Fix a bug about generating undef operand when optimising shuffle vector and insert element in instruction combine.

llvm-svn: 198730

2 files changed, 20 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp b/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
index 1e724106991..c0b9b2fc3e5 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
@@ -763,9 +763,10 @@ InstCombiner::EvaluateInDifferentElementOrder(Value *V, ArrayRef<int> Mask) {
         }
       }
 
+      // If element is not in Mask, no need to handle the operand 1 (element to
+      // be inserted). Just evaluate values in operand 0 according to Mask.
       if (!Found)
-        return UndefValue::get(
-            VectorType::get(V->getType()->getScalarType(), Mask.size()));
+        return EvaluateInDifferentElementOrder(I->getOperand(0), Mask);
 
       Value *V = EvaluateInDifferentElementOrder(I->getOperand(0), Mask);
       return InsertElementInst::Create(V, I->getOperand(1),
diff --git a/llvm/test/Transforms/InstCombine/vec_shuffle.ll b/llvm/test/Transforms/InstCombine/vec_shuffle.ll
index 3ee43dc63a6..a409a911ef1 100644
--- a/llvm/test/Transforms/InstCombine/vec_shuffle.ll
+++ b/llvm/test/Transforms/InstCombine/vec_shuffle.ll
@@ -228,3 +228,20 @@ define <4 x float> @test15b(<4 x float> %LHS, <4 x float> %RHS) {
   ret <4 x float> %tmp5
 }
 
+define <1 x i32> @test16a(i32 %ele) {
+; CHECK-LABEL: @test16a(
+; CHECK-NEXT: ret <1 x i32> <i32 2>
+  %tmp0 = insertelement <2 x i32> <i32 1, i32 undef>, i32 %ele, i32 1
+  %tmp1 = shl <2 x i32> %tmp0, <i32 1, i32 1>
+  %tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <1 x i32> <i32 0>
+  ret <1 x i32> %tmp2
+}
+
+define <4 x i8> @test16b(i8 %ele) {
+; CHECK-LABEL: @test16b(
+; CHECK-NEXT: ret <4 x i8> <i8 2, i8 2, i8 2, i8 2>
+  %tmp0 = insertelement <8 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 undef, i8 1>, i8 %ele, i32 6
+  %tmp1 = shl <8 x i8> %tmp0, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
+  %tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 4>
+  ret <4 x i8> %tmp2
+}
\ No newline at end of file