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
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mcpu=skx -S -passes='loop-vectorize,instcombine,simplifycfg,loop-mssa(licm)' -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize < %s | FileCheck %s -check-prefix=DISABLED_MASKED_STRIDED
; RUN: opt -mcpu=skx -S -passes='loop-vectorize,instcombine,simplifycfg,loop-mssa(licm)' -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses -enable-masked-interleaved-mem-accesses -prefer-predicate-over-epilogue=predicate-dont-vectorize < %s | FileCheck %s -check-prefix=ENABLED_MASKED_STRIDED
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; (1) Interleave-group with factor 4, storing only 2 members out of the 4.
; Check that when we allow masked-memops to support interleave-group with gaps,
; the store is vectorized using a wide masked store, with a 1,1,0,0,1,1,0,0,... mask.
; Check that when we don't allow masked-memops to support interleave-group with gaps,
; the store is scalarized.
; The input IR was generated from this source:
; for(i=0;i<1024;i++){
; points[i*4] = x[i];
; points[i*4 + 1] = y[i];
; }
; (relates to the testcase in PR50566)
; Function Attrs: nofree norecurse nosync nounwind uwtable
define dso_local void @test1(ptr noalias nocapture %points, ptr noalias nocapture readonly %x, ptr noalias nocapture readonly %y) local_unnamed_addr {
; DISABLED_MASKED_STRIDED-LABEL: @test1(
; DISABLED_MASKED_STRIDED-NEXT: entry:
; DISABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; DISABLED_MASKED_STRIDED: vector.body:
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i16>, ptr [[TMP0]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = shl nuw nsw <4 x i64> [[VEC_IND]], <i64 2, i64 2, i64 2, i64 2>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = extractelement <4 x i64> [[TMP1]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = getelementptr inbounds i16, ptr [[POINTS:%.*]], i64 [[TMP2]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[TMP1]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: [[TMP5:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP4]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP6:%.*]] = extractelement <4 x i64> [[TMP1]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP6]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP8:%.*]] = extractelement <4 x i64> [[TMP1]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP8]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP10:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP10]], ptr [[TMP3]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP11:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP11]], ptr [[TMP5]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP12:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP12]], ptr [[TMP7]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP13:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP13]], ptr [[TMP9]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP14:%.*]] = getelementptr inbounds i16, ptr [[Y:%.*]], i64 [[INDEX]]
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i16>, ptr [[TMP14]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP15:%.*]] = or disjoint <4 x i64> [[TMP1]], <i64 1, i64 1, i64 1, i64 1>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP16:%.*]] = extractelement <4 x i64> [[TMP15]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[TMP17:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP16]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP18:%.*]] = extractelement <4 x i64> [[TMP15]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: [[TMP19:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP18]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP20:%.*]] = extractelement <4 x i64> [[TMP15]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP21:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP20]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP22:%.*]] = extractelement <4 x i64> [[TMP15]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: [[TMP23:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP22]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP24:%.*]] = extractelement <4 x i16> [[WIDE_LOAD1]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP24]], ptr [[TMP17]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP25:%.*]] = extractelement <4 x i16> [[WIDE_LOAD1]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP25]], ptr [[TMP19]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP26:%.*]] = extractelement <4 x i16> [[WIDE_LOAD1]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP26]], ptr [[TMP21]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP27:%.*]] = extractelement <4 x i16> [[WIDE_LOAD1]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP27]], ptr [[TMP23]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP28:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP28]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; DISABLED_MASKED_STRIDED: for.end:
; DISABLED_MASKED_STRIDED-NEXT: ret void
;
; ENABLED_MASKED_STRIDED-LABEL: @test1(
; ENABLED_MASKED_STRIDED-NEXT: entry:
; ENABLED_MASKED_STRIDED-NEXT: [[INVARIANT_GEP:%.*]] = getelementptr i8, ptr [[POINTS:%.*]], i64 -2
; ENABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; ENABLED_MASKED_STRIDED: vector.body:
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i16>, ptr [[TMP0]], align 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = shl nuw nsw i64 [[INDEX]], 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = getelementptr inbounds i16, ptr [[Y:%.*]], i64 [[INDEX]]
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i16>, ptr [[TMP2]], align 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = or disjoint i64 [[TMP1]], 1
; ENABLED_MASKED_STRIDED-NEXT: [[GEP:%.*]] = getelementptr i16, ptr [[INVARIANT_GEP]], i64 [[TMP3]]
; ENABLED_MASKED_STRIDED-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <4 x i16> [[WIDE_LOAD]], <4 x i16> [[WIDE_LOAD1]], <16 x i32> <i32 0, i32 4, i32 poison, i32 poison, i32 1, i32 5, i32 poison, i32 poison, i32 2, i32 6, i32 poison, i32 poison, i32 3, i32 7, i32 poison, i32 poison>
; ENABLED_MASKED_STRIDED-NEXT: call void @llvm.masked.store.v16i16.p0(<16 x i16> [[INTERLEAVED_VEC]], ptr [[GEP]], i32 2, <16 x i1> <i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false>)
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; ENABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP4]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; ENABLED_MASKED_STRIDED: for.end:
; ENABLED_MASKED_STRIDED-NEXT: ret void
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i16, ptr %x, i64 %indvars.iv
%0 = load i16, ptr %arrayidx, align 2
%1 = shl nuw nsw i64 %indvars.iv, 2
%arrayidx2 = getelementptr inbounds i16, ptr %points, i64 %1
store i16 %0, ptr %arrayidx2, align 2
%arrayidx4 = getelementptr inbounds i16, ptr %y, i64 %indvars.iv
%2 = load i16, ptr %arrayidx4, align 2
%3 = or disjoint i64 %1, 1
%arrayidx7 = getelementptr inbounds i16, ptr %points, i64 %3
store i16 %2, ptr %arrayidx7, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret void
}
; (2) Same as above, but this time the gaps mask of the store is also And-ed with the
; fold-tail mask. If using masked memops to vectorize interleaved-group with gaps is
; not allowed, the store is scalarized and predicated.
; The input IR was generated from this source:
; for(i=0;i<numPoints;i++){
; points[i*4] = x[i];
; points[i*4 + 1] = y[i];
; }
; Function Attrs: nofree norecurse nosync nounwind uwtable
define dso_local void @test2(ptr noalias nocapture %points, i32 %numPoints, ptr noalias nocapture readonly %x, ptr noalias nocapture readonly %y) local_unnamed_addr {
; DISABLED_MASKED_STRIDED-LABEL: @test2(
; DISABLED_MASKED_STRIDED-NEXT: entry:
; DISABLED_MASKED_STRIDED-NEXT: [[CMP15:%.*]] = icmp sgt i32 [[NUMPOINTS:%.*]], 0
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[CMP15]], label [[VECTOR_PH:%.*]], label [[FOR_END:%.*]]
; DISABLED_MASKED_STRIDED: vector.ph:
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[NUMPOINTS]] to i64
; DISABLED_MASKED_STRIDED-NEXT: [[N_RND_UP:%.*]] = add nuw nsw i64 [[WIDE_TRIP_COUNT]], 3
; DISABLED_MASKED_STRIDED-NEXT: [[N_VEC:%.*]] = and i64 [[N_RND_UP]], 4294967292
; DISABLED_MASKED_STRIDED-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = add nsw i64 [[WIDE_TRIP_COUNT]], -1
; DISABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
; DISABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; DISABLED_MASKED_STRIDED: vector.body:
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE15:%.*]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE15]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = icmp ule <4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr [[TMP1]], i32 2, <4 x i1> [[TMP0]], <4 x i16> poison)
; DISABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = shl nsw <4 x i64> [[VEC_IND]], <i64 2, i64 2, i64 2, i64 2>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = extractelement <4 x i1> [[TMP0]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[TMP2]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[TMP5:%.*]] = getelementptr inbounds i16, ptr [[POINTS:%.*]], i64 [[TMP4]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP6:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP6]], ptr [[TMP5]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE]]
