Index: lib/Transforms/Scalar/SeparateConstOffsetFromGEP.cpp
===================================================================
--- lib/Transforms/Scalar/SeparateConstOffsetFromGEP.cpp
+++ lib/Transforms/Scalar/SeparateConstOffsetFromGEP.cpp
@@ -829,7 +829,7 @@
 
   // The backend can already nicely handle the case where all indices are
   // constant.
-  if (GEP->hasAllConstantIndices())
+  if (GEP->hasAllConstantIndices() || GEP->getNumOperands() == 2)
     return false;
 
   bool Changed = canonicalizeArrayIndicesToPointerSize(GEP);
Index: test/CodeGen/AArch64/arm64-addr-mode-folding.ll
===================================================================
--- test/CodeGen/AArch64/arm64-addr-mode-folding.ll
+++ test/CodeGen/AArch64/arm64-addr-mode-folding.ll
@@ -1,4 +1,4 @@
-; RUN: llc -O3 -mtriple arm64-apple-ios3 -aarch64-gep-opt=false %s -o - | FileCheck %s
+; RUN: llc -O3 -mtriple arm64-apple-ios3 %s -o - | FileCheck %s
 ; <rdar://problem/13621857>
 
 @block = common global i8* null, align 8
Index: test/CodeGen/AArch64/arm64-cse.ll
===================================================================
--- test/CodeGen/AArch64/arm64-cse.ll
+++ test/CodeGen/AArch64/arm64-cse.ll
@@ -1,4 +1,4 @@
-; RUN: llc -O3 < %s -aarch64-atomic-cfg-tidy=0 -aarch64-gep-opt=false -verify-machineinstrs | FileCheck %s
+; RUN: llc -O3 < %s -aarch64-atomic-cfg-tidy=0 -verify-machineinstrs | FileCheck %s
 target triple = "arm64-apple-ios"
 
 ; rdar://12462006
@@ -12,7 +12,7 @@
 ; CHECK-NOT: sub
 ; CHECK: b.ge
 ; CHECK: sub
-; CHECK: sub
+; CHECK: {{sub|add}}
 ; CHECK-NOT: sub
 ; CHECK: ret
  %0 = load i32, i32* %offset, align 4
Index: test/Transforms/SeparateConstOffsetFromGEP/NVPTX/split-gep.ll
===================================================================
--- test/Transforms/SeparateConstOffsetFromGEP/NVPTX/split-gep.ll
+++ test/Transforms/SeparateConstOffsetFromGEP/NVPTX/split-gep.ll
@@ -237,7 +237,7 @@
 
 ; The code that rebuilds an OR expression used to be buggy, and failed on this
 ; test.
-define float* @shl_add_or(i64 %a, float* %ptr) {
+define float* @shl_add_or(i64 %a, [10 x float]* %ptr) {
 ; CHECK-LABEL: @shl_add_or(
 entry:
   %shl = shl i64 %a, 2
@@ -247,8 +247,8 @@
   ; ((a << 2) + 12) and 1 have no common bits. Therefore,
   ; SeparateConstOffsetFromGEP is able to extract the 12.
   ; TODO(jingyue): We could reassociate the expression to combine 12 and 1.
-  %p = getelementptr float, float* %ptr, i64 %or
-; CHECK: [[PTR:%[a-zA-Z0-9]+]] = getelementptr float, float* %ptr, i64 [[OR]]
+  %p = getelementptr [10 x float], [10 x float]* %ptr, i64 %or, i64 0
+; CHECK: [[PTR:%[a-zA-Z0-9]+]] = getelementptr [10 x float], [10 x float]* %ptr, i64 [[OR]], i64 0
 ; CHECK: getelementptr float, float* [[PTR]], i64 12
   ret float* %p
 ; CHECK-NEXT: ret