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
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s | FileCheck %s
declare { <vscale x 1 x i8>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i8(<vscale x 1 x i8>, <vscale x 1 x i8>)
define <vscale x 1 x i8> @smulo_nxv1i8(<vscale x 1 x i8> %x, <vscale x 1 x i8> %y) {
; CHECK-LABEL: smulo_nxv1i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 7
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 1 x i8>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i8(<vscale x 1 x i8> %x, <vscale x 1 x i8> %y)
%b = extractvalue { <vscale x 1 x i8>, <vscale x 1 x i1> } %a, 0
%c = extractvalue { <vscale x 1 x i8>, <vscale x 1 x i1> } %a, 1
%d = select <vscale x 1 x i1> %c, <vscale x 1 x i8> zeroinitializer, <vscale x 1 x i8> %b
ret <vscale x 1 x i8> %d
}
declare { <vscale x 2 x i8>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i8>)
define <vscale x 2 x i8> @smulo_nxv2i8(<vscale x 2 x i8> %x, <vscale x 2 x i8> %y) {
; CHECK-LABEL: smulo_nxv2i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 7
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 2 x i8>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i8(<vscale x 2 x i8> %x, <vscale x 2 x i8> %y)
%b = extractvalue { <vscale x 2 x i8>, <vscale x 2 x i1> } %a, 0
%c = extractvalue { <vscale x 2 x i8>, <vscale x 2 x i1> } %a, 1
%d = select <vscale x 2 x i1> %c, <vscale x 2 x i8> zeroinitializer, <vscale x 2 x i8> %b
ret <vscale x 2 x i8> %d
}
declare { <vscale x 4 x i8>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
define <vscale x 4 x i8> @smulo_nxv4i8(<vscale x 4 x i8> %x, <vscale x 4 x i8> %y) {
; CHECK-LABEL: smulo_nxv4i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 7
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 4 x i8>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i8(<vscale x 4 x i8> %x, <vscale x 4 x i8> %y)
%b = extractvalue { <vscale x 4 x i8>, <vscale x 4 x i1> } %a, 0
%c = extractvalue { <vscale x 4 x i8>, <vscale x 4 x i1> } %a, 1
%d = select <vscale x 4 x i1> %c, <vscale x 4 x i8> zeroinitializer, <vscale x 4 x i8> %b
ret <vscale x 4 x i8> %d
}
declare { <vscale x 8 x i8>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
define <vscale x 8 x i8> @smulo_nxv8i8(<vscale x 8 x i8> %x, <vscale x 8 x i8> %y) {
; CHECK-LABEL: smulo_nxv8i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 7
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 8 x i8>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i8(<vscale x 8 x i8> %x, <vscale x 8 x i8> %y)
%b = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i1> } %a, 0
%c = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i1> } %a, 1
%d = select <vscale x 8 x i1> %c, <vscale x 8 x i8> zeroinitializer, <vscale x 8 x i8> %b
ret <vscale x 8 x i8> %d
}
declare { <vscale x 16 x i8>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
define <vscale x 16 x i8> @smulo_nxv16i8(<vscale x 16 x i8> %x, <vscale x 16 x i8> %y) {
; CHECK-LABEL: smulo_nxv16i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, mu
; CHECK-NEXT: vmulh.vv v12, v8, v10
; CHECK-NEXT: vmul.vv v8, v8, v10
; CHECK-NEXT: vsra.vi v10, v8, 7
; CHECK-NEXT: vmsne.vv v0, v12, v10
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 16 x i8>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i8(<vscale x 16 x i8> %x, <vscale x 16 x i8> %y)
%b = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i1> } %a, 0
%c = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i1> } %a, 1
%d = select <vscale x 16 x i1> %c, <vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> %b
ret <vscale x 16 x i8> %d
}
declare { <vscale x 32 x i8>, <vscale x 32 x i1> } @llvm.smul.with.overflow.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>)
define <vscale x 32 x i8> @smulo_nxv32i8(<vscale x 32 x i8> %x, <vscale x 32 x i8> %y) {
; CHECK-LABEL: smulo_nxv32i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m4, ta, mu
; CHECK-NEXT: vmulh.vv v16, v8, v12
; CHECK-NEXT: vmul.vv v8, v8, v12
; CHECK-NEXT: vsra.vi v12, v8, 7
; CHECK-NEXT: vmsne.vv v0, v16, v12
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 32 x i8>, <vscale x 32 x i1> } @llvm.smul.with.overflow.nxv32i8(<vscale x 32 x i8> %x, <vscale x 32 x i8> %y)
%b = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i1> } %a, 0
