Skip to content

Conversation

christiangnrd
Copy link
Member

@christiangnrd christiangnrd commented Sep 30, 2025

The goal is to allow for kernels to be written without relying on KernelAbstractions macros

@vchuravy @maleadt

Copy link
Contributor

github-actions bot commented Sep 30, 2025

Your PR requires formatting changes to meet the project's style guidelines.
Please consider running Runic (git runic main) to apply these changes.

Click here to view the suggested changes.
diff --git a/test/intrinsics.jl b/test/intrinsics.jl
index e58b58a6..a586de08 100644
--- a/test/intrinsics.jl
+++ b/test/intrinsics.jl
@@ -20,7 +20,7 @@ end
 
 
 function intrinsics_testsuite(backend, AT)
-    @testset "KernelIntrinsics Tests" begin
+    return @testset "KernelIntrinsics Tests" begin
         @testset "Basic intrinsics functionality" begin
 
             # Test with small kernel

@christiangnrd christiangnrd force-pushed the intrinsics branch 3 times, most recently from c16a665 to b166baa Compare October 2, 2025 19:58
@vchuravy
Copy link
Member

vchuravy commented Oct 6, 2025

Can you rebase?

@christiangnrd

This comment was marked as outdated.

@vchuravy vchuravy changed the title More KernelIntrinsics KernelIntrinsics API Oct 6, 2025
@vchuravy vchuravy added this to the 0.10.0 milestone Oct 6, 2025
@vchuravy vchuravy mentioned this pull request Oct 6, 2025
@vchuravy vchuravy linked an issue Oct 6, 2025 that may be closed by this pull request
Comment on lines +54 to +58
function localmemory end
function barrier()
error("Group barrier used outside kernel or not captured")
end
function print end
Copy link
Member

Choose a reason for hiding this comment

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

Needs docs.

@vchuravy
Copy link
Member

vchuravy commented Oct 6, 2025

@christiangnrd do you think we need a lower-level kernel launch interface? Otherwise the three-dimensional indices would be superflous.

@christiangnrd
Copy link
Member Author

christiangnrd commented Oct 6, 2025

do you think we need a lower-level kernel launch interface?

I'd been thinking about that and I think so. Would something that, assuming you wrote the whole kernel with KernelIntrinsics, could be used interchangeably with the backend's kernel launch macro (@cuda, @metal, etc.) make sense/be feasible?

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.

Lower-level kernel form?
2 participants