vscale.ll
15.2 KB
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
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S < %s -basic-aa -gvn -dce | FileCheck %s
; Analyze Load from clobbering Load.
define <vscale x 4 x i32> @load_store_clobber_load(<vscale x 4 x i32> *%p) {
; CHECK-LABEL: @load_store_clobber_load(
; CHECK-NEXT: [[LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* undef, align 16
; CHECK-NEXT: [[ADD:%.*]] = add <vscale x 4 x i32> [[LOAD1]], [[LOAD1]]
; CHECK-NEXT: ret <vscale x 4 x i32> [[ADD]]
;
%load1 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* undef
%load2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p ; <- load to be eliminated
%add = add <vscale x 4 x i32> %load1, %load2
ret <vscale x 4 x i32> %add
}
define <vscale x 4 x i32> @load_store_clobber_load_mayalias(<vscale x 4 x i32>* %p, <vscale x 4 x i32>* %p2) {
; CHECK-LABEL: @load_store_clobber_load_mayalias(
; CHECK-NEXT: [[LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[P2:%.*]], align 16
; CHECK-NEXT: [[LOAD2:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], align 16
; CHECK-NEXT: [[SUB:%.*]] = sub <vscale x 4 x i32> [[LOAD1]], [[LOAD2]]
; CHECK-NEXT: ret <vscale x 4 x i32> [[SUB]]
;
%load1 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %p2
%load2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
%sub = sub <vscale x 4 x i32> %load1, %load2
ret <vscale x 4 x i32> %sub
}
define <vscale x 4 x i32> @load_store_clobber_load_noalias(<vscale x 4 x i32>* noalias %p, <vscale x 4 x i32>* noalias %p2) {
; CHECK-LABEL: @load_store_clobber_load_noalias(
; CHECK-NEXT: [[LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[P2:%.*]], align 16
; CHECK-NEXT: [[ADD:%.*]] = add <vscale x 4 x i32> [[LOAD1]], [[LOAD1]]
; CHECK-NEXT: ret <vscale x 4 x i32> [[ADD]]
;
%load1 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %p2
%load2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p ; <- load to be eliminated
%add = add <vscale x 4 x i32> %load1, %load2
ret <vscale x 4 x i32> %add
}
; TODO: BasicAA return MayAlias for %gep1,%gep2, could improve as MustAlias.
define i32 @load_clobber_load_gep1(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @load_clobber_load_gep1(
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], i64 0, i64 1
; CHECK-NEXT: [[LOAD1:%.*]] = load i32, i32* [[GEP1]], align 4
; CHECK-NEXT: [[P2:%.*]] = bitcast <vscale x 4 x i32>* [[P]] to i32*
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr i32, i32* [[P2]], i64 1
; CHECK-NEXT: [[LOAD2:%.*]] = load i32, i32* [[GEP2]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[LOAD1]], [[LOAD2]]
; CHECK-NEXT: ret i32 [[ADD]]
;
%gep1 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 0, i64 1
%load1 = load i32, i32* %gep1
%p2 = bitcast <vscale x 4 x i32>* %p to i32*
%gep2 = getelementptr i32, i32* %p2, i64 1
%load2 = load i32, i32* %gep2 ; <- load could be eliminated
%add = add i32 %load1, %load2
ret i32 %add
}
define i32 @load_clobber_load_gep2(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @load_clobber_load_gep2(
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], i64 1, i64 0
; CHECK-NEXT: [[LOAD1:%.*]] = load i32, i32* [[GEP1]], align 4
; CHECK-NEXT: [[P2:%.*]] = bitcast <vscale x 4 x i32>* [[P]] to i32*
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr i32, i32* [[P2]], i64 4
; CHECK-NEXT: [[LOAD2:%.*]] = load i32, i32* [[GEP2]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[LOAD1]], [[LOAD2]]
; CHECK-NEXT: ret i32 [[ADD]]
;
%gep1 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 0
%load1 = load i32, i32* %gep1
%p2 = bitcast <vscale x 4 x i32>* %p to i32*
%gep2 = getelementptr i32, i32* %p2, i64 4
%load2 = load i32, i32* %gep2 ; <- can not determine at compile-time if %load1 and %load2 are same addr
%add = add i32 %load1, %load2
ret i32 %add
}
; TODO: BasicAA return MayAlias for %gep1,%gep2, could improve as MustAlias.
define i32 @load_clobber_load_gep3(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @load_clobber_load_gep3(
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], i64 1, i64 0
; CHECK-NEXT: [[LOAD1:%.*]] = load i32, i32* [[GEP1]], align 4
; CHECK-NEXT: [[P2:%.*]] = bitcast <vscale x 4 x i32>* [[P]] to <vscale x 4 x float>*
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr <vscale x 4 x float>, <vscale x 4 x float>* [[P2]], i64 1, i64 0
; CHECK-NEXT: [[LOAD2:%.*]] = load float, float* [[GEP2]], align 4
; CHECK-NEXT: [[CAST:%.*]] = bitcast float [[LOAD2]] to i32
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[LOAD1]], [[CAST]]
; CHECK-NEXT: ret i32 [[ADD]]
;
%gep1 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 0
%load1 = load i32, i32* %gep1
%p2 = bitcast <vscale x 4 x i32>* %p to <vscale x 4 x float>*
%gep2 = getelementptr <vscale x 4 x float>, <vscale x 4 x float>* %p2, i64 1, i64 0
%load2 = load float, float* %gep2 ; <- load could be eliminated
%cast = bitcast float %load2 to i32
%add = add i32 %load1, %cast
ret i32 %add
}
define <vscale x 4 x i32> @load_clobber_load_fence(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @load_clobber_load_fence(
; CHECK-NEXT: [[LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: call void asm "", "~{memory}"()
; CHECK-NEXT: [[LOAD2:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], align 16
; CHECK-NEXT: [[SUB:%.*]] = sub <vscale x 4 x i32> [[LOAD1]], [[LOAD2]]
; CHECK-NEXT: ret <vscale x 4 x i32> [[SUB]]
;
%load1 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
call void asm "", "~{memory}"()
%load2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
%sub = sub <vscale x 4 x i32> %load1, %load2
ret <vscale x 4 x i32> %sub
}
define <vscale x 4 x i32> @load_clobber_load_sideeffect(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @load_clobber_load_sideeffect(
; CHECK-NEXT: [[LOAD1:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: call void asm sideeffect "", ""()
; CHECK-NEXT: [[LOAD2:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], align 16
; CHECK-NEXT: [[ADD:%.*]] = add <vscale x 4 x i32> [[LOAD1]], [[LOAD2]]
; CHECK-NEXT: ret <vscale x 4 x i32> [[ADD]]
;
%load1 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
call void asm sideeffect "", ""()
%load2 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
%add = add <vscale x 4 x i32> %load1, %load2
ret <vscale x 4 x i32> %add
}
; Analyze Load from clobbering Store.
define <vscale x 4 x i32> @store_forward_to_load(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @store_forward_to_load(
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: ret <vscale x 4 x i32> zeroinitializer
;
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %p
%load = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
ret <vscale x 4 x i32> %load
}
define <vscale x 4 x i32> @store_forward_to_load_sideeffect(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @store_forward_to_load_sideeffect(
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: call void asm sideeffect "", ""()
; CHECK-NEXT: [[LOAD:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], align 16
; CHECK-NEXT: ret <vscale x 4 x i32> [[LOAD]]
;
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %p
call void asm sideeffect "", ""()
%load = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p
ret <vscale x 4 x i32> %load
}
define i32 @store_clobber_load() {
; CHECK-LABEL: @store_clobber_load(
; CHECK-NEXT: [[ALLOC:%.*]] = alloca <vscale x 4 x i32>
; CHECK-NEXT: store <vscale x 4 x i32> undef, <vscale x 4 x i32>* [[ALLOC]], align 16
; CHECK-NEXT: [[PTR:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[ALLOC]], i32 0, i32 1
; CHECK-NEXT: [[LOAD:%.*]] = load i32, i32* [[PTR]], align 4
; CHECK-NEXT: ret i32 [[LOAD]]
;
%alloc = alloca <vscale x 4 x i32>
store <vscale x 4 x i32> undef, <vscale x 4 x i32>* %alloc
%ptr = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %alloc, i32 0, i32 1
%load = load i32, i32* %ptr
ret i32 %load
}
; Analyze Load from clobbering MemInst.
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
define i32 @memset_clobber_load(<vscale x 4 x i32> *%p) {
; CHECK-LABEL: @memset_clobber_load(
; CHECK-NEXT: [[CONV:%.*]] = bitcast <vscale x 4 x i32>* [[P:%.*]] to i8*
; CHECK-NEXT: tail call void @llvm.memset.p0i8.i64(i8* [[CONV]], i8 1, i64 200, i1 false)
; CHECK-NEXT: ret i32 16843009
;
%conv = bitcast <vscale x 4 x i32>* %p to i8*
tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i1 false)
%gep = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 0, i64 5
%load = load i32, i32* %gep
ret i32 %load
}
define i32 @memset_clobber_load_vscaled_base(<vscale x 4 x i32> *%p) {
; CHECK-LABEL: @memset_clobber_load_vscaled_base(
; CHECK-NEXT: [[CONV:%.*]] = bitcast <vscale x 4 x i32>* [[P:%.*]] to i8*
; CHECK-NEXT: tail call void @llvm.memset.p0i8.i64(i8* [[CONV]], i8 1, i64 200, i1 false)
; CHECK-NEXT: [[GEP:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], i64 1, i64 1
