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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse2 < %s | FileCheck %s --check-prefix=SSE2
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s --check-prefix=AVX
define <8 x i16> @test1(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: test1:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: psllw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test1:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX-NEXT: vpsllw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
%shl = shl <8 x i16> %A, %vecinit14
ret <8 x i16> %shl
}
define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) {
; SSE2-LABEL: test2:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: xorps %xmm2, %xmm2
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
; SSE2-NEXT: pslld %xmm2, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test2:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
; AVX-NEXT: vpslld %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
%shl = shl <4 x i32> %A, %vecinit6
ret <4 x i32> %shl
}
define <2 x i64> @test3(<2 x i64> %A, <2 x i64> %B) {
; SSE2-LABEL: test3:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: psllq %xmm1, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test3:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpsllq %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit2 = shufflevector <2 x i64> %B, <2 x i64> undef, <2 x i32> zeroinitializer
%shl = shl <2 x i64> %A, %vecinit2
ret <2 x i64> %shl
}
define <8 x i16> @test4(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: test4:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: psrlw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test4:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX-NEXT: vpsrlw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
%shr = lshr <8 x i16> %A, %vecinit14
ret <8 x i16> %shr
}
define <4 x i32> @test5(<4 x i32> %A, <4 x i32> %B) {
; SSE2-LABEL: test5:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: xorps %xmm2, %xmm2
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
; SSE2-NEXT: psrld %xmm2, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test5:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
; AVX-NEXT: vpsrld %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
%shr = lshr <4 x i32> %A, %vecinit6
ret <4 x i32> %shr
}
define <2 x i64> @test6(<2 x i64> %A, <2 x i64> %B) {
; SSE2-LABEL: test6:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: psrlq %xmm1, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test6:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpsrlq %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit2 = shufflevector <2 x i64> %B, <2 x i64> undef, <2 x i32> zeroinitializer
%shr = lshr <2 x i64> %A, %vecinit2
ret <2 x i64> %shr
}
define <8 x i16> @test7(<8 x i16> %A, <8 x i16> %B) {
; SSE2-LABEL: test7:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1]
; SSE2-NEXT: psrldq {{.*#+}} xmm1 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSE2-NEXT: psraw %xmm1, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test7:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
; AVX-NEXT: vpsraw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit14 = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
%shr = ashr <8 x i16> %A, %vecinit14
ret <8 x i16> %shr
}
define <4 x i32> @test8(<4 x i32> %A, <4 x i32> %B) {
; SSE2-LABEL: test8:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: xorps %xmm2, %xmm2
; SSE2-NEXT: movss {{.*#+}} xmm2 = xmm1[0],xmm2[1,2,3]
; SSE2-NEXT: psrad %xmm2, %xmm0
; SSE2-NEXT: retq
;
; AVX-LABEL: test8:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
; AVX-NEXT: vpsrad %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%vecinit6 = shufflevector <4 x i32> %B, <4 x i32> undef, <4 x i32> zeroinitializer
%shr = ashr <4 x i32> %A, %vecinit6
ret <4 x i32> %shr
}
|