================
@@ -1578,11 +1581,92 @@ bool AMDGPUCodeGenPrepareImpl::visitLoadInst(LoadInst
&I) {
return false;
}
+// select (X == 0 || Y == 0), +0.0, (X * Y) -> fmul_legacy(X, Y)
+bool AMDGPUCodeGenPrepareImpl::foldSelectToFMulLegacy(SelectInst &I) const {
+ if (!I.getType()->isFloatTy())
+ return false;
+
+ // Inverted form: select (X != 0 && Y != 0), X * Y, +0.0.
+ bool Inverted = match(I.getFalseValue(), m_PosZeroFP());
+ if (!Inverted && !match(I.getTrueValue(), m_PosZeroFP()))
+ return false;
+
+ Value *X, *Y;
+ if (!match(Inverted ? I.getTrueValue() : I.getFalseValue(),
+ m_OneUse(m_FMul(m_Value(X), m_Value(Y)))))
+ return false;
+
+ // Collect the values compared against zero in the condition.
----------------
arsenm wrote:
This seems like a trivial pattern that shouldn't need a worklist
https://github.com/llvm/llvm-project/pull/229357
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
