Remove AdaptiveCpp workaround in dpl_shim.h to allow for automatic pefetch #180
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
|
@tomdeakin Is this okay now? It addresses your feedback from #177. |
|
Looks good, thanks @illuhad. As long as the CI comes back OK I'll merge. Thanks! |
tomdeakin
approved these changes
Dec 14, 2023
|
CI looks good to me @tomdeakin :) |
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Outdated suggestions cannot be applied.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.
To my knowledge, the AdaptiveCpp-specific workaround in
dpl_shim.his no longer necessary as the linking issue was fixed some time ago.Additionally, this workaround prevents a new optmization in AdaptiveCpp stdpar from taking place: AdaptiveCpp stdpar can now emit automatic data prefetches. But this only works, if the data is managed by the stdpar runtime, which tracks pointers it knows. If sycl::malloc_shared is used directly, the stdpar optimizations do not recognize the pointer and won't apply the optimization.
(the reasoning being that if someone calls SYCL functionality directly, they might want to exert more control and emit prefetches or mem_advise operations by themselves).
Other projects which also use this header like cloverleaf are also affected. Will create a PR there too.