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

Try generating code with unreachable control flow. #944

Merged
merged 1 commit into from
Jun 1, 2021
Merged

Conversation

maleadt
Copy link
Member

@maleadt maleadt commented Jun 1, 2021

For now only when using CUDA 11.3's ptxas, since that seems to pass tests locally.

The benefit of unreachable is that LLVM can remove potentially GPU incompatible code. As encountered in #103, where the boundscheck on an union array resulted in a jl_generic_apply in code following the thrown exception.

@maleadt
Copy link
Member Author

maleadt commented Jun 1, 2021

Good to know our tests still trigger this, but too bad it does still fail on CUDA 11.3 with a sm_61 device. Let's try bounding this on sm_70 and CUDA 11.3.

@maleadt maleadt merged commit c759f2a into master Jun 1, 2021
@maleadt maleadt deleted the tb/unreachable branch June 1, 2021 12:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant