Index: llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3111,6 +3111,12 @@
           // TODO: Merge this shuffle with the ReorderShuffleMask.
           if (!E->ReorderIndices.empty())
             Builder.SetInsertPoint(VL0);
+          else if (auto *I = dyn_cast<Instruction>(V))
+            Builder.SetInsertPoint(I->getParent(),
+                                   std::next(I->getIterator()));
+          else
+            Builder.SetInsertPoint(&F->getEntryBlock(),
+                                   F->getEntryBlock().getFirstInsertionPt());
           V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                           E->ReuseShuffleIndices, "shuffle");
         }
Index: llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
===================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
+++ llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -S -mtriple=aarch64-apple-ios -mcpu=cyclone -o - %s | FileCheck %s
+
+define void @f1(<2 x i16> %x, i16* %a) {
+; CHECK-LABEL: @f1(
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[X:%.*]], <2 x i16> undef, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
+; CHECK-NEXT:    [[PTR0:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 0
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 1
+; CHECK-NEXT:    [[PTR2:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 2
+; CHECK-NEXT:    [[PTR3:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 3
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i16> [[SHUFFLE]], i32 0
+; CHECK-NEXT:    store i16 [[TMP1]], i16* [[A:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16* [[PTR0]] to <4 x i16>*
+; CHECK-NEXT:    store <4 x i16> [[SHUFFLE]], <4 x i16>* [[TMP2]], align 2
+; CHECK-NEXT:    ret void
+;
+  %t2 = extractelement <2 x i16> %x, i32 0
+  %t3 = extractelement <2 x i16> %x, i32 1
+  %ptr0 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 0
+  %ptr1 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 1
+  %ptr2 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 2
+  %ptr3 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 3
+  store i16 %t2, i16* %a
+  store i16 %t2, i16* %ptr0
+  store i16 %t3, i16* %ptr1
+  store i16 %t3, i16* %ptr2
+  store i16 %t2, i16* %ptr3
+  ret void
+}