-
Notifications
You must be signed in to change notification settings - Fork 738
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[SYCL] Fix devicelib identification for NVPTX #15357
Merged
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
Recent upstream changes removed the workaround that required libraries to be named ".cubin". We also renamed the NVPTX libdevice library when we unified it into a single bytecode library. Unfortunately both of these things broke the driver's brittle logic that determined whether or not an object was a device library. This resulted in us not stripping any symbols from the final object, which is both slower and broke some SYCL CTS tests. This commit more clearly delineates logic between NVPTX and Native-CPU, as the latter target didn't actually link against anything containing 'libdevice' so was too lenient.
frasercrmck
had a problem deploying
to
WindowsCILock
September 11, 2024 14:44
— with
GitHub Actions
Failure
frasercrmck
had a problem deploying
to
WindowsCILock
September 11, 2024 15:24
— with
GitHub Actions
Error
frasercrmck
temporarily deployed
to
WindowsCILock
September 11, 2024 15:32
— with
GitHub Actions
Inactive
frasercrmck
temporarily deployed
to
WindowsCILock
September 11, 2024 16:37
— with
GitHub Actions
Inactive
mdtoguchi
reviewed
Sep 11, 2024
frasercrmck
had a problem deploying
to
WindowsCILock
September 12, 2024 09:47
— with
GitHub Actions
Failure
frasercrmck
had a problem deploying
to
WindowsCILock
September 12, 2024 10:21
— with
GitHub Actions
Error
frasercrmck
temporarily deployed
to
WindowsCILock
September 12, 2024 10:32
— with
GitHub Actions
Inactive
frasercrmck
temporarily deployed
to
WindowsCILock
September 12, 2024 11:04
— with
GitHub Actions
Inactive
frasercrmck
temporarily deployed
to
WindowsCILock
September 12, 2024 12:19
— with
GitHub Actions
Inactive
frasercrmck
had a problem deploying
to
WindowsCILock
September 12, 2024 12:51
— with
GitHub Actions
Failure
frasercrmck
temporarily deployed
to
WindowsCILock
September 12, 2024 14:25
— with
GitHub Actions
Inactive
mdtoguchi
approved these changes
Sep 12, 2024
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM - thanks!
@intel/llvm-gatekeepers this is ready to merge, thanks - there's one unrelated unexpected pass |
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.
Recent upstream changes removed the workaround that required libraries to be named ".cubin".
We also renamed the NVPTX libdevice library when we unified it into a single bytecode library.
Unfortunately both of these things broke the driver's brittle logic that determined whether or not an object was a device library. This resulted in us not stripping any symbols from the final object, which is both slower and broke some SYCL CTS tests.
This commit more clearly delineates logic between NVPTX and NativeCPU, as the latter target didn't actually link against anything containing 'libdevice' so was too lenient.