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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt -p loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S %s | FileCheck %s
define i32 @loop_with_at_least_2_iterations_via_guards_order_1(ptr %dst, i32 %n) {
; CHECK-LABEL: define i32 @loop_with_at_least_2_iterations_via_guards_order_1(
; CHECK-SAME: ptr [[DST:%.*]], i32 [[N:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[PRE_0:%.*]] = icmp ne i32 [[N]], 0
; CHECK-NEXT: [[PRE_1:%.*]] = icmp slt i32 [[N]], 5
; CHECK-NEXT: [[AND_PRE:%.*]] = and i1 [[PRE_0]], [[PRE_1]]
; CHECK-NEXT: br i1 [[AND_PRE]], label %[[PH:.*]], label %[[EXIT:.*]]
; CHECK: [[PH]]:
; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1
; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT: store <2 x i32> splat (i32 1), ptr [[TMP1]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT_LOOPEXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[PH]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i32 1, ptr [[GEP]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT_LOOPEXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret i32 0
;
entry:
%pre.0 = icmp ne i32 %n, 0
%pre.1 = icmp slt i32 %n, 5
%and.pre = and i1 %pre.0, %pre.1
br i1 %and.pre, label %ph, label %exit
ph: ; preds = %entry
%n.ext = zext i32 %n to i64
br label %loop
loop: ; preds = %loop, %ph
%iv = phi i64 [ 0, %ph ], [ %iv.next, %loop ]
%gep = getelementptr inbounds i32, ptr %dst, i64 %iv
store i32 1, ptr %gep
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, %n.ext
br i1 %ec, label %exit, label %loop
exit: ; preds = %loop, %entry
ret i32 0
}
; Same as loop_with_at_least_2_iterations_via_guards_order_1 but with operands
; of the AND swapped.
; TODO: Should be able to prove that %min.iters.check is false.
define i32 @loop_with_at_least_2_iterations_via_guards_order_2(ptr %dst, i32 %n) {
; CHECK-LABEL: define i32 @loop_with_at_least_2_iterations_via_guards_order_2(
; CHECK-SAME: ptr [[DST:%.*]], i32 [[N:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[PRE_0:%.*]] = icmp ne i32 [[N]], 0
; CHECK-NEXT: [[PRE_1:%.*]] = icmp slt i32 [[N]], 5
; CHECK-NEXT: [[AND_PRE:%.*]] = and i1 [[PRE_1]], [[PRE_0]]
; CHECK-NEXT: br i1 [[AND_PRE]], label %[[PH:.*]], label %[[EXIT:.*]]
; CHECK: [[PH]]:
; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT: store <2 x i32> splat (i32 1), ptr [[TMP1]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT_LOOPEXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[PH]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i32 1, ptr [[GEP]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT_LOOPEXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret i32 0
;
entry:
%pre.0 = icmp ne i32 %n, 0
%pre.1 = icmp slt i32 %n, 5
%and.pre = and i1 %pre.1, %pre.0
br i1 %and.pre, label %ph, label %exit
ph:
%n.ext = zext i32 %n to i64
br label %loop
loop:
%iv = phi i64 [ 0, %ph ], [ %iv.next, %loop ]
%gep = getelementptr inbounds i32, ptr %dst, i64 %iv
store i32 1, ptr %gep
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, %n.ext
br i1 %ec, label %exit, label %loop
exit:
ret i32 0
}
; TODO: Should be able to prove min.iters.check is false, same as
; @loop_never_executes_precondition_order_1_predicates_flipped.
define void @loop_never_executes_precondition_order_1(i64 %start, ptr %dst) {
; CHECK-LABEL: define void @loop_never_executes_precondition_order_1(
; CHECK-SAME: i64 [[START:%.*]], ptr [[DST:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[PRE_0:%.*]] = icmp ugt i64 [[START]], 1
; CHECK-NEXT: br i1 [[PRE_0]], label %[[EXIT:.*]], label %[[PH:.*]]
; CHECK: [[PH]]:
; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[START]], 1
; CHECK-NEXT: [[PRE_1:%.*]] = icmp slt i64 [[MUL]], [[START]]
; CHECK-NEXT: br i1 [[PRE_1]], label %[[LOOP_PREHEADER:.*]], label %[[EXIT]]
; CHECK: [[LOOP_PREHEADER]]:
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 1, [[START]]
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[START]], [[N_VEC]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <2 x i64> poison, i64 [[START]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <2 x i64> [[DOTSPLATINSERT]], <2 x i64> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i64> [[DOTSPLAT]], <i64 0, i64 1>
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 [[START]], [[INDEX]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: store <2 x i64> [[VEC_IND]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], splat (i64 2)
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT_LOOPEXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[TMP1]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[LOOP_PREHEADER]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i64 [[IV]], ptr [[GEP]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 0
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT_LOOPEXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
%pre.0 = icmp ugt i64 %start, 1
br i1 %pre.0, label %exit, label %ph
ph:
%mul = shl i64 %start, 1
%pre.1 = icmp slt i64 %mul, %start
br i1 %pre.1, label %loop, label %exit
loop:
%iv = phi i64 [ %start, %ph ], [ %iv.next, %loop ]
%gep = getelementptr inbounds i64, ptr %dst, i64 %iv
store i64 %iv, ptr %gep
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, 0
br i1 %ec, label %exit, label %loop
exit:
ret void
}
; TODO: Should be able to prove min.iters.check is false, same as
; @loop_never_executes_precondition_order_1_predicates_flipped.
define void @loop_never_executes_precondition_order_1_predicates_flipped(i64 %start, ptr %dst) {
; CHECK-LABEL: define void @loop_never_executes_precondition_order_1_predicates_flipped(
; CHECK-SAME: i64 [[START:%.*]], ptr [[DST:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[PRE_0:%.*]] = icmp ule i64 [[START]], 1
; CHECK-NEXT: br i1 [[PRE_0]], label %[[PH:.*]], label %[[EXIT:.*]]
; CHECK: [[PH]]:
; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[START]], 1
; CHECK-NEXT: [[PRE_1:%.*]] = icmp slt i64 [[MUL]], [[START]]
; CHECK-NEXT: br i1 [[PRE_1]], label %[[LOOP_PREHEADER:.*]], label %[[EXIT]]
; CHECK: [[LOOP_PREHEADER]]:
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 1, [[START]]
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 2
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[START]], [[N_VEC]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <2 x i64> poison, i64 [[START]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <2 x i64> [[DOTSPLATINSERT]], <2 x i64> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i64> [[DOTSPLAT]], <i64 0, i64 1>
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 [[START]], [[INDEX]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: store <2 x i64> [[VEC_IND]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], splat (i64 2)
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT_LOOPEXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[TMP1]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[LOOP_PREHEADER]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i64 [[IV]], ptr [[GEP]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 0
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT_LOOPEXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
%pre.0 = icmp ule i64 %start, 1
br i1 %pre.0, label %ph, label %exit
ph:
%mul = shl i64 %start, 1
%pre.1 = icmp slt i64 %mul, %start
br i1 %pre.1, label %loop, label %exit
loop:
%iv = phi i64 [ %start, %ph ], [ %iv.next, %loop ]
%gep = getelementptr inbounds i64, ptr %dst, i64 %iv
store i64 %iv, ptr %gep
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, 0
br i1 %ec, label %exit, label %loop
exit:
ret void
}
define void @loop_never_executes_precondition_order_2_predicates_flipped(i64 %start, ptr %dst) {
; CHECK-LABEL: define void @loop_never_executes_precondition_order_2_predicates_flipped(
; CHECK-SAME: i64 [[START:%.*]], ptr [[DST:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[START]], 1
; CHECK-NEXT: [[PRE_1:%.*]] = icmp slt i64 [[MUL]], [[START]]
; CHECK-NEXT: br i1 [[PRE_1]], label %[[PH:.*]], label %[[EXIT:.*]]
; CHECK: [[PH]]:
; CHECK-NEXT: [[PRE_0:%.*]] = icmp ule i64 [[START]], 1
; CHECK-NEXT: br i1 [[PRE_0]], label %[[LOOP_PREHEADER:.*]], label %[[EXIT]]
; CHECK: [[LOOP_PREHEADER]]:
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 1, [[START]]
; CHECK-NEXT: br i1 true, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[START]], [[N_VEC]]
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <2 x i64> poison, i64 [[START]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <2 x i64> [[DOTSPLATINSERT]], <2 x i64> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[INDUCTION:%.*]] = add <2 x i64> [[DOTSPLAT]], <i64 0, i64 1>
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 [[START]], [[INDEX]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: store <2 x i64> [[VEC_IND]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], splat (i64 2)
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT_LOOPEXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[TMP1]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[LOOP_PREHEADER]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], %[[LOOP]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i64 [[IV]], ptr [[GEP]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 0
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT_LOOPEXIT]], label %[[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
%mul = shl i64 %start, 1
%pre.1 = icmp slt i64 %mul, %start
br i1 %pre.1, label %ph, label %exit
ph:
%pre.0 = icmp ule i64 %start, 1
br i1 %pre.0, label %loop, label %exit
loop:
%iv = phi i64 [ %start, %ph ], [ %iv.next, %loop ]
%gep = getelementptr inbounds i64, ptr %dst, i64 %iv
store i64 %iv, ptr %gep
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, 0
br i1 %ec, label %exit, label %loop
exit:
ret void
}
|
