[clang] [llvm] [AMDGPU] Add an async barrier arrival workaround (PR #238539)

Yaxun Liu via cfe-commits cfe-commits at lists.llvm.org
Sat Nov 7 05:54:31 PST 2026


================
@@ -0,0 +1,30 @@
+# NOTE: Do not autogenerate. Check the ordered bank switch and EXEC preservation inside the workaround.
----------------
yxsamliu wrote:

Converted to an IR test. Clobbering the low VGPRs keeps the address above v255.

https://github.com/llvm/llvm-project/pull/238539


More information about the cfe-commits mailing list