Fix memcpy lowering when addresses are 4-byte aligned but size is not multiple of 4.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@43234 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/memcpy-inline.ll b/test/CodeGen/ARM/memcpy-inline.ll
new file mode 100644
index 0000000..665d3ac
--- /dev/null
+++ b/test/CodeGen/ARM/memcpy-inline.ll
@@ -0,0 +1,15 @@
+; RUN: llvm-as < %s | llc -mtriple=arm-apple-darwin | grep ldmia
+; RUN: llvm-as < %s | llc -mtriple=arm-apple-darwin | grep ldrb
+; RUN: llvm-as < %s | llc -mtriple=arm-apple-darwin | grep ldrh
+
+	%struct.x = type { i8, i8, i8, i8, i8, i8, i8, i8, i8, i8, i8 }
+@src = external global %struct.x
+@dst = external global %struct.x
+
+define i32 @t() {
+entry:
+	call void @llvm.memcpy.i32( i8* getelementptr (%struct.x* @dst, i32 0, i32 0), i8* getelementptr (%struct.x* @src, i32 0, i32 0), i32 11, i32 8 )
+	ret i32 0
+}
+
+declare void @llvm.memcpy.i32(i8*, i8*, i32, i32)