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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 16 x i8> @andv_zero_fill(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) #0 {
; CHECK-LABEL: andv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: andv b0, p0, z0.b
; CHECK-NEXT: ret
%t1 = call i8 @llvm.aarch64.sve.andv.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a)
%t2 = insertelement <vscale x 16 x i8> zeroinitializer, i8 %t1, i64 0
ret <vscale x 16 x i8> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 8 x i16> @eorv_zero_fill(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) #0 {
; CHECK-LABEL: eorv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: eorv h0, p0, z0.h
; CHECK-NEXT: ret
%t1 = call i16 @llvm.aarch64.sve.eorv.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%t2 = insertelement <vscale x 8 x i16> zeroinitializer, i16 %t1, i64 0
ret <vscale x 8 x i16> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x double> @fadda_zero_fill(<vscale x 2 x i1> %pg, double %init, <vscale x 2 x double> %a) #0 {
; CHECK-LABEL: fadda_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: fadda d0, p0, d0, z1.d
; CHECK-NEXT: ret
%t1 = call double @llvm.aarch64.sve.fadda.nxv2f64(<vscale x 2 x i1> %pg, double %init, <vscale x 2 x double> %a)
%t2 = insertelement <vscale x 2 x double> zeroinitializer, double %t1, i64 0
ret <vscale x 2 x double> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 4 x float> @faddv_zero_fill(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) #0 {
; CHECK-LABEL: faddv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: faddv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call float @llvm.aarch64.sve.faddv.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a)
%t2 = insertelement <vscale x 4 x float> zeroinitializer, float %t1, i64 0
ret <vscale x 4 x float> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 8 x half> @fmaxv_zero_fill(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
; CHECK-LABEL: fmaxv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxv h0, p0, z0.h
; CHECK-NEXT: ret
%t1 = call half @llvm.aarch64.sve.fmaxv.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a)
%t2 = insertelement <vscale x 8 x half> zeroinitializer, half %t1, i64 0
ret <vscale x 8 x half> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x float> @fmaxnmv_zero_fill(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a) #0 {
; CHECK-LABEL: fmaxnmv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxnmv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call float @llvm.aarch64.sve.fmaxnmv.nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a)
%t2 = insertelement <vscale x 2 x float> zeroinitializer, float %t1, i64 0
ret <vscale x 2 x float> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x float> @fminnmv_zero_fill(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a) #0 {
; CHECK-LABEL: fminnmv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: fminnmv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call float @llvm.aarch64.sve.fminnmv.nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a)
%t2 = insertelement <vscale x 2 x float> zeroinitializer, float %t1, i64 0
ret <vscale x 2 x float> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x float> @fminv_zero_fill(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a) #0 {
; CHECK-LABEL: fminv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: fminv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call float @llvm.aarch64.sve.fminv.nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a)
%t2 = insertelement <vscale x 2 x float> zeroinitializer, float %t1, i64 0
ret <vscale x 2 x float> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 4 x i32> @orv_zero_fill(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) #0 {
; CHECK-LABEL: orv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: orv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call i32 @llvm.aarch64.sve.orv.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a)
%t2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 %t1, i64 0
ret <vscale x 4 x i32> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x i64> @saddv_zero_fill(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) #0 {
; CHECK-LABEL: saddv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: saddv d0, p0, z0.b
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.saddv.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a)
%t2 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t1, i64 0
ret <vscale x 2 x i64> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x i64> @smaxv_zero_fill(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: smaxv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: smaxv d0, p0, z0.d
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.smaxv.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a)
%t2 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t1, i64 0
ret <vscale x 2 x i64> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 4 x i32> @sminv_zero_fill(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a) #0 {
; CHECK-LABEL: sminv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: sminv s0, p0, z0.s
; CHECK-NEXT: ret
%t1 = call i32 @llvm.aarch64.sve.sminv.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a)
%t2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 %t1, i64 0
ret <vscale x 4 x i32> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x i64> @uaddv_zero_fill(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a) #0 {
; CHECK-LABEL: uaddv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: uaddv d0, p0, z0.h
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.uaddv.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%t2 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t1, i64 0
ret <vscale x 2 x i64> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 16 x i8> @umaxv_zero_fill(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a) #0 {
; CHECK-LABEL: umaxv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: umaxv b0, p0, z0.b
; CHECK-NEXT: ret
%t1 = call i8 @llvm.aarch64.sve.umaxv.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a)
%t2 = insertelement <vscale x 16 x i8> zeroinitializer, i8 %t1, i64 0
ret <vscale x 16 x i8> %t2
}
; Ensure we rely on the reduction's implicit zero filling.
define <vscale x 2 x i64> @uminv_zero_fill(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: uminv_zero_fill:
; CHECK: // %bb.0:
; CHECK-NEXT: uminv d0, p0, z0.d
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.uminv.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a)
%t2 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t1, i64 0
ret <vscale x 2 x i64> %t2
}
; Ensure explicit zeroing when inserting into a lane other than 0.
