Commit 0cde91d0 authored by Nathan Luehr's avatar Nathan Luehr
Browse files

GetConvolve*Algorithms fixup take 2 

Move loop to toggle tensor_ops inside GetConvolveAlgorithms functions. Also
tensor_ops are not included in the returned list if they are not supported by
the cuDNN or GPU architecture versions.

This is a re-submit of PR 13252 which seems to have been accidentally squashed
during the merge at hash 37800b95.
parent 63519673
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment