39 KiB
39 KiB
| 1 | Index | KernelName | gpu-id | queue-id | queue-index | pid | tid | grd | wgr | lds | scr | vgpr | sgpr | fbar | sig | obj | DispatchNs | BeginNs | EndNs | CompleteNs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 0 | __amd_rocclr_fillBuffer.kd | 0 | 0 | 0 | 854870 | 854875 | 33554432 | 256 | 0 | 0 | 8 | 32 | 6464 | 0x0 | 0x7f5cd2204180 | 12074933586640071 | 12074933586686810 | 12074933587013047 | 12074933587117989 |
| 3 | 1 | void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] | 0 | 0 | 2 | 854870 | 854875 | 32768 | 256 | 0 | 0 | 24 | 24 | 12480 | 0x0 | 0x7f5cd2235100 | 12074933601595213 | 12074933601700471 | 12074933601707191 | 12074933601713273 |
| 4 | 2 | void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] | 0 | 0 | 4 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 12928 | 0x7f5dddeb8900 | 0x7f5cd2235140 | 12074933601758607 | 12074933601773270 | 12074933601904149 | 12074933601907994 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 36 | 24 | 13632 | 0x7f5dddeb8800 | 0x7f5cd2235180 | 12074933601954291 | 12074933601967829 | 12074933602211026 | 12074933602311404 |
| 6 | 4 | void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] | 0 | 0 | 8 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 14080 | 0x7f5dddeb8700 | 0x7f5cd22351c0 | 12074933602339687 | 12074933602351825 | 12074933602597903 | 12074933602694005 |
| 7 | 5 | void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] | 0 | 0 | 10 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14528 | 0x7f5dddeb8600 | 0x7f5cd2235200 | 12074933602720024 | 12074933602732462 | 12074933602858380 | 12074933602862067 |
| 8 | 6 | void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] | 0 | 0 | 12 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 14976 | 0x7f5dddeb8500 | 0x7f5cd2235240 | 12074933602890300 | 12074933602902060 | 12074933603026859 | 12074933603030420 |
| 9 | 7 | void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] | 0 | 0 | 14 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 15424 | 0x7f5dddeb8400 | 0x7f5cd2235280 | 12074933603087076 | 12074933603098378 | 12074933603223017 | 12074933603226324 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16128 | 0x7f5dddeb8300 | 0x7f5cd22352c0 | 12074933603255429 | 12074933603266857 | 12074933603522214 | 12074933603618764 |
| 11 | 9 | void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] | 0 | 0 | 18 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 16832 | 0x7f5dddeb8a00 | 0x7f5cd2235300 | 12074933603640564 | 12074933603652773 | 12074933603898851 | 12074933603994913 |
| 12 | 10 | void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] | 0 | 0 | 20 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 17536 | 0x7f5dddeb8900 | 0x7f5cd2235340 | 12074933604023887 | 12074933604035330 | 12074933604159808 | 12074933604163386 |
| 13 | 11 | void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] | 0 | 0 | 22 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18240 | 0x7f5dddeb8800 | 0x7f5cd2235380 | 12074933604192620 | 12074933604204288 | 12074933604329087 | 12074933604332640 |
| 14 | 12 | void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] | 0 | 0 | 24 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 18944 | 0x7f5dddeb8700 | 0x7f5cd22353c0 | 12074933604370561 | 12074933604382206 | 12074933604506685 | 12074933604509990 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 19904 | 0x7f5dddeb8600 | 0x7f5cd2235400 | 12074933604536740 | 12074933604548125 | 12074933604792763 | 12074933604864178 |
| 16 | 14 | void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] | 0 | 0 | 28 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 20608 | 0x7f5dddeb8500 | 0x7f5cd2235440 | 12074933604886259 | 12074933604897402 | 12074933605142679 | 12074933605212345 |
| 17 | 15 | void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] | 0 | 0 | 30 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 21312 | 0x7f5dddeb8400 | 0x7f5cd2235480 | 12074933605233795 | 12074933605245558 | 12074933605370517 | 12074933605373735 |
| 18 | 16 | void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] | 0 | 0 | 32 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22016 | 0x7f5dddeb8300 | 0x7f5cd22354c0 | 12074933605400575 | 12074933605411797 | 12074933605537236 | 12074933605540515 |
| 19 | 17 | void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] | 0 | 0 | 34 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 22720 | 0x7f5dddeb8a00 | 0x7f5cd2235500 | 12074933605576853 | 12074933605589395 | 12074933605714194 | 12074933605717574 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 23680 | 0x7f5dddeb8900 | 0x7f5cd2235540 | 12074933605744123 | 12074933605755474 | 12074933606001071 | 12074933606047277 |
| 21 | 19 | void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] | 0 | 0 | 38 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 24384 | 0x7f5dddeb8800 | 0x7f5cd2235580 | 12074933606068476 | 12074933606080271 | 12074933606324589 | 12074933606390344 |
| 22 | 20 | void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] | 0 | 0 | 40 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25088 | 0x7f5dddeb8700 | 0x7f5cd22355c0 | 12074933606413768 | 12074933606425068 | 12074933606550026 | 12074933606553257 |
| 23 | 21 | void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] | 0 | 0 | 42 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 25792 | 0x7f5dddeb8600 | 0x7f5cd2235600 | 12074933606580207 | 12074933606591306 | 12074933606716905 | 12074933606720257 |
| 24 | 22 | void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] | 0 | 0 | 44 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 26496 | 0x7f5dddeb8500 | 0x7f5cd2235640 | 12074933606757857 | 12074933606769064 | 12074933606892903 | 12074933606896405 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 27712 | 0x7f5dddeb8400 | 0x7f5cd2235680 | 12074933606923405 | 12074933606935623 | 12074933607183781 | 12074933607283735 |
| 26 | 24 | void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] | 0 | 0 | 48 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 28416 | 0x7f5dddeb8300 | 0x7f5cd22356c0 | 12074933607305595 | 12074933607316899 | 12074933607561057 | 12074933607657199 |
| 27 | 25 | void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] | 0 | 0 | 50 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 29120 | 0x7f5dddeb8a00 | 0x7f5cd2235700 | 12074933607679610 | 12074933607691136 | 12074933607814815 | 12074933607818358 |
| 28 | 26 | void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] | 0 | 0 | 52 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30080 | 0x7f5dddeb8900 | 0x7f5cd2235740 | 12074933607846811 | 12074933607858654 | 12074933607984253 | 12074933607987663 |
| 29 | 27 | void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] | 0 | 0 | 54 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 30784 | 0x7f5dddeb8800 | 0x7f5cd2235780 | 12074933608028939 | 12074933608039933 | 12074933608164092 | 12074933608167407 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32000 | 0x7f5dddeb8700 | 0x7f5cd22357c0 | 12074933608194207 | 12074933608206171 | 12074933608451609 | 12074933608504674 |
| 31 | 29 | void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] | 0 | 0 | 58 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 32960 | 0x7f5dddeb8600 | 0x7f5cd2235800 | 12074933608526043 | 12074933608537208 | 12074933608785366 | 12074933608862478 |
| 32 | 30 | void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] | 0 | 0 | 60 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 33920 | 0x7f5dddeb8500 | 0x7f5cd2235840 | 12074933608884309 | 12074933608895925 | 12074933609020724 | 12074933609024600 |
| 33 | 31 | void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] | 0 | 0 | 62 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 34880 | 0x7f5dddeb8400 | 0x7f5cd2235880 | 12074933609052472 | 12074933609063603 | 12074933609189042 | 12074933609192662 |
| 34 | 32 | void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] | 0 | 0 | 64 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 35840 | 0x7f5dddeb8300 | 0x7f5cd22358c0 | 12074933609228869 | 12074933609242002 | 12074933609366640 | 12074933609370032 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 37312 | 0x7f5dddeb8a00 | 0x7f5cd2235900 | 12074933609396341 | 12074933609408080 | 12074933609697997 | 12074933609750258 |
| 36 | 34 | void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] | 0 | 0 | 68 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 38272 | 0x7f5dddeb8900 | 0x7f5cd2235940 | 12074933609771428 | 12074933609786157 | 12074933610030314 | 12074933610079680 |
| 37 | 35 | void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] | 0 | 0 | 70 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 39232 | 0x7f5dddeb8800 | 0x7f5cd2235980 | 12074933610101020 | 12074933610113834 | 12074933610239112 | 12074933610242713 |
| 38 | 36 | void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] | 0 | 0 | 72 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 40192 | 0x7f5dddeb8700 | 0x7f5cd22359c0 | 12074933610269303 | 12074933610280072 | 12074933610406311 | 12074933610409523 |
| 39 | 37 | void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] | 0 | 0 | 74 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 41152 | 0x7f5dddeb8600 | 0x7f5cd2235a00 | 12074933610444559 | 12074933610455910 | 12074933610580549 | 12074933610583697 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 42624 | 0x7f5dddeb8500 | 0x7f5cd2235a40 | 12074933610611509 | 12074933610624069 | 12074933610871587 | 12074933610892651 |
| 41 | 39 | void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] | 0 | 0 | 78 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 43584 | 0x7f5dddeb8400 | 0x7f5cd2235a80 | 12074933610914472 | 12074933610925506 | 12074933611172704 | 12074933611223236 |
| 42 | 40 | void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] | 0 | 0 | 80 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 44544 | 0x7f5dddeb8300 | 0x7f5cd2235ac0 | 12074933611248663 | 12074933611260543 | 12074933611385662 | 12074933611388984 |
| 43 | 41 | void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] | 0 | 0 | 82 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 45760 | 0x7f5dddeb8a00 | 0x7f5cd2235b00 | 12074933611416034 | 12074933611427421 | 12074933611553020 | 12074933611556254 |
