[llvm] [AMDGPU] Ensure divergence for v_alignbit (PR #129159)

Brox Chen via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 25 16:46:17 PDT 2025


================
@@ -2500,11 +2500,11 @@ def : AMDGPUPat <
 
 def : ROTRPattern <V_ALIGNBIT_B32_e64>;
 
-def : GCNPat<(i32 (trunc (srl i64:$src0, (and i32:$src1, (i32 31))))),
+def : GCNPat<(i32 (DivergentUnaryFrag<trunc> (srl i64:$src0, (and i32:$src1, (i32 31))))),
----------------
broxigarchen wrote:

Yes I saw the same pattern changes on all modes. Thanks!

https://github.com/llvm/llvm-project/pull/129159


More information about the llvm-commits mailing list