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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK-SSE,CHECK-SSE2
; RUN: llc < %s -mtriple=i686-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK-SSE,CHECK-SSSE3
; RUN: llc < %s -mtriple=i686-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK-AVX
define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK-SSE-LABEL: test1:
; CHECK-SSE: # %bb.0:
; CHECK-SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,2,3,0]
; CHECK-SSE-NEXT: retl
;
; CHECK-AVX-LABEL: test1:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,2,3,0]
; CHECK-AVX-NEXT: retl
%C = shufflevector <4 x i32> %A, <4 x i32> undef, <4 x i32> < i32 1, i32 2, i32 3, i32 0 >
ret <4 x i32> %C
}
define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK-SSE2-LABEL: test2:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; CHECK-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,2],xmm1[2,0]
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test2:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3]
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test2:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3]
; CHECK-AVX-NEXT: retl
%C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 1, i32 2, i32 3, i32 4 >
ret <4 x i32> %C
}
define <4 x i32> @test3(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK-SSE2-LABEL: test3:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,2],xmm1[2,0]
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test3:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3]
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test3:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3]
; CHECK-AVX-NEXT: retl
%C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 1, i32 2, i32 undef, i32 4 >
ret <4 x i32> %C
}
define <4 x i32> @test4(<4 x i32> %A, <4 x i32> %B) nounwind {
; CHECK-SSE2-LABEL: test4:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,3],xmm0[0,1]
; CHECK-SSE2-NEXT: movaps %xmm1, %xmm0
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test4:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7]
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test4:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7]
; CHECK-AVX-NEXT: retl
%C = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> < i32 6, i32 7, i32 undef, i32 1 >
ret <4 x i32> %C
}
define <4 x float> @test5(<4 x float> %A, <4 x float> %B) nounwind {
; CHECK-SSE-LABEL: test5:
; CHECK-SSE: # %bb.0:
; CHECK-SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,3],xmm0[0,1]
; CHECK-SSE-NEXT: movaps %xmm1, %xmm0
; CHECK-SSE-NEXT: retl
;
; CHECK-AVX-LABEL: test5:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vshufpd {{.*#+}} xmm0 = xmm1[1],xmm0[0]
; CHECK-AVX-NEXT: retl
%C = shufflevector <4 x float> %A, <4 x float> %B, <4 x i32> < i32 6, i32 7, i32 undef, i32 1 >
ret <4 x float> %C
}
define <8 x i16> @test6(<8 x i16> %A, <8 x i16> %B) nounwind {
; CHECK-SSE2-LABEL: test6:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero
; CHECK-SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5]
; CHECK-SSE2-NEXT: por %xmm1, %xmm0
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test6:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test6:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
; CHECK-AVX-NEXT: retl
%C = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 3, i32 4, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10 >
ret <8 x i16> %C
}
define <8 x i16> @test7(<8 x i16> %A, <8 x i16> %B) nounwind {
; CHECK-SSE2-LABEL: test7:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7,8,9]
; CHECK-SSE2-NEXT: por %xmm1, %xmm0
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test7:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test7:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
; CHECK-AVX-NEXT: retl
%C = shufflevector <8 x i16> %A, <8 x i16> %B, <8 x i32> < i32 undef, i32 6, i32 undef, i32 8, i32 9, i32 10, i32 11, i32 12 >
ret <8 x i16> %C
}
define <16 x i8> @test8(<16 x i8> %A, <16 x i8> %B) nounwind {
; CHECK-SSE2-LABEL: test8:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero
; CHECK-SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4]
; CHECK-SSE2-NEXT: por %xmm1, %xmm0
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test8:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm1 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test8:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; CHECK-AVX-NEXT: retl
%C = shufflevector <16 x i8> %A, <16 x i8> %B, <16 x i32> < i32 5, i32 6, i32 7, i32 undef, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20 >
ret <16 x i8> %C
}
; Check that we don't do unary (circular on single operand) palignr incorrectly.
; (It is possible, but before this testcase was committed, it was being done
; incorrectly. In particular, one of the operands of the palignr node
; was an UNDEF.)
define <8 x i16> @test9(<8 x i16> %A, <8 x i16> %B) nounwind {
; CHECK-SSE2-LABEL: test9:
; CHECK-SSE2: # %bb.0:
; CHECK-SSE2-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSE2-NEXT: psrldq {{.*#+}} xmm0 = xmm0[2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero,zero
; CHECK-SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; CHECK-SSE2-NEXT: por %xmm1, %xmm0
; CHECK-SSE2-NEXT: retl
;
; CHECK-SSSE3-LABEL: test9:
; CHECK-SSSE3: # %bb.0:
; CHECK-SSSE3-NEXT: movdqa %xmm1, %xmm0
; CHECK-SSSE3-NEXT: palignr {{.*#+}} xmm0 = xmm1[2,3,4,5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1]
; CHECK-SSSE3-NEXT: retl
;
; CHECK-AVX-LABEL: test9:
; CHECK-AVX: # %bb.0:
; CHECK-AVX-NEXT: vpalignr {{.*#+}} xmm0 = xmm1[2,3,4,5,6,7,8,9,10,11,12,13,14,15,0,1]
; CHECK-AVX-NEXT: retl
%C = shufflevector <8 x i16> %B, <8 x i16> %A, <8 x i32> < i32 undef, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 0 >
ret <8 x i16> %C
}
|
