File: vecreduce-fadd.ll

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-12
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,496,180 kB
  • sloc: cpp: 5,593,972; ansic: 986,872; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,538; xml: 953; cs: 573; fortran: 567
file content (285 lines) | stat: -rw-r--r-- 9,846 bytes parent folder | download | duplicates (3) 
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
 
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc --mtriple=aarch64-eabi -aarch64-neon-syntax=generic -mattr=+fullfp16 < %s | FileCheck %s
; RUN: llc --mtriple=aarch64-eabi -aarch64-neon-syntax=generic < %s | FileCheck %s --check-prefix=CHECKNOFP16

define float @add_HalfS(<2 x float> %bin.rdx)  {
; CHECK-LABEL: add_HalfS:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_HalfS:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    faddp s0, v0.2s
; CHECKNOFP16-NEXT:    ret
  %r = call fast float @llvm.vector.reduce.fadd.f32.v2f32(float -0.0, <2 x float> %bin.rdx)
  ret float %r
}

define half @add_HalfH(<4 x half> %bin.rdx)  {
; CHECK-LABEL: add_HalfH:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp v0.4h, v0.4h, v0.4h
; CHECK-NEXT:    faddp h0, v0.2h
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_HalfH:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECKNOFP16-NEXT:    mov h1, v0.h[1]
; CHECKNOFP16-NEXT:    fcvt s2, h0
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s2, s1
; CHECKNOFP16-NEXT:    mov h2, v0.h[2]
; CHECKNOFP16-NEXT:    mov h0, v0.h[3]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s0, h0
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s0, s1, s0
; CHECKNOFP16-NEXT:    fcvt h0, s0
; CHECKNOFP16-NEXT:    ret
  %r = call fast half @llvm.vector.reduce.fadd.f16.v4f16(half -0.0, <4 x half> %bin.rdx)
  ret half %r
}


define half @add_H(<8 x half> %bin.rdx)  {
; CHECK-LABEL: add_H:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp v0.8h, v0.8h, v0.8h
; CHECK-NEXT:    faddp v0.8h, v0.8h, v0.8h
; CHECK-NEXT:    faddp h0, v0.2h
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_H:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    mov h1, v0.h[1]
; CHECKNOFP16-NEXT:    fcvt s2, h0
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s2, s1
; CHECKNOFP16-NEXT:    mov h2, v0.h[2]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    mov h2, v0.h[3]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    mov h2, v0.h[4]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    mov h2, v0.h[5]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    mov h2, v0.h[6]
; CHECKNOFP16-NEXT:    mov h0, v0.h[7]
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s0, h0
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s1, s1, s2
; CHECKNOFP16-NEXT:    fcvt h1, s1
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s0, s1, s0
; CHECKNOFP16-NEXT:    fcvt h0, s0
; CHECKNOFP16-NEXT:    ret
  %r = call fast half @llvm.vector.reduce.fadd.f16.v8f16(half -0.0, <8 x half> %bin.rdx)
  ret half %r
}

define float @add_S(<4 x float> %bin.rdx)  {
; CHECK-LABEL: add_S:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_S:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECKNOFP16-NEXT:    faddp s0, v0.2s
; CHECKNOFP16-NEXT:    ret
  %r = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float -0.0, <4 x float> %bin.rdx)
  ret float %r
}

define double @add_D(<2 x double> %bin.rdx)  {
; CHECK-LABEL: add_D:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp d0, v0.2d
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_D:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    faddp d0, v0.2d
; CHECKNOFP16-NEXT:    ret
  %r = call fast double @llvm.vector.reduce.fadd.f64.v2f64(double -0.0, <2 x double> %bin.rdx)
  ret double %r
}

define half @add_2H(<16 x half> %bin.rdx)  {
; CHECK-LABEL: add_2H:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd v0.8h, v0.8h, v1.8h
; CHECK-NEXT:    faddp v0.8h, v0.8h, v0.8h
; CHECK-NEXT:    faddp v0.8h, v0.8h, v0.8h
; CHECK-NEXT:    faddp h0, v0.2h
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_2H:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    mov h2, v1.h[1]
; CHECKNOFP16-NEXT:    mov h3, v0.h[1]
; CHECKNOFP16-NEXT:    fcvt s4, h1
; CHECKNOFP16-NEXT:    fcvt s5, h0
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fadd s4, s5, s4
; CHECKNOFP16-NEXT:    mov h5, v0.h[2]
; CHECKNOFP16-NEXT:    fadd s2, s3, s2
; CHECKNOFP16-NEXT:    mov h3, v1.h[2]
; CHECKNOFP16-NEXT:    fcvt h4, s4
; CHECKNOFP16-NEXT:    fcvt s5, h5
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s4, h4
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s3, s5, s3
; CHECKNOFP16-NEXT:    mov h5, v0.h[3]
; CHECKNOFP16-NEXT:    fadd s2, s4, s2
; CHECKNOFP16-NEXT:    mov h4, v1.h[3]
; CHECKNOFP16-NEXT:    fcvt h3, s3
; CHECKNOFP16-NEXT:    fcvt s5, h5
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s4, h4
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s4, s5, s4
; CHECKNOFP16-NEXT:    mov h5, v0.h[4]
; CHECKNOFP16-NEXT:    fadd s2, s2, s3
; CHECKNOFP16-NEXT:    mov h3, v1.h[4]
; CHECKNOFP16-NEXT:    fcvt h4, s4
; CHECKNOFP16-NEXT:    fcvt s5, h5
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s4, h4
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s3, s5, s3
; CHECKNOFP16-NEXT:    mov h5, v0.h[5]
; CHECKNOFP16-NEXT:    fadd s2, s2, s4
; CHECKNOFP16-NEXT:    mov h4, v1.h[5]
; CHECKNOFP16-NEXT:    fcvt h3, s3
; CHECKNOFP16-NEXT:    fcvt s5, h5
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s4, h4
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s4, s5, s4
; CHECKNOFP16-NEXT:    mov h5, v0.h[6]
; CHECKNOFP16-NEXT:    mov h0, v0.h[7]
; CHECKNOFP16-NEXT:    fadd s2, s2, s3
; CHECKNOFP16-NEXT:    mov h3, v1.h[6]
; CHECKNOFP16-NEXT:    fcvt h4, s4
; CHECKNOFP16-NEXT:    fcvt s5, h5
; CHECKNOFP16-NEXT:    mov h1, v1.h[7]
; CHECKNOFP16-NEXT:    fcvt s0, h0
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s4, h4
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s3, s5, s3
; CHECKNOFP16-NEXT:    fadd s0, s0, s1
; CHECKNOFP16-NEXT:    fadd s2, s2, s4
; CHECKNOFP16-NEXT:    fcvt h3, s3
; CHECKNOFP16-NEXT:    fcvt h0, s0
; CHECKNOFP16-NEXT:    fcvt h2, s2
; CHECKNOFP16-NEXT:    fcvt s3, h3
; CHECKNOFP16-NEXT:    fcvt s0, h0
; CHECKNOFP16-NEXT:    fcvt s2, h2
; CHECKNOFP16-NEXT:    fadd s2, s2, s3
; CHECKNOFP16-NEXT:    fcvt h1, s2
; CHECKNOFP16-NEXT:    fcvt s1, h1
; CHECKNOFP16-NEXT:    fadd s0, s1, s0
; CHECKNOFP16-NEXT:    fcvt h0, s0
; CHECKNOFP16-NEXT:    ret
  %r = call fast half @llvm.vector.reduce.fadd.f16.v16f16(half -0.0, <16 x half> %bin.rdx)
  ret half %r
}

define float @add_2S(<8 x float> %bin.rdx)  {
; CHECK-LABEL: add_2S:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd v0.4s, v0.4s, v1.4s
; CHECK-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_2S:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    fadd v0.4s, v0.4s, v1.4s
; CHECKNOFP16-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECKNOFP16-NEXT:    faddp s0, v0.2s
; CHECKNOFP16-NEXT:    ret
  %r = call fast float @llvm.vector.reduce.fadd.f32.v8f32(float -0.0, <8 x float> %bin.rdx)
  ret float %r
}

define double @add_2D(<4 x double> %bin.rdx)  {
; CHECK-LABEL: add_2D:
; CHECK:       // %bb.0:
; CHECK-NEXT:    fadd v0.2d, v0.2d, v1.2d
; CHECK-NEXT:    faddp d0, v0.2d
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_2D:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    fadd v0.2d, v0.2d, v1.2d
; CHECKNOFP16-NEXT:    faddp d0, v0.2d
; CHECKNOFP16-NEXT:    ret
  %r = call fast double @llvm.vector.reduce.fadd.f64.v4f64(double -0.0, <4 x double> %bin.rdx)
  ret double %r
}

; Added at least one test where the start value is not -0.0.
define float @add_S_init_42(<4 x float> %bin.rdx)  {
; CHECK-LABEL: add_S_init_42:
; CHECK:       // %bb.0:
; CHECK-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECK-NEXT:    mov w8, #1109917696
; CHECK-NEXT:    fmov s1, w8
; CHECK-NEXT:    faddp s0, v0.2s
; CHECK-NEXT:    fadd s0, s0, s1
; CHECK-NEXT:    ret
;
; CHECKNOFP16-LABEL: add_S_init_42:
; CHECKNOFP16:       // %bb.0:
; CHECKNOFP16-NEXT:    faddp v0.4s, v0.4s, v0.4s
; CHECKNOFP16-NEXT:    mov w8, #1109917696
; CHECKNOFP16-NEXT:    fmov s1, w8
; CHECKNOFP16-NEXT:    faddp s0, v0.2s
; CHECKNOFP16-NEXT:    fadd s0, s0, s1
; CHECKNOFP16-NEXT:    ret
  %r = call fast float @llvm.vector.reduce.fadd.f32.v4f32(float 42.0, <4 x float> %bin.rdx)
  ret float %r
}

; Function Attrs: nounwind readnone
declare half @llvm.vector.reduce.fadd.f16.v4f16(half, <4 x half>)
declare half @llvm.vector.reduce.fadd.f16.v8f16(half, <8 x half>)
declare half @llvm.vector.reduce.fadd.f16.v16f16(half, <16 x half>)
declare float @llvm.vector.reduce.fadd.f32.v2f32(float, <2 x float>)
declare float @llvm.vector.reduce.fadd.f32.v4f32(float, <4 x float>)
declare float @llvm.vector.reduce.fadd.f32.v8f32(float, <8 x float>)
declare double @llvm.vector.reduce.fadd.f64.v2f64(double, <2 x double>)
declare double @llvm.vector.reduce.fadd.f64.v4f64(double, <4 x double>)