Task04 Данил Конев SPbU #139
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Локальный вывод
$ ./matrix_transpose OpenCL devices: Device #0: GPU. Apple M2. Total memory: 5461 Mb Using device #0: GPU. Apple M2. Total memory: 5461 Mb Data generated for M=4096, K=4096 [matrix_transpose_naive] GPU: 0.00183733+-3.80516e-05 s GPU: 9131.29 millions/s [matrix_transpose_local_bad_banks] GPU: 0.00182022+-2.45853e-05 s GPU: 9217.15 millions/s [matrix_transpose_local_good_banks] GPU: 0.00180377+-2.44093e-05 s GPU: 9301.21 millions/s $ ./matrix_multiplication OpenCL devices: Device #0: GPU. Apple M2. Total memory: 5461 Mb Using device #0: GPU. Apple M2. Total memory: 5461 Mb Data generated for M=1024, K=1024, N=1024 CPU: 3.79174+-1.41629e-08 s CPU: 0.527462 GFlops [naive, ts=4] GPU: 0.0122115+-0.000476769 s GPU: 163.78 GFlops Average difference: 0% [naive, ts=8] GPU: 0.0161957+-0.000438779 s GPU: 123.49 GFlops Average difference: 0% [naive, ts=16] GPU: 0.0118767+-0.00039979 s GPU: 168.397 GFlops Average difference: 0% [local, ts=4] GPU: 0.016141+-0.000714008 s GPU: 123.908 GFlops Average difference: 0% [local, ts=8] GPU: 0.00592617+-0.000109758 s GPU: 337.486 GFlops Average difference: 0% [local, ts=16] GPU: 0.00522333+-0.000135656 s GPU: 382.897 GFlops Average difference: 0% [local wpt, ts=4, wpt=2] GPU: 0.0223027+-0.000515098 s GPU: 89.6754 GFlops Average difference: 0% [local wpt, ts=4, wpt=4] GPU: 0.0370613+-0.000280732 s GPU: 53.9646 GFlops Average difference: 0% [local wpt, ts=8, wpt=2] GPU: 0.00453133+-2.25807e-05 s GPU: 441.371 GFlops Average difference: 0% [local wpt, ts=8, wpt=4] GPU: 0.00747317+-2.97681e-05 s GPU: 267.624 GFlops Average difference: 0% [local wpt, ts=8, wpt=8] GPU: 0.0173278+-0.000459474 s GPU: 115.421 GFlops Average difference: 0% [local wpt, ts=16, wpt=2] GPU: 0.00449667+-3.01367e-05 s GPU: 444.774 GFlops Average difference: 0% [local wpt, ts=16, wpt=4] GPU: 0.00366533+-2.25955e-05 s GPU: 545.653 GFlops Average difference: 0% [local wpt, ts=16, wpt=8] GPU: 0.0040725+-2.22017e-05 s GPU: 491.099 GFlops Average difference: 0% [local wpt, ts=16, wpt=16] GPU: 0.0114167+-9.26942e-05 s GPU: 175.182 GFlops Average difference: 0%Вывод Github CI
$ ./matrix_transpose OpenCL devices: Device #0: CPU. AMD EPYC 7763 64-Core Processor . Intel(R) Corporation. Total memory: 15991 Mb Using device #0: CPU. AMD EPYC 7763 64-Core Processor . Intel(R) Corporation. Total memory: 15991 Mb Data generated for M=4096, K=4096 [matrix_transpose_naive] GPU: 0.0161321+-0.000144695 s GPU: 1039.99 millions/s [matrix_transpose_local_bad_banks] GPU: 0.0133337+-5.87615e-05 s GPU: 1258.26 millions/s [matrix_transpose_local_good_banks] GPU: 0.0142759+-5.10294e-05 s GPU: 1175.21 millions/s $ ./matrix_multiplication OpenCL devices: Device #0: CPU. AMD EPYC 7763 64-Core Processor . Intel(R) Corporation. Total memory: 15991 Mb Using device #0: CPU. AMD EPYC 7763 64-Core Processor . Intel(R) Corporation. Total memory: 15991 Mb Data generated for M=1024, K=1024, N=1024 CPU: 6.08544+-0 s CPU: 0.328653 GFlops [naive, ts=4] GPU: 0.278694+-0.00796799 s GPU: 7.17632 GFlops Average difference: 0.000149043% [naive, ts=8] GPU: 0.271026+-0.00315905 s GPU: 7.37937 GFlops Average difference: 0.000149043% [naive, ts=16] GPU: 0.31961+-0.0282449 s GPU: 6.25762 GFlops Average difference: 0.000149043% [local, ts=4] GPU: 0.594748+-0.000545432 s GPU: 3.36277 GFlops Average difference: 0.000149043% [local, ts=8] GPU: 0.109308+-0.000198738 s GPU: 18.2969 GFlops Average difference: 0.000149043% [local, ts=16] GPU: 0.0699212+-0.000325857 s GPU: 28.6036 GFlops Average difference: 0.000149043% [local wpt, ts=4, wpt=2] GPU: 0.539262+-0.00272789 s GPU: 3.70877 GFlops Average difference: 0.000149043% [local wpt, ts=4, wpt=4] GPU: 0.475112+-0.00168706 s GPU: 4.20954 GFlops Average difference: 0.000149043% [local wpt, ts=8, wpt=2] GPU: 0.135911+-0.000502784 s GPU: 14.7155 GFlops Average difference: 0.000149043% [local wpt, ts=8, wpt=4] GPU: 0.151507+-0.000329341 s GPU: 13.2007 GFlops Average difference: 0.000149043% [local wpt, ts=8, wpt=8] GPU: 0.143789+-0.000426475 s GPU: 13.9093 GFlops Average difference: 0.000149043% [local wpt, ts=16, wpt=2] GPU: 0.0847648+-0.000240268 s GPU: 23.5947 GFlops Average difference: 0.000149043% [local wpt, ts=16, wpt=4] GPU: 0.0771217+-0.000196725 s GPU: 25.933 GFlops Average difference: 0.000149043% [local wpt, ts=16, wpt=8] GPU: 0.0788197+-0.000917917 s GPU: 25.3744 GFlops Average difference: 0.000149043% [local wpt, ts=16, wpt=16] GPU: 0.0921885+-0.000260632 s GPU: 21.6947 GFlops Average difference: 0.000149043%