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
|
// RUN: %clang_cc1 %s -emit-llvm -o - -triple=armv5-unknown-freebsd -std=c11 | FileCheck %s
// Test that we are generating atomicrmw instructions, rather than
// compare-exchange loops for common atomic ops. This makes a big difference
// on RISC platforms, where the compare-exchange loop becomes a ll/sc pair for
// the load and then another ll/sc in the loop, expanding to about 30
// instructions when it should be only 4. It has a smaller, but still
// noticeable, impact on platforms like x86 and RISC-V, where there are atomic
// RMW instructions.
//
// We currently emit cmpxchg loops for most operations on _Bools, because
// they're sufficiently rare that it's not worth making sure that the semantics
// are correct.
struct elem;
struct ptr {
struct elem *ptr;
};
// CHECK-DAG: %struct.ptr = type { %struct.elem* }
struct elem {
_Atomic(struct ptr) link;
};
// CHECK-DAG: %struct.elem = type { %struct.ptr }
struct ptr object;
// CHECK-DAG: @object = common global %struct.ptr zeroinitializer
// CHECK-DAG: @testStructGlobal = global {{.*}} { i16 1, i16 2, i16 3, i16 4 }
// CHECK-DAG: @testPromotedStructGlobal = global {{.*}} { %{{.*}} { i16 1, i16 2, i16 3 }, [2 x i8] zeroinitializer }
typedef int __attribute__((vector_size(16))) vector;
_Atomic(_Bool) b;
_Atomic(int) i;
_Atomic(long long) l;
_Atomic(short) s;
_Atomic(char*) p;
_Atomic(float) f;
_Atomic(vector) v;
// CHECK: testinc
void testinc(void)
{
// Special case for suffix bool++, sets to true and returns the old value.
// CHECK: atomicrmw xchg i8* @b, i8 1 seq_cst
b++;
// CHECK: atomicrmw add i32* @i, i32 1 seq_cst
i++;
// CHECK: atomicrmw add i64* @l, i64 1 seq_cst
l++;
// CHECK: atomicrmw add i16* @s, i16 1 seq_cst
s++;
// Prefix increment
// Special case for bool: set to true and return true
// CHECK: store atomic i8 1, i8* @b seq_cst, align 1
++b;
// Currently, we have no variant of atomicrmw that returns the new value, so
// we have to generate an atomic add, which returns the old value, and then a
// non-atomic add.
// CHECK: atomicrmw add i32* @i, i32 1 seq_cst
// CHECK: add i32
++i;
// CHECK: atomicrmw add i64* @l, i64 1 seq_cst
// CHECK: add i64
++l;
// CHECK: atomicrmw add i16* @s, i16 1 seq_cst
// CHECK: add i16
++s;
}
// CHECK: testdec
void testdec(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
b--;
// CHECK: atomicrmw sub i32* @i, i32 1 seq_cst
i--;
// CHECK: atomicrmw sub i64* @l, i64 1 seq_cst
l--;
// CHECK: atomicrmw sub i16* @s, i16 1 seq_cst
s--;
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
--b;
// CHECK: atomicrmw sub i32* @i, i32 1 seq_cst
// CHECK: sub i32
--i;
// CHECK: atomicrmw sub i64* @l, i64 1 seq_cst
// CHECK: sub i64
--l;
// CHECK: atomicrmw sub i16* @s, i16 1 seq_cst
// CHECK: sub i16
--s;
}
// CHECK: testaddeq
void testaddeq(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
// CHECK: atomicrmw add i32* @i, i32 42 seq_cst
// CHECK: atomicrmw add i64* @l, i64 42 seq_cst
// CHECK: atomicrmw add i16* @s, i16 42 seq_cst
b += 42;
i += 42;
l += 42;
s += 42;
}
// CHECK: testsubeq
void testsubeq(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
// CHECK: atomicrmw sub i32* @i, i32 42 seq_cst
// CHECK: atomicrmw sub i64* @l, i64 42 seq_cst
// CHECK: atomicrmw sub i16* @s, i16 42 seq_cst
b -= 42;
i -= 42;
l -= 42;
s -= 42;
}
// CHECK: testxoreq
void testxoreq(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
// CHECK: atomicrmw xor i32* @i, i32 42 seq_cst
// CHECK: atomicrmw xor i64* @l, i64 42 seq_cst
// CHECK: atomicrmw xor i16* @s, i16 42 seq_cst
b ^= 42;
i ^= 42;
l ^= 42;
s ^= 42;
}
// CHECK: testoreq
void testoreq(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
// CHECK: atomicrmw or i32* @i, i32 42 seq_cst
// CHECK: atomicrmw or i64* @l, i64 42 seq_cst
