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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
|
; 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 --check-prefix=CHECK-NOFP
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon,+fullfp16 | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FP
declare half @llvm.vector.reduce.fmax.v1f16(<1 x half> %a)
declare float @llvm.vector.reduce.fmax.v1f32(<1 x float> %a)
declare double @llvm.vector.reduce.fmax.v1f64(<1 x double> %a)
declare fp128 @llvm.vector.reduce.fmax.v1f128(<1 x fp128> %a)
declare half @llvm.vector.reduce.fmax.v4f16(<4 x half> %a)
declare half @llvm.vector.reduce.fmax.v11f16(<11 x half> %a)
declare float @llvm.vector.reduce.fmax.v3f32(<3 x float> %a)
declare fp128 @llvm.vector.reduce.fmax.v2f128(<2 x fp128> %a)
declare float @llvm.vector.reduce.fmax.v16f32(<16 x float> %a)
define half @test_v1f16(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call nnan half @llvm.vector.reduce.fmax.v1f16(<1 x half> %a)
ret half %b
}
define float @test_v1f32(<1 x float> %a) nounwind {
; CHECK-LABEL: test_v1f32:
; 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 nnan float @llvm.vector.reduce.fmax.v1f32(<1 x float> %a)
ret float %b
}
define double @test_v1f64(<1 x double> %a) nounwind {
; CHECK-LABEL: test_v1f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call nnan double @llvm.vector.reduce.fmax.v1f64(<1 x double> %a)
ret double %b
}
define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
; CHECK-LABEL: test_v1f128:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call nnan fp128 @llvm.vector.reduce.fmax.v1f128(<1 x fp128> %a)
ret fp128 %b
}
define half @test_v4f16(<4 x half> %a) nounwind {
; CHECK-NOFP-LABEL: test_v4f16:
; CHECK-NOFP: // %bb.0:
; CHECK-NOFP-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NOFP-NEXT: mov h3, v0.h[1]
; CHECK-NOFP-NEXT: mov h1, v0.h[3]
; CHECK-NOFP-NEXT: mov h2, v0.h[2]
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: ret
;
; CHECK-FP-LABEL: test_v4f16:
; CHECK-FP: // %bb.0:
; CHECK-FP-NEXT: fmaxnmv h0, v0.4h
; CHECK-FP-NEXT: ret
%b = call nnan half @llvm.vector.reduce.fmax.v4f16(<4 x half> %a)
ret half %b
}
define half @test_v4f16_ninf(<4 x half> %a) nounwind {
; CHECK-NOFP-LABEL: test_v4f16_ninf:
; CHECK-NOFP: // %bb.0:
; CHECK-NOFP-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NOFP-NEXT: mov h3, v0.h[1]
; CHECK-NOFP-NEXT: mov h1, v0.h[3]
; CHECK-NOFP-NEXT: mov h2, v0.h[2]
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: ret
;
; CHECK-FP-LABEL: test_v4f16_ninf:
; CHECK-FP: // %bb.0:
; CHECK-FP-NEXT: fmaxnmv h0, v0.4h
; CHECK-FP-NEXT: ret
%b = call nnan ninf half @llvm.vector.reduce.fmax.v4f16(<4 x half> %a)
ret half %b
}
define half @test_v11f16(<11 x half> %a) nounwind {
; CHECK-NOFP-LABEL: test_v11f16:
; CHECK-NOFP: // %bb.0:
; CHECK-NOFP-NEXT: ldr h18, [sp, #8]
; CHECK-NOFP-NEXT: ldr h17, [sp]
; CHECK-NOFP-NEXT: ldr h16, [sp, #16]
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fcvt s18, h18
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcmp s1, s18
; CHECK-NOFP-NEXT: fcvt s17, h17
; CHECK-NOFP-NEXT: adrp x8, .LCPI6_0
; CHECK-NOFP-NEXT: fcsel s1, s1, s18, gt
; CHECK-NOFP-NEXT: fcmp s0, s17
; CHECK-NOFP-NEXT: ldr h18, [x8, :lo12:.LCPI6_0]
; CHECK-NOFP-NEXT: fcsel s0, s0, s17, gt
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s16, h16
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s2, s16
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s2, s2, s16, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: mov w8, #-8388608
; CHECK-NOFP-NEXT: fcvt s18, h18
; CHECK-NOFP-NEXT: fcvt h2, s2
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fmov s17, w8