; DISABLED_MASKED_STRIDED: pred.store.continue:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP7:%.*]] = extractelement <4 x i1> [[TMP0]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if1:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP8:%.*]] = extractelement <4 x i64> [[TMP2]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP8]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP10:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP10]], ptr [[TMP9]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE2]]
; DISABLED_MASKED_STRIDED: pred.store.continue2:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP11:%.*]] = extractelement <4 x i1> [[TMP0]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if3:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP12:%.*]] = extractelement <4 x i64> [[TMP2]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP13:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP12]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP14:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP14]], ptr [[TMP13]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE4]]
; DISABLED_MASKED_STRIDED: pred.store.continue4:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP15:%.*]] = extractelement <4 x i1> [[TMP0]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP15]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if5:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP16:%.*]] = extractelement <4 x i64> [[TMP2]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: [[TMP17:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP16]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP18:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP18]], ptr [[TMP17]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE6]]
; DISABLED_MASKED_STRIDED: pred.store.continue6:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP19:%.*]] = getelementptr inbounds i16, ptr [[Y:%.*]], i64 [[INDEX]]
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_MASKED_LOAD7:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr [[TMP19]], i32 2, <4 x i1> [[TMP0]], <4 x i16> poison)
; DISABLED_MASKED_STRIDED-NEXT: [[TMP20:%.*]] = or disjoint <4 x i64> [[TMP2]], <i64 1, i64 1, i64 1, i64 1>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP21:%.*]] = extractelement <4 x i1> [[TMP0]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP21]], label [[PRED_STORE_IF8:%.*]], label [[PRED_STORE_CONTINUE9:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if8:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP22:%.*]] = extractelement <4 x i64> [[TMP20]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[TMP23:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP22]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP24:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD7]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP24]], ptr [[TMP23]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE9]]
; DISABLED_MASKED_STRIDED: pred.store.continue9:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP25:%.*]] = extractelement <4 x i1> [[TMP0]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP25]], label [[PRED_STORE_IF10:%.*]], label [[PRED_STORE_CONTINUE11:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if10:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP26:%.*]] = extractelement <4 x i64> [[TMP20]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: [[TMP27:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP26]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP28:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD7]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP28]], ptr [[TMP27]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE11]]
; DISABLED_MASKED_STRIDED: pred.store.continue11:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP29:%.*]] = extractelement <4 x i1> [[TMP0]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP29]], label [[PRED_STORE_IF12:%.*]], label [[PRED_STORE_CONTINUE13:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if12:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP30:%.*]] = extractelement <4 x i64> [[TMP20]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP31:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP30]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP32:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD7]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP32]], ptr [[TMP31]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE13]]
; DISABLED_MASKED_STRIDED: pred.store.continue13:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP33:%.*]] = extractelement <4 x i1> [[TMP0]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP33]], label [[PRED_STORE_IF14:%.*]], label [[PRED_STORE_CONTINUE15]]
; DISABLED_MASKED_STRIDED: pred.store.if14:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP34:%.*]] = extractelement <4 x i64> [[TMP20]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: [[TMP35:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP34]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP36:%.*]] = extractelement <4 x i16> [[WIDE_MASKED_LOAD7]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP36]], ptr [[TMP35]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE15]]
; DISABLED_MASKED_STRIDED: pred.store.continue15:
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP37:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP37]], label [[FOR_END_LOOPEXIT:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; DISABLED_MASKED_STRIDED: for.end.loopexit:
; DISABLED_MASKED_STRIDED-NEXT: br label [[FOR_END]]
; DISABLED_MASKED_STRIDED: for.end:
; DISABLED_MASKED_STRIDED-NEXT: ret void
;
; ENABLED_MASKED_STRIDED-LABEL: @test2(
; ENABLED_MASKED_STRIDED-NEXT: entry:
; ENABLED_MASKED_STRIDED-NEXT: [[CMP15:%.*]] = icmp sgt i32 [[NUMPOINTS:%.*]], 0
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[CMP15]], label [[VECTOR_PH:%.*]], label [[FOR_END:%.*]]
; ENABLED_MASKED_STRIDED: vector.ph:
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[NUMPOINTS]] to i64
; ENABLED_MASKED_STRIDED-NEXT: [[N_RND_UP:%.*]] = add nuw nsw i64 [[WIDE_TRIP_COUNT]], 3
; ENABLED_MASKED_STRIDED-NEXT: [[N_VEC:%.*]] = and i64 [[N_RND_UP]], 4294967292
; ENABLED_MASKED_STRIDED-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = add nsw i64 [[WIDE_TRIP_COUNT]], -1
; ENABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; ENABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
; ENABLED_MASKED_STRIDED-NEXT: [[INVARIANT_GEP:%.*]] = getelementptr i8, ptr [[POINTS:%.*]], i64 -2
; ENABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; ENABLED_MASKED_STRIDED: vector.body:
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; ENABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
; ENABLED_MASKED_STRIDED-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT1]], <4 x i64> poison, <4 x i32> zeroinitializer
; ENABLED_MASKED_STRIDED-NEXT: [[VEC_IV:%.*]] = or disjoint <4 x i64> [[BROADCAST_SPLAT2]], <i64 0, i64 1, i64 2, i64 3>
; ENABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr [[TMP1]], i32 2, <4 x i1> [[TMP0]], <4 x i16> poison)
; ENABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = shl nsw i64 [[INDEX]], 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = getelementptr inbounds i16, ptr [[Y:%.*]], i64 [[INDEX]]
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_MASKED_LOAD3:%.*]] = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr [[TMP3]], i32 2, <4 x i1> [[TMP0]], <4 x i16> poison)
; ENABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = or disjoint i64 [[TMP2]], 1
; ENABLED_MASKED_STRIDED-NEXT: [[GEP:%.*]] = getelementptr i16, ptr [[INVARIANT_GEP]], i64 [[TMP4]]
; ENABLED_MASKED_STRIDED-NEXT: [[INTERLEAVED_VEC:%.*]] = shufflevector <4 x i16> [[WIDE_MASKED_LOAD]], <4 x i16> [[WIDE_MASKED_LOAD3]], <16 x i32> <i32 0, i32 4, i32 poison, i32 poison, i32 1, i32 5, i32 poison, i32 poison, i32 2, i32 6, i32 poison, i32 poison, i32 3, i32 7, i32 poison, i32 poison>
; ENABLED_MASKED_STRIDED-NEXT: [[INTERLEAVED_MASK:%.*]] = shufflevector <4 x i1> [[TMP0]], <4 x i1> poison, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1, i32 2, i32 2, i32 2, i32 2, i32 3, i32 3, i32 3, i32 3>
; ENABLED_MASKED_STRIDED-NEXT: [[TMP5:%.*]] = and <16 x i1> [[INTERLEAVED_MASK]], <i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false>
; ENABLED_MASKED_STRIDED-NEXT: call void @llvm.masked.store.v16i16.p0(<16 x i16> [[INTERLEAVED_VEC]], ptr [[GEP]], i32 2, <16 x i1> [[TMP5]])
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; ENABLED_MASKED_STRIDED-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP6]], label [[FOR_END_LOOPEXIT:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; ENABLED_MASKED_STRIDED: for.end.loopexit:
; ENABLED_MASKED_STRIDED-NEXT: br label [[FOR_END]]
; ENABLED_MASKED_STRIDED: for.end:
; ENABLED_MASKED_STRIDED-NEXT: ret void
;
entry:
%cmp15 = icmp sgt i32 %numPoints, 0
br i1 %cmp15, label %for.body.preheader, label %for.end
for.body.preheader:
%wide.trip.count = zext i32 %numPoints to i64
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i16, ptr %x, i64 %indvars.iv
%0 = load i16, ptr %arrayidx, align 2
%1 = shl nsw i64 %indvars.iv, 2
%arrayidx2 = getelementptr inbounds i16, ptr %points, i64 %1
store i16 %0, ptr %arrayidx2, align 2
%arrayidx4 = getelementptr inbounds i16, ptr %y, i64 %indvars.iv
%2 = load i16, ptr %arrayidx4, align 2
%3 = or disjoint i64 %1, 1
%arrayidx7 = getelementptr inbounds i16, ptr %points, i64 %3
store i16 %2, ptr %arrayidx7, align 2
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond.not, label %for.end.loopexit, label %for.body
for.end.loopexit:
br label %for.end
for.end:
ret void
}
; (3) Testing a scenario of a conditional store. The gaps mask of the store is also
; And-ed with the condition mask (x[i] > 0).
