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
|
; 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
declare {<1 x i32>, <1 x i1>} @llvm.uadd.with.overflow.v1i32(<1 x i32>, <1 x i32>)
declare {<2 x i32>, <2 x i1>} @llvm.uadd.with.overflow.v2i32(<2 x i32>, <2 x i32>)
declare {<3 x i32>, <3 x i1>} @llvm.uadd.with.overflow.v3i32(<3 x i32>, <3 x i32>)
declare {<4 x i32>, <4 x i1>} @llvm.uadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
declare {<6 x i32>, <6 x i1>} @llvm.uadd.with.overflow.v6i32(<6 x i32>, <6 x i32>)
declare {<8 x i32>, <8 x i1>} @llvm.uadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)
declare {<16 x i8>, <16 x i1>} @llvm.uadd.with.overflow.v16i8(<16 x i8>, <16 x i8>)
declare {<8 x i16>, <8 x i1>} @llvm.uadd.with.overflow.v8i16(<8 x i16>, <8 x i16>)
declare {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
declare {<4 x i24>, <4 x i1>} @llvm.uadd.with.overflow.v4i24(<4 x i24>, <4 x i24>)
declare {<4 x i1>, <4 x i1>} @llvm.uadd.with.overflow.v4i1(<4 x i1>, <4 x i1>)
declare {<2 x i128>, <2 x i1>} @llvm.uadd.with.overflow.v2i128(<2 x i128>, <2 x i128>)
define <1 x i32> @uaddo_v1i32(<1 x i32> %a0, <1 x i32> %a1, <1 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v1i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add v1.2s, v0.2s, v1.2s
; CHECK-NEXT: cmhi v0.2s, v0.2s, v1.2s
; CHECK-NEXT: str s1, [x0]
; CHECK-NEXT: ret
%t = call {<1 x i32>, <1 x i1>} @llvm.uadd.with.overflow.v1i32(<1 x i32> %a0, <1 x i32> %a1)
%val = extractvalue {<1 x i32>, <1 x i1>} %t, 0
%obit = extractvalue {<1 x i32>, <1 x i1>} %t, 1
%res = sext <1 x i1> %obit to <1 x i32>
store <1 x i32> %val, <1 x i32>* %p2
ret <1 x i32> %res
}
define <2 x i32> @uaddo_v2i32(<2 x i32> %a0, <2 x i32> %a1, <2 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add v1.2s, v0.2s, v1.2s
; CHECK-NEXT: cmhi v0.2s, v0.2s, v1.2s
; CHECK-NEXT: str d1, [x0]
; CHECK-NEXT: ret
%t = call {<2 x i32>, <2 x i1>} @llvm.uadd.with.overflow.v2i32(<2 x i32> %a0, <2 x i32> %a1)
%val = extractvalue {<2 x i32>, <2 x i1>} %t, 0
%obit = extractvalue {<2 x i32>, <2 x i1>} %t, 1
%res = sext <2 x i1> %obit to <2 x i32>
store <2 x i32> %val, <2 x i32>* %p2
ret <2 x i32> %res
}
define <3 x i32> @uaddo_v3i32(<3 x i32> %a0, <3 x i32> %a1, <3 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v3i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add v1.4s, v0.4s, v1.4s
; CHECK-NEXT: add x8, x0, #8
; CHECK-NEXT: cmhi v0.4s, v0.4s, v1.4s
; CHECK-NEXT: st1 { v1.s }[2], [x8]
; CHECK-NEXT: str d1, [x0]
; CHECK-NEXT: ret
%t = call {<3 x i32>, <3 x i1>} @llvm.uadd.with.overflow.v3i32(<3 x i32> %a0, <3 x i32> %a1)
%val = extractvalue {<3 x i32>, <3 x i1>} %t, 0
%obit = extractvalue {<3 x i32>, <3 x i1>} %t, 1
%res = sext <3 x i1> %obit to <3 x i32>
store <3 x i32> %val, <3 x i32>* %p2
ret <3 x i32> %res
}
define <4 x i32> @uaddo_v4i32(<4 x i32> %a0, <4 x i32> %a1, <4 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v4i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add v1.4s, v0.4s, v1.4s
; CHECK-NEXT: cmhi v0.4s, v0.4s, v1.4s
; CHECK-NEXT: str q1, [x0]
; CHECK-NEXT: ret
%t = call {<4 x i32>, <4 x i1>} @llvm.uadd.with.overflow.v4i32(<4 x i32> %a0, <4 x i32> %a1)
%val = extractvalue {<4 x i32>, <4 x i1>} %t, 0
%obit = extractvalue {<4 x i32>, <4 x i1>} %t, 1
%res = sext <4 x i1> %obit to <4 x i32>
store <4 x i32> %val, <4 x i32>* %p2
ret <4 x i32> %res
}
define <6 x i32> @uaddo_v6i32(<6 x i32> %a0, <6 x i32> %a1, <6 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v6i32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov s0, w6
; CHECK-NEXT: fmov s1, w0
; CHECK-NEXT: mov x8, sp
; CHECK-NEXT: add x9, sp, #8
; CHECK-NEXT: ldr s2, [sp, #16]
; CHECK-NEXT: fmov s3, w4
; CHECK-NEXT: mov v0.s[1], w7
; CHECK-NEXT: mov v1.s[1], w1
; CHECK-NEXT: mov v3.s[1], w5
; CHECK-NEXT: ld1 { v0.s }[2], [x8]
; CHECK-NEXT: add x8, sp, #24
; CHECK-NEXT: mov v1.s[2], w2
; CHECK-NEXT: ld1 { v2.s }[1], [x8]
; CHECK-NEXT: ld1 { v0.s }[3], [x9]
; CHECK-NEXT: mov v1.s[3], w3
; CHECK-NEXT: ldr x8, [sp, #32]
; CHECK-NEXT: add v2.4s, v3.4s, v2.4s
; CHECK-NEXT: add v0.4s, v1.4s, v0.4s
; CHECK-NEXT: cmhi v3.4s, v3.4s, v2.4s
; CHECK-NEXT: str d2, [x8, #16]
; CHECK-NEXT: cmhi v1.4s, v1.4s, v0.4s
; CHECK-NEXT: str q0, [x8]
; CHECK-NEXT: mov w5, v3.s[1]
; CHECK-NEXT: fmov w4, s3
; CHECK-NEXT: mov w1, v1.s[1]
; CHECK-NEXT: mov w2, v1.s[2]
; CHECK-NEXT: mov w3, v1.s[3]
; CHECK-NEXT: fmov w0, s1
; CHECK-NEXT: ret
%t = call {<6 x i32>, <6 x i1>} @llvm.uadd.with.overflow.v6i32(<6 x i32> %a0, <6 x i32> %a1)
%val = extractvalue {<6 x i32>, <6 x i1>} %t, 0
%obit = extractvalue {<6 x i32>, <6 x i1>} %t, 1
%res = sext <6 x i1> %obit to <6 x i32>
store <6 x i32> %val, <6 x i32>* %p2
ret <6 x i32> %res
}
define <8 x i32> @uaddo_v8i32(<8 x i32> %a0, <8 x i32> %a1, <8 x i32>* %p2) nounwind {
; CHECK-LABEL: uaddo_v8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add v3.4s, v1.4s, v3.4s
; CHECK-NEXT: add v2.4s, v0.4s, v2.4s
; CHECK-NEXT: cmhi v1.4s, v1.4s, v3.4s
; CHECK-NEXT: cmhi v0.4s, v0.4s, v2.4s
; CHECK-NEXT: stp q2, q3, [x0]
; CHECK-NEXT: ret
%t = call {<8 x i32>, <8 x i1>} @llvm.uadd.with.overflow.v8i32(<8 x i32> %a0, <8 x i32> %a1)
%val = extractvalue {<8 x i32>, <8 x i1>} %t, 0
%obit = extractvalue {<8 x i32>, <8 x i1>} %t, 1
%res = sext <8 x i1> %obit to <8 x i32>
store <8 x i32> %val, <8 x i32>* %p2
ret <8 x i32> %res
}
define <16 x i32> @uaddo_v16i8(<16 x i8> %a0, <16 x i8> %a1, <16 x i8>* %p2) nounwind {
; CHECK-LABEL: uaddo_v16i8:
; CHECK: // %bb.0:
; CHECK-NEXT: add v4.16b, v0.16b, v1.16b
; CHECK-NEXT: cmhi v0.16b, v0.16b, v4.16b
; CHECK-NEXT: str q4, [x0]
; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: zip1 v2.8b, v0.8b, v0.8b
; CHECK-NEXT: zip2 v0.8b, v0.8b, v0.8b
; CHECK-NEXT: ushll v2.4s, v2.4h, #0
; CHECK-NEXT: zip1 v3.8b, v1.8b, v0.8b
; CHECK-NEXT: zip2 v1.8b, v1.8b, v0.8b
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v2.4s, v2.4s, #31
; CHECK-NEXT: ushll v3.4s, v3.4h, #0
; CHECK-NEXT: ushll v1.4s, v1.4h, #0
; CHECK-NEXT: shl v5.4s, v0.4s, #31
; CHECK-NEXT: cmlt v0.4s, v2.4s, #0
; CHECK-NEXT: shl v3.4s, v3.4s, #31
; CHECK-NEXT: shl v6.4s, v1.4s, #31
; CHECK-NEXT: cmlt v1.4s, v5.4s, #0
; CHECK-NEXT: cmlt v2.4s, v3.4s, #0
; CHECK-NEXT: cmlt v3.4s, v6.4s, #0
; CHECK-NEXT: ret
%t = call {<16 x i8>, <16 x i1>} @llvm.uadd.with.overflow.v16i8(<16 x i8> %a0, <16 x i8> %a1)
%val = extractvalue {<16 x i8>, <16 x i1>} %t, 0
%obit = extractvalue {<16 x i8>, <16 x i1>} %t, 1
%res = sext <16 x i1> %obit to <16 x i32>
store <16 x i8> %val, <16 x i8>* %p2
ret <16 x i32> %res
}
define <8 x i32> @uaddo_v8i16(<8 x i16> %a0, <8 x i16> %a1, <8 x i16>* %p2) nounwind {
; CHECK-LABEL: uaddo_v8i16:
; CHECK: // %bb.0:
; CHECK-NEXT: add v2.8h, v0.8h, v1.8h
; CHECK-NEXT: cmhi v0.8h, v0.8h, v2.8h
; CHECK-NEXT: str q2, [x0]
; CHECK-NEXT: xtn v0.8b, v0.8h
; CHECK-NEXT: zip1 v1.8b, v0.8b, v0.8b
; CHECK-NEXT: zip2 v0.8b, v0.8b, v0.8b
; CHECK-NEXT: ushll v1.4s, v1.4h, #0
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v1.4s, v1.4s, #31
; CHECK-NEXT: shl v3.4s, v0.4s, #31
; CHECK-NEXT: cmlt v0.4s, v1.4s, #0
; CHECK-NEXT: cmlt v1.4s, v3.4s, #0
; CHECK-NEXT: ret
%t = call {<8 x i16>, <8 x i1>} @llvm.uadd.with.overflow.v8i16(<8 x i16> %a0, <8 x i16> %a1)
%val = extractvalue {<8 x i16>, <8 x i1>} %t, 0
%obit = extractvalue {<8 x i16>, <8 x i1>} %t, 1
%res = sext <8 x i1> %obit to <8 x i32>
store <8 x i16> %val, <8 x i16>* %p2
ret <8 x i32> %res
}
define <2 x i32> @uaddo_v2i64(<2 x i64> %a0, <2 x i64> %a1, <2 x i64>* %p2) nounwind {
; CHECK-LABEL: uaddo_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: add v1.2d, v0.2d, v1.2d
; CHECK-NEXT: cmhi v0.2d, v0.2d, v1.2d
; CHECK-NEXT: str q1, [x0]
; CHECK-NEXT: xtn v0.2s, v0.2d
; CHECK-NEXT: ret
%t = call {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64> %a0, <2 x i64> %a1)
%val = extractvalue {<2 x i64>, <2 x i1>} %t, 0
%obit = extractvalue {<2 x i64>, <2 x i1>} %t, 1
%res = sext <2 x i1> %obit to <2 x i32>
store <2 x i64> %val, <2 x i64>* %p2
ret <2 x i32> %res
}
define <4 x i32> @uaddo_v4i24(<4 x i24> %a0, <4 x i24> %a1, <4 x i24>* %p2) nounwind {
; CHECK-LABEL: uaddo_v4i24:
; CHECK: // %bb.0:
; CHECK-NEXT: bic v1.4s, #255, lsl #24
; CHECK-NEXT: bic v0.4s, #255, lsl #24
; CHECK-NEXT: add v0.4s, v0.4s, v1.4s
; CHECK-NEXT: mov v1.16b, v0.16b
; CHECK-NEXT: mov w8, v0.s[3]
; CHECK-NEXT: mov w9, v0.s[2]
; CHECK-NEXT: mov w10, v0.s[1]
; CHECK-NEXT: fmov w11, s0
; CHECK-NEXT: bic v1.4s, #255, lsl #24
; CHECK-NEXT: sturh w8, [x0, #9]
; CHECK-NEXT: lsr w8, w8, #16
; CHECK-NEXT: strh w9, [x0, #6]
; CHECK-NEXT: sturh w10, [x0, #3]
; CHECK-NEXT: lsr w9, w9, #16
; CHECK-NEXT: strh w11, [x0]
; CHECK-NEXT: cmeq v1.4s, v1.4s, v0.4s
; CHECK-NEXT: strb w8, [x0, #11]
; CHECK-NEXT: lsr w8, w10, #16
; CHECK-NEXT: lsr w10, w11, #16
; CHECK-NEXT: strb w9, [x0, #8]
; CHECK-NEXT: mvn v0.16b, v1.16b
; CHECK-NEXT: strb w8, [x0, #5]
; CHECK-NEXT: strb w10, [x0, #2]
; CHECK-NEXT: ret
%t = call {<4 x i24>, <4 x i1>} @llvm.uadd.with.overflow.v4i24(<4 x i24> %a0, <4 x i24> %a1)
%val = extractvalue {<4 x i24>, <4 x i1>} %t, 0
%obit = extractvalue {<4 x i24>, <4 x i1>} %t, 1
%res = sext <4 x i1> %obit to <4 x i32>
store <4 x i24> %val, <4 x i24>* %p2
ret <4 x i32> %res
}
define <4 x i32> @uaddo_v4i1(<4 x i1> %a0, <4 x i1> %a1, <4 x i1>* %p2) nounwind {
; CHECK-LABEL: uaddo_v4i1:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v2.4h, #1
; CHECK-NEXT: and v1.8b, v1.8b, v2.8b
; CHECK-NEXT: and v0.8b, v0.8b, v2.8b
; CHECK-NEXT: add v0.4h, v0.4h, v1.4h
; CHECK-NEXT: and v1.8b, v0.8b, v2.8b
; CHECK-NEXT: umov w8, v0.h[1]
; CHECK-NEXT: umov w9, v0.h[2]
; CHECK-NEXT: umov w10, v0.h[0]
; CHECK-NEXT: umov w11, v0.h[3]
; CHECK-NEXT: cmeq v1.4h, v1.4h, v0.4h
; CHECK-NEXT: and w8, w8, #0x1
; CHECK-NEXT: and w9, w9, #0x1
; CHECK-NEXT: bfi w10, w8, #1, #1
; CHECK-NEXT: mvn v1.8b, v1.8b
; CHECK-NEXT: bfi w10, w9, #2, #1
; CHECK-NEXT: bfi w10, w11, #3, #29
; CHECK-NEXT: and w8, w10, #0xf
; CHECK-NEXT: sshll v0.4s, v1.4h, #0
; CHECK-NEXT: strb w8, [x0]
; CHECK-NEXT: ret
%t = call {<4 x i1>, <4 x i1>} @llvm.uadd.with.overflow.v4i1(<4 x i1> %a0, <4 x i1> %a1)
%val = extractvalue {<4 x i1>, <4 x i1>} %t, 0
%obit = extractvalue {<4 x i1>, <4 x i1>} %t, 1
%res = sext <4 x i1> %obit to <4 x i32>
store <4 x i1> %val, <4 x i1>* %p2
ret <4 x i32> %res
}
define <2 x i32> @uaddo_v2i128(<2 x i128> %a0, <2 x i128> %a1, <2 x i128>* %p2) nounwind {
; CHECK-LABEL: uaddo_v2i128:
; CHECK: // %bb.0:
; CHECK-NEXT: adds x8, x2, x6
; CHECK-NEXT: adcs x9, x3, x7
; CHECK-NEXT: cmp x8, x2
; CHECK-NEXT: cset w10, lo
; CHECK-NEXT: cmp x9, x3
; CHECK-NEXT: cset w11, lo
; CHECK-NEXT: csel w10, w10, w11, eq
; CHECK-NEXT: adds x11, x0, x4
; CHECK-NEXT: adcs x12, x1, x5
; CHECK-NEXT: cmp x11, x0
; CHECK-NEXT: cset w13, lo
; CHECK-NEXT: cmp x12, x1
; CHECK-NEXT: cset w14, lo
; CHECK-NEXT: csel w13, w13, w14, eq
; CHECK-NEXT: fmov s0, w13
; CHECK-NEXT: mov v0.s[1], w10
; CHECK-NEXT: ldr x10, [sp]
; CHECK-NEXT: stp x8, x9, [x10, #16]
; CHECK-NEXT: shl v0.2s, v0.2s, #31
; CHECK-NEXT: stp x11, x12, [x10]
; CHECK-NEXT: cmlt v0.2s, v0.2s, #0
; CHECK-NEXT: ret
%t = call {<2 x i128>, <2 x i1>} @llvm.uadd.with.overflow.v2i128(<2 x i128> %a0, <2 x i128> %a1)
%val = extractvalue {<2 x i128>, <2 x i1>} %t, 0
%obit = extractvalue {<2 x i128>, <2 x i1>} %t, 1
%res = sext <2 x i1> %obit to <2 x i32>
store <2 x i128> %val, <2 x i128>* %p2
ret <2 x i32> %res
}
|
