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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-apple-ios7.0 -o - %s | FileCheck %s
; RUN: llc -mtriple=aarch64-apple-ios7.0 -mattr=+outline-atomics -o - %s | FileCheck %s --check-prefix=OUTLINE-ATOMICS
define i32 @test_return(i32* %p, i32 %oldval, i32 %newval) {
; CHECK-LABEL: test_return:
; CHECK: ; %bb.0:
; CHECK-NEXT: LBB0_1: ; %cmpxchg.start
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldaxr w8, [x0]
; CHECK-NEXT: cmp w8, w1
; CHECK-NEXT: b.ne LBB0_4
; CHECK-NEXT: ; %bb.2: ; %cmpxchg.trystore
; CHECK-NEXT: ; in Loop: Header=BB0_1 Depth=1
; CHECK-NEXT: stlxr w8, w2, [x0]
; CHECK-NEXT: cbnz w8, LBB0_1
; CHECK-NEXT: ; %bb.3:
; CHECK-NEXT: mov w0, #1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB0_4: ; %cmpxchg.nostore
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: clrex
; CHECK-NEXT: ret
;
; OUTLINE-ATOMICS-LABEL: test_return:
; OUTLINE-ATOMICS: ; %bb.0:
; OUTLINE-ATOMICS-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: .cfi_def_cfa_offset 32
; OUTLINE-ATOMICS-NEXT: .cfi_offset w30, -8
; OUTLINE-ATOMICS-NEXT: .cfi_offset w29, -16
; OUTLINE-ATOMICS-NEXT: .cfi_offset w19, -24
; OUTLINE-ATOMICS-NEXT: .cfi_offset w20, -32
; OUTLINE-ATOMICS-NEXT: mov x8, x0
; OUTLINE-ATOMICS-NEXT: mov w19, w1
; OUTLINE-ATOMICS-NEXT: mov w0, w1
; OUTLINE-ATOMICS-NEXT: mov w1, w2
; OUTLINE-ATOMICS-NEXT: mov x2, x8
; OUTLINE-ATOMICS-NEXT: bl ___aarch64_cas4_acq_rel
; OUTLINE-ATOMICS-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: cmp w0, w19
; OUTLINE-ATOMICS-NEXT: cset w0, eq
; OUTLINE-ATOMICS-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ret
%pair = cmpxchg i32* %p, i32 %oldval, i32 %newval seq_cst seq_cst
%success = extractvalue { i32, i1 } %pair, 1
%conv = zext i1 %success to i32
ret i32 %conv
}
; FIXME: DAG combine should be able to deal with this EOR better.
define i1 @test_return_bool(i8* %value, i8 %oldValue, i8 %newValue) {
; CHECK-LABEL: test_return_bool:
; CHECK: ; %bb.0:
; CHECK-NEXT: and w8, w1, #0xff
; CHECK-NEXT: ; kill: def $w2 killed $w2 def $x2
; CHECK-NEXT: LBB1_1: ; %cmpxchg.start
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldaxrb w9, [x0]
; CHECK-NEXT: cmp w9, w8
; CHECK-NEXT: b.ne LBB1_4
; CHECK-NEXT: ; %bb.2: ; %cmpxchg.trystore
; CHECK-NEXT: ; in Loop: Header=BB1_1 Depth=1
; CHECK-NEXT: stlxrb w9, w2, [x0]
; CHECK-NEXT: cbnz w9, LBB1_1
; CHECK-NEXT: ; %bb.3:
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: eor w0, w8, #0x1
; CHECK-NEXT: ret
; CHECK-NEXT: LBB1_4: ; %cmpxchg.nostore
; CHECK-NEXT: eor w0, wzr, #0x1
; CHECK-NEXT: clrex
; CHECK-NEXT: ret
;
; OUTLINE-ATOMICS-LABEL: test_return_bool:
; OUTLINE-ATOMICS: ; %bb.0:
; OUTLINE-ATOMICS-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: .cfi_def_cfa_offset 32
; OUTLINE-ATOMICS-NEXT: .cfi_offset w30, -8
; OUTLINE-ATOMICS-NEXT: .cfi_offset w29, -16
; OUTLINE-ATOMICS-NEXT: .cfi_offset w19, -24
; OUTLINE-ATOMICS-NEXT: .cfi_offset w20, -32
; OUTLINE-ATOMICS-NEXT: mov x8, x0
; OUTLINE-ATOMICS-NEXT: mov w19, w1
; OUTLINE-ATOMICS-NEXT: mov w0, w1
; OUTLINE-ATOMICS-NEXT: mov w1, w2
; OUTLINE-ATOMICS-NEXT: mov x2, x8
; OUTLINE-ATOMICS-NEXT: bl ___aarch64_cas1_acq_rel
; OUTLINE-ATOMICS-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: cmp w0, w19, uxtb
; OUTLINE-ATOMICS-NEXT: cset w8, eq
; OUTLINE-ATOMICS-NEXT: eor w0, w8, #0x1
; OUTLINE-ATOMICS-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ret
%pair = cmpxchg i8* %value, i8 %oldValue, i8 %newValue acq_rel monotonic
%success = extractvalue { i8, i1 } %pair, 1
%failure = xor i1 %success, 1
ret i1 %failure
}
define void @test_conditional(i32* %p, i32 %oldval, i32 %newval) {
; CHECK-LABEL: test_conditional:
; CHECK: ; %bb.0:
; CHECK-NEXT: LBB2_1: ; %cmpxchg.start
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldaxr w8, [x0]
; CHECK-NEXT: cmp w8, w1
; CHECK-NEXT: b.ne LBB2_4
; CHECK-NEXT: ; %bb.2: ; %cmpxchg.trystore
; CHECK-NEXT: ; in Loop: Header=BB2_1 Depth=1
; CHECK-NEXT: stlxr w8, w2, [x0]
; CHECK-NEXT: cbnz w8, LBB2_1
; CHECK-NEXT: ; %bb.3: ; %true
; CHECK-NEXT: b _bar
; CHECK-NEXT: LBB2_4: ; %cmpxchg.nostore
; CHECK-NEXT: clrex
; CHECK-NEXT: b _baz
;
; OUTLINE-ATOMICS-LABEL: test_conditional:
; OUTLINE-ATOMICS: ; %bb.0:
; OUTLINE-ATOMICS-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: .cfi_def_cfa_offset 32
; OUTLINE-ATOMICS-NEXT: .cfi_offset w30, -8
; OUTLINE-ATOMICS-NEXT: .cfi_offset w29, -16
; OUTLINE-ATOMICS-NEXT: .cfi_offset w19, -24
; OUTLINE-ATOMICS-NEXT: .cfi_offset w20, -32
; OUTLINE-ATOMICS-NEXT: mov x8, x0
; OUTLINE-ATOMICS-NEXT: mov w19, w1
; OUTLINE-ATOMICS-NEXT: mov w0, w1
; OUTLINE-ATOMICS-NEXT: mov w1, w2
; OUTLINE-ATOMICS-NEXT: mov x2, x8
; OUTLINE-ATOMICS-NEXT: bl ___aarch64_cas4_acq_rel
; OUTLINE-ATOMICS-NEXT: cmp w0, w19
; OUTLINE-ATOMICS-NEXT: b.ne LBB2_2
; OUTLINE-ATOMICS-NEXT: ; %bb.1: ; %true
; OUTLINE-ATOMICS-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: b _bar
; OUTLINE-ATOMICS-NEXT: LBB2_2: ; %false
; OUTLINE-ATOMICS-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: b _baz
%pair = cmpxchg i32* %p, i32 %oldval, i32 %newval seq_cst seq_cst
%success = extractvalue { i32, i1 } %pair, 1
br i1 %success, label %true, label %false
true:
tail call void @bar() #2
br label %end
false:
tail call void @baz() #2
br label %end
end:
ret void
}
declare void @bar()
declare void @baz()
; verify the preheader is simplified by simplifycfg.
define i1 @test_conditional2(i32 %a, i32 %b, i32* %c) {
; CHECK-LABEL: test_conditional2:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: stp x22, x21, [sp, #-48]! ; 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #16] ; 16-byte Folded Spill
; CHECK-NEXT: stp x29, x30, [sp, #32] ; 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 48
; CHECK-NEXT: .cfi_offset w30, -8
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: .cfi_offset w19, -24
; CHECK-NEXT: .cfi_offset w20, -32
; CHECK-NEXT: .cfi_offset w21, -40
; CHECK-NEXT: .cfi_offset w22, -48
; CHECK-NEXT: mov x19, x2
; CHECK-NEXT: mov w20, w1
; CHECK-NEXT: mov w21, w0
; CHECK-NEXT: LBB3_1: ; %cmpxchg.start
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldaxr w8, [x19]
; CHECK-NEXT: cmp w8, w21
; CHECK-NEXT: b.ne LBB3_4
; CHECK-NEXT: ; %bb.2: ; %cmpxchg.trystore
; CHECK-NEXT: ; in Loop: Header=BB3_1 Depth=1
; CHECK-NEXT: stlxr w8, w20, [x19]
; CHECK-NEXT: cbnz w8, LBB3_1
; CHECK-NEXT: ; %bb.3:
; CHECK-NEXT: mov w8, #1
; CHECK-NEXT: b LBB3_5
; CHECK-NEXT: LBB3_4: ; %cmpxchg.nostore
; CHECK-NEXT: mov w8, wzr
; CHECK-NEXT: clrex
; CHECK-NEXT: LBB3_5: ; %for.cond.preheader
; CHECK-NEXT: mov w22, #2
; CHECK-NEXT: LBB3_6: ; %for.cond
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
; CHECK-NEXT: cbz w22, LBB3_9
; CHECK-NEXT: ; %bb.7: ; %for.body
; CHECK-NEXT: ; in Loop: Header=BB3_6 Depth=1
; CHECK-NEXT: sub w22, w22, #1
; CHECK-NEXT: orr w9, w21, w20
; CHECK-NEXT: ldr w10, [x19, w22, sxtw #2]
; CHECK-NEXT: cmp w9, w10
; CHECK-NEXT: b.eq LBB3_6
; CHECK-NEXT: ; %bb.8: ; %if.then
; CHECK-NEXT: ; in Loop: Header=BB3_6 Depth=1
; CHECK-NEXT: sxtw x8, w22
; CHECK-NEXT: str w9, [x19, x8, lsl #2]
; CHECK-NEXT: bl _foo
; CHECK-NEXT: mov w8, wzr
; CHECK-NEXT: b LBB3_6
; CHECK-NEXT: LBB3_9: ; %for.cond.cleanup
; CHECK-NEXT: ldp x29, x30, [sp, #32] ; 16-byte Folded Reload
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ldp x20, x19, [sp, #16] ; 16-byte Folded Reload
; CHECK-NEXT: ldp x22, x21, [sp], #48 ; 16-byte Folded Reload
; CHECK-NEXT: ret
;
; OUTLINE-ATOMICS-LABEL: test_conditional2:
; OUTLINE-ATOMICS: ; %bb.0: ; %entry
; OUTLINE-ATOMICS-NEXT: stp x22, x21, [sp, #-48]! ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: stp x20, x19, [sp, #16] ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: stp x29, x30, [sp, #32] ; 16-byte Folded Spill
; OUTLINE-ATOMICS-NEXT: .cfi_def_cfa_offset 48
; OUTLINE-ATOMICS-NEXT: .cfi_offset w30, -8
; OUTLINE-ATOMICS-NEXT: .cfi_offset w29, -16
; OUTLINE-ATOMICS-NEXT: .cfi_offset w19, -24
; OUTLINE-ATOMICS-NEXT: .cfi_offset w20, -32
; OUTLINE-ATOMICS-NEXT: .cfi_offset w21, -40
; OUTLINE-ATOMICS-NEXT: .cfi_offset w22, -48
; OUTLINE-ATOMICS-NEXT: mov x19, x2
; OUTLINE-ATOMICS-NEXT: mov w20, w1
; OUTLINE-ATOMICS-NEXT: mov w21, w0
; OUTLINE-ATOMICS-NEXT: bl ___aarch64_cas4_acq_rel
; OUTLINE-ATOMICS-NEXT: cmp w0, w21
; OUTLINE-ATOMICS-NEXT: mov w22, #2
; OUTLINE-ATOMICS-NEXT: cset w8, eq
; OUTLINE-ATOMICS-NEXT: LBB3_1: ; %for.cond
; OUTLINE-ATOMICS-NEXT: ; =>This Inner Loop Header: Depth=1
; OUTLINE-ATOMICS-NEXT: cbz w22, LBB3_4
; OUTLINE-ATOMICS-NEXT: ; %bb.2: ; %for.body
; OUTLINE-ATOMICS-NEXT: ; in Loop: Header=BB3_1 Depth=1
; OUTLINE-ATOMICS-NEXT: sub w22, w22, #1
; OUTLINE-ATOMICS-NEXT: orr w9, w21, w20
; OUTLINE-ATOMICS-NEXT: ldr w10, [x19, w22, sxtw #2]
; OUTLINE-ATOMICS-NEXT: cmp w9, w10
; OUTLINE-ATOMICS-NEXT: b.eq LBB3_1
; OUTLINE-ATOMICS-NEXT: ; %bb.3: ; %if.then
; OUTLINE-ATOMICS-NEXT: ; in Loop: Header=BB3_1 Depth=1
; OUTLINE-ATOMICS-NEXT: sxtw x8, w22
; OUTLINE-ATOMICS-NEXT: str w9, [x19, x8, lsl #2]
; OUTLINE-ATOMICS-NEXT: bl _foo
; OUTLINE-ATOMICS-NEXT: mov w8, wzr
; OUTLINE-ATOMICS-NEXT: b LBB3_1
; OUTLINE-ATOMICS-NEXT: LBB3_4: ; %for.cond.cleanup
; OUTLINE-ATOMICS-NEXT: ldp x29, x30, [sp, #32] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: and w0, w8, #0x1
; OUTLINE-ATOMICS-NEXT: ldp x20, x19, [sp, #16] ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ldp x22, x21, [sp], #48 ; 16-byte Folded Reload
; OUTLINE-ATOMICS-NEXT: ret
entry:
%pair = cmpxchg i32* %c, i32 %a, i32 %b seq_cst seq_cst
%success = extractvalue { i32, i1 } %pair, 1
br label %for.cond
for.cond: ; preds = %if.end, %entry
%i.0 = phi i32 [ 2, %entry ], [ %dec, %if.end ]
%changed.0.off0 = phi i1 [ %success, %entry ], [ %changed.1.off0, %if.end ]
%dec = add nsw i32 %i.0, -1
%tobool = icmp eq i32 %i.0, 0
br i1 %tobool, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%changed.0.off0.lcssa = phi i1 [ %changed.0.off0, %for.cond ]
ret i1 %changed.0.off0.lcssa
for.body: ; preds = %for.cond
%or = or i32 %a, %b
%idxprom = sext i32 %dec to i64
%arrayidx = getelementptr inbounds i32, i32* %c, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%cmp = icmp eq i32 %or, %0
br i1 %cmp, label %if.end, label %if.then
if.then: ; preds = %for.body
store i32 %or, i32* %arrayidx, align 4
tail call void @foo()
br label %if.end
if.end: ; preds = %for.body, %if.then
%changed.1.off0 = phi i1 [ false, %if.then ], [ %changed.0.off0, %for.body ]
br label %for.cond
}
declare void @foo()
|
