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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-- | FileCheck %s
; Check that building up a vector w/ only one non-zero lane initializes
; efficiently.
define <8 x i8> @v8i8z(i8 %t, i8 %s) nounwind {
; CHECK-LABEL: v8i8z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0000000000000000
; CHECK-NEXT: mov v0.b[7], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <8 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 undef>, i8 %s, i32 7
ret <8 x i8> %v
}
define <16 x i8> @v16i8z(i8 %t, i8 %s) nounwind {
; CHECK-LABEL: v16i8z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: mov v0.b[15], w1
; CHECK-NEXT: ret
%v = insertelement <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 undef>, i8 %s, i32 15
ret <16 x i8> %v
}
define <4 x i16> @v4i16z(i16 %t, i16 %s) nounwind {
; CHECK-LABEL: v4i16z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0000000000000000
; CHECK-NEXT: mov v0.h[3], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <4 x i16> <i16 0, i16 0, i16 0, i16 undef>, i16 %s, i32 3
ret <4 x i16> %v
}
define <8 x i16> @v8i16z(i16 %t, i16 %s) nounwind {
; CHECK-LABEL: v8i16z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: mov v0.h[7], w1
; CHECK-NEXT: ret
%v = insertelement <8 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 undef>, i16 %s, i32 7
ret <8 x i16> %v
}
define <2 x i32> @v2i32z(i32 %t, i32 %s) nounwind {
; CHECK-LABEL: v2i32z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0000000000000000
; CHECK-NEXT: mov v0.s[1], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <2 x i32> <i32 0, i32 undef>, i32 %s, i32 1
ret <2 x i32> %v
}
define <4 x i32> @v4i32z(i32 %t, i32 %s) nounwind {
; CHECK-LABEL: v4i32z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: mov v0.s[3], w1
; CHECK-NEXT: ret
%v = insertelement <4 x i32> <i32 0, i32 0, i32 0, i32 undef>, i32 %s, i32 3
ret <4 x i32> %v
}
define <2 x i64> @v2i64z(i64 %t, i64 %s) nounwind {
; CHECK-LABEL: v2i64z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: mov v0.d[1], x1
; CHECK-NEXT: ret
%v = insertelement <2 x i64> <i64 0, i64 undef>, i64 %s, i32 1
ret <2 x i64> %v
}
define <2 x float> @v2f32z(float %t, float %s) nounwind {
; CHECK-LABEL: v2f32z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0000000000000000
; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1
; CHECK-NEXT: mov v0.s[1], v1.s[0]
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <2 x float> <float 0.0, float undef>, float %s, i32 1
ret <2 x float> %v
}
define <4 x float> @v4f32z(float %t, float %s) nounwind {
; CHECK-LABEL: v4f32z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1
; CHECK-NEXT: mov v0.s[3], v1.s[0]
; CHECK-NEXT: ret
%v = insertelement <4 x float> <float 0.0, float 0.0, float 0.0, float undef>, float %s, i32 3
ret <4 x float> %v
}
define <2 x double> @v2f64z(double %t, double %s) nounwind {
; CHECK-LABEL: v2f64z:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0000000000000000
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
; CHECK-NEXT: mov v0.d[1], v1.d[0]
; CHECK-NEXT: ret
%v = insertelement <2 x double> <double 0.0, double undef>, double %s, i32 1
ret <2 x double> %v
}
; Check that building up a vector w/ only one non-ones lane initializes
; efficiently.
define <8 x i8> @v8i8m(i8 %t, i8 %s) nounwind {
; CHECK-LABEL: v8i8m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0xffffffffffffffff
; CHECK-NEXT: mov v0.b[7], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <8 x i8> <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 undef>, i8 %s, i32 7
ret <8 x i8> %v
}
define <16 x i8> @v16i8m(i8 %t, i8 %s) nounwind {
; CHECK-LABEL: v16i8m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0xffffffffffffffff
; CHECK-NEXT: mov v0.b[15], w1
; CHECK-NEXT: ret
%v = insertelement <16 x i8> <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 undef>, i8 %s, i32 15
ret <16 x i8> %v
}
define <4 x i16> @v4i16m(i16 %t, i16 %s) nounwind {
; CHECK-LABEL: v4i16m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0xffffffffffffffff
; CHECK-NEXT: mov v0.h[3], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <4 x i16> <i16 -1, i16 -1, i16 -1, i16 undef>, i16 %s, i32 3
ret <4 x i16> %v
}
define <8 x i16> @v8i16m(i16 %t, i16 %s) nounwind {
; CHECK-LABEL: v8i16m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0xffffffffffffffff
; CHECK-NEXT: mov v0.h[7], w1
; CHECK-NEXT: ret
%v = insertelement <8 x i16> <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 undef>, i16 %s, i32 7
ret <8 x i16> %v
}
define <2 x i32> @v2i32m(i32 %t, i32 %s) nounwind {
; CHECK-LABEL: v2i32m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0xffffffffffffffff
; CHECK-NEXT: mov v0.s[1], w1
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT: ret
%v = insertelement <2 x i32> <i32 -1, i32 undef>, i32 %s, i32 1
ret <2 x i32> %v
}
define <4 x i32> @v4i32m(i32 %t, i32 %s) nounwind {
; CHECK-LABEL: v4i32m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0xffffffffffffffff
; CHECK-NEXT: mov v0.s[3], w1
; CHECK-NEXT: ret
%v = insertelement <4 x i32> <i32 -1, i32 -1, i32 -1, i32 undef>, i32 %s, i32 3
ret <4 x i32> %v
}
define <2 x i64> @v2i64m(i64 %t, i64 %s) nounwind {
; CHECK-LABEL: v2i64m:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2d, #0xffffffffffffffff
; CHECK-NEXT: mov v0.d[1], x1
; CHECK-NEXT: ret
%v = insertelement <2 x i64> <i64 -1, i64 undef>, i64 %s, i32 1
ret <2 x i64> %v
}
; Check that building up a vector w/ some constants initializes efficiently.
define void @v8i8st(<8 x i8>* %p, i8 %s) nounwind {
; CHECK-LABEL: v8i8st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.8b, #1
; CHECK-NEXT: mov v0.b[7], w1
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
%v = insertelement <8 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 undef>, i8 %s, i32 7
store <8 x i8> %v, <8 x i8>* %p, align 8
ret void
}
define void @v16i8st(<16 x i8>* %p, i8 %s) nounwind {
; CHECK-LABEL: v16i8st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.16b, #128
; CHECK-NEXT: mov v0.b[15], w1
; CHECK-NEXT: str q0, [x0]
; CHECK-NEXT: ret
%v = insertelement <16 x i8> <i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 -128, i8 undef>, i8 %s, i32 15
store <16 x i8> %v, <16 x i8>* %p, align 16
ret void
}
define void @v4i16st(<4 x i16>* %p, i16 %s) nounwind {
; CHECK-LABEL: v4i16st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.4h, #85, lsl #8
; CHECK-NEXT: mov v0.h[3], w1
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
%v = insertelement <4 x i16> <i16 21760, i16 21760, i16 21760, i16 undef>, i16 %s, i32 3
store <4 x i16> %v, <4 x i16>* %p, align 8
ret void
}
define void @v8i16st(<8 x i16>* %p, i16 %s) nounwind {
; CHECK-LABEL: v8i16st:
; CHECK: // %bb.0:
; CHECK-NEXT: mvni v0.8h, #85, lsl #8
; CHECK-NEXT: mov v0.h[7], w1
; CHECK-NEXT: str q0, [x0]
; CHECK-NEXT: ret
%v = insertelement <8 x i16> <i16 -21761, i16 -21761, i16 -21761, i16 -21761, i16 -21761, i16 -21761, i16 -21761, i16 undef>, i16 %s, i32 7
store <8 x i16> %v, <8 x i16>* %p, align 16
ret void
}
define void @v2i32st(<2 x i32>* %p, i32 %s) nounwind {
; CHECK-LABEL: v2i32st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.2s, #15, lsl #16
; CHECK-NEXT: mov v0.s[1], w1
; CHECK-NEXT: str d0, [x0]
; CHECK-NEXT: ret
%v = insertelement <2 x i32> <i32 983040, i32 undef>, i32 %s, i32 1
store <2 x i32> %v, <2 x i32>* %p, align 8
ret void
}
define void @v4i32st(<4 x i32>* %p, i32 %s) nounwind {
; CHECK-LABEL: v4i32st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v0.4s, #248, msl #16
; CHECK-NEXT: mov v0.s[3], w1
; CHECK-NEXT: str q0, [x0]
; CHECK-NEXT: ret
%v = insertelement <4 x i32> <i32 16318463, i32 16318463, i32 16318463, i32 undef>, i32 %s, i32 3
store <4 x i32> %v, <4 x i32>* %p, align 16
ret void
}
define void @v2i64st(<2 x i64>* %p, i64 %s) nounwind {
; CHECK-LABEL: v2i64st:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov v0.2d, #-2.00000000
; CHECK-NEXT: mov v0.d[1], x1
; CHECK-NEXT: str q0, [x0]
; CHECK-NEXT: ret
%v = insertelement <2 x i64> <i64 13835058055282163712, i64 undef>, i64 %s, i32 1
store <2 x i64> %v, <2 x i64>* %p, align 16
ret void
}
define void @v2f32st(<2 x float>* %p, float %s) nounwind {
; CHECK-LABEL: v2f32st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v1.2s, #64, lsl #24
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
; CHECK-NEXT: mov v1.s[1], v0.s[0]
; CHECK-NEXT: str d1, [x0]
; CHECK-NEXT: ret
%v = insertelement <2 x float> <float 2.0, float undef>, float %s, i32 1
store <2 x float> %v, <2 x float>* %p, align 8
ret void
}
define void @v4f32st(<4 x float>* %p, float %s) nounwind {
; CHECK-LABEL: v4f32st:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v1.4s, #192, lsl #24
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
; CHECK-NEXT: mov v1.s[3], v0.s[0]
; CHECK-NEXT: str q1, [x0]
; CHECK-NEXT: ret
%v = insertelement <4 x float> <float -2.0, float -2.0, float -2.0, float undef>, float %s, i32 3
store <4 x float> %v, <4 x float>* %p, align 16
ret void
}
define void @v2f64st(<2 x double>* %p, double %s) nounwind {
; CHECK-LABEL: v2f64st:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov v1.2d, #2.00000000
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: mov v1.d[1], v0.d[0]
; CHECK-NEXT: str q1, [x0]
; CHECK-NEXT: ret
%v = insertelement <2 x double> <double 2.0, double undef>, double %s, i32 1
store <2 x double> %v, <2 x double>* %p, align 16
ret void
}
; In this test the illegal type has a preferred alignment greater than the
; stack alignment, that gets reduced to the alignment of a broken down
; legal type.
define <32 x i8> @test_lanex_32xi8(<32 x i8> %a, i32 %x) {
; CHECK-LABEL: test_lanex_32xi8:
; CHECK: // %bb.0:
; CHECK-NEXT: sub sp, sp, #32
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: // kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: and x9, x0, #0x1f
; CHECK-NEXT: mov x8, sp
; CHECK-NEXT: mov w10, #30
; CHECK-NEXT: stp q0, q1, [sp]
; CHECK-NEXT: strb w10, [x8, x9]
; CHECK-NEXT: ldp q0, q1, [sp], #32
; CHECK-NEXT: ret
%b = insertelement <32 x i8> %a, i8 30, i32 %x
ret <32 x i8> %b
}
|
