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

llvm/cuda: Do not use shared memory for inputs #2731

Merged
merged 2 commits into from
Jul 11, 2023

Conversation

jvesely
Copy link
Collaborator

@jvesely jvesely commented Jul 11, 2023

The size of the input array is dynamically determined so it can't use static allocation of GPU shared memory.
Enable PEC GPU tests.

@jvesely jvesely added compiler Runtime Compiler CUDA CUDA target for the runtime compiler tests Test changes labels Jul 11, 2023
@github-actions
Copy link

This PR causes the following changes to the html docs (ubuntu-latest-3.7-x64):

No differences!

...

See CI logs for the full diff.

jvesely added 2 commits July 11, 2023 16:56
The size of inputs is dynamic and the destination cannot be allocated
statically. Dynamic shared memory allocation is possible, but the
benefits for inputs are unclear since the input array is iterated over
in the outermost loop of the kernel.

Signed-off-by: Jan Vesely <[email protected]>
@github-actions
Copy link

This PR causes the following changes to the html docs (ubuntu-latest-3.7-x64):

No differences!

...

See CI logs for the full diff.

@jvesely jvesely merged commit a2e75ad into PrincetonUniversity:devel Jul 11, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
compiler Runtime Compiler CUDA CUDA target for the runtime compiler tests Test changes
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant