | 12073374001307157 | 12073374001566035 | 12073374001613203 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f0b33d44600 | 0x7f0a03a36600 | 0 | 0 | 0 | 12073374001640143 | 12073374001813234 | 12073374001949714 | 12073374001953636 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f0b33d44500 | 0x7f0a03a36640 | 0 | 0 | 0 | 12073374002007045 | 12073374002166992 | 12073374002342192 | 12073374002346426 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f0b33d44400 | 0x7f0a03a36680 | 0 | 0 | 0 | 12073374002409613 | 12073374002565230 | 12073374002739470 | 12073374002743544 |
| 90 | 88 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 176 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f0b33d44300 | 0x7f0a03a366c0 | 0 | 0 | 0 | 12073374002792705 | 12073374002954508 | 12073374003219307 | 12073374003267417 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f0b33d44a00 | 0x7f0a03a36700 | 0 | 0 | 0 | 12073374003295860 | 12073374003466506 | 12073374003726505 | 12073374003773909 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f0b33d44900 | 0x7f0a03a36740 | 0 | 0 | 0 | 12073374003801710 | 12073374003971303 | 12073374004108583 | 12073374004113149 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f0b33d44800 | 0x7f0a03a36780 | 0 | 0 | 0 | 12073374004162330 | 12073374004321222 | 12073374004504901 | 12073374004508824 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f0b33d44700 | 0x7f0a03a367c0 | 0 | 0 | 0 | 12073374004570920 | 12073374004726180 | 12073374004867299 | 12073374004871388 |
| 95 | 93 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 186 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f0b33d44600 | 0x7f0a03a36800 | 0 | 0 | 0 | 12073374004920500 | 12073374005082658 | 12073374005350016 | 12073374005397486 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f0b33d44500 | 0x7f0a03a36840 | 0 | 0 | 0 | 12073374005423935 | 12073374005598975 | 12073374005854494 | 12073374005902995 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f0b33d44400 | 0x7f0a03a36880 | 0 | 0 | 0 | 12073374005930867 | 12073374006104093 | 12073374006239292 | 12073374006243588 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f0b33d44300 | 0x7f0a03a368c0 | 0 | 0 | 0 | 12073374006298861 | 12073374006456091 | 12073374006647290 | 12073374006695077 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f0b33d44a00 | 0x7f0a03a36900 | 0 | 0 | 0 | 12073374006735412 | 12073374006890489 | 12073374007030328 | 12073374007034558 |
| 100 | 98 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 196 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f0b33d44900 | 0x7f0a03a36940 | 0 | 0 | 0 | 12073374007083890 | 12073374007248567 | 12073374007532405 | 12073374007579832 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f0b33d44800 | 0x7f0a03a36980 | 0 | 0 | 0 | 12073374007607403 | 12073374007775444 | 12073374008039443 | 12073374008089569 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f0b33d44700 | 0x7f0a03a369c0 | 0 | 0 | 0 | 12073374008117080 | 12073374008299442 | 12073374008435441 | 12073374008439439 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f0b33d44600 | 0x7f0a03a36a00 | 0 | 0 | 0 | 12073374008489763 | 12073374008644880 | 12073374008855599 | 12073374008905495 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f0b33d44500 | 0x7f0a03a36a40 | 0 | 0 | 0 | 12073374008945830 | 12073374009115277 | 12073374009255277 | 12073374009259363 |
| 105 | 103 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 206 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f0b33d44400 | 0x7f0a03a36a80 | 0 | 0 | 0 | 12073374009308644 | 12073374009476236 | 12073374009813674 | 12073374009861321 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f0b33d44300 | 0x7f0a03a36ac0 | 0 | 0 | 0 | 12073374009890395 | 12073374010057993 | 12073374010313671 | 12073374010364216 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f0b33d44a00 | 0x7f0a03a36b00 | 0 | 0 | 0 | 12073374010392799 | 12073374010561670 | 12073374010699910 | 12073374010703967 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f0b33d44900 | 0x7f0a03a36b40 | 0 | 0 | 0 | 12073374010754752 | 12073374010909028 | 12073374011136707 | 12073374011186063 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f0b33d44800 | 0x7f0a03a36b80 | 0 | 0 | 0 | 12073374011227069 | 12073374011384226 | 12073374011523425 | 12073374011527518 |
| 110 | 108 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 216 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f0b33d44700 | 0x7f0a03a36bc0 | 0 | 0 | 0 | 12073374011576639 | 12073374011733504 | 12073374012091103 | 12073374012116212 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f0b33d44600 | 0x7f0a03a36c00 | 0 | 0 | 0 | 12073374012163530 | 12073374012321661 | 12073374012584700 | 12073374012631890 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f0b33d44500 | 0x7f0a03a36c40 | 0 | 0 | 0 | 12073374012659101 | 12073374012835899 | 12073374012974458 | 12073374012978444 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f0b33d44400 | 0x7f0a03a36c80 | 0 | 0 | 0 | 12073374013032555 | 12073374013211897 | 12073374013457656 | 12073374013507838 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f0b33d44300 | 0x7f0a03a36cc0 | 0 | 0 | 0 | 12073374013545568 | 12073374013702934 | 12073374013842774 | 12073374013846998 |
