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
| ; RUN: opt -S < %s -instcombine | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-macosx10.7.0"
; Check transforms involving atomic operations
define i32 @test1(i32* %p) {
; CHECK-LABEL: define i32 @test1(
; CHECK: %x = load atomic i32, i32* %p seq_cst, align 4
; CHECK: shl i32 %x, 1
%x = load atomic i32, i32* %p seq_cst, align 4
%y = load i32, i32* %p, align 4
%z = add i32 %x, %y
ret i32 %z
}
define i32 @test2(i32* %p) {
; CHECK-LABEL: define i32 @test2(
; CHECK: %x = load volatile i32, i32* %p, align 4
; CHECK: %y = load volatile i32, i32* %p, align 4
%x = load volatile i32, i32* %p, align 4
%y = load volatile i32, i32* %p, align 4
%z = add i32 %x, %y
ret i32 %z
}
; The exact semantics of mixing volatile and non-volatile on the same
; memory location are a bit unclear, but conservatively, we know we don't
; want to remove the volatile.
define i32 @test3(i32* %p) {
; CHECK-LABEL: define i32 @test3(
; CHECK: %x = load volatile i32, i32* %p, align 4
%x = load volatile i32, i32* %p, align 4
%y = load i32, i32* %p, align 4
%z = add i32 %x, %y
ret i32 %z
}
; Forwarding from a stronger ordered atomic is fine
define i32 @test4(i32* %p) {
; CHECK-LABEL: define i32 @test4(
; CHECK: %x = load atomic i32, i32* %p seq_cst, align 4
; CHECK: shl i32 %x, 1
%x = load atomic i32, i32* %p seq_cst, align 4
%y = load atomic i32, i32* %p unordered, align 4
%z = add i32 %x, %y
ret i32 %z
}
; Forwarding from a non-atomic is not. (The earlier load
; could in priciple be promoted to atomic and then forwarded,
; but we can't just drop the atomic from the load.)
define i32 @test5(i32* %p) {
; CHECK-LABEL: define i32 @test5(
; CHECK: %x = load atomic i32, i32* %p unordered, align 4
%x = load atomic i32, i32* %p unordered, align 4
%y = load i32, i32* %p, align 4
%z = add i32 %x, %y
ret i32 %z
}
; Forwarding atomic to atomic is fine
define i32 @test6(i32* %p) {
; CHECK-LABEL: define i32 @test6(
; CHECK: %x = load atomic i32, i32* %p unordered, align 4
; CHECK: shl i32 %x, 1
%x = load atomic i32, i32* %p unordered, align 4
%y = load atomic i32, i32* %p unordered, align 4
%z = add i32 %x, %y
ret i32 %z
}
; FIXME: we currently don't do anything for monotonic
define i32 @test7(i32* %p) {
; CHECK-LABEL: define i32 @test7(
; CHECK: %x = load atomic i32, i32* %p seq_cst, align 4
; CHECK: %y = load atomic i32, i32* %p monotonic, align 4
%x = load atomic i32, i32* %p seq_cst, align 4
%y = load atomic i32, i32* %p monotonic, align 4
%z = add i32 %x, %y
ret i32 %z
}
; FIXME: We could forward in racy code
define i32 @test8(i32* %p) {
; CHECK-LABEL: define i32 @test8(
; CHECK: %x = load atomic i32, i32* %p seq_cst, align 4
; CHECK: %y = load atomic i32, i32* %p acquire, align 4
%x = load atomic i32, i32* %p seq_cst, align 4
%y = load atomic i32, i32* %p acquire, align 4
%z = add i32 %x, %y
ret i32 %z
}
; An unordered access to null is still unreachable. There's no
; ordering imposed.
