Minor fixes to build with both CUDA < 11 and >= 11 #34
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
nbeams
added
CUDA
nbeams
force-pushed
the
sparse-fixes-cuda-lt-11
branch
from
0c0d222 to
196f3b3
Compare
nbeams
changed the title
|
LGTM |
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Outdated suggestions cannot be applied.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.
In #32, I accidentally broke CUDA < 11 while fixing the csr2csc function use for CUDA >= 11. By altering the order of the parameters in the macro and not the main source code, we can fix CUDA 11 without breaking CUDA 10 or older.
TODO:
Update: When building with CUDA 10.2 to test the sparse changes, I ran into minor issues with some dense routines: shpotrf_gpu (cuBLAS usage) and *gbtf2_native[_v2] (complications building/linking due to cooperative groups). Some minor changes have been added, and the PR title has been updated accordingly. We maintain CUDA 10 support for now, but the *gbtf2_native routines are disabled for CUDA < 11.