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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK
; Same as vecreduce-fadd-legalization.ll, but without fmf.
declare half @llvm.vector.reduce.fadd.f16.v1f16(half, <1 x half>)
declare float @llvm.vector.reduce.fadd.f32.v1f32(float, <1 x float>)
declare double @llvm.vector.reduce.fadd.f64.v1f64(double, <1 x double>)
declare fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128, <1 x fp128>)
declare float @llvm.vector.reduce.fadd.f32.v3f32(float, <3 x float>)
declare float @llvm.vector.reduce.fadd.f32.v5f32(float, <5 x float>)
declare fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128, <2 x fp128>)
declare float @llvm.vector.reduce.fadd.f32.v16f32(float, <16 x float>)
define half @test_v1f16(<1 x half> %a, half %s) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fcvt s0, h0
; CHECK-NEXT: fcvt s1, h1
; CHECK-NEXT: fadd s0, s1, s0
; CHECK-NEXT: fcvt h0, s0
; CHECK-NEXT: ret
%b = call half @llvm.vector.reduce.fadd.f16.v1f16(half %s, <1 x half> %a)
ret half %b
}
define half @test_v1f16_neutral(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call half @llvm.vector.reduce.fadd.f16.v1f16(half -0.0, <1 x half> %a)
ret half %b
}
define float @test_v1f32(<1 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v1f32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: fadd s0, s1, s0
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v1f32(float %s, <1 x float> %a)
ret float %b
}
define float @test_v1f32_neutral(<1 x float> %a) nounwind {
; CHECK-LABEL: test_v1f32_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v1f32(float -0.0, <1 x float> %a)
ret float %b
}
define double @test_v1f64(<1 x double> %a, double %s) nounwind {
; CHECK-LABEL: test_v1f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd d0, d1, d0
; CHECK-NEXT: ret
%b = call double @llvm.vector.reduce.fadd.f64.v1f64(double %s, <1 x double> %a)
ret double %b
}
define double @test_v1f64_neutral(<1 x double> %a) nounwind {
; CHECK-LABEL: test_v1f64_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call double @llvm.vector.reduce.fadd.f64.v1f64(double -0.0, <1 x double> %a)
ret double %b
}
define fp128 @test_v1f128(<1 x fp128> %a, fp128 %s) nounwind {
; CHECK-LABEL: test_v1f128:
; CHECK: // %bb.0:
; CHECK-NEXT: mov v2.16b, v0.16b
; CHECK-NEXT: mov v0.16b, v1.16b
; CHECK-NEXT: mov v1.16b, v2.16b
; CHECK-NEXT: b __addtf3
%b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 %s, <1 x fp128> %a)
ret fp128 %b
}
define fp128 @test_v1f128_neutral(<1 x fp128> %a) nounwind {
; CHECK-LABEL: test_v1f128_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call fp128 @llvm.vector.reduce.fadd.f128.v1f128(fp128 0xL00000000000000008000000000000000, <1 x fp128> %a)
ret fp128 %b
}
define float @test_v3f32(<3 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd s1, s1, s0
; CHECK-NEXT: mov s2, v0.s[1]
; CHECK-NEXT: mov s0, v0.s[2]
; CHECK-NEXT: fadd s1, s1, s2
; CHECK-NEXT: fadd s0, s1, s0
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v3f32(float %s, <3 x float> %a)
ret float %b
}
define float @test_v3f32_neutral(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: mov s1, v0.s[2]
; CHECK-NEXT: faddp s0, v0.2s
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v3f32(float -0.0, <3 x float> %a)
ret float %b
}
define float @test_v5f32(<5 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v5f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd s0, s5, s0
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: fadd s0, s0, s3
; CHECK-NEXT: fadd s0, s0, s4
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v5f32(float %s, <5 x float> %a)
ret float %b
}
define float @test_v5f32_neutral(<5 x float> %a) nounwind {
; CHECK-LABEL: test_v5f32_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: fadd s0, s0, s3
; CHECK-NEXT: fadd s0, s0, s4
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v5f32(float -0.0, <5 x float> %a)
ret float %b
}
define fp128 @test_v2f128(<2 x fp128> %a, fp128 %s) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK: // %bb.0:
; CHECK-NEXT: sub sp, sp, #32
; CHECK-NEXT: str q1, [sp] // 16-byte Folded Spill
; CHECK-NEXT: mov v1.16b, v0.16b
; CHECK-NEXT: mov v0.16b, v2.16b
; CHECK-NEXT: str x30, [sp, #16] // 8-byte Folded Spill
; CHECK-NEXT: bl __addtf3
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
; CHECK-NEXT: ldr x30, [sp, #16] // 8-byte Folded Reload
; CHECK-NEXT: add sp, sp, #32
; CHECK-NEXT: b __addtf3
%b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 %s, <2 x fp128> %a)
ret fp128 %b
}
define fp128 @test_v2f128_neutral(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: b __addtf3
%b = call fp128 @llvm.vector.reduce.fadd.f128.v2f128(fp128 0xL00000000000000008000000000000000, <2 x fp128> %a)
ret fp128 %b
}
define float @test_v16f32(<16 x float> %a, float %s) nounwind {
; CHECK-LABEL: test_v16f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov s6, v0.s[1]
; CHECK-NEXT: fadd s4, s4, s0
; CHECK-NEXT: mov s7, v0.s[2]
; CHECK-NEXT: mov s0, v0.s[3]
; CHECK-NEXT: mov s5, v2.s[1]
; CHECK-NEXT: fadd s4, s4, s6
; CHECK-NEXT: mov s6, v1.s[2]
; CHECK-NEXT: fadd s4, s4, s7
; CHECK-NEXT: fadd s0, s4, s0
; CHECK-NEXT: mov s4, v1.s[1]
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v1.s[3]
; CHECK-NEXT: fadd s0, s0, s4
; CHECK-NEXT: fadd s0, s0, s6
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v2.s[2]
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: mov s2, v2.s[3]
; CHECK-NEXT: fadd s0, s0, s5
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v3.s[1]
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: mov s2, v3.s[2]
; CHECK-NEXT: fadd s0, s0, s3
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v3.s[3]
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v16f32(float %s, <16 x float> %a)
ret float %b
}
define float @test_v16f32_neutral(<16 x float> %a) nounwind {
; CHECK-LABEL: test_v16f32_neutral:
; CHECK: // %bb.0:
; CHECK-NEXT: mov s5, v0.s[2]
; CHECK-NEXT: faddp s6, v0.2s
; CHECK-NEXT: mov s0, v0.s[3]
; CHECK-NEXT: mov s4, v1.s[1]
; CHECK-NEXT: fadd s5, s6, s5
; CHECK-NEXT: fadd s0, s5, s0
; CHECK-NEXT: mov s5, v1.s[2]
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v1.s[3]
; CHECK-NEXT: fadd s0, s0, s4
; CHECK-NEXT: mov s4, v2.s[2]
; CHECK-NEXT: fadd s0, s0, s5
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v2.s[1]
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v2.s[3]
; CHECK-NEXT: mov s2, v3.s[2]
; CHECK-NEXT: fadd s0, s0, s4
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v3.s[1]
; CHECK-NEXT: fadd s0, s0, s3
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: mov s1, v3.s[3]
; CHECK-NEXT: fadd s0, s0, s2
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fadd.f32.v16f32(float -0.0, <16 x float> %a)
ret float %b
}
|