| 44 | 42 | void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] | 0 | 0 | 84 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 46720 | 0x7f5dddeb8900 | 0x7f5cd2235b40 | 12074933611592291 | 12074933611603900 | 12074933611728539 | 12074933611731951 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 48448 | 0x7f5dddeb8800 | 0x7f5cd2235b80 | 12074933611757919 | 12074933611769338 | 12074933612030456 | 12074933612056214 |
| 46 | 44 | void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] | 0 | 0 | 88 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 49408 | 0x7f5dddeb8700 | 0x7f5cd2235bc0 | 12074933612078445 | 12074933612091415 | 12074933612375093 | 12074933612398269 |
| 47 | 45 | void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] | 0 | 0 | 90 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 50368 | 0x7f5dddeb8600 | 0x7f5cd2235c00 | 12074933612418126 | 12074933612429172 | 12074933612553491 | 12074933612557064 |
| 48 | 46 | void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] | 0 | 0 | 92 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 51584 | 0x7f5dddeb8500 | 0x7f5cd2235c40 | 12074933612585026 | 12074933612596531 | 12074933612722290 | 12074933612725567 |
| 49 | 47 | void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] | 0 | 0 | 94 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 52544 | 0x7f5dddeb8400 | 0x7f5cd2235c80 | 12074933612762246 | 12074933612773649 | 12074933612898608 | 12074933612901915 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 54272 | 0x7f5dddeb8300 | 0x7f5cd2235cc0 | 12074933612928845 | 12074933612941328 | 12074933613197005 | 12074933613228783 |
| 51 | 49 | void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] | 0 | 0 | 98 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 55488 | 0x7f5dddeb8a00 | 0x7f5cd2235d00 | 12074933613250824 | 12074933613261965 | 12074933613509482 | 12074933613537106 |
| 52 | 50 | void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] | 0 | 0 | 100 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 56704 | 0x7f5dddeb8900 | 0x7f5cd2235d40 | 12074933613558846 | 12074933613570602 | 12074933613695241 | 12074933613698485 |
| 53 | 51 | void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] | 0 | 0 | 102 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 58176 | 0x7f5dddeb8800 | 0x7f5cd2235d80 | 12074933613724694 | 12074933613736040 | 12074933613863879 | 12074933613867089 |
| 54 | 52 | void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] | 0 | 0 | 104 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 59392 | 0x7f5dddeb8700 | 0x7f5cd2235dc0 | 12074933613903847 | 12074933613915239 | 12074933614040037 | 12074933614043296 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 61376 | 0x7f5dddeb8600 | 0x7f5cd2235e00 | 12074933614070166 | 12074933614081477 | 12074933614333635 | 12074933614357230 |
| 56 | 54 | void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] | 0 | 0 | 108 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 62592 | 0x7f5dddeb8500 | 0x7f5cd2235e40 | 12074933614378599 | 12074933614390434 | 12074933614635872 | 12074933614661535 |
| 57 | 55 | void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] | 0 | 0 | 110 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 63808 | 0x7f5dddeb8400 | 0x7f5cd2235e80 | 12074933614686622 | 12074933614699391 | 12074933614824990 | 12074933614828395 |
| 58 | 56 | void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] | 0 | 0 | 112 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 65280 | 0x7f5dddeb8300 | 0x7f5cd2235ec0 | 12074933614855926 | 12074933614867070 | 12074933614996669 | 12074933615000024 |
| 59 | 57 | void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] | 0 | 0 | 114 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 66496 | 0x7f5dddeb8a00 | 0x7f5cd2235f00 | 12074933615036943 | 12074933615049148 | 12074933615174267 | 12074933615177564 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 68480 | 0x7f5dddeb8900 | 0x7f5cd2235f40 | 12074933615204885 | 12074933615215707 | 12074933615474744 | 12074933615503119 |
| 61 | 59 | void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] | 0 | 0 | 118 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 69696 | 0x7f5dddeb8800 | 0x7f5cd2235f80 | 12074933615525300 | 12074933615536504 | 12074933615782261 | 12074933615804790 |
| 62 | 60 | void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] | 0 | 0 | 120 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 70912 | 0x7f5dddeb8700 | 0x7f5cd2235fc0 | 12074933615827813 | 12074933615838901 | 12074933615964180 | 12074933615967432 |
| 63 | 61 | void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] | 0 | 0 | 122 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 72384 | 0x7f5dddeb8600 | 0x7f5cd2236000 | 12074933615994112 | 12074933616005459 | 12074933616141138 | 12074933616144681 |
| 64 | 62 | void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] | 0 | 0 | 124 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 73600 | 0x7f5dddeb8500 | 0x7f5cd2236040 | 12074933616183153 | 12074933616194898 | 12074933616319376 | 12074933616322652 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 75840 | 0x7f5dddeb8400 | 0x7f5cd2236080 | 12074933616349813 | 12074933616361616 | 12074933616622094 | 12074933616645352 |
| 66 | 64 | void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] | 0 | 0 | 128 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 77056 | 0x7f5dddeb8300 | 0x7f5cd22360c0 | 12074933616666651 | 12074933616677613 | 12074933616964170 | 12074933616986165 |
| 67 | 65 | void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] | 0 | 0 | 130 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 78272 | 0x7f5dddeb8a00 | 0x7f5cd2236100 | 12074933617012063 | 12074933617024330 | 12074933617150089 | 12074933617153997 |
| 68 | 66 | void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] | 0 | 0 | 132 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 80000 | 0x7f5dddeb8900 | 0x7f5cd2236140 | 12074933617180997 | 12074933617192488 | 12074933617334727 | 12074933617337979 |
| 69 | 67 | void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] | 0 | 0 | 134 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 81216 | 0x7f5dddeb8800 | 0x7f5cd2236180 | 12074933617374337 | 12074933617386567 | 12074933617511525 | 12074933617515008 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 83456 | 0x7f5dddeb8700 | 0x7f5cd22361c0 | 12074933617542148 | 12074933617553445 | 12074933617810403 | 12074933617832899 |
| 71 | 69 | void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] | 0 | 0 | 138 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 84928 | 0x7f5dddeb8600 | 0x7f5cd2236200 | 12074933617854479 | 12074933617865922 | 12074933618109920 | 12074933618133908 |
| 72 | 70 | void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] | 0 | 0 | 140 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 86400 | 0x7f5dddeb8500 | 0x7f5cd2236240 | 12074933618158414 | 12074933618169759 | 12074933618295038 | 12074933618298334 |
| 73 | 71 | void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] | 0 | 0 | 142 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 88128 | 0x7f5dddeb8400 | 0x7f5cd2236280 | 12074933618324302 | 12074933618335838 | 12074933618485596 | 12074933618488908 |
| 74 | 72 | void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] | 0 | 0 | 144 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 89600 | 0x7f5dddeb8300 | 0x7f5cd22362c0 | 12074933618541015 | 12074933618552316 | 12074933618678075 | 12074933618681526 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 92096 | 0x7f5dddeb8a00 | 0x7f5cd2236300 | 12074933618708275 | 12074933618719674 | 12074933618984312 | 12074933619008343 |
| 76 | 74 | void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] | 0 | 0 | 148 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 93568 | 0x7f5dddeb8900 | 0x7f5cd2236340 | 12074933619029653 | 12074933619041271 | 12074933619288629 | 12074933619309803 |
| 77 | 75 | void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] | 0 | 0 | 150 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 95040 | 0x7f5dddeb8800 | 0x7f5cd2236380 | 12074933619331864 | 12074933619342869 | 12074933619468627 | 12074933619471905 |
| 78 | 76 | void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] | 0 | 0 | 152 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 96768 | 0x7f5dddeb8700 | 0x7f5cd22363c0 | 12074933619498183 | 12074933619509747 | 12074933619666546 | 12074933619669862 |
| 79 | 77 | void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] | 0 | 0 | 154 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 98240 | 0x7f5dddeb8600 | 0x7f5cd2236400 | 12074933619707302 | 12074933619718385 | 12074933619843184 | 12074933619846491 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 100736 | 0x7f5dddeb8500 | 0x7f5cd2236440 | 12074933619873240 | 12074933619884944 | 12074933620147981 | 12074933620177135 |
| 81 | 79 | void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] | 0 | 0 | 158 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 102208 | 0x7f5dddeb8400 | 0x7f5cd2236480 | 12074933620198996 | 12074933620209901 | 12074933620455498 | 12074933620478746 |
| 82 | 80 | void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] | 0 | 0 | 160 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 103680 | 0x7f5dddeb8300 | 0x7f5cd22364c0 | 12074933620501378 | 12074933620512778 | 12074933620639337 | 12074933620642670 |
| 83 | 81 | void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] | 0 | 0 | 162 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 105664 | 0x7f5dddeb8a00 | 0x7f5cd2236500 | 12074933620669139 | 12074933620680456 | 12074933620846375 | 12074933620849725 |
| 84 | 82 | void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] | 0 | 0 | 164 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 107136 | 0x7f5dddeb8900 | 0x7f5cd2236540 | 12074933620886714 | 12074933620898694 | 12074933621024773 | 12074933621027976 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 109888 | 0x7f5dddeb8800 | 0x7f5cd2236580 | 12074933621055898 | 12074933621067653 | 12074933621330530 | 12074933621353581 |
