1 ; RUN: llvm-as < %s | llc -march=arm -mattr=+neon > %t
2 ; RUN: grep {vaba\\.s8} %t | count 2
3 ; RUN: grep {vaba\\.s16} %t | count 2
4 ; RUN: grep {vaba\\.s32} %t | count 2
5 ; RUN: grep {vaba\\.u8} %t | count 2
6 ; RUN: grep {vaba\\.u16} %t | count 2
7 ; RUN: grep {vaba\\.u32} %t | count 2
9 define <8 x i8> @vabas8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
10 %tmp1 = load <8 x i8>* %A
11 %tmp2 = load <8 x i8>* %B
12 %tmp3 = load <8 x i8>* %C
13 %tmp4 = call <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
17 define <4 x i16> @vabas16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
18 %tmp1 = load <4 x i16>* %A
19 %tmp2 = load <4 x i16>* %B
20 %tmp3 = load <4 x i16>* %C
21 %tmp4 = call <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
25 define <2 x i32> @vabas32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
26 %tmp1 = load <2 x i32>* %A
27 %tmp2 = load <2 x i32>* %B
28 %tmp3 = load <2 x i32>* %C
29 %tmp4 = call <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
33 define <8 x i8> @vabau8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
34 %tmp1 = load <8 x i8>* %A
35 %tmp2 = load <8 x i8>* %B
36 %tmp3 = load <8 x i8>* %C
37 %tmp4 = call <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
41 define <4 x i16> @vabau16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
42 %tmp1 = load <4 x i16>* %A
43 %tmp2 = load <4 x i16>* %B
44 %tmp3 = load <4 x i16>* %C
45 %tmp4 = call <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
49 define <2 x i32> @vabau32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
50 %tmp1 = load <2 x i32>* %A
51 %tmp2 = load <2 x i32>* %B
52 %tmp3 = load <2 x i32>* %C
53 %tmp4 = call <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
57 define <16 x i8> @vabaQs8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
58 %tmp1 = load <16 x i8>* %A
59 %tmp2 = load <16 x i8>* %B
60 %tmp3 = load <16 x i8>* %C
61 %tmp4 = call <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3)
65 define <8 x i16> @vabaQs16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
66 %tmp1 = load <8 x i16>* %A
67 %tmp2 = load <8 x i16>* %B
68 %tmp3 = load <8 x i16>* %C
69 %tmp4 = call <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3)
73 define <4 x i32> @vabaQs32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
74 %tmp1 = load <4 x i32>* %A
75 %tmp2 = load <4 x i32>* %B
76 %tmp3 = load <4 x i32>* %C
77 %tmp4 = call <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3)
81 define <16 x i8> @vabaQu8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
82 %tmp1 = load <16 x i8>* %A
83 %tmp2 = load <16 x i8>* %B
84 %tmp3 = load <16 x i8>* %C
85 %tmp4 = call <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3)
89 define <8 x i16> @vabaQu16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
90 %tmp1 = load <8 x i16>* %A
91 %tmp2 = load <8 x i16>* %B
92 %tmp3 = load <8 x i16>* %C
93 %tmp4 = call <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3)
97 define <4 x i32> @vabaQu32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
98 %tmp1 = load <4 x i32>* %A
99 %tmp2 = load <4 x i32>* %B
100 %tmp3 = load <4 x i32>* %C
101 %tmp4 = call <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3)
105 declare <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone
106 declare <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone
107 declare <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone
109 declare <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone
110 declare <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone
111 declare <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone
113 declare <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
114 declare <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone
115 declare <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone
117 declare <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
118 declare <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone
119 declare <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone