diff --git a/clang/lib/CodeGen/CGDecl.cpp b/clang/lib/CodeGen/CGDecl.cpp
--- a/clang/lib/CodeGen/CGDecl.cpp
+++ b/clang/lib/CodeGen/CGDecl.cpp
@@ -2252,16 +2252,17 @@
 
   // Shift the address back by one element.
   llvm::Value *negativeOne = llvm::ConstantInt::get(SizeTy, -1, true);
+  llvm::Type *llvmElementType = ConvertTypeForMem(elementType);
   llvm::Value *element = Builder.CreateInBoundsGEP(
-      elementPast->getType()->getPointerElementType(), elementPast, negativeOne,
-      "arraydestroy.element");
+      llvmElementType, elementPast, negativeOne, "arraydestroy.element");
 
   if (useEHCleanup)
     pushRegularPartialArrayCleanup(begin, element, elementType, elementAlign,
                                    destroyer);
 
   // Perform the actual destruction there.
-  destroyer(*this, Address(element, elementAlign), elementType);
+  destroyer(*this, Address(element, llvmElementType, elementAlign),
+            elementType);
 
   if (useEHCleanup)
     PopCleanupBlock();
diff --git a/clang/lib/CodeGen/CGDeclCXX.cpp b/clang/lib/CodeGen/CGDeclCXX.cpp
--- a/clang/lib/CodeGen/CGDeclCXX.cpp
+++ b/clang/lib/CodeGen/CGDeclCXX.cpp
@@ -136,6 +136,7 @@
     }
   // Otherwise, the standard logic requires a helper function.
   } else {
+    Addr = Addr.getElementBitCast(CGF.ConvertTypeForMem(Type));
     Func = CodeGenFunction(CGM)
            .generateDestroyHelper(Addr, Type, CGF.getDestroyer(DtorKind),
                                   CGF.needsEHCleanup(DtorKind), &D);
diff --git a/clang/test/CodeGenCXX/global-array-destruction.cpp b/clang/test/CodeGenCXX/global-array-destruction.cpp
--- a/clang/test/CodeGenCXX/global-array-destruction.cpp
+++ b/clang/test/CodeGenCXX/global-array-destruction.cpp
@@ -39,7 +39,7 @@
 T t[2][3] = { 1.0, 2, 3.0, 4, 5.0, 6, 7.0, 8, 9.0, 10, 11.0, 12 };
 
 // CHECK: call {{.*}} @__cxa_atexit
-// CHECK: getelementptr inbounds ([2 x [3 x {{.*}}]], [2 x [3 x {{.*}}]]* @t, i64 1, i64 0, i64 0)
+// CHECK: getelementptr inbounds ([2 x [3 x %struct.T]], [2 x [3 x %struct.T]]* bitcast ([2 x [3 x { double, i32 }]]* @t to [2 x [3 x %struct.T]]*), i64 1, i64 0, i64 0)
 // CHECK: call void @_ZN1TD1Ev
 // CHECK: icmp eq {{.*}} @t
 // CHECK: br i1 {{.*}}
@@ -47,7 +47,7 @@
 static T t2[2][3] = { 1.0, 2, 3.0, 4, 5.0, 6, 7.0, 8, 9.0, 10, 11.0, 12 };
 
 // CHECK: call {{.*}} @__cxa_atexit
-// CHECK: getelementptr inbounds ([2 x [3 x {{.*}}]], [2 x [3 x {{.*}}]]* @_ZL2t2, i64 1, i64 0, i64 0)
+// CHECK: getelementptr inbounds ([2 x [3 x %struct.T]], [2 x [3 x %struct.T]]* bitcast ([2 x [3 x { double, i32 }]]* @_ZL2t2 to [2 x [3 x %struct.T]]*), i64 1, i64 0, i64 0)
 // CHECK: call void @_ZN1TD1Ev
 // CHECK: icmp eq {{.*}} @_ZL2t2
 // CHECK: br i1 {{.*}}
@@ -56,7 +56,7 @@
 U &&u = U{ {{1.0, 2}, {3.0, 4}, {5.0, 6}}, {{7.0, 8}, {9.0, 10}, {11.0, 12}} };
 
 // CHECK: call {{.*}} @__cxa_atexit
-// CHECK: getelementptr inbounds ([2 x [3 x {{.*}}]], [2 x [3 x {{.*}}]]* @_ZGR1u_, i64 1, i64 0, i64 0)
+// CHECK: getelementptr inbounds ([2 x [3 x %struct.T]], [2 x [3 x %struct.T]]* @_ZGR1u_, i64 1, i64 0, i64 0)
 // CHECK: call void @_ZN1TD1Ev
 // CHECK: icmp eq {{.*}} @_ZGR1u_
 // CHECK: br i1 {{.*}}