================
@@ -1054,6 +1055,68 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned
BuiltinID,
Value *Mul = Builder.CreateNUWMul(M, A);
return Builder.CreateNUWAdd(Mul, B);
}
+ case Builtin::BI__builtin_hlsl_mul: {
+ Value *Op0 = EmitScalarExpr(E->getArg(0));
+ Value *Op1 = EmitScalarExpr(E->getArg(1));
+ QualType QTy0 = E->getArg(0)->getType();
+ QualType QTy1 = E->getArg(1)->getType();
+
+ bool IsVec0 = QTy0->isVectorType();
+ bool IsVec1 = QTy1->isVectorType();
+ bool IsMat0 = QTy0->isConstantMatrixType();
+ bool IsMat1 = QTy1->isConstantMatrixType();
+
+ if (IsVec0 && IsVec1) {
+ // Case 5: vector * vector -> scalar (dot product)
----------------
farzonl wrote:
It is possible there are performance improvements with higher levels of
optimization because clang builtins get ignored by most passes.
That said codgen will be significantly worse with no optimization because the
helper functions will not have been inlined.
https://github.com/llvm/llvm-project/pull/184882
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
