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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
|
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @test_vrev64D8(<8 x i8>* %A) nounwind {
;CHECK: test_vrev64D8:
;CHECK: vrev64.8
%tmp1 = load <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i8> %tmp2
}
define <4 x i16> @test_vrev64D16(<4 x i16>* %A) nounwind {
;CHECK: test_vrev64D16:
;CHECK: vrev64.16
%tmp1 = load <4 x i16>* %A
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
ret <4 x i16> %tmp2
}
define <2 x i32> @test_vrev64D32(<2 x i32>* %A) nounwind {
;CHECK: test_vrev64D32:
;CHECK: vrev64.32
%tmp1 = load <2 x i32>* %A
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <2 x i32> <i32 1, i32 0>
ret <2 x i32> %tmp2
}
define <2 x float> @test_vrev64Df(<2 x float>* %A) nounwind {
;CHECK: test_vrev64Df:
;CHECK: vrev64.32
%tmp1 = load <2 x float>* %A
%tmp2 = shufflevector <2 x float> %tmp1, <2 x float> undef, <2 x i32> <i32 1, i32 0>
ret <2 x float> %tmp2
}
define <16 x i8> @test_vrev64Q8(<16 x i8>* %A) nounwind {
;CHECK: test_vrev64Q8:
;CHECK: vrev64.8
%tmp1 = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8>
ret <16 x i8> %tmp2
}
define <8 x i16> @test_vrev64Q16(<8 x i16>* %A) nounwind {
;CHECK: test_vrev64Q16:
;CHECK: vrev64.16
%tmp1 = load <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x i16> %tmp2
}
define <4 x i32> @test_vrev64Q32(<4 x i32>* %A) nounwind {
;CHECK: test_vrev64Q32:
;CHECK: vrev64.32
%tmp1 = load <4 x i32>* %A
%tmp2 = shufflevector <4 x i32> %tmp1, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x i32> %tmp2
}
define <4 x float> @test_vrev64Qf(<4 x float>* %A) nounwind {
;CHECK: test_vrev64Qf:
;CHECK: vrev64.32
%tmp1 = load <4 x float>* %A
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x float> %tmp2
}
define <8 x i8> @test_vrev32D8(<8 x i8>* %A) nounwind {
;CHECK: test_vrev32D8:
;CHECK: vrev32.8
%tmp1 = load <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
ret <8 x i8> %tmp2
}
define <4 x i16> @test_vrev32D16(<4 x i16>* %A) nounwind {
;CHECK: test_vrev32D16:
;CHECK: vrev32.16
%tmp1 = load <4 x i16>* %A
%tmp2 = shufflevector <4 x i16> %tmp1, <4 x i16> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x i16> %tmp2
}
define <16 x i8> @test_vrev32Q8(<16 x i8>* %A) nounwind {
;CHECK: test_vrev32Q8:
;CHECK: vrev32.8
%tmp1 = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
ret <16 x i8> %tmp2
}
define <8 x i16> @test_vrev32Q16(<8 x i16>* %A) nounwind {
;CHECK: test_vrev32Q16:
;CHECK: vrev32.16
%tmp1 = load <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x i16> %tmp2
}
define <8 x i8> @test_vrev16D8(<8 x i8>* %A) nounwind {
;CHECK: test_vrev16D8:
;CHECK: vrev16.8
%tmp1 = load <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
ret <8 x i8> %tmp2
}
define <16 x i8> @test_vrev16Q8(<16 x i8>* %A) nounwind {
;CHECK: test_vrev16Q8:
;CHECK: vrev16.8
%tmp1 = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp1, <16 x i8> undef, <16 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6, i32 9, i32 8, i32 11, i32 10, i32 13, i32 12, i32 15, i32 14>
ret <16 x i8> %tmp2
}
; Undef shuffle indices should not prevent matching to VREV:
define <8 x i8> @test_vrev64D8_undef(<8 x i8>* %A) nounwind {
;CHECK: test_vrev64D8_undef:
;CHECK: vrev64.8
%tmp1 = load <8 x i8>* %A
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <8 x i32> <i32 7, i32 undef, i32 undef, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i8> %tmp2
}
define <8 x i16> @test_vrev32Q16_undef(<8 x i16>* %A) nounwind {
;CHECK: test_vrev32Q16_undef:
;CHECK: vrev32.16
%tmp1 = load <8 x i16>* %A
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <8 x i32> <i32 undef, i32 0, i32 undef, i32 2, i32 5, i32 4, i32 7, i32 undef>
ret <8 x i16> %tmp2
}
; A vcombine feeding a VREV should not obscure things. Radar 8597007.
define void @test_with_vcombine(<4 x float>* %v) nounwind {
;CHECK: test_with_vcombine:
;CHECK-NOT: vext
;CHECK: vrev64.32
%tmp1 = load <4 x float>* %v, align 16
%tmp2 = bitcast <4 x float> %tmp1 to <2 x double>
%tmp3 = extractelement <2 x double> %tmp2, i32 0
%tmp4 = bitcast double %tmp3 to <2 x float>
%tmp5 = extractelement <2 x double> %tmp2, i32 1
%tmp6 = bitcast double %tmp5 to <2 x float>
%tmp7 = fadd <2 x float> %tmp6, %tmp6
%tmp8 = shufflevector <2 x float> %tmp4, <2 x float> %tmp7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
store <4 x float> %tmp8, <4 x float>* %v, align 16
ret void
}
; vrev <4 x i16> should use VREV32 and not VREV64
define void @test_vrev64(<4 x i16>* nocapture %source, <2 x i16>* nocapture %dst) nounwind ssp {
; CHECK: test_vrev64:
; CHECK: vext.16
; CHECK: vrev32.16
entry:
%0 = bitcast <4 x i16>* %source to <8 x i16>*
%tmp2 = load <8 x i16>* %0, align 4
%tmp3 = extractelement <8 x i16> %tmp2, i32 6
%tmp5 = insertelement <2 x i16> undef, i16 %tmp3, i32 0
%tmp9 = extractelement <8 x i16> %tmp2, i32 5
%tmp11 = insertelement <2 x i16> %tmp5, i16 %tmp9, i32 1
store <2 x i16> %tmp11, <2 x i16>* %dst, align 4
ret void
}
|
