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
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: webassembly-registered-target
// RUN: %clang_cc1 -triple wasm32-unknown-unknown -emit-llvm -o - %s | FileCheck %s
// Multiple targets use emitVoidPtrVAArg to lower va_arg instructions in clang
// PPC is complicated, excluding from this case analysis
// ForceRightAdjust is false for all non-PPC targets
// AllowHigherAlign is only false for two Microsoft targets, both of which
// pass most things by reference.
//
// Address emitVoidPtrVAArg(CodeGenFunction &CGF, Address VAListAddr,
// QualType ValueTy, bool IsIndirect,
// TypeInfoChars ValueInfo, CharUnits SlotSizeAndAlign,
// bool AllowHigherAlign, bool ForceRightAdjust =
// false);
//
// Target IsIndirect SlotSize AllowHigher ForceRightAdjust
// ARC false four true false
// ARM varies four true false
// Mips false 4 or 8 true false
// RISCV varies register true false
// PPC elided
// LoongArch varies register true false
// NVPTX WIP
// AMDGPU WIP
// X86_32 false four true false
// X86_64 MS varies eight false false
// CSKY false four true false
// Webassembly varies four true false
// AArch64 false eight true false
// AArch64 MS false eight false false
//
// Webassembly passes indirectly iff it's an aggregate of multiple values
// Choosing this as a representative architecture to check IR generation
// partly because it has a relatively simple variadic calling convention.
// Int, by itself and packed in structs
// CHECK-LABEL: @raw_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
int raw_int(__builtin_va_list list) { return __builtin_va_arg(list, int); }
typedef struct {
int x;
} one_int_t;
// CHECK-LABEL: @one_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_ONE_INT_T:%.*]], align 4
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 4, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_ONE_INT_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[COERCE_DIVE]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
one_int_t one_int(__builtin_va_list list) {
return __builtin_va_arg(list, one_int_t);
}
typedef struct {
int x;
int y;
} two_int_t;
// CHECK-LABEL: @two_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[AGG_RESULT:%.*]], ptr align 4 [[TMP0]], i32 8, i1 false)
// CHECK-NEXT: ret void
//
two_int_t two_int(__builtin_va_list list) {
return __builtin_va_arg(list, two_int_t);
}
// Double, by itself and packed in structs
// CHECK-LABEL: @raw_double(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 7
// CHECK-NEXT: [[ARGP_CUR_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i32(ptr [[TMP0]], i32 -8)
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR_ALIGNED]], i32 8
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load double, ptr [[ARGP_CUR_ALIGNED]], align 8
// CHECK-NEXT: ret double [[TMP1]]
//
double raw_double(__builtin_va_list list) {
return __builtin_va_arg(list, double);
}
typedef struct {
double x;
} one_double_t;
// CHECK-LABEL: @one_double(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_ONE_DOUBLE_T:%.*]], align 8
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 7
// CHECK-NEXT: [[ARGP_CUR_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i32(ptr [[TMP0]], i32 -8)
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR_ALIGNED]], i32 8
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[RETVAL]], ptr align 8 [[ARGP_CUR_ALIGNED]], i32 8, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_ONE_DOUBLE_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP1:%.*]] = load double, ptr [[COERCE_DIVE]], align 8
// CHECK-NEXT: ret double [[TMP1]]
//
one_double_t one_double(__builtin_va_list list) {
return __builtin_va_arg(list, one_double_t);
}
typedef struct {
double x;
double y;
} two_double_t;
// CHECK-LABEL: @two_double(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[AGG_RESULT:%.*]], ptr align 8 [[TMP0]], i32 16, i1 false)
// CHECK-NEXT: ret void
//
two_double_t two_double(__builtin_va_list list) {
return __builtin_va_arg(list, two_double_t);
}
// Scalar smaller than the slot size (C would promote a short to int)
typedef struct {
char x;
} one_char_t;
// CHECK-LABEL: @one_char(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_ONE_CHAR_T:%.*]], align 1
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 1 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 1, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_ONE_CHAR_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[COERCE_DIVE]], align 1
// CHECK-NEXT: ret i8 [[TMP0]]
//
one_char_t one_char(__builtin_va_list list) {
return __builtin_va_arg(list, one_char_t);
}
typedef struct {
short x;
} one_short_t;
// CHECK-LABEL: @one_short(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_ONE_SHORT_T:%.*]], align 2
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 2 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 2, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_ONE_SHORT_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr [[COERCE_DIVE]], align 2
// CHECK-NEXT: ret i16 [[TMP0]]
//
one_short_t one_short(__builtin_va_list list) {
return __builtin_va_arg(list, one_short_t);
}
// Composite smaller than the slot size
typedef struct {
_Alignas(2) char x;
char y;
} char_pair_t;
// CHECK-LABEL: @char_pair(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 2 [[AGG_RESULT:%.*]], ptr align 2 [[TMP0]], i32 2, i1 false)
// CHECK-NEXT: ret void
//
char_pair_t char_pair(__builtin_va_list list) {
return __builtin_va_arg(list, char_pair_t);
}
// Empty struct
typedef struct {
} empty_t;
// CHECK-LABEL: @empty(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_EMPTY_T:%.*]], align 1
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 0
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 1 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 0, i1 false)
// CHECK-NEXT: ret void
//
empty_t empty(__builtin_va_list list) {
return __builtin_va_arg(list, empty_t);
}
typedef struct {
empty_t x;
int y;
} empty_int_t;
// CHECK-LABEL: @empty_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_EMPTY_INT_T:%.*]], align 4
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 4, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_EMPTY_INT_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[COERCE_DIVE]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
empty_int_t empty_int(__builtin_va_list list) {
return __builtin_va_arg(list, empty_int_t);
}
typedef struct {
int x;
empty_t y;
} int_empty_t;
// CHECK-LABEL: @int_empty(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_INT_EMPTY_T:%.*]], align 4
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[RETVAL]], ptr align 4 [[ARGP_CUR]], i32 4, i1 false)
// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_INT_EMPTY_T]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[COERCE_DIVE]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
int_empty_t int_empty(__builtin_va_list list) {
return __builtin_va_arg(list, int_empty_t);
}
// Need multiple va_arg instructions to check the postincrement
// Using types that are passed directly as the indirect handling
// is independent of the alignment handling in emitVoidPtrDirectVAArg.
