Add support for NEON VLD2-dup instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120236 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/vlddup.ll b/test/CodeGen/ARM/vlddup.ll
index f172ed5..00dd134 100644
--- a/test/CodeGen/ARM/vlddup.ll
+++ b/test/CodeGen/ARM/vlddup.ll
@@ -39,3 +39,35 @@
 	%tmp3 = shufflevector <16 x i8> %tmp2, <16 x i8> undef, <16 x i32> zeroinitializer
         ret <16 x i8> %tmp3
 }
+
+%struct.__neon_int8x8x2_t = type { <8 x i8>, <8 x i8> }
+%struct.__neon_int2x32x2_t = type { <2 x i32>, <2 x i32> }
+
+define <8 x i8> @vld2dupi8(i8* %A) nounwind {
+;CHECK: vld2dupi8:
+;Check the (default) alignment value.
+;CHECK: vld2.8 {d16[], d17[]}, [r0]
+	%tmp0 = tail call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> undef, <8 x i8> undef, i32 0, i32 1)
+	%tmp1 = extractvalue %struct.__neon_int8x8x2_t %tmp0, 0
+	%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> zeroinitializer
+	%tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp0, 1
+	%tmp4 = shufflevector <8 x i8> %tmp3, <8 x i8> undef, <8 x i32> zeroinitializer
+        %tmp5 = add <8 x i8> %tmp2, %tmp4
+        ret <8 x i8> %tmp5
+}
+
+define <2 x i32> @vld2dupi32(i32* %A) nounwind {
+;CHECK: vld2dupi32:
+;Check the alignment value.  Max for this instruction is 64 bits:
+;CHECK: vld2.32 {d16[], d17[]}, [r0, :64]
+	%tmp0 = tail call %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i32* %A, <2 x i32> undef, <2 x i32> undef, i32 0, i32 16)
+	%tmp1 = extractvalue %struct.__neon_int2x32x2_t %tmp0, 0
+	%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> zeroinitializer
+	%tmp3 = extractvalue %struct.__neon_int2x32x2_t %tmp0, 1
+	%tmp4 = shufflevector <2 x i32> %tmp3, <2 x i32> undef, <2 x i32> zeroinitializer
+        %tmp5 = add <2 x i32> %tmp2, %tmp4
+        ret <2 x i32> %tmp5
+}
+
+declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind readonly
+declare %struct.__neon_int2x32x2_t @llvm.arm.neon.vld2lane.v2i32(i32*, <2 x i32>, <2 x i32>, i32, i32) nounwind readonly