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
|
; RUN: opt -S < %s | FileCheck %s
; RUN: llvm-dis < %s.bc | FileCheck %s
define float @fadd_v2(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_v2
; CHECK: %res = call float @llvm.vector.reduce.fadd.v4f32(float %acc, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fadd_v2_fast(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fadd_v2_fast
; CHECK: %res = call fast float @llvm.vector.reduce.fadd.v4f32(float %acc, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fmul_v2(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_v2
; CHECK: %res = call float @llvm.vector.reduce.fmul.v4f32(float %acc, <4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fmul_v2_fast(<4 x float> %in, float %acc) {
; CHECK-LABEL: @fmul_v2_fast
; CHECK: %res = call fast float @llvm.vector.reduce.fmul.v4f32(float %acc, <4 x float> %in)
%res = call fast float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float %acc, <4 x float> %in)
ret float %res
}
define float @fmin(<4 x float> %in) {
; CHECK-LABEL: @fmin
; CHECK: %res = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float> %in)
ret float %res
}
define float @fmax(<4 x float> %in) {
; CHECK-LABEL: @fmax
; CHECK: %res = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> %in)
%res = call float @llvm.experimental.vector.reduce.fmax.v4f32(<4 x float> %in)
ret float %res
}
define i32 @and(<4 x i32> %in) {
; CHECK-LABEL: @and
; CHECK: %res = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.and.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @or(<4 x i32> %in) {
; CHECK-LABEL: @or
; CHECK: %res = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.or.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @xor(<4 x i32> %in) {
; CHECK-LABEL: @xor
; CHECK: %res = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.xor.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @smin(<4 x i32> %in) {
; CHECK-LABEL: @smin
; CHECK: %res = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.smin.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @smax(<4 x i32> %in) {
; CHECK-LABEL: @smax
; CHECK: %res = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.smax.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @umin(<4 x i32> %in) {
; CHECK-LABEL: @umin
; CHECK: %res = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.umin.v4i32(<4 x i32> %in)
ret i32 %res
}
define i32 @umax(<4 x i32> %in) {
; CHECK-LABEL: @umax
; CHECK: %res = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %in)
%res = call i32 @llvm.experimental.vector.reduce.umax.v4i32(<4 x i32> %in)
ret i32 %res
}
declare float @llvm.experimental.vector.reduce.v2.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v4f32(float, <4 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float>)
; CHECK: declare float @llvm.vector.reduce.fmin.v4f32(<4 x float>)
declare float @llvm.experimental.vector.reduce.fmax.v4f32(<4 x float>)
; CHECK: declare float @llvm.vector.reduce.fmax.v4f32(<4 x float>)
declare i32 @llvm.experimental.vector.reduce.and.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.or.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.or.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.xor.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.xor.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.smin.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.smax.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.umin.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32>)
declare i32 @llvm.experimental.vector.reduce.umax.v4i32(<4 x i32>)
; CHECK: declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32>)
|
