[llvm-branch-commits] [llvm] AMDGPU: Handle legal v2f16/v2bf16 atomicrmw fadd for global/flat (PR #95394)
Matt Arsenault via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Jun 14 12:05:46 PDT 2024
================
@@ -15931,6 +15931,26 @@ static OptimizationRemark emitAtomicRMWLegalRemark(const AtomicRMWInst *RMW) {
<< " operation at memory scope " << MemScope;
}
+static bool isHalf2OrBFloat2(Type *Ty) {
----------------
arsenm wrote:
Both instructions were added together. The currently defined feature is HasAtomicFlatPkAdd16Insts, so this mirrors that
https://github.com/llvm/llvm-project/pull/95394
More information about the llvm-branch-commits
mailing list