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
|
; REQUIRES: asserts
; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -passes=loop-vectorize -S < %s 2>&1 | FileCheck %s
; RUN: opt -mtriple=aarch64-none-linux-gnu -mattr=+sve -passes=loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck --check-prefix=CHECK-DBG %s
; RUN: opt -mtriple=aarch64-none-linux-gnu -passes=loop-vectorize -pass-remarks-analysis=loop-vectorize -debug-only=loop-vectorize -S < %s 2>%t | FileCheck --check-prefix=CHECK-NO-SVE %s
; RUN: cat %t | FileCheck %s -check-prefix=CHECK-NO-SVE-REMARKS
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
; These tests validate the behaviour of scalable vectorization factor hints,
; where the following applies:
;
; * If the backend does not support scalable vectors, ignore the hint and let
; the vectorizer pick a VF.
; * If there are no dependencies and assuming the VF is a power of 2 the VF
; should be accepted. This applies to both fixed and scalable VFs.
; * If the dependency is too small to use scalable vectors, change the VF to
; fixed, where existing behavior applies (clamping).
; * If scalable vectorization is feasible given the dependency and the VF is
; valid, accept it. Otherwise, clamp to the max scalable VF.
; test1
;
; Scalable vectorization unfeasible, clamp VF from (4, scalable) -> (4, fixed).
;
; The pragma applied to this loop implies a scalable vector <vscale x 4 x i32>
; be used for vectorization. For fixed vectors the MaxVF=8, otherwise there
; would be a dependence between vector lanes for vectors greater than 256 bits.
;
; void test1(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(4, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 8] = a[i] + b[i];
; }
; }
;
; For scalable vectorization 'vscale' has to be considered, for this example
; unless max(vscale)=2 it's unsafe to vectorize. For SVE max(vscale)=16, check
; fixed-width vectorization is used instead.
; CHECK-DBG: LV: Checking a loop in 'test1'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: Max legal vector width too small, scalable vectorization unfeasible.
; CHECK-DBG: remark: <unknown>:0:0: Max legal vector width too small, scalable vectorization unfeasible.
; CHECK-DBG: LV: The max safe fixed VF is: 8.
; CHECK-DBG: LV: Selecting VF: 4.
; CHECK-LABEL: @test1
; CHECK: <4 x i32>
define void @test1(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 8
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !0
exit:
ret void
}
!0 = !{!0, !1, !2}
!1 = !{!"llvm.loop.vectorize.width", i32 4}
!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; test2
;
; Scalable vectorization unfeasible, clamp VF from (8, scalable) -> (4, fixed).
;
; void test2(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(8, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 4] = a[i] + b[i];
; }
; }
; CHECK-DBG: LV: Checking a loop in 'test2'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: Max legal vector width too small, scalable vectorization unfeasible.
; CHECK-DBG: LV: The max safe fixed VF is: 4.
; CHECK-DBG: LV: User VF=vscale x 8 is unsafe. Ignoring scalable UserVF.
; CHECK-DBG: LV: Selecting VF: 4.
; CHECK-LABEL: @test2
; CHECK: <4 x i32>
define void @test2(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 4
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !3
exit:
ret void
}
!3 = !{!3, !4, !5}
!4 = !{!"llvm.loop.vectorize.width", i32 8}
!5 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; test3
;
; Scalable vectorization feasible and the VF is valid.
;
; Specifies a vector of <vscale x 2 x i32>, i.e. maximum of 32 x i32 with 2
; words per 128-bits (unpacked).
;
; void test3(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(2, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 32] = a[i] + b[i];
; }
; }
;
; Max fixed VF=32, Max scalable VF=2, safe to vectorize.
; CHECK-DBG-LABEL: LV: Checking a loop in 'test3'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: The max safe scalable VF is: vscale x 2.
; CHECK-DBG: LV: Using user VF vscale x 2.
; CHECK-LABEL: @test3
; CHECK: <vscale x 2 x i32>
define void @test3(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 32
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !6
exit:
ret void
}
!6 = !{!6, !7, !8}
!7 = !{!"llvm.loop.vectorize.width", i32 2}
!8 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; test4
;
; Scalable vectorization feasible, but the given VF is unsafe. Should ignore
; the hint and leave it to the vectorizer to pick a more suitable VF.
;
; Specifies a vector of <vscale x 4 x i32>, i.e. maximum of 64 x i32 with 4
; words per 128-bits (packed).
;
; void test4(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(4, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 32] = a[i] + b[i];
; }
; }
;
; Max fixed VF=32, Max scalable VF=2, unsafe to vectorize.
; CHECK-DBG-LABEL: LV: Checking a loop in 'test4'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: The max safe scalable VF is: vscale x 2.
; CHECK-DBG: LV: User VF=vscale x 4 is unsafe. Ignoring scalable UserVF.
; CHECK-DBG: remark: <unknown>:0:0: User-specified vectorization factor vscale x 4 is unsafe. Ignoring the hint to let the compiler pick a more suitable value.
; CHECK-DBG: Found feasible scalable VF = vscale x 2
; CHECK-DBG: LV: Selecting VF: vscale x 2.
; CHECK-LABEL: @test4
; CHECK: <vscale x 2 x i32>
define void @test4(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 32
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !9
exit:
ret void
}
!9 = !{!9, !10, !11}
!10 = !{!"llvm.loop.vectorize.width", i32 4}
!11 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; test5
;
; Scalable vectorization feasible and the VF is valid.
;
; Specifies a vector of <vscale x 4 x i32>, i.e. maximum of 64 x i32 with 4
; words per 128-bits (packed).
;
; void test5(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(4, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 128] = a[i] + b[i];
; }
; }
;
; Max fixed VF=128, Max scalable VF=8, safe to vectorize.
; CHECK-DBG-LABEL: LV: Checking a loop in 'test5'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: The max safe scalable VF is: vscale x 8.
; CHECK-DBG: LV: Using user VF vscale x 4
; CHECK-LABEL: @test5
; CHECK: <vscale x 4 x i32>
define void @test5(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 128
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !12
exit:
ret void
}
!12 = !{!12, !13, !14}
!13 = !{!"llvm.loop.vectorize.width", i32 4}
!14 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; test6
;
; Scalable vectorization feasible, but the VF is unsafe. Should ignore
; the hint and leave it to the vectorizer to pick a more suitable VF.
;
; Specifies a vector of <vscale x 16 x i32>, i.e. maximum of 256 x i32.
;
; void test6(int *a, int *b, int N) {
; #pragma clang loop vectorize(enable) vectorize_width(16, scalable)
; for (int i=0; i<N; ++i) {
; a[i + 128] = a[i] + b[i];
; }
; }
;
; Max fixed VF=128, Max scalable VF=8, unsafe to vectorize.
; CHECK-DBG-LABEL: LV: Checking a loop in 'test6'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: LV: The max safe scalable VF is: vscale x 8.
; CHECK-DBG: LV: User VF=vscale x 16 is unsafe. Ignoring scalable UserVF.
; CHECK-DBG: remark: <unknown>:0:0: User-specified vectorization factor vscale x 16 is unsafe. Ignoring the hint to let the compiler pick a more suitable value.
; CHECK-DBG: LV: Found feasible scalable VF = vscale x 4
; CHECK-DBG: Selecting VF: vscale x 4.
; CHECK-LABEL: @test6
; CHECK: <vscale x 4 x i32>
define void @test6(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 128
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !15
exit:
ret void
}
!15 = !{!15, !16, !17}
!16 = !{!"llvm.loop.vectorize.width", i32 16}
!17 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; CHECK-NO-SVE-REMARKS-LABEL: LV: Checking a loop in 'test_no_sve'
; CHECK-NO-SVE-REMARKS: LV: User VF=vscale x 4 is ignored because scalable vectors are not available.
; CHECK-NO-SVE-REMARKS: remark: <unknown>:0:0: User-specified vectorization factor vscale x 4 is ignored because the target does not support scalable vectors. The compiler will pick a more suitable value.
; CHECK-NO-SVE-REMARKS: LV: Selecting VF: 4.
; CHECK-NO-SVE-LABEL: @test_no_sve
; CHECK-NO-SVE: <4 x i32>
; CHECK-NO-SVE-NOT: <vscale x 4 x i32>
define void @test_no_sve(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
store i32 %add, ptr %arrayidx, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !18
exit:
ret void
}
!18 = !{!18, !19, !20}
!19 = !{!"llvm.loop.vectorize.width", i32 4}
!20 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
; Test the LV falls back to fixed-width vectorization if scalable vectors are
; supported but max vscale is undefined.
;
; CHECK-DBG-LABEL: LV: Checking a loop in 'test_no_max_vscale'
; CHECK-DBG: LV: Scalable vectorization is available
; CHECK-DBG: The max safe fixed VF is: 4.
; CHECK-DBG: LV: User VF=vscale x 4 is unsafe. Ignoring scalable UserVF.
; CHECK-DBG: LV: Selecting VF: 4.
; CHECK-LABEL: @test_no_max_vscale
; CHECK: <4 x i32>
define void @test_no_max_vscale(ptr %a, ptr %b) #0 {
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr %b, i64 %iv
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %1, %0
%2 = add nuw nsw i64 %iv, 4
%arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %2
store i32 %add, ptr %arrayidx5, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, 1024
br i1 %exitcond.not, label %exit, label %loop, !llvm.loop !21
exit:
ret void
}
attributes #0 = { vscale_range(1, 16) }
!21 = !{!21, !22, !23}
!22 = !{!"llvm.loop.vectorize.width", i32 4}
!23 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
|
