Index: lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ 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: test/Transforms/SLPVectorizer/AArch64/PR38339.ll
===================================================================
--- /dev/null
+++ test/Transforms/SLPVectorizer/AArch64/PR38339.ll
@@ -0,0 +1,48 @@
+; 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
+
+@a = dso_local global i16 0, align 2
+
+define void @f1() {
+; CHECK-LABEL: @f1(
+; CHECK-NEXT:    [[TMP1:%.*]] = ptrtoint <2 x i16*> undef to <2 x i16>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[TMP1]], <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:    br label [[BB1:%.*]]
+; CHECK:       bb1:
+; CHECK-NEXT:    br i1 undef, label [[BB3:%.*]], label [[BB2:%.*]]
+; CHECK:       bb2:
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i16> [[SHUFFLE]], i32 0
+; CHECK-NEXT:    store i16 [[TMP2]], i16* @a, align 2
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i16* [[PTR0]] to <4 x i16>*
+; CHECK-NEXT:    store <4 x i16> [[SHUFFLE]], <4 x i16>* [[TMP3]], align 2
+; CHECK-NEXT:    br label [[BB1]]
+; CHECK:       bb3:
+; CHECK-NEXT:    ret void
+;
+  %1 = ptrtoint <2 x i16*> undef to <2 x i16>
+  %2 = extractelement <2 x i16> %1, i32 0
+  %3 = extractelement <2 x i16> %1, 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
+  br label %bb1
+
+bb1:                                              ; preds = %bb2, %0
+  br i1 undef, label %bb3, label %bb2
+
+bb2:                                              ; preds = %bb1
+  store i16 %2, i16* @a,    align 2
+  store i16 %2, i16* %ptr0, align 2
+  store i16 %3, i16* %ptr1, align 2
+  store i16 %3, i16* %ptr2, align 2
+  store i16 %2, i16* %ptr3, align 2
+  br label %bb1
+
+bb3:                                              ; preds = %bb1
+  ret void
+}