maximum number of threads per block for sm_86 is 1536 #45889
Conversation
|
Thanks for the PR |
There was a problem hiding this comment.
@ngimel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
ngimel
changed the title
|
I'm concerned though, since we don't (and won't) compile binaries for 8.6, does it mean we could potentially compute wrong number of blocks per sm for 8.0 binaries run on 8.6? I think it's benign, and should not lead to "insufficient resources" error, but could you guys double check? |
There was a problem hiding this comment.
@ngimel has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
Codecov Report
@@ Coverage Diff @@
## master #45889 +/- ##
=======================================
Coverage 68.19% 68.19%
=======================================
Files 410 410
Lines 53226 53226
=======================================
Hits 36297 36297
Misses 16929 16929 Continue to review full report at Codecov.
|
Summary: according to https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications Pull Request resolved: pytorch#45889 Reviewed By: albanD Differential Revision: D24131188 Pulled By: ngimel fbshipit-source-id: 31d3038f7b1bc403751448c62b19609573c67a49
according to https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications