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
|
; 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.fmaximum.v1f16(<1 x half> %a)
declare float @llvm.vector.reduce.fmaximum.v1f32(<1 x float> %a)
declare double @llvm.vector.reduce.fmaximum.v1f64(<1 x double> %a)
declare fp128 @llvm.vector.reduce.fmaximum.v1f128(<1 x fp128> %a)
declare half @llvm.vector.reduce.fmaximum.v4f16(<4 x half> %a)
declare half @llvm.vector.reduce.fmaximum.v11f16(<11 x half> %a)
declare float @llvm.vector.reduce.fmaximum.v3f32(<3 x float> %a)
declare fp128 @llvm.vector.reduce.fmaximum.v2f128(<2 x fp128> %a)
declare float @llvm.vector.reduce.fmaximum.v16f32(<16 x float> %a)
declare double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> %a)
define half @test_v1f16(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call half @llvm.vector.reduce.fmaximum.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 float @llvm.vector.reduce.fmaximum.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 double @llvm.vector.reduce.fmaximum.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 fp128 @llvm.vector.reduce.fmaximum.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 h1, v0.h[1]
; CHECK-NOFP-NEXT: fcvt s2, h0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmax s1, s2, s1
; CHECK-NOFP-NEXT: mov h2, v0.h[2]
; CHECK-NOFP-NEXT: mov h0, v0.h[3]
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmax s1, s1, s2
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmax s0, s1, s0
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: ret
;
; CHECK-FP-LABEL: test_v4f16:
; CHECK-FP: // %bb.0:
; CHECK-FP-NEXT: fmaxv h0, v0.4h
; CHECK-FP-NEXT: ret
%b = call half @llvm.vector.reduce.fmaximum.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 h16, [sp, #8]
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: ldr h17, [sp]
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s2, h2
; CHECK-NOFP-NEXT: fcvt s16, h16
; CHECK-NOFP-NEXT: fcvt s17, h17
; CHECK-NOFP-NEXT: fmax s1, s1, s16
; CHECK-NOFP-NEXT: ldr h16, [sp, #16]
; CHECK-NOFP-NEXT: fmax s0, s0, s17
; CHECK-NOFP-NEXT: fcvt s16, h16
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fmax s1, s2, s16
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt h1, s1
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fcvt s1, h1
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s1, h3
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s1, h4
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s1, h5
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s1, h6
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax s0, s0, s1
; CHECK-NOFP-NEXT: fcvt s1, h7
; CHECK-NOFP-NEXT: fcvt h0, s0
; CHECK-NOFP-NEXT: fcvt s0, h0
; CHECK-NOFP-NEXT: fmax 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: // 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: mov x8, sp
; 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: movi v1.8h, #252, lsl #8
; CHECK-FP-NEXT: mov v0.h[2], v2.h[0]
; CHECK-FP-NEXT: ld1 { v1.h }[0], [x8]
; CHECK-FP-NEXT: add x8, sp, #8
; CHECK-FP-NEXT: mov v0.h[3], v3.h[0]
; CHECK-FP-NEXT: ld1 { v1.h }[1], [x8]
; CHECK-FP-NEXT: add x8, sp, #16
; CHECK-FP-NEXT: mov v0.h[4], v4.h[0]
; CHECK-FP-NEXT: ld1 { v1.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: fmax v0.8h, v0.8h, v1.8h
; CHECK-FP-NEXT: fmaxv h0, v0.8h
; CHECK-FP-NEXT: ret
%b = call half @llvm.vector.reduce.fmaximum.v11f16(<11 x half> %a)
ret half %b
}
; Neutral element is negative infinity which is chosen for padding the widened
; vector.
define float @test_v3f32(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-8388608 // =0xff800000
; CHECK-NEXT: fmov s1, w8
; CHECK-NEXT: mov v0.s[3], v1.s[0]
; CHECK-NEXT: fmaxv s0, v0.4s
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fmaximum.v3f32(<3 x float> %a)
ret float %b
}
; Neutral element chosen for padding the widened vector is not negative infinity.
define float @test_v3f32_ninf(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32_ninf:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-8388609 // =0xff7fffff
; CHECK-NEXT: fmov s1, w8
; CHECK-NEXT: mov v0.s[3], v1.s[0]
; CHECK-NEXT: fmaxv s0, v0.4s
; CHECK-NEXT: ret
%b = call ninf float @llvm.vector.reduce.fmaximum.v3f32(<3 x float> %a)
ret float %b
}
; Cannot legalize f128. See PR63267 - The underlying fmaximum has no default
; expansion and no libcalls.
;define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
; %b = call fp128 @llvm.vector.reduce.fmaximum.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: fmax v1.4s, v1.4s, v3.4s
; CHECK-NEXT: fmax v0.4s, v0.4s, v2.4s
; CHECK-NEXT: fmax v0.4s, v0.4s, v1.4s
; CHECK-NEXT: fmaxv s0, v0.4s
; CHECK-NEXT: ret
%b = call float @llvm.vector.reduce.fmaximum.v16f32(<16 x float> %a)
ret float %b
}
define double @test_v2f64(<2 x double> %a) nounwind {
; CHECK-LABEL: test_v2f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxp d0, v0.2d
; CHECK-NEXT: ret
%b = call double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> %a)
ret double %b
}
|