| 86 | 84 | void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] | 0 | 0 | 168 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 111360 | 0x7f5dddeb8700 | 0x7f5cd22365c0 | 12074933621374771 | 12074933621385890 | 12074933621667327 | 12074933621690818 |
| 87 | 85 | void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] | 0 | 0 | 170 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 112832 | 0x7f5dddeb8600 | 0x7f5cd2236600 | 12074933621715414 | 12074933621727007 | 12074933621852125 | 12074933621855695 |
| 88 | 86 | void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] | 0 | 0 | 172 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 114816 | 0x7f5dddeb8500 | 0x7f5cd2236640 | 12074933621882314 | 12074933621894205 | 12074933622066683 | 12074933622070303 |
| 89 | 87 | void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] | 0 | 0 | 174 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 116288 | 0x7f5dddeb8400 | 0x7f5cd2236680 | 12074933622107392 | 12074933622119323 | 12074933622245402 | 12074933622248665 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 119040 | 0x7f5dddeb8300 | 0x7f5cd22366c0 | 12074933622276446 | 12074933622288121 | 12074933622541719 | 12074933622560925 |
| 91 | 89 | void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] | 0 | 0 | 178 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 120768 | 0x7f5dddeb8a00 | 0x7f5cd2236700 | 12074933622581604 | 12074933622592919 | 12074933622841716 | 12074933622864569 |
| 92 | 90 | void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] | 0 | 0 | 180 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 122496 | 0x7f5dddeb8900 | 0x7f5cd2236740 | 12074933622888434 | 12074933622899796 | 12074933623025875 | 12074933623029155 |
| 93 | 91 | void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] | 0 | 0 | 182 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 124736 | 0x7f5dddeb8800 | 0x7f5cd2236780 | 12074933623056316 | 12074933623067954 | 12074933623250033 | 12074933623253622 |
| 94 | 92 | void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] | 0 | 0 | 184 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 126464 | 0x7f5dddeb8700 | 0x7f5cd22367c0 | 12074933623291172 | 12074933623302192 | 12074933623428751 | 12074933623432084 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 127936 | 0x7f5dddeb8600 | 0x7f5cd2236800 | 12074933623458473 | 12074933623470511 | 12074933623735308 | 12074933623754393 |
| 96 | 94 | void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] | 0 | 0 | 188 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 129664 | 0x7f5dddeb8500 | 0x7f5cd2236840 | 12074933623779149 | 12074933623790188 | 12074933624038185 | 12074933624065621 |
| 97 | 95 | void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] | 0 | 0 | 190 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 131392 | 0x7f5dddeb8400 | 0x7f5cd2236880 | 12074933624087061 | 12074933624098025 | 12074933624224264 | 12074933624227542 |
| 98 | 96 | void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] | 0 | 0 | 192 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 133632 | 0x7f5dddeb8300 | 0x7f5cd22368c0 | 12074933624255624 | 12074933624266983 | 12074933624457541 | 12074933624461798 |
| 99 | 97 | void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] | 0 | 0 | 194 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 135360 | 0x7f5dddeb8a00 | 0x7f5cd2236900 | 12074933624496672 | 12074933624507621 | 12074933624634980 | 12074933624638376 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 136832 | 0x7f5dddeb8900 | 0x7f5cd2236940 | 12074933624665656 | 12074933624677059 | 12074933624958657 | 12074933624981574 |
| 101 | 99 | void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] | 0 | 0 | 198 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 138560 | 0x7f5dddeb8800 | 0x7f5cd2236980 | 12074933625008003 | 12074933625018816 | 12074933625266974 | 12074933625293884 |
| 102 | 100 | void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] | 0 | 0 | 200 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 140288 | 0x7f5dddeb8700 | 0x7f5cd22369c0 | 12074933625316426 | 12074933625327293 | 12074933625453692 | 12074933625457077 |
| 103 | 101 | void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] | 0 | 0 | 202 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 142784 | 0x7f5dddeb8600 | 0x7f5cd2236a00 | 12074933625484869 | 12074933625495772 | 12074933625704090 | 12074933625726889 |
| 104 | 102 | void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] | 0 | 0 | 204 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 144768 | 0x7f5dddeb8500 | 0x7f5cd2236a40 | 12074933625757305 | 12074933625769049 | 12074933625896888 | 12074933625900301 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 145728 | 0x7f5dddeb8400 | 0x7f5cd2236a80 | 12074933625925798 | 12074933625936888 | 12074933626243125 | 12074933626267283 |
| 106 | 104 | void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] | 0 | 0 | 208 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 147712 | 0x7f5dddeb8300 | 0x7f5cd2236ac0 | 12074933626288072 | 12074933626299124 | 12074933626549522 | 12074933626576978 |
