[Driver][SYCL][NewOffload] Fix duplication of device targets #14091
Conversation
This file contains hidden or 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
When passing along multiple targets in the form of -fsycl-targets=intel_gpu_dg1,intel_gpu_pvc, the number of the device compilations was n*n as opposed to just n. Due to how we were handling duplicate entries for toolchain generation, the different names used even though they had the same target triple (spir64_gen) we being considered as unique, causing the multiple entries.
bader
reviewed
Jun 7, 2024
Also, fix problem with toolchain access.
hchilama
approved these changes
Jun 10, 2024
|
@intel/llvm-gatekeepers, this PR looks ready to merge - thanks! |
|
@mdtoguchi - Clang :: Driver/sycl-offload-new-driver.c fails in post-commit after this. Revert in #14134. |
mdtoguchi
added a commit
to mdtoguchi/llvm
that referenced
this pull request
Jun 11, 2024
A cross checkin of intel#14091 and intel#14066 caused a difference in expected ordering of options passed to the packager. Update the test accordingly.
ianayl
pushed a commit
to ianayl/sycl
that referenced
this pull request
Jun 13, 2024
…4091) When passing along multiple targets in the form of -fsycl-targets=intel_gpu_dg1,intel_gpu_pvc, the number of the device compilations was n*n as opposed to just n. Due to how we were handling duplicate entries for toolchain generation, the different names used even though they had the same target triple (spir64_gen) we being considered as unique, causing the multiple entries.
ianayl
pushed a commit
to ianayl/sycl
that referenced
this pull request
Jun 13, 2024
…intel#14134) Reverts intel#14091 due to failure in Clang :: Driver/sycl-offload-new-driver.c in post-commit.
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.
When passing along multiple targets in the form of -fsycl-targets=intel_gpu_dg1,intel_gpu_pvc, the number of the device compilations was n*n as opposed to just n. Due to how we were handling duplicate entries for toolchain generation, the different names used even though they had the same target triple (spir64_gen) we being considered as unique, causing the multiple entries.