%c = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i1> } %a, 1
%d = select <vscale x 32 x i1> %c, <vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> %b
ret <vscale x 32 x i8> %d
}
declare { <vscale x 64 x i8>, <vscale x 64 x i1> } @llvm.smul.with.overflow.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>)
define <vscale x 64 x i8> @smulo_nxv64i8(<vscale x 64 x i8> %x, <vscale x 64 x i8> %y) {
; CHECK-LABEL: smulo_nxv64i8:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, mu
; CHECK-NEXT: vmulh.vv v24, v8, v16
; CHECK-NEXT: vmul.vv v8, v8, v16
; CHECK-NEXT: vsra.vi v16, v8, 7
; CHECK-NEXT: vmsne.vv v0, v24, v16
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 64 x i8>, <vscale x 64 x i1> } @llvm.smul.with.overflow.nxv64i8(<vscale x 64 x i8> %x, <vscale x 64 x i8> %y)
%b = extractvalue { <vscale x 64 x i8>, <vscale x 64 x i1> } %a, 0
%c = extractvalue { <vscale x 64 x i8>, <vscale x 64 x i1> } %a, 1
%d = select <vscale x 64 x i1> %c, <vscale x 64 x i8> zeroinitializer, <vscale x 64 x i8> %b
ret <vscale x 64 x i8> %d
}
declare { <vscale x 1 x i16>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i16(<vscale x 1 x i16>, <vscale x 1 x i16>)
define <vscale x 1 x i16> @smulo_nxv1i16(<vscale x 1 x i16> %x, <vscale x 1 x i16> %y) {
; CHECK-LABEL: smulo_nxv1i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 15
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 1 x i16>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i16(<vscale x 1 x i16> %x, <vscale x 1 x i16> %y)
%b = extractvalue { <vscale x 1 x i16>, <vscale x 1 x i1> } %a, 0
%c = extractvalue { <vscale x 1 x i16>, <vscale x 1 x i1> } %a, 1
%d = select <vscale x 1 x i1> %c, <vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> %b
ret <vscale x 1 x i16> %d
}
declare { <vscale x 2 x i16>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
define <vscale x 2 x i16> @smulo_nxv2i16(<vscale x 2 x i16> %x, <vscale x 2 x i16> %y) {
; CHECK-LABEL: smulo_nxv2i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 15
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 2 x i16>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i16(<vscale x 2 x i16> %x, <vscale x 2 x i16> %y)
%b = extractvalue { <vscale x 2 x i16>, <vscale x 2 x i1> } %a, 0
%c = extractvalue { <vscale x 2 x i16>, <vscale x 2 x i1> } %a, 1
%d = select <vscale x 2 x i1> %c, <vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> %b
ret <vscale x 2 x i16> %d
}
declare { <vscale x 4 x i16>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
define <vscale x 4 x i16> @smulo_nxv4i16(<vscale x 4 x i16> %x, <vscale x 4 x i16> %y) {
; CHECK-LABEL: smulo_nxv4i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 15
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 4 x i16>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i16(<vscale x 4 x i16> %x, <vscale x 4 x i16> %y)
%b = extractvalue { <vscale x 4 x i16>, <vscale x 4 x i1> } %a, 0
%c = extractvalue { <vscale x 4 x i16>, <vscale x 4 x i1> } %a, 1
%d = select <vscale x 4 x i1> %c, <vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> %b
ret <vscale x 4 x i16> %d
}
declare { <vscale x 8 x i16>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
define <vscale x 8 x i16> @smulo_nxv8i16(<vscale x 8 x i16> %x, <vscale x 8 x i16> %y) {
; CHECK-LABEL: smulo_nxv8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, mu
; CHECK-NEXT: vmulh.vv v12, v8, v10
; CHECK-NEXT: vmul.vv v8, v8, v10
; CHECK-NEXT: vsra.vi v10, v8, 15
; CHECK-NEXT: vmsne.vv v0, v12, v10
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 8 x i16>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i16(<vscale x 8 x i16> %x, <vscale x 8 x i16> %y)
%b = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i1> } %a, 0
%c = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i1> } %a, 1
%d = select <vscale x 8 x i1> %c, <vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> %b
ret <vscale x 8 x i16> %d
}
declare { <vscale x 16 x i16>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>)
define <vscale x 16 x i16> @smulo_nxv16i16(<vscale x 16 x i16> %x, <vscale x 16 x i16> %y) {
; CHECK-LABEL: smulo_nxv16i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, mu
; CHECK-NEXT: vmulh.vv v16, v8, v12
; CHECK-NEXT: vmul.vv v8, v8, v12
; CHECK-NEXT: vsra.vi v12, v8, 15
; CHECK-NEXT: vmsne.vv v0, v16, v12
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 16 x i16>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i16(<vscale x 16 x i16> %x, <vscale x 16 x i16> %y)
%b = extractvalue { <vscale x 16 x i16>, <vscale x 16 x i1> } %a, 0
%c = extractvalue { <vscale x 16 x i16>, <vscale x 16 x i1> } %a, 1
%d = select <vscale x 16 x i1> %c, <vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> %b
ret <vscale x 16 x i16> %d
}
declare { <vscale x 32 x i16>, <vscale x 32 x i1> } @llvm.smul.with.overflow.nxv32i16(<vscale x 32 x i16>, <vscale x 32 x i16>)
define <vscale x 32 x i16> @smulo_nxv32i16(<vscale x 32 x i16> %x, <vscale x 32 x i16> %y) {
; CHECK-LABEL: smulo_nxv32i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, mu
; CHECK-NEXT: vmulh.vv v24, v8, v16
; CHECK-NEXT: vmul.vv v8, v8, v16
; CHECK-NEXT: vsra.vi v16, v8, 15
; CHECK-NEXT: vmsne.vv v0, v24, v16
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 32 x i16>, <vscale x 32 x i1> } @llvm.smul.with.overflow.nxv32i16(<vscale x 32 x i16> %x, <vscale x 32 x i16> %y)
%b = extractvalue { <vscale x 32 x i16>, <vscale x 32 x i1> } %a, 0
%c = extractvalue { <vscale x 32 x i16>, <vscale x 32 x i1> } %a, 1
%d = select <vscale x 32 x i1> %c, <vscale x 32 x i16> zeroinitializer, <vscale x 32 x i16> %b
ret <vscale x 32 x i16> %d
}
declare { <vscale x 1 x i32>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i32(<vscale x 1 x i32>, <vscale x 1 x i32>)
define <vscale x 1 x i32> @smulo_nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y) {
; CHECK-LABEL: smulo_nxv1i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 31
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 1 x i32>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y)
%b = extractvalue { <vscale x 1 x i32>, <vscale x 1 x i1> } %a, 0
%c = extractvalue { <vscale x 1 x i32>, <vscale x 1 x i1> } %a, 1
%d = select <vscale x 1 x i1> %c, <vscale x 1 x i32> zeroinitializer, <vscale x 1 x i32> %b
ret <vscale x 1 x i32> %d
}
declare { <vscale x 2 x i32>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
define <vscale x 2 x i32> @smulo_nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y) {
; CHECK-LABEL: smulo_nxv2i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: vsra.vi v9, v8, 31
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 2 x i32>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y)
%b = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i1> } %a, 0
%c = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i1> } %a, 1
%d = select <vscale x 2 x i1> %c, <vscale x 2 x i32> zeroinitializer, <vscale x 2 x i32> %b
ret <vscale x 2 x i32> %d
}
declare { <vscale x 4 x i32>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
define <vscale x 4 x i32> @smulo_nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) {
; CHECK-LABEL: smulo_nxv4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, mu
; CHECK-NEXT: vmulh.vv v12, v8, v10
; CHECK-NEXT: vmul.vv v8, v8, v10
; CHECK-NEXT: vsra.vi v10, v8, 31
; CHECK-NEXT: vmsne.vv v0, v12, v10
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 4 x i32>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y)
%b = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i1> } %a, 0
%c = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i1> } %a, 1
%d = select <vscale x 4 x i1> %c, <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> %b
ret <vscale x 4 x i32> %d
}
declare { <vscale x 8 x i32>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
define <vscale x 8 x i32> @smulo_nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %y) {
; CHECK-LABEL: smulo_nxv8i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, mu
; CHECK-NEXT: vmulh.vv v16, v8, v12
; CHECK-NEXT: vmul.vv v8, v8, v12
; CHECK-NEXT: vsra.vi v12, v8, 31
; CHECK-NEXT: vmsne.vv v0, v16, v12
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 8 x i32>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %y)
%b = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i1> } %a, 0
%c = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i1> } %a, 1
%d = select <vscale x 8 x i1> %c, <vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> %b
ret <vscale x 8 x i32> %d
}
