Index: lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- lib/CodeGen/CodeGenPrepare.cpp
+++ lib/CodeGen/CodeGenPrepare.cpp
@@ -1286,7 +1286,8 @@
         continue;
       APInt Offset(TD->getPointerSizeInBits(
                      cast<PointerType>(Arg->getType())->getAddressSpace()), 0);
-      Value *Val = Arg->stripAndAccumulateInBoundsConstantOffsets(*TD, Offset);
+      Value *Val = Arg->stripAndAccumulateInBoundsConstantOffsets(*TD, Offset,
+                          /*LookThroughNoAlias*/true);
       uint64_t Offset2 = Offset.getLimitedValue();
       if ((Offset2 & (PrefAlign-1)) != 0)
         continue;
Index: test/CodeGen/ARM/memfunc.ll
===================================================================
--- test/CodeGen/ARM/memfunc.ll
+++ test/CodeGen/ARM/memfunc.ll
@@ -68,6 +68,50 @@
   unreachable
 }
 
+; From @f2 above, but make sure that a noalias call does not prevent the
+; optimization.
+define void @f2a(i8* %dest, i32 %n) {
+entry:
+  ; CHECK-LABEL: f2a
+
+  ; IOS (ARMv7) should 8-byte align, others should 4-byte align
+  ; CHECK-IOS: add r1, sp, #32
+  ; CHECK-IOS: memmove
+  ; CHECK-DARWIN: add r1, sp, #28
+  ; CHECK-DARWIN: memmove
+  ; CHECK-EABI: add r1, sp, #28
+  ; CHECK-EABI: __aeabi_memmove
+  %arr0 = alloca [9 x i8], align 1
+  %0 = bitcast [9 x i8]* %arr0 to i8*
+  %q = call i8* @llvm.noalias.p0i8(i8* %0, metadata !1)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %q, i32 %n, i32 0, i1 false)
+
+  ; CHECK: add r1, sp, #16
+  ; CHECK-IOS: memcpy
+  ; CHECK-DARWIN: memcpy
+  ; CHECK-EABI: __aeabi_memcpy
+  %arr1 = alloca [9 x i8], align 1
+  %1 = bitcast [9 x i8]* %arr1 to i8*
+  %r = call i8* @llvm.noalias.p0i8(i8* %1, metadata !1)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %r, i32 %n, i32 0, i1 false)
+
+  ; CHECK-IOS: mov r0, sp
+  ; CHECK-IOS: mov r1, #0
+  ; CHECK-IOS: memset
+  ; CHECK-DARINW: add r0, sp, #4
+  ; CHECK-DARWIN: movs r1, #0
+  ; CHECK-DARWIN: memset
+  ; CHECK-EABI: add r0, sp, #4
+  ; CHECK-EABI: mov r2, #0
+  ; CHECK-EABI: __aeabi_memset
+  %arr2 = alloca [9 x i8], align 1
+  %2 = bitcast [9 x i8]* %arr2 to i8*
+  %s = call i8* @llvm.noalias.p0i8(i8* %2, metadata !1)
+  call void @llvm.memset.p0i8.i32(i8* %s, i8 0, i32 %n, i32 0, i1 false)
+
+  unreachable
+}
+
 ; Check that alloca arguments are not aligned if less than 8 bytes in size
 define void @f3(i8* %dest, i32 %n) {
 entry:
@@ -322,3 +366,9 @@
 declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
 declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
 declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+
+declare i8* @llvm.noalias.p0i8(i8*, metadata) nounwind
+
+!0 = !{!0, !"some domain"}
+!1 = !{!1, !0, !"some scope"}
+