; If using masked memops to vectorize interleaved-group with gaps is
; not allowed, the store is scalarized and predicated.
; Here the Interleave-group is with factor 3, storing only 1 member out of the 3.
; The input IR was generated from this source:
; for(i=0;i<1024;i++){
; if (x[i] > 0)
; points[i*3] = x[i];
; }
; Function Attrs: nofree norecurse nosync nounwind uwtable
define dso_local void @test(ptr noalias nocapture %points, ptr noalias nocapture readonly %x, ptr noalias nocapture readnone %y) local_unnamed_addr {
; DISABLED_MASKED_STRIDED-LABEL: @test(
; DISABLED_MASKED_STRIDED-NEXT: entry:
; DISABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; DISABLED_MASKED_STRIDED: vector.body:
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE6]] ]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; DISABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i16>, ptr [[TMP0]], align 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i16> [[WIDE_LOAD]], zeroinitializer
; DISABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = mul nuw nsw <4 x i64> [[VEC_IND]], <i64 3, i64 3, i64 3, i64 3>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = extractelement <4 x i1> [[TMP1]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[TMP2]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: [[TMP5:%.*]] = getelementptr inbounds i16, ptr [[POINTS:%.*]], i64 [[TMP4]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP6:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 0
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP6]], ptr [[TMP5]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE]]
; DISABLED_MASKED_STRIDED: pred.store.continue:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP7:%.*]] = extractelement <4 x i1> [[TMP1]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if1:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP8:%.*]] = extractelement <4 x i64> [[TMP2]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP8]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP10:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 1
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP10]], ptr [[TMP9]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE2]]
; DISABLED_MASKED_STRIDED: pred.store.continue2:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP11:%.*]] = extractelement <4 x i1> [[TMP1]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
; DISABLED_MASKED_STRIDED: pred.store.if3:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP12:%.*]] = extractelement <4 x i64> [[TMP2]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: [[TMP13:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP12]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP14:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 2
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP14]], ptr [[TMP13]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE4]]
; DISABLED_MASKED_STRIDED: pred.store.continue4:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP15:%.*]] = extractelement <4 x i1> [[TMP1]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP15]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6]]
; DISABLED_MASKED_STRIDED: pred.store.if5:
; DISABLED_MASKED_STRIDED-NEXT: [[TMP16:%.*]] = extractelement <4 x i64> [[TMP2]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: [[TMP17:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP16]]
; DISABLED_MASKED_STRIDED-NEXT: [[TMP18:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 3
; DISABLED_MASKED_STRIDED-NEXT: store i16 [[TMP18]], ptr [[TMP17]], align 2
; DISABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE6]]
; DISABLED_MASKED_STRIDED: pred.store.continue6:
; DISABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; DISABLED_MASKED_STRIDED-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; DISABLED_MASKED_STRIDED-NEXT: [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; DISABLED_MASKED_STRIDED-NEXT: br i1 [[TMP19]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; DISABLED_MASKED_STRIDED: for.end:
; DISABLED_MASKED_STRIDED-NEXT: ret void
;
; ENABLED_MASKED_STRIDED-LABEL: @test(
; ENABLED_MASKED_STRIDED-NEXT: entry:
; ENABLED_MASKED_STRIDED-NEXT: br label [[VECTOR_BODY:%.*]]