define i32 @test9() {
; CHECK-LABEL: define i32 @test9(
; CHECK: store i32 undef, i32* null
%x = load atomic i32, i32* null unordered, align 4
ret i32 %x
}
define i32 @test9_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test9_no_null_opt(
; CHECK: load atomic i32, i32* null unordered
%x = load atomic i32, i32* null unordered, align 4
ret i32 %x
}
; FIXME: Could also fold
define i32 @test10() {
; CHECK-LABEL: define i32 @test10(
; CHECK: load atomic i32, i32* null monotonic
%x = load atomic i32, i32* null monotonic, align 4
ret i32 %x
}
define i32 @test10_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test10_no_null_opt(
; CHECK: load atomic i32, i32* null monotonic
%x = load atomic i32, i32* null monotonic, align 4
ret i32 %x
}
; Would this be legal to fold? Probably?
define i32 @test11() {
; CHECK-LABEL: define i32 @test11(
; CHECK: load atomic i32, i32* null seq_cst
%x = load atomic i32, i32* null seq_cst, align 4
ret i32 %x
}
define i32 @test11_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test11_no_null_opt(
; CHECK: load atomic i32, i32* null seq_cst
%x = load atomic i32, i32* null seq_cst, align 4
ret i32 %x
}
; An unordered access to null is still unreachable. There's no
; ordering imposed.
define i32 @test12() {
; CHECK-LABEL: define i32 @test12(
; CHECK: store atomic i32 undef, i32* null
store atomic i32 0, i32* null unordered, align 4
ret i32 0
}
define i32 @test12_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test12_no_null_opt(
; CHECK: store atomic i32 0, i32* null unordered
store atomic i32 0, i32* null unordered, align 4
ret i32 0
}
; FIXME: Could also fold
define i32 @test13() {
; CHECK-LABEL: define i32 @test13(
; CHECK: store atomic i32 0, i32* null monotonic
store atomic i32 0, i32* null monotonic, align 4
ret i32 0
}
define i32 @test13_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test13_no_null_opt(
; CHECK: store atomic i32 0, i32* null monotonic
store atomic i32 0, i32* null monotonic, align 4
ret i32 0
}
; Would this be legal to fold? Probably?
define i32 @test14() {
; CHECK-LABEL: define i32 @test14(
; CHECK: store atomic i32 0, i32* null seq_cst
store atomic i32 0, i32* null seq_cst, align 4
ret i32 0
}
define i32 @test14_no_null_opt() #0 {
; CHECK-LABEL: define i32 @test14_no_null_opt(
; CHECK: store atomic i32 0, i32* null seq_cst
store atomic i32 0, i32* null seq_cst, align 4
ret i32 0
}
@a = external global i32
@b = external global i32
define i32 @test15(i1 %cnd) {
; CHECK-LABEL: define i32 @test15(
; CHECK: load atomic i32, i32* @a unordered, align 4
; CHECK: load atomic i32, i32* @b unordered, align 4
%addr = select i1 %cnd, i32* @a, i32* @b
%x = load atomic i32, i32* %addr unordered, align 4
ret i32 %x
}
; FIXME: This would be legal to transform
define i32 @test16(i1 %cnd) {
; CHECK-LABEL: define i32 @test16(
; CHECK: load atomic i32, i32* %addr monotonic, align 4
%addr = select i1 %cnd, i32* @a, i32* @b
%x = load atomic i32, i32* %addr monotonic, align 4
ret i32 %x
}
; FIXME: This would be legal to transform
define i32 @test17(i1 %cnd) {
; CHECK-LABEL: define i32 @test17(
; CHECK: load atomic i32, i32* %addr seq_cst, align 4
%addr = select i1 %cnd, i32* @a, i32* @b
%x = load atomic i32, i32* %addr seq_cst, align 4
ret i32 %x
}
define i32 @test22(i1 %cnd) {
; CHECK-LABEL: define i32 @test22(