declare { <vscale x 16 x i32>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i32(<vscale x 16 x i32>, <vscale x 16 x i32>)
define <vscale x 16 x i32> @smulo_nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y) {
; CHECK-LABEL: smulo_nxv16i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, mu
; CHECK-NEXT: vmulh.vv v24, v8, v16
; CHECK-NEXT: vmul.vv v8, v8, v16
; CHECK-NEXT: vsra.vi v16, v8, 31
; CHECK-NEXT: vmsne.vv v0, v24, v16
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 16 x i32>, <vscale x 16 x i1> } @llvm.smul.with.overflow.nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y)
%b = extractvalue { <vscale x 16 x i32>, <vscale x 16 x i1> } %a, 0
%c = extractvalue { <vscale x 16 x i32>, <vscale x 16 x i1> } %a, 1
%d = select <vscale x 16 x i1> %c, <vscale x 16 x i32> zeroinitializer, <vscale x 16 x i32> %b
ret <vscale x 16 x i32> %d
}
declare { <vscale x 1 x i64>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
define <vscale x 1 x i64> @smulo_nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y) {
; CHECK-LABEL: smulo_nxv1i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, mu
; CHECK-NEXT: vmulh.vv v10, v8, v9
; CHECK-NEXT: vmul.vv v8, v8, v9
; CHECK-NEXT: li a0, 63
; CHECK-NEXT: vsra.vx v9, v8, a0
; CHECK-NEXT: vmsne.vv v0, v10, v9
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 1 x i64>, <vscale x 1 x i1> } @llvm.smul.with.overflow.nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y)
%b = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i1> } %a, 0
%c = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i1> } %a, 1
%d = select <vscale x 1 x i1> %c, <vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> %b
ret <vscale x 1 x i64> %d
}
declare { <vscale x 2 x i64>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
define <vscale x 2 x i64> @smulo_nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) {
; CHECK-LABEL: smulo_nxv2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, mu
; CHECK-NEXT: vmulh.vv v12, v8, v10
; CHECK-NEXT: vmul.vv v8, v8, v10
; CHECK-NEXT: li a0, 63
; CHECK-NEXT: vsra.vx v10, v8, a0
; CHECK-NEXT: vmsne.vv v0, v12, v10
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 2 x i64>, <vscale x 2 x i1> } @llvm.smul.with.overflow.nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y)
%b = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i1> } %a, 0
%c = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i1> } %a, 1
%d = select <vscale x 2 x i1> %c, <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> %b
ret <vscale x 2 x i64> %d
}
declare { <vscale x 4 x i64>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
define <vscale x 4 x i64> @smulo_nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y) {
; CHECK-LABEL: smulo_nxv4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m4, ta, mu
; CHECK-NEXT: vmulh.vv v16, v8, v12
; CHECK-NEXT: vmul.vv v8, v8, v12
; CHECK-NEXT: li a0, 63
; CHECK-NEXT: vsra.vx v12, v8, a0
; CHECK-NEXT: vmsne.vv v0, v16, v12
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 4 x i64>, <vscale x 4 x i1> } @llvm.smul.with.overflow.nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y)
%b = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i1> } %a, 0
%c = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i1> } %a, 1
%d = select <vscale x 4 x i1> %c, <vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> %b
ret <vscale x 4 x i64> %d
}
declare { <vscale x 8 x i64>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i64(<vscale x 8 x i64>, <vscale x 8 x i64>)
define <vscale x 8 x i64> @smulo_nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y) {
; CHECK-LABEL: smulo_nxv8i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e64, m8, ta, mu
; CHECK-NEXT: vmulh.vv v24, v8, v16
; CHECK-NEXT: vmul.vv v8, v8, v16
; CHECK-NEXT: li a0, 63
; CHECK-NEXT: vsra.vx v16, v8, a0
; CHECK-NEXT: vmsne.vv v0, v24, v16
; CHECK-NEXT: vmerge.vim v8, v8, 0, v0
; CHECK-NEXT: ret
%a = call { <vscale x 8 x i64>, <vscale x 8 x i1> } @llvm.smul.with.overflow.nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y)
%b = extractvalue { <vscale x 8 x i64>, <vscale x 8 x i1> } %a, 0
%c = extractvalue { <vscale x 8 x i64>, <vscale x 8 x i1> } %a, 1
%d = select <vscale x 8 x i1> %c, <vscale x 8 x i64> zeroinitializer, <vscale x 8 x i64> %b
ret <vscale x 8 x i64> %d
}
|
