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
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
;CHECK-LABEL: vsel_float:
;CHECK: blendps
;CHECK: ret
define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x float> %v1, <4 x float> %v2
ret <4 x float> %vsel
}
;CHECK-LABEL: vsel_4xi8:
;CHECK: blendps
;CHECK: ret
define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) {
%vsel = select <4 x i1> <i1 true, i1 true, i1 false, i1 true>, <4 x i8> %v1, <4 x i8> %v2
ret <4 x i8> %vsel
}
;CHECK-LABEL: vsel_4xi16:
;CHECK: blendps
;CHECK: ret
define <4 x i16> @vsel_4xi16(<4 x i16> %v1, <4 x i16> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x i16> %v1, <4 x i16> %v2
ret <4 x i16> %vsel
}
;CHECK-LABEL: vsel_i32:
;CHECK: blendps
;CHECK: ret
define <4 x i32> @vsel_i32(<4 x i32> %v1, <4 x i32> %v2) {
%vsel = select <4 x i1> <i1 true, i1 true, i1 false, i1 true>, <4 x i32> %v1, <4 x i32> %v2
ret <4 x i32> %vsel
}
;CHECK-LABEL: vsel_double:
;CHECK: movsd
;CHECK: ret
define <4 x double> @vsel_double(<4 x double> %v1, <4 x double> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> %v1, <4 x double> %v2
ret <4 x double> %vsel
}
;CHECK-LABEL: vsel_i64:
;CHECK: movsd
;CHECK: ret
define <4 x i64> @vsel_i64(<4 x i64> %v1, <4 x i64> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> %v1, <4 x i64> %v2
ret <4 x i64> %vsel
}
;CHECK-LABEL: vsel_i8:
;CHECK: pblendvb
;CHECK: ret
define <16 x i8> @vsel_i8(<16 x i8> %v1, <16 x i8> %v2) {
%vsel = select <16 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <16 x i8> %v1, <16 x i8> %v2
ret <16 x i8> %vsel
}
;; TEST blend + compares
; CHECK: A
define <2 x double> @A(<2 x double> %x, <2 x double> %y) {
; CHECK: cmplepd
; CHECK: blendvpd
%max_is_x = fcmp oge <2 x double> %x, %y
%max = select <2 x i1> %max_is_x, <2 x double> %x, <2 x double> %y
ret <2 x double> %max
}
; CHECK: B
define <2 x double> @B(<2 x double> %x, <2 x double> %y) {
; CHECK: cmpnlepd
; CHECK: blendvpd
%min_is_x = fcmp ult <2 x double> %x, %y
%min = select <2 x i1> %min_is_x, <2 x double> %x, <2 x double> %y
ret <2 x double> %min
}
; CHECK: float_crash
define void @float_crash() nounwind {
entry:
%merge205vector_func.i = select <4 x i1> undef, <4 x double> undef, <4 x double> undef
%extract214vector_func.i = extractelement <4 x double> %merge205vector_func.i, i32 0
store double %extract214vector_func.i, double addrspace(1)* undef, align 8
ret void
}
; If we can figure out a blend has a constant mask, we should emit the
; blend instruction with an immediate mask
define <2 x double> @constant_blendvpd(<2 x double> %xy, <2 x double> %ab) {
; In this case, we emit a simple movss
; CHECK-LABEL: constant_blendvpd
; CHECK: movsd
; CHECK: ret
%1 = select <2 x i1> <i1 true, i1 false>, <2 x double> %xy, <2 x double> %ab
ret <2 x double> %1
}
define <4 x float> @constant_blendvps(<4 x float> %xyzw, <4 x float> %abcd) {
; CHECK-LABEL: constant_blendvps
; CHECK-NOT: mov
; CHECK: blendps $7
; CHECK: ret
%1 = select <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x float> %xyzw, <4 x float> %abcd
ret <4 x float> %1
}
define <16 x i8> @constant_pblendvb(<16 x i8> %xyzw, <16 x i8> %abcd) {
; CHECK-LABEL: constant_pblendvb:
; CHECK: movaps
; CHECK: pblendvb
; CHECK: ret
%1 = select <16 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <16 x i8> %xyzw, <16 x i8> %abcd
ret <16 x i8> %1
}
declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>)
declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>)
declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>)
;; 2 tests for shufflevectors that optimize to blend + immediate
; CHECK-LABEL: @blend_shufflevector_4xfloat
; CHECK: blendps $6, %xmm1, %xmm0
; CHECK: ret
define <4 x float> @blend_shufflevector_4xfloat(<4 x float> %a, <4 x float> %b) {
%1 = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 5, i32 6, i32 3>
ret <4 x float> %1
}
; CHECK-LABEL: @blend_shufflevector_8xi16
; CHECK: pblendw $134, %xmm1, %xmm0
; CHECK: ret
define <8 x i16> @blend_shufflevector_8xi16(<8 x i16> %a, <8 x i16> %b) {
%1 = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 3, i32 4, i32 5, i32 6, i32 15>
ret <8 x i16> %1
}
|
