aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/SLPVectorizer/X86/addsub.ll
blob: 8303bc8181efd6a1749f8865d81ddbfc6dbf7935 (plain)
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
; RUN: opt < %s -basicaa -slp-vectorizer -S | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

@b = common global [4 x i32] zeroinitializer, align 16
@c = common global [4 x i32] zeroinitializer, align 16
@d = common global [4 x i32] zeroinitializer, align 16
@e = common global [4 x i32] zeroinitializer, align 16
@a = common global [4 x i32] zeroinitializer, align 16
@fb = common global [4 x float] zeroinitializer, align 16
@fc = common global [4 x float] zeroinitializer, align 16
@fa = common global [4 x float] zeroinitializer, align 16

; CHECK-LABEL: @addsub
; CHECK: %5 = add <4 x i32> %3, %4
; CHECK: %6 = add <4 x i32> %2, %5
; CHECK: %7 = sub <4 x i32> %2, %5
; CHECK: %8 = shufflevector <4 x i32> %6, <4 x i32> %7, <4 x i32> <i32 0, i32 5, i32 2, i32 7>

; Function Attrs: nounwind uwtable
define void @addsub() #0 {
entry:
  %0 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 0), align 4
  %1 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 0), align 4
  %add = add nsw i32 %0, %1
  %2 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 0), align 4
  %3 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 0), align 4
  %add1 = add nsw i32 %2, %3
  %add2 = add nsw i32 %add, %add1
  store i32 %add2, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 0), align 4
  %4 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 1), align 4
  %5 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 1), align 4
  %add3 = add nsw i32 %4, %5
  %6 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 1), align 4
  %7 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 1), align 4
  %add4 = add nsw i32 %6, %7
  %sub = sub nsw i32 %add3, %add4
  store i32 %sub, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 1), align 4
  %8 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 2), align 4
  %9 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 2), align 4
  %add5 = add nsw i32 %8, %9
  %10 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 2), align 4
  %11 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 2), align 4
  %add6 = add nsw i32 %10, %11
  %add7 = add nsw i32 %add5, %add6
  store i32 %add7, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 2), align 4
  %12 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 3), align 4
  %13 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 3), align 4
  %add8 = add nsw i32 %12, %13
  %14 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 3), align 4
  %15 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 3), align 4
  %add9 = add nsw i32 %14, %15
  %sub10 = sub nsw i32 %add8, %add9
  store i32 %sub10, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 3), align 4
  ret void
}

; CHECK-LABEL: @subadd
; CHECK:  %5 = add <4 x i32> %3, %4
; CHECK:  %6 = sub <4 x i32> %2, %5
; CHECK:  %7 = add <4 x i32> %2, %5
; CHECK:  %8 = shufflevector <4 x i32> %6, <4 x i32> %7, <4 x i32> <i32 0, i32 5, i32 2, i32 7>

; Function Attrs: nounwind uwtable
define void @subadd() #0 {
entry:
  %0 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 0), align 4
  %1 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 0), align 4
  %add = add nsw i32 %0, %1
  %2 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 0), align 4
  %3 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 0), align 4
  %add1 = add nsw i32 %2, %3
  %sub = sub nsw i32 %add, %add1
  store i32 %sub, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 0), align 4
  %4 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 1), align 4
  %5 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 1), align 4
  %add2 = add nsw i32 %4, %5
  %6 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 1), align 4
  %7 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 1), align 4
  %add3 = add nsw i32 %6, %7
  %add4 = add nsw i32 %add2, %add3
  store i32 %add4, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 1), align 4
  %8 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 2), align 4
  %9 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 2), align 4
  %add5 = add nsw i32 %8, %9
  %10 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 2), align 4
  %11 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 2), align 4
  %add6 = add nsw i32 %10, %11
  %sub7 = sub nsw i32 %add5, %add6
  store i32 %sub7, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 2), align 4
  %12 = load i32* getelementptr inbounds ([4 x i32]* @b, i32 0, i64 3), align 4
  %13 = load i32* getelementptr inbounds ([4 x i32]* @c, i32 0, i64 3), align 4
  %add8 = add nsw i32 %12, %13
  %14 = load i32* getelementptr inbounds ([4 x i32]* @d, i32 0, i64 3), align 4
  %15 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i64 3), align 4
  %add9 = add nsw i32 %14, %15
  %add10 = add nsw i32 %add8, %add9
  store i32 %add10, i32* getelementptr inbounds ([4 x i32]* @a, i32 0, i64 3), align 4
  ret void
}

; CHECK-LABEL: @faddfsub
; CHECK: %2 = fadd <4 x float> %0, %1
; CHECK: %3 = fsub <4 x float> %0, %1
; CHECK: %4 = shufflevector <4 x float> %2, <4 x float> %3, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
; Function Attrs: nounwind uwtable
define void @faddfsub() #0 {
entry:
  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
  %add = fadd float %0, %1
  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
  %sub = fsub float %2, %3
  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
  %add1 = fadd float %4, %5
  store float %add1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
  %sub2 = fsub float %6, %7
  store float %sub2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
  ret void
}

; CHECK-LABEL: @fsubfadd
; CHECK: %2 = fsub <4 x float> %0, %1
; CHECK: %3 = fadd <4 x float> %0, %1
; CHECK: %4 = shufflevector <4 x float> %2, <4 x float> %3, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
; Function Attrs: nounwind uwtable
define void @fsubfadd() #0 {
entry:
  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
  %sub = fsub float %0, %1
  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
  %add = fadd float %2, %3
  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
  %sub1 = fsub float %4, %5
  store float %sub1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
  %add2 = fadd float %6, %7
  store float %add2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
  ret void
}

; CHECK-LABEL: @No_faddfsub
; CHECK-NOT: fadd <4 x float>
; CHECK-NOT: fsub <4 x float>
; CHECK-NOT: shufflevector
; Function Attrs: nounwind uwtable
define void @No_faddfsub() #0 {
entry:
  %0 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 0), align 4
  %1 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 0), align 4
  %add = fadd float %0, %1
  store float %add, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 0), align 4
  %2 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 1), align 4
  %3 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 1), align 4
  %add1 = fadd float %2, %3
  store float %add1, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 1), align 4
  %4 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 2), align 4
  %5 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 2), align 4
  %add2 = fadd float %4, %5
  store float %add2, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 2), align 4
  %6 = load float* getelementptr inbounds ([4 x float]* @fb, i32 0, i64 3), align 4
  %7 = load float* getelementptr inbounds ([4 x float]* @fc, i32 0, i64 3), align 4
  %sub = fsub float %6, %7
  store float %sub, float* getelementptr inbounds ([4 x float]* @fa, i32 0, i64 3), align 4
  ret void
}

attributes #0 = { nounwind }