Index: lib/Transforms/InstCombine/InstructionCombining.cpp
===================================================================
--- lib/Transforms/InstCombine/InstructionCombining.cpp
+++ lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -2029,9 +2029,17 @@
           areMatchingArrayAndVecTypes(GEPEltType, SrcEltType)) ||
          (GEPEltType->isVectorTy() && SrcEltType->isArrayTy() &&
           areMatchingArrayAndVecTypes(SrcEltType, GEPEltType)))) {
-      GEP.setOperand(0, SrcOp);
-      GEP.setSourceElementType(SrcEltType);
-      return &GEP;
+
+      Value *NGEP =
+            GEP.isInBounds()
+                ? Builder.CreateInBoundsGEP(nullptr, SrcOp, makeArrayRef(Ops).slice(1))
+                : Builder.CreateGEP(nullptr, SrcOp,makeArrayRef(Ops).slice(1));
+      NGEP->takeName(&GEP);
+
+      if (NGEP->getType()->getPointerAddressSpace() != GEP.getAddressSpace())
+        return new AddrSpaceCastInst(NGEP, GEPType);
+
+      return replaceInstUsesWith(GEP, NGEP);
     }
 
     // See if we can simplify:
Index: test/Transforms/InstCombine/gep-addrspace.ll
===================================================================
--- test/Transforms/InstCombine/gep-addrspace.ll
+++ test/Transforms/InstCombine/gep-addrspace.ll
@@ -84,3 +84,21 @@
   store <16 x i32> %call, <16 x i32> addrspace(3)* %t4
   ret void
 }
+
+declare void @extern_vec_pointers_func(<16 x i32 addrspace(3)*>)
+
+define void @insertelem_after_gep(<16 x i32>* %t0) {
+; CHECK-LABEL: @insertelem_after_gep(
+; CHECK-NEXT:    [[T3:%.*]] = getelementptr inbounds <16 x i32>, <16 x i32>* [[T0:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[TMP1:%.*]] = addrspacecast i32* [[T3]] to i32 addrspace(3)*
+; CHECK-NEXT:    [[T4:%.*]] = insertelement <16 x i32 addrspace(3)*> undef, i32 addrspace(3)* [[TMP1]], i32 0
+; CHECK-NEXT:    call void @extern_vec_pointers_func(<16 x i32 addrspace(3)*> [[T4]])
+; CHECK-NEXT:    ret void
+;
+  %t1 = bitcast <16 x i32>* %t0 to [16 x i32]*
+  %t2 = addrspacecast [16 x i32]* %t1 to [16 x i32] addrspace(3)*
+  %t3 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(3)* %t2, i64 0, i64 0
+  %t4 = insertelement <16 x i32 addrspace(3)*> undef, i32 addrspace(3)* %t3, i32 0
+  call void @extern_vec_pointers_func(<16 x i32 addrspace(3)*> %t4)
+  ret void
+}