// CHECK: atomicrmw or i16* @s, i16 42 seq_cst
b |= 42;
i |= 42;
l |= 42;
s |= 42;
}
// CHECK: testandeq
void testandeq(void)
{
// CHECK: call arm_aapcscc zeroext i1 @__atomic_compare_exchange(i32 1, i8* @b
// CHECK: atomicrmw and i32* @i, i32 42 seq_cst
// CHECK: atomicrmw and i64* @l, i64 42 seq_cst
// CHECK: atomicrmw and i16* @s, i16 42 seq_cst
b &= 42;
i &= 42;
l &= 42;
s &= 42;
}
// CHECK-LABEL: define arm_aapcscc void @testFloat(float*
void testFloat(_Atomic(float) *fp) {
// CHECK: [[FP:%.*]] = alloca float*
// CHECK-NEXT: [[X:%.*]] = alloca float
// CHECK-NEXT: [[F:%.*]] = alloca float
// CHECK-NEXT: [[TMP0:%.*]] = alloca float
// CHECK-NEXT: [[TMP1:%.*]] = alloca float
// CHECK-NEXT: store float* {{%.*}}, float** [[FP]]
// CHECK-NEXT: [[T0:%.*]] = load float*, float** [[FP]]
// CHECK-NEXT: store float 1.000000e+00, float* [[T0]], align 4
__c11_atomic_init(fp, 1.0f);
// CHECK-NEXT: store float 2.000000e+00, float* [[X]], align 4
_Atomic(float) x = 2.0f;
// CHECK-NEXT: [[T0:%.*]] = load float*, float** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast float* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast float* [[TMP0]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_load(i32 4, i8* [[T1]], i8* [[T2]], i32 5)
// CHECK-NEXT: [[T3:%.*]] = load float, float* [[TMP0]], align 4
// CHECK-NEXT: store float [[T3]], float* [[F]]
float f = *fp;
// CHECK-NEXT: [[T0:%.*]] = load float, float* [[F]], align 4
// CHECK-NEXT: [[T1:%.*]] = load float*, float** [[FP]], align 4
// CHECK-NEXT: store float [[T0]], float* [[TMP1]], align 4
// CHECK-NEXT: [[T2:%.*]] = bitcast float* [[T1]] to i8*
// CHECK-NEXT: [[T3:%.*]] = bitcast float* [[TMP1]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_store(i32 4, i8* [[T2]], i8* [[T3]], i32 5)
*fp = f;
// CHECK-NEXT: ret void
}
// CHECK: define arm_aapcscc void @testComplexFloat([[CF:{ float, float }]]*
void testComplexFloat(_Atomic(_Complex float) *fp) {
// CHECK: [[FP:%.*]] = alloca [[CF]]*, align 4
// CHECK-NEXT: [[X:%.*]] = alloca [[CF]], align 8
// CHECK-NEXT: [[F:%.*]] = alloca [[CF]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = alloca [[CF]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = alloca [[CF]], align 8
// CHECK-NEXT: store [[CF]]*
// CHECK-NEXT: [[P:%.*]] = load [[CF]]*, [[CF]]** [[FP]]
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[P]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[P]], i32 0, i32 1
// CHECK-NEXT: store float 1.000000e+00, float* [[T0]]
// CHECK-NEXT: store float 0.000000e+00, float* [[T1]]
__c11_atomic_init(fp, 1.0f);
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[X]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[X]], i32 0, i32 1
// CHECK-NEXT: store float 2.000000e+00, float* [[T0]]
// CHECK-NEXT: store float 0.000000e+00, float* [[T1]]
_Atomic(_Complex float) x = 2.0f;
// CHECK-NEXT: [[T0:%.*]] = load [[CF]]*, [[CF]]** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast [[CF]]* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[CF]]* [[TMP0]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_load(i32 8, i8* [[T1]], i8* [[T2]], i32 5)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[R:%.*]] = load float, float* [[T0]]
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[TMP0]], i32 0, i32 1
// CHECK-NEXT: [[I:%.*]] = load float, float* [[T0]]
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[F]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[F]], i32 0, i32 1
// CHECK-NEXT: store float [[R]], float* [[T0]]
// CHECK-NEXT: store float [[I]], float* [[T1]]
_Complex float f = *fp;
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[F]], i32 0, i32 0
// CHECK-NEXT: [[R:%.*]] = load float, float* [[T0]]
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[F]], i32 0, i32 1
