Merge a bunch of NEON tests into larger files so they run faster.

[oota-llvm.git] / test / CodeGen / ARM / vhadd.ll

diff --git a/test/CodeGen/ARM/vhadd.ll b/test/CodeGen/ARM/vhadd.ll
index d7670971d6caa6fd15468b6166c63a38c4fa8cde..379e062838f61b341421a5e4cd8a2074b220ba30 100644 (file)
--- a/test/CodeGen/ARM/vhadd.ll
+++ b/test/CodeGen/ARM/vhadd.ll
@@ -123,3 +123,127 @@ declare <4 x i32> @llvm.arm.neon.vhadds.v4i32(<4 x i32>, <4 x i32>) nounwind rea
 declare <16 x i8> @llvm.arm.neon.vhaddu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
 declare <8 x i16> @llvm.arm.neon.vhaddu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
 declare <4 x i32> @llvm.arm.neon.vhaddu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
+
+define <8 x i8> @vrhadds8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vrhadds8:
+;CHECK: vrhadd.s8
+       %tmp1 = load <8 x i8>* %A
+       %tmp2 = load <8 x i8>* %B
+       %tmp3 = call <8 x i8> @llvm.arm.neon.vrhadds.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
+       ret <8 x i8> %tmp3
+}
+
+define <4 x i16> @vrhadds16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vrhadds16:
+;CHECK: vrhadd.s16
+       %tmp1 = load <4 x i16>* %A
+       %tmp2 = load <4 x i16>* %B
+       %tmp3 = call <4 x i16> @llvm.arm.neon.vrhadds.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
+       ret <4 x i16> %tmp3
+}
+
+define <2 x i32> @vrhadds32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vrhadds32:
+;CHECK: vrhadd.s32
+       %tmp1 = load <2 x i32>* %A
+       %tmp2 = load <2 x i32>* %B
+       %tmp3 = call <2 x i32> @llvm.arm.neon.vrhadds.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
+       ret <2 x i32> %tmp3
+}
+
+define <8 x i8> @vrhaddu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
+;CHECK: vrhaddu8:
+;CHECK: vrhadd.u8
+       %tmp1 = load <8 x i8>* %A
+       %tmp2 = load <8 x i8>* %B
+       %tmp3 = call <8 x i8> @llvm.arm.neon.vrhaddu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
+       ret <8 x i8> %tmp3
+}
+
+define <4 x i16> @vrhaddu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
+;CHECK: vrhaddu16:
+;CHECK: vrhadd.u16
+       %tmp1 = load <4 x i16>* %A
+       %tmp2 = load <4 x i16>* %B
+       %tmp3 = call <4 x i16> @llvm.arm.neon.vrhaddu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
+       ret <4 x i16> %tmp3
+}
+
+define <2 x i32> @vrhaddu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
+;CHECK: vrhaddu32:
+;CHECK: vrhadd.u32
+       %tmp1 = load <2 x i32>* %A
+       %tmp2 = load <2 x i32>* %B
+       %tmp3 = call <2 x i32> @llvm.arm.neon.vrhaddu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
+       ret <2 x i32> %tmp3
+}
+
+define <16 x i8> @vrhaddQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vrhaddQs8:
+;CHECK: vrhadd.s8
+       %tmp1 = load <16 x i8>* %A
+       %tmp2 = load <16 x i8>* %B
+       %tmp3 = call <16 x i8> @llvm.arm.neon.vrhadds.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
+       ret <16 x i8> %tmp3
+}
+
+define <8 x i16> @vrhaddQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vrhaddQs16:
+;CHECK: vrhadd.s16
+       %tmp1 = load <8 x i16>* %A
+       %tmp2 = load <8 x i16>* %B
+       %tmp3 = call <8 x i16> @llvm.arm.neon.vrhadds.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
+       ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vrhaddQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vrhaddQs32:
+;CHECK: vrhadd.s32
+       %tmp1 = load <4 x i32>* %A
+       %tmp2 = load <4 x i32>* %B
+       %tmp3 = call <4 x i32> @llvm.arm.neon.vrhadds.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
+       ret <4 x i32> %tmp3
+}
+
+define <16 x i8> @vrhaddQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
+;CHECK: vrhaddQu8:
+;CHECK: vrhadd.u8
+       %tmp1 = load <16 x i8>* %A
+       %tmp2 = load <16 x i8>* %B
+       %tmp3 = call <16 x i8> @llvm.arm.neon.vrhaddu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
+       ret <16 x i8> %tmp3
+}
+
+define <8 x i16> @vrhaddQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
+;CHECK: vrhaddQu16:
+;CHECK: vrhadd.u16
+       %tmp1 = load <8 x i16>* %A
+       %tmp2 = load <8 x i16>* %B
+       %tmp3 = call <8 x i16> @llvm.arm.neon.vrhaddu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
+       ret <8 x i16> %tmp3
+}
+
+define <4 x i32> @vrhaddQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
+;CHECK: vrhaddQu32:
+;CHECK: vrhadd.u32
+       %tmp1 = load <4 x i32>* %A
+       %tmp2 = load <4 x i32>* %B
+       %tmp3 = call <4 x i32> @llvm.arm.neon.vrhaddu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
+       ret <4 x i32> %tmp3
+}
+
+declare <8 x i8>  @llvm.arm.neon.vrhadds.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vrhadds.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vrhadds.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <8 x i8>  @llvm.arm.neon.vrhaddu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i16> @llvm.arm.neon.vrhaddu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i32> @llvm.arm.neon.vrhaddu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vrhadds.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vrhadds.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vrhadds.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
+
+declare <16 x i8> @llvm.arm.neon.vrhaddu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
+declare <8 x i16> @llvm.arm.neon.vrhaddu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vrhaddu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone