[llvm-branch-commits] [llvm] AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. (PR #95592)

[Shilei Tian via llvm-branch-commits]

================
@@ -1699,7 +1709,7 @@ multiclass SIBufferAtomicPat_Common<string OpPrefix, ValueType vt, string Inst,
 
 multiclass SIBufferAtomicPat<string OpPrefix, ValueType vt, string Inst,
                              list<string> RtnModes = ["ret", "noret"]> {
-  let SubtargetPredicate = HasUnrestrictedSOffset in {
+  let OtherPredicates = [HasUnrestrictedSOffset] in {
----------------
shiltian wrote:

A side question, what is the difference between `OtherPredicates` and `SubtargetPredicate`? It looks like you swapped a couple of them here.

https://github.com/llvm/llvm-project/pull/95592