Skip to content
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

[NFC-ish] Finish MSAN handling (Refs. #6513) #6516

Merged
merged 2 commits into from
Jan 4, 2022

Conversation

LebedevRI
Copy link
Contributor

Somehow, initially i missed that there was MSan support,
so it might be good to actually mention that we don't need to run
any MSan passes here, and that we didn't forget to run them.

Secondly, it seems inconsistent not annotate the functions
with Attribute::SanitizeMemory, like we do for others.

I suppose it isn't strictly required, since they are used
to actually drive the instrumentation passes, and we don't
run MSan pass, but they are also used to disable some LLVM optimizations,
and that //might// be important. Or not, but then i suppose
there should be a comment about it?

Let me know if i should replace the second change with a comment too.

Somehow, initially i missed that there was MSan support,
so it might be good to actually mention that we don't need to run
any MSan passes here, and that we didn't forget to run them.

Secondly, it seems inconsistent not annotate the functions
with `Attribute::SanitizeMemory`, like we do for others.

I suppose it isn't strictly required, since they are used
to actually drive the instrumentation passes, and we don't
run MSan pass, but they are also used to disable some LLVM optimizations,
and that //might// be important. Or not, but then i suppose
there should be a comment about it?
@LebedevRI LebedevRI changed the title [NFC-ish] Finish MSAN handling [NFC-ish] Finish MSAN handling (Refs. #6513) Dec 25, 2021
@alexreinking
Copy link
Member

Failures are again unrelated... same arm64/llvm14 failure.

@alexreinking alexreinking added the code_cleanup No functional changes. Reformatting, reorganizing, or refactoring existing code. label Dec 29, 2021
@alexreinking
Copy link
Member

Secondly, it seems inconsistent not annotate the functions with Attribute::SanitizeMemory, like we do for others.

I suppose it isn't strictly required, since they are used to actually drive the instrumentation passes, and we don't run MSan pass, but they are also used to disable some LLVM optimizations, and that //might// be important. Or not, but then i suppose there should be a comment about it?

Let me know if i should replace the second change with a comment too.

Requesting a review from @steven-johnson (whenever he's back) to address this. IIRC he implemented MSAN support and I'm not sure why this wouldn't be annotated.

Copy link
Contributor

@steven-johnson steven-johnson left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM pending green buildbots -- I think the arm failure are just stale from bad LLVM revisions, rerunning them now

@steven-johnson
Copy link
Contributor

Thanks for the fix!

@steven-johnson steven-johnson merged commit 7eb9949 into halide:master Jan 4, 2022
@LebedevRI LebedevRI deleted the msan branch January 4, 2022 16:40
@LebedevRI
Copy link
Contributor Author

@alexreinking @steven-johnson Thank you!

alexreinking pushed a commit that referenced this pull request Jan 5, 2022
Somehow, initially i missed that there was MSan support,
so it might be good to actually mention that we don't need to run
any MSan passes here, and that we didn't forget to run them.

Secondly, it seems inconsistent not annotate the functions
with `Attribute::SanitizeMemory`, like we do for others.

I suppose it isn't strictly required, since they are used
to actually drive the instrumentation passes, and we don't
run MSan pass, but they are also used to disable some LLVM optimizations,
and that //might// be important. Or not, but then i suppose
there should be a comment about it?

Co-authored-by: Steven Johnson <[email protected]>
(cherry picked from commit 7eb9949)
alexreinking pushed a commit that referenced this pull request Jan 6, 2022
Somehow, initially i missed that there was MSan support,
so it might be good to actually mention that we don't need to run
any MSan passes here, and that we didn't forget to run them.

Secondly, it seems inconsistent not annotate the functions
with `Attribute::SanitizeMemory`, like we do for others.

I suppose it isn't strictly required, since they are used
to actually drive the instrumentation passes, and we don't
run MSan pass, but they are also used to disable some LLVM optimizations,
and that //might// be important. Or not, but then i suppose
there should be a comment about it?

Co-authored-by: Steven Johnson <[email protected]>
(cherry picked from commit 7eb9949)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
code_cleanup No functional changes. Reformatting, reorganizing, or refactoring existing code.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants