1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O0 -mtriple=mipsel-linux-gnu -global-isel -mcpu=mips32r5 -mattr=+msa,+fp64,+nan2008 -verify-machineinstrs %s -o -| FileCheck %s -check-prefixes=P5600
declare <16 x i8> @llvm.mips.addv.b(<16 x i8>, <16 x i8>)
define void @add_v16i8_builtin(<16 x i8>* %a, <16 x i8>* %b, <16 x i8>* %c) {
; P5600-LABEL: add_v16i8_builtin:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.b $w0, 0($4)
; P5600-NEXT: ld.b $w1, 0($5)
; P5600-NEXT: addv.b $w0, $w0, $w1
; P5600-NEXT: st.b $w0, 0($6)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <16 x i8>, <16 x i8>* %a, align 16
%1 = load <16 x i8>, <16 x i8>* %b, align 16
%2 = tail call <16 x i8> @llvm.mips.addv.b(<16 x i8> %0, <16 x i8> %1)
store <16 x i8> %2, <16 x i8>* %c, align 16
ret void
}
declare <8 x i16> @llvm.mips.addv.h(<8 x i16>, <8 x i16>)
define void @add_v8i16_builtin(<8 x i16>* %a, <8 x i16>* %b, <8 x i16>* %c) {
; P5600-LABEL: add_v8i16_builtin:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.h $w0, 0($4)
; P5600-NEXT: ld.h $w1, 0($5)
; P5600-NEXT: addv.h $w0, $w0, $w1
; P5600-NEXT: st.h $w0, 0($6)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <8 x i16>, <8 x i16>* %a, align 16
%1 = load <8 x i16>, <8 x i16>* %b, align 16
%2 = tail call <8 x i16> @llvm.mips.addv.h(<8 x i16> %0, <8 x i16> %1)
store <8 x i16> %2, <8 x i16>* %c, align 16
ret void
}
declare <4 x i32> @llvm.mips.addv.w(<4 x i32>, <4 x i32>)
define void @add_v4i32_builtin(<4 x i32>* %a, <4 x i32>* %b, <4 x i32>* %c) {
; P5600-LABEL: add_v4i32_builtin:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.w $w0, 0($4)
; P5600-NEXT: ld.w $w1, 0($5)
; P5600-NEXT: addv.w $w0, $w0, $w1
; P5600-NEXT: st.w $w0, 0($6)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <4 x i32>, <4 x i32>* %a, align 16
%1 = load <4 x i32>, <4 x i32>* %b, align 16
%2 = tail call <4 x i32> @llvm.mips.addv.w(<4 x i32> %0, <4 x i32> %1)
store <4 x i32> %2, <4 x i32>* %c, align 16
ret void
}
declare <2 x i64> @llvm.mips.addv.d(<2 x i64>, <2 x i64>)
define void @add_v2i64_builtin(<2 x i64>* %a, <2 x i64>* %b, <2 x i64>* %c) {
; P5600-LABEL: add_v2i64_builtin:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.d $w0, 0($4)
; P5600-NEXT: ld.d $w1, 0($5)
; P5600-NEXT: addv.d $w0, $w0, $w1
; P5600-NEXT: st.d $w0, 0($6)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <2 x i64>, <2 x i64>* %a, align 16
%1 = load <2 x i64>, <2 x i64>* %b, align 16
%2 = tail call <2 x i64> @llvm.mips.addv.d(<2 x i64> %0, <2 x i64> %1)
store <2 x i64> %2, <2 x i64>* %c, align 16
ret void
}
declare <16 x i8> @llvm.mips.addvi.b(<16 x i8>, i32 immarg)
define void @add_v16i8_builtin_imm(<16 x i8>* %a, <16 x i8>* %c) {
; P5600-LABEL: add_v16i8_builtin_imm:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.b $w0, 0($4)
; P5600-NEXT: addvi.b $w0, $w0, 3
; P5600-NEXT: st.b $w0, 0($5)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <16 x i8>, <16 x i8>* %a, align 16
%1 = tail call <16 x i8> @llvm.mips.addvi.b(<16 x i8> %0, i32 3)
store <16 x i8> %1, <16 x i8>* %c, align 16
ret void
}
declare <8 x i16> @llvm.mips.addvi.h(<8 x i16>, i32 immarg)
define void @add_v8i16_builtin_imm(<8 x i16>* %a, <8 x i16>* %c) {
; P5600-LABEL: add_v8i16_builtin_imm:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.h $w0, 0($4)
; P5600-NEXT: addvi.h $w0, $w0, 18
; P5600-NEXT: st.h $w0, 0($5)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <8 x i16>, <8 x i16>* %a, align 16
%1 = tail call <8 x i16> @llvm.mips.addvi.h(<8 x i16> %0, i32 18)
store <8 x i16> %1, <8 x i16>* %c, align 16
ret void
}
declare <4 x i32> @llvm.mips.addvi.w(<4 x i32>, i32 immarg)
define void @add_v4i32_builtin_imm(<4 x i32>* %a, <4 x i32>* %c) {
; P5600-LABEL: add_v4i32_builtin_imm:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.w $w0, 0($4)
; P5600-NEXT: addvi.w $w0, $w0, 25
; P5600-NEXT: st.w $w0, 0($5)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <4 x i32>, <4 x i32>* %a, align 16
%1 = tail call <4 x i32> @llvm.mips.addvi.w(<4 x i32> %0, i32 25)
store <4 x i32> %1, <4 x i32>* %c, align 16
ret void
}
declare <2 x i64> @llvm.mips.addvi.d(<2 x i64>, i32 immarg)
define void @add_v2i64_builtin_imm(<2 x i64>* %a, <2 x i64>* %c) {
; P5600-LABEL: add_v2i64_builtin_imm:
; P5600: # %bb.0: # %entry
; P5600-NEXT: ld.d $w0, 0($4)
; P5600-NEXT: addvi.d $w0, $w0, 31
; P5600-NEXT: st.d $w0, 0($5)
; P5600-NEXT: jr $ra
; P5600-NEXT: nop
entry:
%0 = load <2 x i64>, <2 x i64>* %a, align 16
%1 = tail call <2 x i64> @llvm.mips.addvi.d(<2 x i64> %0, i32 31)
store <2 x i64> %1, <2 x i64>* %c, align 16
ret void
}
|