Return device total global memory for MaxAllocSize #1181
Merged
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
Codecov ReportAll modified and coverable lines are covered by tests ✅
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## main #1181 +/- ##
=========================================
+ Coverage 0 15.74% +15.74%
=========================================
Files 0 223 +223
Lines 0 31464 +31464
Branches 0 3556 +3556
=========================================
+ Hits 0 4954 +4954
- Misses 0 26460 +26460
- Partials 0 50 +50 ☔ View full report in Codecov by Sentry. |
mmoadeli
reviewed
Dec 13, 2023
mmoadeli
approved these changes
Dec 14, 2023
kbenzie
added
cuda
The SYCL specifiction inherits an OpenCL query for the maximum single allocaton that can be made, and requires that at least one-quarter of the device's reported global memory size can be allocated. CUDA doesn't really have such a limitation as far as I can tell, and will happily allocate anything up to the total size of global memory in one go. This means returning that size is a reasonable guess for MaxAllocSize.
kbenzie
force-pushed
the
cuda-mem-size-fix
branch
from
4e9507b
to
c02d137
Compare
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Outdated suggestions cannot be applied.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.
The SYCL specifiction inherits an OpenCL query for the maximum single allocaton that can be made, and requires that at least one-quarter of the device's reported global memory size can be allocated.
CUDA doesn't really have such a limitation as far as I can tell, and will happily allocate anything up to the total size of global memory in one go. This means returning that size is a reasonable guess for MaxAllocSize.