1 files changed, 107 insertions, 0 deletions
diff --git a/test/CodeGen/ARM/vhsub.ll b/test/CodeGen/ARM/vhsub.ll
new file mode 100644
index 0000000000..32a66e5479
--- /dev/null
+++ b/test/CodeGen/ARM/vhsub.ll
@@ -0,0 +1,107 @@
+; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
+; RUN: grep {vhsub\\.s8} %t | count 2
+; RUN: grep {vhsub\\.s16} %t | count 2
+; RUN: grep {vhsub\\.s32} %t | count 2
+; RUN: grep {vhsub\\.u8} %t | count 2
+; RUN: grep {vhsub\\.u16} %t | count 2
+; RUN: grep {vhsub\\.u32} %t | count 2
+
+define <8 x i8> @vhsubs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+	%tmp1 = load <8 x i8>* %A
+	%tmp2 = load <8 x i8>* %B
+	%tmp3 = call <8 x i8> @llvm.arm.neon.vhsubs.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
+	ret <8 x i8> %tmp3
+}
+
+define <4 x i16> @vhsubs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+	%tmp1 = load <4 x i16>* %A
+	%tmp2 = load <4 x i16>* %B
+	%tmp3 = call <4 x i16> @llvm.arm.neon.vhsubs.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
+	ret <4 x i16> %tmp3
+}
+
+define <2 x i32> @vhsubs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+	%tmp1 = load <2 x i32>* %A
+	%tmp2 = load <2 x i32>* %B
+	%tmp3 = call <2 x i32> @llvm.arm.neon.vhsubs.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
+	ret <2 x i32> %tmp3
+}
+
+define <8 x i8> @vhsubu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+	%tmp1 = load <8 x i8>* %A
+	%tmp2 = load <8 x i8>* %B
+	%tmp3 = call <8 x i8> @llvm.arm.neon.vhsubu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
+	ret <8 x i8> %tmp3
+}
+
+define <4 x i16> @vhsubu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+	%tmp1 = load <4 x i16>* %A
+	%tmp2 = load <4 x i16>* %B
+	%tmp3 = call <4 x i16> @llvm.arm.neon.vhsubu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
+	ret <4 x i16> %tmp3
+}
+
+define <2 x i32> @vhsubu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+	%tmp1 = load <2 x i32>* %A
+	%tmp2 = load <2 x i32>* %B
+	%tmp3 = call <2 x i32> @llvm.arm.neon.vhsubu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
+	ret <2 x i32> %tmp3
+}
+
+define <16 x i8> @vhsubQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+	%tmp1 = load <16 x i8>* %A
+	%tmp2 = load <16 x i8>* %B
+	%tmp3 = call <16 x i8> @llvm.arm.neon.vhsubs.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
+	ret <16 x i8> %tmp3
+}
+
+define <8 x i16> @vhsubQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+	%tmp1 = load <8 x i16>* %A
+	%tmp2 = load <8 x i16>* %B
+	%tmp3 = call <8 x i16> @llvm.arm.neon.vhsubs.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
+	ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vhsubQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+	%tmp1 = load <4 x i32>* %A
+	%tmp2 = load <4 x i32>* %B
+	%tmp3 = call <4 x i32> @llvm.arm.neon.vhsubs.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
+	ret <4 x i32> %tmp3
+}
+
+define <16 x i8> @vhsubQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+	%tmp1 = load <16 x i8>* %A
+	%tmp2 = load <16 x i8>* %B
+	%tmp3 = call <16 x i8> @llvm.arm.neon.vhsubu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
+	ret <16 x i8> %tmp3
+}
+
+define <8 x i16> @vhsubQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+	%tmp1 = load <8 x i16>* %A
+	%tmp2 = load <8 x i16>* %B
+	%tmp3 = call <8 x i16> @llvm.arm.neon.vhsubu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
+	ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vhsubQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+	%tmp1 = load <4 x i32>* %A
+	%tmp2 = load <4 x i32>* %B
+	%tmp3 = call <4 x i32> @llvm.arm.neon.vhsubu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
+	ret <4 x i32> %tmp3
+}
+
+declare <8 x i8>  @llvm.arm.neon.vhsubs.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vhsubs.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vhsubs.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <8 x i8>  @llvm.arm.neon.vhsubu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vhsubu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vhsubu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vhsubs.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vhsubs.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vhsubs.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vhsubu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vhsubu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vhsubu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone