[llvm] [AMDGPU] Add v2i32 and/or patterns for VOP3 AND_OR and OR3 operations (PR #188375)

Wooseok Lee via llvm-commits llvm-commits at lists.llvm.org
Mon Apr 6 08:56:47 PDT 2026


wooseoklee wrote:

> amdgpu_ps should only be used as a scalar use, not any of the cases that actually match

I restored the change, but I had to update some auto-generated checks manually using update_llc_tests.py as it fails to generate checks due to the conflicts in GFX10.

https://github.com/llvm/llvm-project/pull/188375


More information about the llvm-commits mailing list