| 107 | 105 | void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] | 0 | 0 | 210 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 149696 | 0x7f5dddeb8a00 | 0x7f5cd2236b00 | 12074933626599100 | 12074933626610642 | 12074933626737360 | 12074933626740813 |
| 108 | 106 | void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] | 0 | 0 | 212 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 152192 | 0x7f5dddeb8900 | 0x7f5cd2236b40 | 12074933626766931 | 12074933626778320 | 12074933627005998 | 12074933627033276 |
| 109 | 107 | void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] | 0 | 0 | 214 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 154176 | 0x7f5dddeb8800 | 0x7f5cd2236b80 | 12074933627066889 | 12074933627078157 | 12074933627204556 | 12074933627208141 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 155648 | 0x7f5dddeb8700 | 0x7f5cd2236bc0 | 12074933627235131 | 12074933627246956 | 12074933627576073 | 12074933627602634 |
| 111 | 109 | void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] | 0 | 0 | 218 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 157632 | 0x7f5dddeb8600 | 0x7f5cd2236c00 | 12074933627623423 | 12074933627634152 | 12074933627891430 | 12074933627917990 |
| 112 | 110 | void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] | 0 | 0 | 220 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 159616 | 0x7f5dddeb8500 | 0x7f5cd2236c40 | 12074933627938579 | 12074933627949829 | 12074933628078948 | 12074933628082416 |
| 113 | 111 | void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] | 0 | 0 | 222 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 162368 | 0x7f5dddeb8400 | 0x7f5cd2236c80 | 12074933628109186 | 12074933628120548 | 12074933628397985 | 12074933628426546 |
| 114 | 112 | void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] | 0 | 0 | 224 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 164608 | 0x7f5dddeb8300 | 0x7f5cd2236cc0 | 12074933628457082 | 12074933628468544 | 12074933628597823 | 12074933628601551 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 166336 | 0x7f5dddeb8a00 | 0x7f5cd2236d00 | 12074933628628741 | 12074933628640063 | 12074933629014299 | 12074933629038523 |
| 116 | 114 | void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] | 0 | 0 | 228 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 168576 | 0x7f5dddeb8900 | 0x7f5cd2236d40 | 12074933629060414 | 12074933629071899 | 12074933629323737 | 12074933629346766 |
| 117 | 115 | void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] | 0 | 0 | 230 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 170816 | 0x7f5dddeb8800 | 0x7f5cd2236d80 | 12074933629370229 | 12074933629381336 | 12074933629511255 | 12074933629514668 |
| 118 | 116 | void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] | 0 | 0 | 232 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 174080 | 0x7f5dddeb8700 | 0x7f5cd2236dc0 | 12074933629540606 | 12074933629551574 | 12074933629861332 | 12074933629883844 |
| 119 | 117 | void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] | 0 | 0 | 234 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 176576 | 0x7f5dddeb8600 | 0x7f5cd2236e00 | 12074933629914240 | 12074933629925971 | 12074933630060210 | 12074933630064169 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 177792 | 0x7f5dddeb8500 | 0x7f5cd2236e40 | 12074933630090498 | 12074933630102129 | 12074933630524206 | 12074933630550893 |
| 121 | 119 | void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] | 0 | 0 | 238 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 180288 | 0x7f5dddeb8400 | 0x7f5cd2236e80 | 12074933630572423 | 12074933630583085 | 12074933630839243 | 12074933630862422 |
| 122 | 120 | void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] | 0 | 0 | 240 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 182784 | 0x7f5dddeb8300 | 0x7f5cd2236ec0 | 12074933630882690 | 12074933630895082 | 12074933631029481 | 12074933631033430 |
| 123 | 121 | void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] | 0 | 0 | 242 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 186304 | 0x7f5dddeb8a00 | 0x7f5cd2236f00 | 12074933631060430 | 12074933631071880 | 12074933631385158 | 12074933631412414 |
| 124 | 122 | void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] | 0 | 0 | 244 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 189312 | 0x7f5dddeb8900 | 0x7f5cd2236f40 | 12074933631444113 | 12074933631455717 | 12074933631607556 | 12074933631611064 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 190784 | 0x7f5dddeb8800 | 0x7f5cd2236f80 | 12074933631638054 | 12074933631649795 | 12074933632165630 | 12074933632193336 |
| 126 | 124 | void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] | 0 | 0 | 248 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 193792 | 0x7f5dddeb8700 | 0x7f5cd2236fc0 | 12074933632219344 | 12074933632230590 | 12074933632528987 | 12074933632555699 |
| 127 | 125 | void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] | 0 | 0 | 250 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 196800 | 0x7f5dddeb8600 | 0x7f5cd2237000 | 12074933632577570 | 12074933632588507 | 12074933632742905 | 12074933632746313 |
| 128 | 126 | void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] | 0 | 0 | 252 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 201088 | 0x7f5dddeb8500 | 0x7f5cd2237040 | 12074933632772512 | 12074933632783865 | 12074933633169621 | 12074933633196941 |
| 129 | 127 | void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] | 0 | 0 | 254 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 204608 | 0x7f5dddeb8400 | 0x7f5cd2237080 | 12074933633228519 | 12074933633240501 | 12074933633416819 | 12074933633420246 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 206080 | 0x7f5dddeb8300 | 0x7f5cd22370c0 | 12074933633446745 | 12074933633457939 | 12074933634080333 | 12074933634107563 |
| 131 | 129 | void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] | 0 | 0 | 258 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 209600 | 0x7f5dddeb8a00 | 0x7f5cd2237100 | 12074933634133371 | 12074933634144812 | 12074933634470569 | 12074933634497237 |
| 132 | 130 | void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] | 0 | 0 | 260 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 213120 | 0x7f5dddeb8900 | 0x7f5cd2237140 | 12074933634524097 | 12074933634535849 | 12074933634714567 | 12074933634718078 |
| 133 | 131 | void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] | 0 | 0 | 262 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 218176 | 0x7f5dddeb8800 | 0x7f5cd2237180 | 12074933634744657 | 12074933634755527 | 12074933635210242 | 12074933635238505 |
| 134 | 132 | void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] | 0 | 0 | 264 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 222208 | 0x7f5dddeb8700 | 0x7f5cd22371c0 | 12074933635269663 | 12074933635281282 | 12074933635480640 | 12074933635506643 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 223936 | 0x7f5dddeb8600 | 0x7f5cd2237200 | 12074933635526139 | 12074933635537279 | 12074933636238713 | 12074933636267076 |
| 136 | 134 | void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] | 0 | 0 | 268 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 227968 | 0x7f5dddeb8500 | 0x7f5cd2237240 | 12074933636290870 | 12074933636301592 | 12074933636699509 | 12074933636726209 |
| 137 | 135 | void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] | 0 | 0 | 270 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 232000 | 0x7f5dddeb8400 | 0x7f5cd2237280 | 12074933636747789 | 12074933636759028 | 12074933636960946 | 12074933636983758 |
| 138 | 136 | void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] | 0 | 0 | 272 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 237824 | 0x7f5dddeb8300 | 0x7f5cd22372c0 | 12074933637008684 | 12074933637020146 | 12074933637544461 | 12074933637577030 |
| 139 | 137 | void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] | 0 | 0 | 274 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 242368 | 0x7f5dddeb8a00 | 0x7f5cd2237300 | 12074933637609280 | 12074933637622060 | 12074933637845258 | 12074933637871548 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 243584 | 0x7f5dddeb8900 | 0x7f5cd2237340 | 12074933637892547 | 12074933637903498 | 12074933638700130 | 12074933638728060 |
| 141 | 139 | void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] | 0 | 0 | 278 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 248128 | 0x7f5dddeb8800 | 0x7f5cd2237380 | 12074933638749750 | 12074933638760450 | 12074933639178686 | 12074933639205928 |
| 142 | 140 | void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] | 0 | 0 | 280 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 252672 | 0x7f5dddeb8700 | 0x7f5cd22373c0 | 12074933639233298 | 12074933639244125 | 12074933639468923 | 12074933639494915 |
| 143 | 141 | void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] | 0 | 0 | 282 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 259264 | 0x7f5dddeb8600 | 0x7f5cd2237400 | 12074933639517416 | 12074933639528603 | 12074933640125237 | 12074933640153158 |
| 144 | 142 | void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] | 0 | 0 | 284 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 264832 | 0x7f5dddeb8500 | 0x7f5cd2237440 | 12074933640184747 | 12074933640195796 | 12074933640464114 | 12074933640490565 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 266304 | 0x7f5dddeb8400 | 0x7f5cd2237480 | 12074933640512516 | 12074933640523633 | 12074933641507944 | 12074933641535677 |
| 146 | 144 | void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] | 0 | 0 | 288 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 28 | 24 | 271872 | 0x7f5dddeb8300 | 0x7f5cd22374c0 | 12074933641559411 | 12074933641570024 | 12074933642082819 | 12074933642111217 |
| 147 | 145 | void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] | 0 | 0 | 290 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 277440 | 0x7f5dddeb8a00 | 0x7f5cd2237500 | 12074933642140451 | 12074933642151938 | 12074933642423616 | 12074933642450157 |
| 148 | 146 | void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] | 0 | 0 | 292 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 279936 | 0x7f5dddeb8900 | 0x7f5cd2237540 | 12074933642472388 | 12074933642483455 | 12074933643220249 | 12074933643248310 |
| 149 | 147 | void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] | 0 | 0 | 294 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 286528 | 0x7f5dddeb8800 | 0x7f5cd2237580 | 12074933643278997 | 12074933643290008 | 12074933643605365 | 12074933643631732 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 288000 | 0x7f5dddeb8700 | 0x7f5cd22375c0 | 12074933643654204 | 12074933643667284 | 12074933644837994 | 12074933644865876 |
| 151 | 149 | void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] | 0 | 0 | 298 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 32 | 24 | 294592 | 0x7f5dddeb8600 | 0x7f5cd2237600 | 12074933644890933 | 12074933644901833 | 12074933645511267 | 12074933645544217 |
| 152 | 150 | void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] | 0 | 0 | 300 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 301184 | 0x7f5dddeb8500 | 0x7f5cd2237640 | 12074933645568762 | 12074933645579747 | 12074933645897984 | 12074933645926387 |
| 153 | 151 | void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] | 0 | 0 | 302 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 304960 | 0x7f5dddeb8400 | 0x7f5cd2237680 | 12074933645947987 | 12074933645958943 | 12074933646835575 | 12074933646865221 |
| 154 | 152 | void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] | 0 | 0 | 304 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 24 | 24 | 313600 | 0x7f5dddeb8300 | 0x7f5cd22376c0 | 12074933646898333 | 12074933646909655 | 12074933647318291 | 12074933647347768 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 314816 | 0x7f5dddeb8a00 | 0x7f5cd2237700 | 12074933647370490 | 12074933647381490 | 12074933648928516 | 12074933648978358 |
| 156 | 154 | void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] | 0 | 0 | 308 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 317568 | 0x7f5dddeb8900 | 0x7f5cd2237740 | 12074933649007152 | 12074933649019474 | 12074933649811308 | 12074933649888039 |
| 157 | 155 | void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] | 0 | 0 | 310 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 320320 | 0x7f5dddeb8800 | 0x7f5cd2237780 | 12074933649912334 | 12074933649923786 | 12074933650337223 | 12074933650407765 |
| 158 | 156 | void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] | 0 | 0 | 312 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 324096 | 0x7f5dddeb8700 | 0x7f5cd22377c0 | 12074933650430818 | 12074933650442342 | 12074933651600413 | 12074933651671213 |
| 159 | 157 | void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] | 0 | 0 | 314 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 328896 | 0x7f5dddeb8600 | 0x7f5cd2237800 | 12074933651706799 | 12074933651718012 | 12074933652503126 | 12074933652574141 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 330112 | 0x7f5dddeb8500 | 0x7f5cd2237840 | 12074933652600780 | 12074933652612885 | 12074933655663421 | 12074933655734524 |
| 161 | 159 | void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] | 0 | 0 | 318 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 332864 | 0x7f5dddeb8400 | 0x7f5cd2237880 | 12074933655761193 | 12074933655772540 | 12074933657314288 | 12074933657385171 |
| 162 | 160 | void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] | 0 | 0 | 320 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 335616 | 0x7f5dddeb8300 | 0x7f5cd22378c0 | 12074933657413835 | 12074933657425967 | 12074933658214601 | 12074933658285114 |
| 163 | 161 | void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] | 0 | 0 | 322 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 339392 | 0x7f5dddeb8a00 | 0x7f5cd2237900 | 12074933658312024 | 12074933658323400 | 12074933660603862 | 12074933660676107 |
| 164 | 162 | void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] | 0 | 0 | 324 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 344192 | 0x7f5dddeb8900 | 0x7f5cd2237940 | 12074933660708016 | 12074933660719701 | 12074933662255209 | 12074933662326224 |
| 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 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 345408 | 0x7f5dddeb8800 | 0x7f5cd2237980 | 12074933662347002 | 12074933662358408 | 12074933668411640 | 12074933668483366 |
| 166 | 164 | void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] | 0 | 0 | 328 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 20 | 24 | 348160 | 0x7f5dddeb8700 | 0x7f5cd22379c0 | 12074933668509474 | 12074933668522039 | 12074933671562175 | 12074933671633360 |
| 167 | 165 | void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] | 0 | 0 | 330 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 350912 | 0x7f5dddeb8600 | 0x7f5cd2237a00 | 12074933671659528 | 12074933671672094 | 12074933673210642 | 12074933673281543 |
| 168 | 166 | void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] | 0 | 0 | 332 | 854870 | 854875 | 4194304 | 256 | 0 | 0 | 12 | 24 | 0 | 0x7f5dddeb8500 | 0x7f5cd2237a40 | 12074933673306018 | 12074933673318641 | 12074933677844205 | 12074933677915083 |