[X86] Replace avx2 broadcast intrinsics with native IR.

[oota-llvm.git] / lib / IR / AutoUpgrade.cpp

diff --git a/lib/IR/AutoUpgrade.cpp b/lib/IR/AutoUpgrade.cpp
index f1c6ebd4846ec1daa9dd3635a61251384447821b..aeefa38f74d6cb6ebe4f1092020915339ce33700 100644 (file)
--- a/lib/IR/AutoUpgrade.cpp
+++ b/lib/IR/AutoUpgrade.cpp
@@ -129,6 +129,8 @@ static bool UpgradeIntrinsicFunction1(Function *F, Function *&NewFn) {
         Name.startswith("x86.sse2.pcmpgt.") ||
         Name.startswith("x86.avx2.pcmpeq.") ||
         Name.startswith("x86.avx2.pcmpgt.") ||
+        Name.startswith("x86.avx2.vbroadcast") ||
+        Name.startswith("x86.avx2.pbroadcast") ||
         Name.startswith("x86.avx.vpermil.") ||
         Name == "x86.avx.vinsertf128.pd.256" ||
         Name == "x86.avx.vinsertf128.ps.256" ||
@@ -447,6 +449,14 @@ void llvm::UpgradeIntrinsicCall(CallInst *CI, Function *NewFn) {
       const int Idxs[4] = { 0, 1, 0, 1 };
       Rep = Builder.CreateShuffleVector(Load, UndefValue::get(Load->getType()),
                                         Idxs);
+    } else if (Name.startswith("llvm.x86.avx2.pbroadcast") ||
+               Name.startswith("llvm.x86.avx2.vbroadcast")) {
+      // Replace vp?broadcasts with a vector shuffle.
+      Value *Op = CI->getArgOperand(0);
+      unsigned NumElts = CI->getType()->getVectorNumElements();
+      Type *MaskTy = VectorType::get(Type::getInt32Ty(C), NumElts);
+      Rep = Builder.CreateShuffleVector(Op, UndefValue::get(Op->getType()),
+                                        Constant::getNullValue(MaskTy));
     } else if (Name == "llvm.x86.sse2.psll.dq") {
       // 128-bit shift left specified in bits.
       unsigned Shift = cast<ConstantInt>(CI->getArgOperand(1))->getZExtValue();