[X86] When creating a select for scalar masked sqrt and div builtins make sure we optimize the all ones mask case.

This case occurs in the intrinsic headers so we should avoid emitting the mask in those cases.

Factor the code into a helper function to make this easy.

llvm-svn: 336472

1 files changed, 19 insertions, 12 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index f2efca8cc9c..3ebf584ac8e 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -8517,6 +8517,21 @@ static Value *EmitX86Select(CodeGenFunction &CGF,
   return CGF.Builder.CreateSelect(Mask, Op0, Op1);
 }
 
+static Value *EmitX86ScalarSelect(CodeGenFunction &CGF,
+                                  Value *Mask, Value *Op0, Value *Op1) {
+  // If the mask is all ones just return first argument.
+  if (const auto *C = dyn_cast<Constant>(Mask))
+    if (C->isAllOnesValue())
+      return Op0;
+
+  llvm::VectorType *MaskTy =
+    llvm::VectorType::get(CGF.Builder.getInt1Ty(),
+                          Mask->getType()->getIntegerBitWidth());
+  Mask = CGF.Builder.CreateBitCast(Mask, MaskTy);
+  Mask = CGF.Builder.CreateExtractElement(Mask, (uint64_t)0);
+  return CGF.Builder.CreateSelect(Mask, Op0, Op1);
+}
+
 static Value *EmitX86MaskedCompareResult(CodeGenFunction &CGF, Value *Cmp,
                                          unsigned NumElts, Value *MaskIn) {
   if (MaskIn) {
@@ -9884,12 +9899,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
     }
     Value *A = Builder.CreateExtractElement(Ops[1], (uint64_t)0);
     Function *F = CGM.getIntrinsic(Intrinsic::sqrt, A->getType());
+    A = Builder.CreateCall(F, A);
     Value *Src = Builder.CreateExtractElement(Ops[2], (uint64_t)0);
-    int MaskSize = Ops[3]->getType()->getScalarSizeInBits();
-    llvm::Type *MaskTy = llvm::VectorType::get(Builder.getInt1Ty(), MaskSize);
-    Value *Mask = Builder.CreateBitCast(Ops[3], MaskTy);
-    Mask = Builder.CreateExtractElement(Mask, (uint64_t)0);
-    A = Builder.CreateSelect(Mask, Builder.CreateCall(F, {A}), Src);
+    A = EmitX86ScalarSelect(*this, Ops[3], A, Src);
     return Builder.CreateInsertElement(Ops[0], A, (uint64_t)0);
   }
   case X86::BI__builtin_ia32_sqrtpd256:
@@ -10024,14 +10036,9 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
     Value *A = Builder.CreateExtractElement(Ops[0], (uint64_t)0);
     Value *B = Builder.CreateExtractElement(Ops[1], (uint64_t)0);
     Value *C = Builder.CreateExtractElement(Ops[2], (uint64_t)0);
-    Value *Mask = Ops[3];
     Value *Div = Builder.CreateFDiv(A, B);
-    llvm::VectorType *MaskTy = llvm::VectorType::get(Builder.getInt1Ty(),
-                             cast<IntegerType>(Mask->getType())->getBitWidth());
-    Mask = Builder.CreateBitCast(Mask, MaskTy);
-    Mask = Builder.CreateExtractElement(Mask, (uint64_t)0);
-    Value *Select = Builder.CreateSelect(Mask, Div, C);
-    return Builder.CreateInsertElement(Ops[0], Select, (uint64_t)0);
+    Div = EmitX86ScalarSelect(*this, Ops[3], Div, C);
+    return Builder.CreateInsertElement(Ops[0], Div, (uint64_t)0);
   }
 
   // 3DNow!