; CHECK: [[PHI:%.*]] = phi i32
; CHECK: store atomic i32 [[PHI]], i32* @a unordered, align 4
br i1 %cnd, label %block1, label %block2
block1:
store atomic i32 1, i32* @a unordered, align 4
br label %merge
block2:
store atomic i32 2, i32* @a unordered, align 4
br label %merge
merge:
ret i32 0
}
; TODO: probably also legal here
define i32 @test23(i1 %cnd) {
; CHECK-LABEL: define i32 @test23(
; CHECK: br i1 %cnd, label %block1, label %block2
br i1 %cnd, label %block1, label %block2
block1:
store atomic i32 1, i32* @a monotonic, align 4
br label %merge
block2:
store atomic i32 2, i32* @a monotonic, align 4
br label %merge
merge:
ret i32 0
}
declare void @clobber()
define i32 @test18(float* %p) {
; CHECK-LABEL: define i32 @test18(
; CHECK: load atomic i32, i32* [[A:%.*]] unordered, align 4
; CHECK: store atomic i32 [[B:%.*]], i32* [[C:%.*]] unordered, align 4
%x = load atomic float, float* %p unordered, align 4
call void @clobber() ;; keep the load around
store atomic float %x, float* %p unordered, align 4
ret i32 0
}
; TODO: probably also legal in this case
define i32 @test19(float* %p) {
; CHECK-LABEL: define i32 @test19(
; CHECK: load atomic float, float* %p seq_cst, align 4
; CHECK: store atomic float %x, float* %p seq_cst, align 4
%x = load atomic float, float* %p seq_cst, align 4
call void @clobber() ;; keep the load around
store atomic float %x, float* %p seq_cst, align 4
ret i32 0
}
define i32 @test20(i32** %p, i8* %v) {
; CHECK-LABEL: define i32 @test20(
; CHECK: store atomic i8* %v, i8** [[D:%.*]] unordered, align 4
%cast = bitcast i8* %v to i32*
store atomic i32* %cast, i32** %p unordered, align 4
ret i32 0
}
define i32 @test21(i32** %p, i8* %v) {
; CHECK-LABEL: define i32 @test21(
; CHECK: store atomic i32* %cast, i32** %p monotonic, align 4
%cast = bitcast i8* %v to i32*
store atomic i32* %cast, i32** %p monotonic, align 4
ret i32 0
}
define void @pr27490a(i8** %p1, i8** %p2) {
; CHECK-LABEL: define void @pr27490
; CHECK: %1 = bitcast i8** %p1 to i64*
; CHECK: %l1 = load i64, i64* %1, align 8
; CHECK: %2 = bitcast i8** %p2 to i64*
; CHECK: store volatile i64 %l1, i64* %2, align 8
%l = load i8*, i8** %p1
store volatile i8* %l, i8** %p2
ret void
}
define void @pr27490b(i8** %p1, i8** %p2) {
; CHECK-LABEL: define void @pr27490
; CHECK: %1 = bitcast i8** %p1 to i64*
; CHECK: %l1 = load i64, i64* %1, align 8
; CHECK: %2 = bitcast i8** %p2 to i64*
; CHECK: store atomic i64 %l1, i64* %2 seq_cst, align 8
%l = load i8*, i8** %p1
store atomic i8* %l, i8** %p2 seq_cst, align 8
ret void
}
;; At the moment, we can't form atomic vectors by folding since these are
;; not representable in the IR. This was pr29121. The right long term
;; solution is to extend the IR to handle this case.
define <2 x float> @no_atomic_vector_load(i64* %p) {
; CHECK-LABEL @no_atomic_vector_load
; CHECK: load atomic i64, i64* %p unordered, align 8
%load = load atomic i64, i64* %p unordered, align 8
%.cast = bitcast i64 %load to <2 x float>
ret <2 x float> %.cast
}
define void @no_atomic_vector_store(<2 x float> %p, i8* %p2) {
; CHECK-LABEL: @no_atomic_vector_store
; CHECK: store atomic i64 %1, i64* %2 unordered, align 8
%1 = bitcast <2 x float> %p to i64
%2 = bitcast i8* %p2 to i64*
store atomic i64 %1, i64* %2 unordered, align 8
ret void
}
attributes #0 = { "null-pointer-is-valid"="true" }
|