Merge a bunch of NEON tests into larger files so they run faster.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83667 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/ARM/vmla.ll b/test/CodeGen/ARM/vmla.ll
index 58ac6b0..8405218 100644
--- a/test/CodeGen/ARM/vmla.ll
+++ b/test/CodeGen/ARM/vmla.ll
@@ -87,3 +87,107 @@
%tmp5 = add <4 x float> %tmp1, %tmp4
ret <4 x float> %tmp5
}
+
+define <8 x i16> @vmlals8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlals8:
+;CHECK: vmlal.s8
+ %tmp1 = load <8 x i16>* %A
+ %tmp2 = load <8 x i8>* %B
+ %tmp3 = load <8 x i8>* %C
+ %tmp4 = call <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
+ ret <8 x i16> %tmp4
+}
+
+define <4 x i32> @vmlals16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlals16:
+;CHECK: vmlal.s16
+ %tmp1 = load <4 x i32>* %A
+ %tmp2 = load <4 x i16>* %B
+ %tmp3 = load <4 x i16>* %C
+ %tmp4 = call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
+ ret <4 x i32> %tmp4
+}
+
+define <2 x i64> @vmlals32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlals32:
+;CHECK: vmlal.s32
+ %tmp1 = load <2 x i64>* %A
+ %tmp2 = load <2 x i32>* %B
+ %tmp3 = load <2 x i32>* %C
+ %tmp4 = call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
+ ret <2 x i64> %tmp4
+}
+
+define <8 x i16> @vmlalu8(<8 x i16>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
+;CHECK: vmlalu8:
+;CHECK: vmlal.u8
+ %tmp1 = load <8 x i16>* %A
+ %tmp2 = load <8 x i8>* %B
+ %tmp3 = load <8 x i8>* %C
+ %tmp4 = call <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
+ ret <8 x i16> %tmp4
+}
+
+define <4 x i32> @vmlalu16(<4 x i32>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
+;CHECK: vmlalu16:
+;CHECK: vmlal.u16
+ %tmp1 = load <4 x i32>* %A
+ %tmp2 = load <4 x i16>* %B
+ %tmp3 = load <4 x i16>* %C
+ %tmp4 = call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
+ ret <4 x i32> %tmp4
+}
+
+define <2 x i64> @vmlalu32(<2 x i64>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
+;CHECK: vmlalu32:
+;CHECK: vmlal.u32
+ %tmp1 = load <2 x i64>* %A
+ %tmp2 = load <2 x i32>* %B
+ %tmp3 = load <2 x i32>* %C
+ %tmp4 = call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
+ ret <2 x i64> %tmp4
+}
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmlal_lanes16(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %arg2_int16x4_t) nounwind readnone {
+entry:
+; CHECK: test_vmlal_lanes16
+; CHECK: vmlal.s16 q0, d2, d3[1]
+ %0 = shufflevector <4 x i16> %arg2_int16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
+ %1 = tail call <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32> %arg0_int32x4_t, <4 x i16> %arg1_int16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
+ ret <4 x i32> %1
+}
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmlal_lanes32(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %arg2_int32x2_t) nounwind readnone {
+entry:
+; CHECK: test_vmlal_lanes32
+; CHECK: vmlal.s32 q0, d2, d3[1]
+ %0 = shufflevector <2 x i32> %arg2_int32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
+ %1 = tail call <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64> %arg0_int64x2_t, <2 x i32> %arg1_int32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
+ ret <2 x i64> %1
+}
+
+define arm_aapcs_vfpcc <4 x i32> @test_vmlal_laneu16(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %arg2_uint16x4_t) nounwind readnone {
+entry:
+; CHECK: test_vmlal_laneu16
+; CHECK: vmlal.u16 q0, d2, d3[1]
+ %0 = shufflevector <4 x i16> %arg2_uint16x4_t, <4 x i16> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x i16>> [#uses=1]
+ %1 = tail call <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32> %arg0_uint32x4_t, <4 x i16> %arg1_uint16x4_t, <4 x i16> %0) ; <<4 x i32>> [#uses=1]
+ ret <4 x i32> %1
+}
+
+define arm_aapcs_vfpcc <2 x i64> @test_vmlal_laneu32(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %arg2_uint32x2_t) nounwind readnone {
+entry:
+; CHECK: test_vmlal_laneu32
+; CHECK: vmlal.u32 q0, d2, d3[1]
+ %0 = shufflevector <2 x i32> %arg2_uint32x2_t, <2 x i32> undef, <2 x i32> <i32 1, i32 1> ; <<2 x i32>> [#uses=1]
+ %1 = tail call <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64> %arg0_uint64x2_t, <2 x i32> %arg1_uint32x2_t, <2 x i32> %0) ; <<2 x i64>> [#uses=1]
+ ret <2 x i64> %1
+}
+
+declare <8 x i16> @llvm.arm.neon.vmlals.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vmlals.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i64> @llvm.arm.neon.vmlals.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone
+
+declare <8 x i16> @llvm.arm.neon.vmlalu.v8i16(<8 x i16>, <8 x i8>, <8 x i8>) nounwind readnone
+declare <4 x i32> @llvm.arm.neon.vmlalu.v4i32(<4 x i32>, <4 x i16>, <4 x i16>) nounwind readnone
+declare <2 x i64> @llvm.arm.neon.vmlalu.v2i64(<2 x i64>, <2 x i32>, <2 x i32>) nounwind readnone