[llvm] [AMDGPU] SIFoldOperands: Add REQ_SEQUENCE subregister use fold (PR #188451)

Frederik Harwath via llvm-commits llvm-commits at lists.llvm.org
Wed Mar 25 06:04:16 PDT 2026


================

----------------
frederik-h wrote:

This test shows the si-peephole-sdwa optimizations that are enabled by this PR.

https://github.com/llvm/llvm-project/pull/188451


More information about the llvm-commits mailing list