; NOTE: This test doesn't care about the exact way an insert is code generated,
; so only checks the presence of one instruction from the expected chain.
define <vscale x 2 x i64> @zero_fill_non_zero_index(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: zero_fill_non_zero_index:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: uminv d0, p0, z0.d
; CHECK-NEXT: fmov x9, d0
; CHECK-NEXT: index z1.d, #0, #1
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: mov z0.d, x8
; CHECK-NEXT: cmpeq p0.d, p0/z, z1.d, z0.d
; CHECK-NEXT: mov z0.d, #0 // =0x0
; CHECK-NEXT: mov z0.d, p0/m, x9
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.uminv.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a)
%t2 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t1, i64 1
ret <vscale x 2 x i64> %t2
}
; Ensure explicit zeroing when the result vector is larger than that produced by
; the reduction instruction.
define <vscale x 4 x i64> @zero_fill_type_mismatch(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: zero_fill_type_mismatch:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z1.d, #0 // =0x0
; CHECK-NEXT: uminv d0, p0, z0.d
; CHECK-NEXT: ret
%t1 = call i64 @llvm.aarch64.sve.uminv.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a)
%t2 = insertelement <vscale x 4 x i64> zeroinitializer, i64 %t1, i64 0
ret <vscale x 4 x i64> %t2
}
; Ensure explicit zeroing when extracting an element from an operation that
; cannot guarantee lanes 1-N are zero.
; NOTE: This test doesn't care about the exact way an insert is code generated,
; so only checks the presence of one instruction from the expected chain.
define <vscale x 2 x i64> @zero_fill_no_zero_upper_lanes(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: zero_fill_no_zero_upper_lanes:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z0.d, p0/m, z0.d, z0.d
; CHECK-NEXT: ptrue p0.d, vl1
; CHECK-NEXT: fmov x8, d0
; CHECK-NEXT: mov z0.d, #0 // =0x0
; CHECK-NEXT: mov z0.d, p0/m, x8
; CHECK-NEXT: ret
%t1 = call <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %a)
%t2 = extractelement <vscale x 2 x i64> %t1, i64 0
%t3 = insertelement <vscale x 2 x i64> zeroinitializer, i64 %t2, i64 0
ret <vscale x 2 x i64> %t3
}
declare i8 @llvm.aarch64.sve.andv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i8 @llvm.aarch64.sve.andv.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>)
declare i8 @llvm.aarch64.sve.eorv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i16 @llvm.aarch64.sve.eorv.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>)
declare float @llvm.aarch64.sve.fadda.nxv2f32(<vscale x 2 x i1>, float, <vscale x 2 x float>)
declare double @llvm.aarch64.sve.fadda.nxv2f64(<vscale x 2 x i1>, double, <vscale x 2 x double>)
declare float @llvm.aarch64.sve.faddv.nxv2f32(<vscale x 2 x i1>, <vscale x 2 x float>)
declare float @llvm.aarch64.sve.faddv.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare float @llvm.aarch64.sve.fmaxnmv.nxv2f32(<vscale x 2 x i1>, <vscale x 2 x float>)
declare half @llvm.aarch64.sve.fmaxv.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare float @llvm.aarch64.sve.fmaxv.nxv2f32(<vscale x 2 x i1>, <vscale x 2 x float>)
declare float @llvm.aarch64.sve.fminv.nxv2f32(<vscale x 2 x i1>, <vscale x 2 x float>)
declare float @llvm.aarch64.sve.fminnmv.nxv2f32(<vscale x 2 x i1>, <vscale x 2 x float>)
declare i8 @llvm.aarch64.sve.orv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i32 @llvm.aarch64.sve.orv.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>)
declare i64 @llvm.aarch64.sve.saddv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i64 @llvm.aarch64.sve.saddv.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>)
declare i8 @llvm.aarch64.sve.smaxv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i64 @llvm.aarch64.sve.smaxv.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>)
declare i8 @llvm.aarch64.sve.sminv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i32 @llvm.aarch64.sve.sminv.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>)
declare i64 @llvm.aarch64.sve.uaddv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i64 @llvm.aarch64.sve.uaddv.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>)
declare i8 @llvm.aarch64.sve.umaxv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i8 @llvm.aarch64.sve.umaxv.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>)
declare i8 @llvm.aarch64.sve.uminv.nxv2i8(<vscale x 2 x i1>, <vscale x 2 x i8>)
declare i64 @llvm.aarch64.sve.uminv.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.umin.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
attributes #0 = { "target-features"="+sve" }
|