; CHECK-NOFP-NEXT: fcmp s3, s18
; CHECK-NOFP-NEXT: fcvt s1, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s3, s3, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s4, h4
; CHECK-NOFP-NEXT: fcvt h2, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s4, s18
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s3, s4, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
; CHECK-NOFP-NEXT: fcvt s5, h5
; CHECK-NOFP-NEXT: fcvt h3, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s5, s18
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s4, s5, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
; CHECK-NOFP-NEXT: fcvt s6, h6
; CHECK-NOFP-NEXT: fcvt h4, s4
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s6, s18
; CHECK-NOFP-NEXT: fcvt s1, h4
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s5, s6, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s7, h7
; CHECK-NOFP-NEXT: fcvt h4, s5
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s7, s18
; CHECK-NOFP-NEXT: fcvt s4, h4
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s5, s7, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s4
; CHECK-NOFP-NEXT: fcvt h5, s5
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h5
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: ret
;
; CHECK-FP-LABEL: test_v11f16:
; CHECK-FP: // %bb.0:
; CHECK-FP-NEXT: movi v16.8h, #252, lsl #8
; CHECK-FP-NEXT: mov x8, sp
; CHECK-FP-NEXT: ld1 { v16.h }[0], [x8]
; CHECK-FP-NEXT: add x8, sp, #8 // =8
; CHECK-FP-NEXT: // kill: def $h0 killed $h0 def $q0
; CHECK-FP-NEXT: // kill: def $h1 killed $h1 def $q1
; CHECK-FP-NEXT: // kill: def $h2 killed $h2 def $q2
; CHECK-FP-NEXT: // kill: def $h3 killed $h3 def $q3
; CHECK-FP-NEXT: // kill: def $h4 killed $h4 def $q4
; CHECK-FP-NEXT: // kill: def $h5 killed $h5 def $q5
; CHECK-FP-NEXT: // kill: def $h6 killed $h6 def $q6
; CHECK-FP-NEXT: // kill: def $h7 killed $h7 def $q7
; CHECK-FP-NEXT: mov v0.h[1], v1.h[0]
; CHECK-FP-NEXT: ld1 { v16.h }[1], [x8]
; CHECK-FP-NEXT: mov v0.h[2], v2.h[0]
; CHECK-FP-NEXT: mov v0.h[3], v3.h[0]
; CHECK-FP-NEXT: add x8, sp, #16 // =16
; CHECK-FP-NEXT: mov v0.h[4], v4.h[0]
; CHECK-FP-NEXT: ld1 { v16.h }[2], [x8]
; CHECK-FP-NEXT: mov v0.h[5], v5.h[0]
; CHECK-FP-NEXT: mov v0.h[6], v6.h[0]
; CHECK-FP-NEXT: mov v0.h[7], v7.h[0]
; CHECK-FP-NEXT: fmaxnm v0.8h, v0.8h, v16.8h
; CHECK-FP-NEXT: fmaxnmv h0, v0.8h
; CHECK-FP-NEXT: ret
%b = call nnan half @llvm.vector.reduce.fmax.v11f16(<11 x half> %a)
ret half %b
}
define half @test_v11f16_ninf(<11 x half> %a) nounwind {
; CHECK-NOFP-LABEL: test_v11f16_ninf:
; CHECK-NOFP: // %bb.0:
; CHECK-NOFP-NEXT: ldr h18, [sp, #8]
; CHECK-NOFP-NEXT: ldr h17, [sp]
; CHECK-NOFP-NEXT: ldr h16, [sp, #16]
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fcvt s18, h18
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcmp s1, s18
; CHECK-NOFP-NEXT: fcvt s17, h17
; CHECK-NOFP-NEXT: adrp x8, .LCPI7_0
; CHECK-NOFP-NEXT: fcsel s1, s1, s18, gt
; CHECK-NOFP-NEXT: fcmp s0, s17
; CHECK-NOFP-NEXT: ldr h18, [x8, :lo12:.LCPI7_0]
; CHECK-NOFP-NEXT: fcsel s0, s0, s17, gt
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s16, h16
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s2, s16
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: mov w8, #57344
; CHECK-NOFP-NEXT: fcsel s2, s2, s16, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: movk w8, #51071, lsl #16
; CHECK-NOFP-NEXT: fcvt s18, h18
; CHECK-NOFP-NEXT: fcvt h2, s2
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fmov s17, w8
; CHECK-NOFP-NEXT: fcmp s3, s18
; CHECK-NOFP-NEXT: fcvt s1, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s3, s3, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s4, h4