; CHECK-NEXT: [[LOAD:%.*]] = load i32, i32* [[GEP]], align 4
; CHECK-NEXT: ret i32 [[LOAD]]
;
%conv = bitcast <vscale x 4 x i32>* %p to i8*
tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i1 false)
%gep = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 1
%load = load i32, i32* %gep
ret i32 %load
}
define i32 @memset_clobber_load_nonconst_index(<vscale x 4 x i32> *%p, i64 %idx1, i64 %idx2) {
; CHECK-LABEL: @memset_clobber_load_nonconst_index(
; CHECK-NEXT: [[CONV:%.*]] = bitcast <vscale x 4 x i32>* [[P:%.*]] to i8*
; CHECK-NEXT: tail call void @llvm.memset.p0i8.i64(i8* [[CONV]], i8 1, i64 200, i1 false)
; CHECK-NEXT: [[GEP:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], i64 [[IDX1:%.*]], i64 [[IDX2:%.*]]
; CHECK-NEXT: [[LOAD:%.*]] = load i32, i32* [[GEP]], align 4
; CHECK-NEXT: ret i32 [[LOAD]]
;
%conv = bitcast <vscale x 4 x i32>* %p to i8*
tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i1 false)
%gep = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 %idx1, i64 %idx2
%load = load i32, i32* %gep
ret i32 %load
}
; Load elimination across BBs
define <vscale x 4 x i32>* @load_from_alloc_replaced_with_undef() {
; CHECK-LABEL: @load_from_alloc_replaced_with_undef(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca <vscale x 4 x i32>
; CHECK-NEXT: br i1 undef, label [[IF_END:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[A]], align 16
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: ret <vscale x 4 x i32>* [[A]]
;
entry:
%a = alloca <vscale x 4 x i32>
%gep = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %a, i64 0, i64 1
%load = load i32, i32* %gep ; <- load to be eliminated
%tobool = icmp eq i32 %load, 0 ; <- icmp to be eliminated
br i1 %tobool, label %if.end, label %if.then
if.then:
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %a
br label %if.end
if.end:
ret <vscale x 4 x i32>* %a
}
define i32 @redundant_load_elimination_1(<vscale x 4 x i32>* %p) {
; CHECK-LABEL: @redundant_load_elimination_1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[GEP:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], i64 1, i64 1
; CHECK-NEXT: [[LOAD1:%.*]] = load i32, i32* [[GEP]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[LOAD1]], 0
; CHECK-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: ret i32 [[LOAD1]]
;
entry:
%gep = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 1
%load1 = load i32, i32* %gep
%cmp = icmp eq i32 %load1, 0
br i1 %cmp, label %if.then, label %if.end
if.then:
%load2 = load i32, i32* %gep ; <- load to be eliminated
%add = add i32 %load1, %load2
br label %if.end
if.end:
%result = phi i32 [ %add, %if.then ], [ %load1, %entry ]
ret i32 %result
}
; TODO: BasicAA return MayAlias for %gep1,%gep2, could improve as NoAlias.
define void @redundant_load_elimination_2(i1 %c, <vscale x 4 x i32>* %p, i32* %q, <vscale x 4 x i32> %v) {
; CHECK-LABEL: @redundant_load_elimination_2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P:%.*]], i64 1, i64 1
; CHECK-NEXT: store i32 0, i32* [[GEP1]], align 4
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], i64 1, i64 0
; CHECK-NEXT: store i32 1, i32* [[GEP2]], align 4
; CHECK-NEXT: br i1 [[C:%.*]], label [[IF_ELSE:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: [[T:%.*]] = load i32, i32* [[GEP1]], align 4
; CHECK-NEXT: store i32 [[T]], i32* [[Q:%.*]], align 4
; CHECK-NEXT: ret void
; CHECK: if.else:
; CHECK-NEXT: ret void
;
entry:
%gep1 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 1
store i32 0, i32* %gep1
%gep2 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1, i64 0
store i32 1, i32* %gep2
br i1 %c, label %if.else, label %if.then
if.then:
%t = load i32, i32* %gep1 ; <- load could be eliminated
store i32 %t, i32* %q
ret void
if.else:
ret void
}
; TODO: load in if.then could have been eliminated
define void @missing_load_elimination(i1 %c, <vscale x 4 x i32>* %p, <vscale x 4 x i32>* %q, <vscale x 4 x i32> %v) {
; CHECK-LABEL: @missing_load_elimination(
; CHECK-NEXT: entry:
; CHECK-NEXT: store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* [[P:%.*]], align 16
; CHECK-NEXT: [[P1:%.*]] = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], i64 1
; CHECK-NEXT: store <vscale x 4 x i32> [[V:%.*]], <vscale x 4 x i32>* [[P1]], align 16
; CHECK-NEXT: br i1 [[C:%.*]], label [[IF_ELSE:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: [[T:%.*]] = load <vscale x 4 x i32>, <vscale x 4 x i32>* [[P]], align 16
; CHECK-NEXT: store <vscale x 4 x i32> [[T]], <vscale x 4 x i32>* [[Q:%.*]], align 16
; CHECK-NEXT: ret void
; CHECK: if.else:
; CHECK-NEXT: ret void
;
entry:
store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %p
%p1 = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %p, i64 1
store <vscale x 4 x i32> %v, <vscale x 4 x i32>* %p1
br i1 %c, label %if.else, label %if.then
if.then:
%t = load <vscale x 4 x i32>, <vscale x 4 x i32>* %p ; load could be eliminated
store <vscale x 4 x i32> %t, <vscale x 4 x i32>* %q
ret void
if.else:
ret void
}