; ENABLED_MASKED_STRIDED: vector.body:
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
; ENABLED_MASKED_STRIDED-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE6]] ]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP0:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i64 [[INDEX]]
; ENABLED_MASKED_STRIDED-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i16>, ptr [[TMP0]], align 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i16> [[WIDE_LOAD]], zeroinitializer
; ENABLED_MASKED_STRIDED-NEXT: [[TMP2:%.*]] = mul nuw nsw <4 x i64> [[VEC_IND]], <i64 3, i64 3, i64 3, i64 3>
; ENABLED_MASKED_STRIDED-NEXT: [[TMP3:%.*]] = extractelement <4 x i1> [[TMP1]], i64 0
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
; ENABLED_MASKED_STRIDED: pred.store.if:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[TMP2]], i64 0
; ENABLED_MASKED_STRIDED-NEXT: [[TMP5:%.*]] = getelementptr inbounds i16, ptr [[POINTS:%.*]], i64 [[TMP4]]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP6:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 0
; ENABLED_MASKED_STRIDED-NEXT: store i16 [[TMP6]], ptr [[TMP5]], align 2
; ENABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE]]
; ENABLED_MASKED_STRIDED: pred.store.continue:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP7:%.*]] = extractelement <4 x i1> [[TMP1]], i64 1
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
; ENABLED_MASKED_STRIDED: pred.store.if1:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP8:%.*]] = extractelement <4 x i64> [[TMP2]], i64 1
; ENABLED_MASKED_STRIDED-NEXT: [[TMP9:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP8]]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP10:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 1
; ENABLED_MASKED_STRIDED-NEXT: store i16 [[TMP10]], ptr [[TMP9]], align 2
; ENABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE2]]
; ENABLED_MASKED_STRIDED: pred.store.continue2:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP11:%.*]] = extractelement <4 x i1> [[TMP1]], i64 2
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
; ENABLED_MASKED_STRIDED: pred.store.if3:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP12:%.*]] = extractelement <4 x i64> [[TMP2]], i64 2
; ENABLED_MASKED_STRIDED-NEXT: [[TMP13:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP12]]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP14:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 2
; ENABLED_MASKED_STRIDED-NEXT: store i16 [[TMP14]], ptr [[TMP13]], align 2
; ENABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE4]]
; ENABLED_MASKED_STRIDED: pred.store.continue4:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP15:%.*]] = extractelement <4 x i1> [[TMP1]], i64 3
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP15]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6]]
; ENABLED_MASKED_STRIDED: pred.store.if5:
; ENABLED_MASKED_STRIDED-NEXT: [[TMP16:%.*]] = extractelement <4 x i64> [[TMP2]], i64 3
; ENABLED_MASKED_STRIDED-NEXT: [[TMP17:%.*]] = getelementptr inbounds i16, ptr [[POINTS]], i64 [[TMP16]]
; ENABLED_MASKED_STRIDED-NEXT: [[TMP18:%.*]] = extractelement <4 x i16> [[WIDE_LOAD]], i64 3
; ENABLED_MASKED_STRIDED-NEXT: store i16 [[TMP18]], ptr [[TMP17]], align 2
; ENABLED_MASKED_STRIDED-NEXT: br label [[PRED_STORE_CONTINUE6]]
; ENABLED_MASKED_STRIDED: pred.store.continue6:
; ENABLED_MASKED_STRIDED-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; ENABLED_MASKED_STRIDED-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
; ENABLED_MASKED_STRIDED-NEXT: [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; ENABLED_MASKED_STRIDED-NEXT: br i1 [[TMP19]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; ENABLED_MASKED_STRIDED: for.end:
; ENABLED_MASKED_STRIDED-NEXT: ret void
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%arrayidx = getelementptr inbounds i16, ptr %x, i64 %indvars.iv
%0 = load i16, ptr %arrayidx, align 2
%cmp1 = icmp sgt i16 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then:
%1 = mul nuw nsw i64 %indvars.iv, 3
%arrayidx6 = getelementptr inbounds i16, ptr %points, i64 %1
store i16 %0, ptr %arrayidx6, align 2
br label %for.inc
for.inc:
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret void
}
|
