offload: move (un)register lib into global_ctors #150893
Open
+132
−117
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
rustbot
added
A-LLVM
Collaborator
|
|
This comment has been minimized.
This comment has been minimized.
ZuseZ4
force-pushed
the
move-un-register-lib
branch
2 times, most recently
from
788ce48 to
542e8e2
Compare
This comment has been minimized.
This comment has been minimized.
ZuseZ4
force-pushed
the
move-un-register-lib
branch
2 times, most recently
from
b305773 to
c5134ae
Compare
ZuseZ4
force-pushed
the
move-un-register-lib
branch
from
c5134ae to
79a9d30
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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.
Right now we initialize the omp/offload runtime before every single offload call, and tear it down directly afterwards.
What we should rather do is initialize it once in the binary startup code, and tear it down at the end of the binary execution. Here I implement these changes.
Part 2 also removes the calls to
@__tgt_init_all_rtls, since it doesn't seem to be needed right now and I also can't find it in similar clang IR anymore. It might also allow the ompOpt pass to perform more optimizations.Together, our generated IR has a lot less usage of globals, which in turn simplifies the refactoring in #150683, where I introduce a new variant of our offload intrinsic.
@Sa4dUs can you please confirm that this doesn't break NVIDIA or any of your benchmarks?
r? oli-obk