// CHECK-NEXT: [[I:%.*]] = load float, float* [[T0]]
// CHECK-NEXT: [[DEST:%.*]] = load [[CF]]*, [[CF]]** [[FP]], align 4
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[TMP1]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[CF]], [[CF]]* [[TMP1]], i32 0, i32 1
// CHECK-NEXT: store float [[R]], float* [[T0]]
// CHECK-NEXT: store float [[I]], float* [[T1]]
// CHECK-NEXT: [[T0:%.*]] = bitcast [[CF]]* [[DEST]] to i8*
// CHECK-NEXT: [[T1:%.*]] = bitcast [[CF]]* [[TMP1]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_store(i32 8, i8* [[T0]], i8* [[T1]], i32 5)
*fp = f;
// CHECK-NEXT: ret void
}
typedef struct { short x, y, z, w; } S;
_Atomic S testStructGlobal = (S){1, 2, 3, 4};
// CHECK: define arm_aapcscc void @testStruct([[S:.*]]*
void testStruct(_Atomic(S) *fp) {
// CHECK: [[FP:%.*]] = alloca [[S]]*, align 4
// CHECK-NEXT: [[X:%.*]] = alloca [[S]], align 8
// CHECK-NEXT: [[F:%.*]] = alloca [[S:%.*]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = alloca [[S]], align 8
// CHECK-NEXT: store [[S]]*
// CHECK-NEXT: [[P:%.*]] = load [[S]]*, [[S]]** [[FP]]
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[P]], i32 0, i32 0
// CHECK-NEXT: store i16 1, i16* [[T0]], align 8
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[P]], i32 0, i32 1
// CHECK-NEXT: store i16 2, i16* [[T0]], align 2
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[P]], i32 0, i32 2
// CHECK-NEXT: store i16 3, i16* [[T0]], align 4
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[P]], i32 0, i32 3
// CHECK-NEXT: store i16 4, i16* [[T0]], align 2
__c11_atomic_init(fp, (S){1,2,3,4});
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[X]], i32 0, i32 0
// CHECK-NEXT: store i16 1, i16* [[T0]], align 8
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[X]], i32 0, i32 1
// CHECK-NEXT: store i16 2, i16* [[T0]], align 2
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[X]], i32 0, i32 2
// CHECK-NEXT: store i16 3, i16* [[T0]], align 4
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[S]], [[S]]* [[X]], i32 0, i32 3
// CHECK-NEXT: store i16 4, i16* [[T0]], align 2
_Atomic(S) x = (S){1,2,3,4};
// CHECK-NEXT: [[T0:%.*]] = load [[S]]*, [[S]]** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast [[S]]* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[S]]* [[F]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_load(i32 8, i8* [[T1]], i8* [[T2]], i32 5)
S f = *fp;
// CHECK-NEXT: [[T0:%.*]] = load [[S]]*, [[S]]** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast [[S]]* [[TMP0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[S]]* [[F]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[T1]], i8* [[T2]], i32 8, i32 2, i1 false)
// CHECK-NEXT: [[T3:%.*]] = bitcast [[S]]* [[T0]] to i8*
// CHECK-NEXT: [[T4:%.*]] = bitcast [[S]]* [[TMP0]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_store(i32 8, i8* [[T3]], i8* [[T4]], i32 5)
*fp = f;
// CHECK-NEXT: ret void
}
typedef struct { short x, y, z; } PS;
_Atomic PS testPromotedStructGlobal = (PS){1, 2, 3};
// CHECK: define arm_aapcscc void @testPromotedStruct([[APS:.*]]*
void testPromotedStruct(_Atomic(PS) *fp) {
// CHECK: [[FP:%.*]] = alloca [[APS]]*, align 4
// CHECK-NEXT: [[X:%.*]] = alloca [[APS]], align 8
// CHECK-NEXT: [[F:%.*]] = alloca [[PS:%.*]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = alloca [[APS]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = alloca [[APS]], align 8
// CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[TMP2:%.*]] = alloca %struct.PS, align 2
// CHECK-NEXT: [[TMP3:%.*]] = alloca [[APS]], align 8
// CHECK-NEXT: store [[APS]]*
// CHECK-NEXT: [[P:%.*]] = load [[APS]]*, [[APS]]** [[FP]]
// CHECK-NEXT: [[T0:%.*]] = bitcast [[APS]]* [[P]] to i8*
// CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[T0]], i8 0, i64 8, i32 8, i1 false)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[APS]], [[APS]]* [[P]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 0
// CHECK-NEXT: store i16 1, i16* [[T1]], align 8
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 1
// CHECK-NEXT: store i16 2, i16* [[T1]], align 2
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 2
// CHECK-NEXT: store i16 3, i16* [[T1]], align 4
__c11_atomic_init(fp, (PS){1,2,3});
// CHECK-NEXT: [[T0:%.*]] = bitcast [[APS]]* [[X]] to i8*
// CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* [[T0]], i8 0, i32 8, i32 8, i1 false)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[APS]], [[APS]]* [[X]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 0
// CHECK-NEXT: store i16 1, i16* [[T1]], align 8
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 1
// CHECK-NEXT: store i16 2, i16* [[T1]], align 2
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[PS]], [[PS]]* [[T0]], i32 0, i32 2
// CHECK-NEXT: store i16 3, i16* [[T1]], align 4
_Atomic(PS) x = (PS){1,2,3};
// CHECK-NEXT: [[T0:%.*]] = load [[APS]]*, [[APS]]** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast [[APS]]* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[APS]]* [[TMP0]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_load(i32 8, i8* [[T1]], i8* [[T2]], i32 5)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[APS]], [[APS]]* [[TMP0]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = bitcast [[PS]]* [[F]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[PS]]* [[T0]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[T1]], i8* [[T2]], i32 6, i32 2, i1 false)
PS f = *fp;
// CHECK-NEXT: [[T0:%.*]] = load [[APS]]*, [[APS]]** [[FP]]
// CHECK-NEXT: [[T1:%.*]] = bitcast { %struct.PS, [2 x i8] }* [[TMP1]] to i8*
// CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* [[T1]], i8 0, i32 8, i32 8, i1 false)
// CHECK-NEXT: [[T1:%.*]] = getelementptr inbounds [[APS]], [[APS]]* [[TMP1]], i32 0, i32 0
// CHECK-NEXT: [[T2:%.*]] = bitcast [[PS]]* [[T1]] to i8*
// CHECK-NEXT: [[T3:%.*]] = bitcast [[PS]]* [[F]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[T2]], i8* [[T3]], i32 6, i32 2, i1 false)
// CHECK-NEXT: [[T4:%.*]] = bitcast [[APS]]* [[T0]] to i8*
// CHECK-NEXT: [[T5:%.*]] = bitcast [[APS]]* [[TMP1]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_store(i32 8, i8* [[T4]], i8* [[T5]], i32 5)
*fp = f;
// CHECK-NEXT: [[T0:%.*]] = load [[APS]]*, [[APS]]** [[FP]], align 4
// CHECK-NEXT: [[T1:%.*]] = bitcast [[APS]]* [[T0]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast [[APS]]* [[TMP3]] to i8*
// CHECK-NEXT: call arm_aapcscc void @__atomic_load(i32 8, i8* [[T1]], i8* [[T2]], i32 5)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds [[APS]], [[APS]]* [[TMP3]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = bitcast %struct.PS* [[TMP2]] to i8*
// CHECK-NEXT: [[T2:%.*]] = bitcast %struct.PS* [[T0]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[T1]], i8* [[T2]], i32 6, i32 2, i1 false)
// CHECK-NEXT: [[T0:%.*]] = getelementptr inbounds %struct.PS, %struct.PS* [[TMP2]], i32 0, i32 0
// CHECK-NEXT: [[T1:%.*]] = load i16, i16* [[T0]], align 2
// CHECK-NEXT: [[T2:%.*]] = sext i16 [[T1]] to i32
// CHECK-NEXT: store i32 [[T2]], i32* [[A]], align 4
int a = ((PS)*fp).x;
// CHECK-NEXT: ret void
}
// CHECK: define arm_aapcscc void @testPromotedStructOps([[APS:.*]]*
// FIXME: none of these look right, but we can leave the "test" here
// to make sure they at least don't crash.
void testPromotedStructOps(_Atomic(PS) *p) {
PS a = __c11_atomic_load(p, 5);
__c11_atomic_store(p, a, 5);
PS b = __c11_atomic_exchange(p, a, 5);
_Bool v = __c11_atomic_compare_exchange_strong(p, &b, a, 5, 5);
v = __c11_atomic_compare_exchange_weak(p, &b, a, 5, 5);
}
|