; CHECK-NOFP-NEXT: fcvt h2, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s4, s18
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s3, s4, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s2
; CHECK-NOFP-NEXT: fcvt s5, h5
; CHECK-NOFP-NEXT: fcvt h3, s3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s5, s18
; CHECK-NOFP-NEXT: fcvt s3, h3
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s4, s5, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s3
; CHECK-NOFP-NEXT: fcvt s6, h6
; CHECK-NOFP-NEXT: fcvt h4, s4
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s6, s18
; CHECK-NOFP-NEXT: fcvt s1, h4
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s5, s6, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s7, h7
; CHECK-NOFP-NEXT: fcvt h4, s5
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcmp s7, s18
; CHECK-NOFP-NEXT: fcvt s4, h4
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcsel s5, s7, s17, gt
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s4
; CHECK-NOFP-NEXT: fcvt h5, s5
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h5
; CHECK-NOFP-NEXT: fmaxnm s0, s0, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: ret
;
; CHECK-FP-LABEL: test_v11f16_ninf:
; CHECK-FP: // %bb.0:
; CHECK-FP-NEXT: mvni v16.8h, #4, lsl #8
; CHECK-FP-NEXT: mov x8, sp
; CHECK-FP-NEXT: ld1 { v16.h }[0], [x8]
; CHECK-FP-NEXT: add x8, sp, #8 // =8
; CHECK-FP-NEXT: // kill: def $h0 killed $h0 def $q0
; CHECK-FP-NEXT: // kill: def $h1 killed $h1 def $q1
; CHECK-FP-NEXT: // kill: def $h2 killed $h2 def $q2
; CHECK-FP-NEXT: // kill: def $h3 killed $h3 def $q3
; CHECK-FP-NEXT: // kill: def $h4 killed $h4 def $q4
; CHECK-FP-NEXT: // kill: def $h5 killed $h5 def $q5
; CHECK-FP-NEXT: // kill: def $h6 killed $h6 def $q6
; CHECK-FP-NEXT: // kill: def $h7 killed $h7 def $q7
; CHECK-FP-NEXT: mov v0.h[1], v1.h[0]
; CHECK-FP-NEXT: ld1 { v16.h }[1], [x8]
; CHECK-FP-NEXT: mov v0.h[2], v2.h[0]
; CHECK-FP-NEXT: mov v0.h[3], v3.h[0]
; CHECK-FP-NEXT: add x8, sp, #16 // =16
; CHECK-FP-NEXT: mov v0.h[4], v4.h[0]
; CHECK-FP-NEXT: ld1 { v16.h }[2], [x8]
; CHECK-FP-NEXT: mov v0.h[5], v5.h[0]
; CHECK-FP-NEXT: mov v0.h[6], v6.h[0]
; CHECK-FP-NEXT: mov v0.h[7], v7.h[0]
; CHECK-FP-NEXT: fmaxnm v0.8h, v0.8h, v16.8h
; CHECK-FP-NEXT: fmaxnmv h0, v0.8h
; CHECK-FP-NEXT: ret
%b = call nnan ninf half @llvm.vector.reduce.fmax.v11f16(<11 x half> %a)
ret half %b
}
define float @test_v3f32(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-8388608
; CHECK-NEXT: fmov s1, w8
; CHECK-NEXT: mov v0.s[3], v1.s[0]
; CHECK-NEXT: fmaxnmv s0, v0.4s
; CHECK-NEXT: ret
%b = call nnan float @llvm.vector.reduce.fmax.v3f32(<3 x float> %a)
ret float %b
}
define float @test_v3f32_ninf(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32_ninf:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-8388609
; CHECK-NEXT: fmov s1, w8
; CHECK-NEXT: mov v0.s[3], v1.s[0]
; CHECK-NEXT: fmaxnmv s0, v0.4s
; CHECK-NEXT: ret
%b = call nnan ninf float @llvm.vector.reduce.fmax.v3f32(<3 x float> %a)
ret float %b
}
define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK: // %bb.0:
; CHECK-NEXT: b fmaxl
%b = call nnan fp128 @llvm.vector.reduce.fmax.v2f128(<2 x fp128> %a)
ret fp128 %b
}
define float @test_v16f32(<16 x float> %a) nounwind {
; CHECK-LABEL: test_v16f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxnm v1.4s, v1.4s, v3.4s
; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v2.4s
; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v1.4s
; CHECK-NEXT: fmaxnmv s0, v0.4s
; CHECK-NEXT: ret
%b = call nnan float @llvm.vector.reduce.fmax.v16f32(<16 x float> %a)
ret float %b
}
|