| 115 | 113 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 226 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f0b33d44a00 | 0x7f0a03a36d00 | 0 | 0 | 0 | 12073374013897011 | 12073374014059672 | 12073374014435351 | 12073374014489162 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f0b33d44900 | 0x7f0a03a36d40 | 0 | 0 | 0 | 12073374014512565 | 12073374014688949 | 12073374014955508 | 12073374015005682 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f0b33d44800 | 0x7f0a03a36d80 | 0 | 0 | 0 | 12073374015034645 | 12073374015203827 | 12073374015343346 | 12073374015346876 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f0b33d44700 | 0x7f0a03a36dc0 | 0 | 0 | 0 | 12073374015400986 | 12073374015557265 | 12073374015836624 | 12073374015883182 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f0b33d44600 | 0x7f0a03a36e00 | 0 | 0 | 0 | 12073374015922525 | 12073374016086863 | 12073374016223022 | 12073374016226621 |
| 120 | 118 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 236 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f0b33d44500 | 0x7f0a03a36e40 | 0 | 0 | 0 | 12073374016277946 | 12073374016433582 | 12073374016881100 | 12073374016927734 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f0b33d44400 | 0x7f0a03a36e80 | 0 | 0 | 0 | 12073374016955966 | 12073374017132299 | 12073374017399018 | 12073374017446458 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f0b33d44300 | 0x7f0a03a36ec0 | 0 | 0 | 0 | 12073374017475151 | 12073374017645097 | 12073374017783656 | 12073374017787060 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f0b33d44a00 | 0x7f0a03a36f00 | 0 | 0 | 0 | 12073374017838726 | 12073374017993575 | 12073374018308774 | 12073374018358332 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f0b33d44900 | 0x7f0a03a36f40 | 0 | 0 | 0 | 12073374018394038 | 12073374018560773 | 12073374018713412 | 12073374018716928 |
| 125 | 123 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 246 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f0b33d44800 | 0x7f0a03a36f80 | 0 | 0 | 0 | 12073374018766230 | 12073374018929731 | 12073374019448449 | 12073374019497068 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f0b33d44700 | 0x7f0a03a36fc0 | 0 | 0 | 0 | 12073374019525541 | 12073374019695968 | 12073374019994047 | 12073374020043163 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f0b33d44600 | 0x7f0a03a37000 | 0 | 0 | 0 | 12073374020071035 | 12073374020242686 | 12073374020397405 | 12073374020400908 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f0b33d44500 | 0x7f0a03a37040 | 0 | 0 | 0 | 12073374020447755 | 12073374020610044 | 12073374020996283 | 12073374021019477 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f0b33d44400 | 0x7f0a03a37080 | 0 | 0 | 0 | 12073374021079880 | 12073374021239802 | 12073374021416601 | 12073374021419912 |
| 130 | 128 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 256 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f0b33d44300 | 0x7f0a03a370c0 | 0 | 0 | 0 | 12073374021468352 | 12073374021630680 | 12073374022242198 | 12073374022290249 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f0b33d44a00 | 0x7f0a03a37100 | 0 | 0 | 0 | 12073374022319213 | 12073374022498037 | 12073374022826835 | 12073374022876058 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f0b33d44900 | 0x7f0a03a37140 | 0 | 0 | 0 | 12073374022903529 | 12073374023086834 | 12073374023266034 | 12073374023269639 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f0b33d44800 | 0x7f0a03a37180 | 0 | 0 | 0 | 12073374023320714 | 12073374023487793 | 12073374023944911 | 12073374023993164 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f0b33d44700 | 0x7f0a03a371c0 | 0 | 0 | 0 | 12073374024040071 | 12073374024198510 | 12073374024399789 | 12073374024449131 |
| 135 | 133 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 266 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f0b33d44600 | 0x7f0a03a37200 | 0 | 0 | 0 | 12073374024477444 | 12073374024645388 | 12073374025349225 | 12073374025397944 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f0b33d44500 | 0x7f0a03a37240 | 0 | 0 | 0 | 12073374025426548 | 12073374025597064 | 12073374025971142 | 12073374026020061 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f0b33d44400 | 0x7f0a03a37280 | 0 | 0 | 0 | 12073374026052240 | 12073374026222181 | 12073374026425381 | 12073374026473072 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f0b33d44300 | 0x7f0a03a372c0 | 0 | 0 | 0 | 12073374026499632 | 12073374026668260 | 12073374027196737 | 12073374027244837 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f0b33d44a00 | 0x7f0a03a37300 | 0 | 0 | 0 | 12073374027283448 | 12073374027443616 | 12073374027668736 | 12073374027716253 |
| 140 | 138 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 276 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f0b33d44900 | 0x7f0a03a37340 | 0 | 0 | 0 | 12073374027741970 | 12073374027918974 | 12073374028719131 | 12073374028770382 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f0b33d44800 | 0x7f0a03a37380 | 0 | 0 | 0 | 12073374028798734 | 12073374028969850 | 12073374029393848 | 12073374029442671 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f0b33d44700 | 0x7f0a03a373c0 | 0 | 0 | 0 | 12073374029469080 | 12073374029646807 | 12073374029873046 | 12073374029922473 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f0b33d44600 | 0x7f0a03a37400 | 0 | 0 | 0 | 12073374029950194 | 12073374030127125 | 12073374030725043 | 12073374030773725 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f0b33d44500 | 0x7f0a03a37440 | 0 | 0 | 0 | 12073374030815242 | 12073374030971442 | 12073374031241841 | 12073374031291507 |
| 145 | 143 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 286 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f0b33d44400 | 0x7f0a03a37480 | 0 | 0 | 0 | 12073374031319058 | 12073374031491920 | 12073374032476876 | 12073374032545377 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f0b33d44300 | 0x7f0a03a374c0 | 0 | 0 | 0 | 12073374032577036 | 12073374032758475 | 12073374033276553 | 12073374033344462 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f0b33d44a00 | 0x7f0a03a37500 | 0 | 0 | 0 | 12073374033375259 | 12073374033552871 | 12073374033825510 | 12073374033892400 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f0b33d44900 | 0x7f0a03a37540 | 0 | 0 | 0 | 12073374033918459 | 12073374034101669 | 12073374034840546 | 12073374034909160 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f0b33d44800 | 0x7f0a03a37580 | 0 | 0 | 0 | 12073374034952080 | 12073374035117185 | 12073374035434784 | 12073374035501941 |
| 150 | 148 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 296 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f0b33d44700 | 0x7f0a03a375c0 | 0 | 0 | 0 | 12073374035528952 | 12073374035699743 | 12073374036870778 | 12073374036938892 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f0b33d44600 | 0x7f0a03a37600 | 0 | 0 | 0 | 12073374036971362 | 12073374037155577 | 12073374037765334 | 12073374037834767 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f0b33d44500 | 0x7f0a03a37640 | 0 | 0 | 0 | 12073374037861967 | 12073374038047413 | 12073374038367892 | 12073374038437176 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f0b33d44400 | 0x7f0a03a37680 | 0 | 0 | 0 | 12073374038465038 | 12073374038636211 | 12073374039514927 | 12073374039582244 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f0b33d44300 | 0x7f0a03a376c0 | 0 | 0 | 0 | 12073374039624302 | 12073374039784366 | 12073374040195084 | 12073374040264011 |
| 155 | 153 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 306 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f0b33d44a00 | 0x7f0a03a37700 | 0 | 0 | 0 | 12073374040297644 | 12073374040461643 | 12073374042010437 | 12073374042078323 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f0b33d44900 | 0x7f0a03a37740 | 0 | 0 | 0 | 12073374042111224 | 12073374042287556 | 12073374043082272 | 12073374043150806 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f0b33d44800 | 0x7f0a03a37780 | 0 | 0 | 0 | 12073374043180862 | 12073374043357631 | 12073374043773470 | 12073374043840007 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f0b33d44700 | 0x7f0a03a377c0 | 0 | 0 | 0 | 12073374043867849 | 12073374044050748 | 12073374045210584 | 12073374045280013 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f0b33d44600 | 0x7f0a03a37800 | 0 | 0 | 0 | 12073374045320448 | 12073374045481623 | 12073374046267379 | 12073374046335444 |
| 160 | 158 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 316 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f0b33d44500 | 0x7f0a03a37840 | 0 | 0 | 0 | 12073374046366973 | 12073374046541618 | 12073374049591206 | 12073374049659261 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f0b33d44400 | 0x7f0a03a37880 | 0 | 0 | 0 | 12073374049691451 | 12073374049869445 | 12073374051411198 | 12073374051480947 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f0b33d44300 | 0x7f0a03a378c0 | 0 | 0 | 0 | 12073374051505352 | 12073374051689597 | 12073374052479514 | 12073374052547549 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f0b33d44a00 | 0x7f0a03a37900 | 0 | 0 | 0 | 12073374052578166 | 12073374052753113 | 12073374055034863 | 12073374055103088 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f0b33d44900 | 0x7f0a03a37940 | 0 | 0 | 0 | 12073374055147731 | 12073374055309262 | 12073374056845736 | 12073374056914204 |
| 165 | 163 | void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] | 0 | 0 | 326 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f0b33d44800 | 0x7f0a03a37980 | 0 | 0 | 0 | 12073374056944821 | 12073374057128615 | 12073374063182990 | 12073374063256450 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f0b33d44700 | 0x7f0a03a379c0 | 0 | 0 | 0 | 12073374063284332 | 12073374063456909 | 12073374066496416 | 12073374066567082 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f0b33d44600 | 0x7f0a03a37a00 | 0 | 0 | 0 | 12073374066597719 | 12073374066777215 | 12073374068316569 | 12073374068385121 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 760307 | 760312 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f0b33d44500 | 0x7f0a03a37a40 | 0 | 0 | 0 | 12073374068417772 | 12073374068586648 | 12073374073113509 | 12073374073181935 |