// CHECK-LABEL: @multiple_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT0_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT1_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT2_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT0:%.*]], ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT1:%.*]], ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT2:%.*]], ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[TMP1]], align 4
// CHECK-NEXT: [[ARGP_CUR1:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT2:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR1]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT2]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARGP_CUR1]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP2]], ptr [[TMP3]], align 4
// CHECK-NEXT: [[ARGP_CUR3:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT4:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR3]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT4]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[ARGP_CUR3]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = load ptr, ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP4]], ptr [[TMP5]], align 4
// CHECK-NEXT: ret void
//
void multiple_int(__builtin_va_list list, int *out0, int *out1, int *out2) {
*out0 = __builtin_va_arg(list, int);
*out1 = __builtin_va_arg(list, int);
*out2 = __builtin_va_arg(list, int);
}
// Scalars in structs are an easy way of specifying alignment from C
// CHECK-LABEL: @increasing_alignment(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT0_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT1_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT2_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT3_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT0:%.*]], ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT1:%.*]], ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT2:%.*]], ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT3:%.*]], ptr [[OUT3_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 1 [[TMP0]], ptr align 4 [[ARGP_CUR]], i32 1, i1 false)
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR1:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT2:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR1]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT2]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 2 [[TMP1]], ptr align 4 [[ARGP_CUR1]], i32 2, i1 false)
// CHECK-NEXT: [[ARGP_CUR3:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT4:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR3]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT4]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARGP_CUR3]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP2]], ptr [[TMP3]], align 4
// CHECK-NEXT: [[ARGP_CUR5:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR5]], i32 7
// CHECK-NEXT: [[ARGP_CUR5_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i32(ptr [[TMP4]], i32 -8)
// CHECK-NEXT: [[ARGP_NEXT6:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR5_ALIGNED]], i32 8
// CHECK-NEXT: store ptr [[ARGP_NEXT6]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = load double, ptr [[ARGP_CUR5_ALIGNED]], align 8
// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[OUT3_ADDR]], align 4
// CHECK-NEXT: store double [[TMP5]], ptr [[TMP6]], align 8
// CHECK-NEXT: ret void
//
void increasing_alignment(__builtin_va_list list, one_char_t *out0,
one_short_t *out1, int *out2, double *out3) {
*out0 = __builtin_va_arg(list, one_char_t);
*out1 = __builtin_va_arg(list, one_short_t);
*out2 = __builtin_va_arg(list, int);
*out3 = __builtin_va_arg(list, double);
}
// CHECK-LABEL: @decreasing_alignment(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT0_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT1_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT2_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT3_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT0:%.*]], ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT1:%.*]], ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT2:%.*]], ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT3:%.*]], ptr [[OUT3_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 7
// CHECK-NEXT: [[ARGP_CUR_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i32(ptr [[TMP0]], i32 -8)
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR_ALIGNED]], i32 8
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load double, ptr [[ARGP_CUR_ALIGNED]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[OUT0_ADDR]], align 4
// CHECK-NEXT: store double [[TMP1]], ptr [[TMP2]], align 8
// CHECK-NEXT: [[ARGP_CUR1:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT2:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR1]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT2]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[ARGP_CUR1]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[OUT1_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP3]], ptr [[TMP4]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = load ptr, ptr [[OUT2_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR3:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT4:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR3]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT4]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 2 [[TMP5]], ptr align 4 [[ARGP_CUR3]], i32 2, i1 false)
// CHECK-NEXT: [[TMP6:%.*]] = load ptr, ptr [[OUT3_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR5:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT6:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR5]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT6]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 1 [[TMP6]], ptr align 4 [[ARGP_CUR5]], i32 1, i1 false)
// CHECK-NEXT: ret void
//
void decreasing_alignment(__builtin_va_list list, double *out0, int *out1,
one_short_t *out2, one_char_t *out3) {
*out0 = __builtin_va_arg(list, double);
*out1 = __builtin_va_arg(list, int);
*out2 = __builtin_va_arg(list, one_short_t);
*out3 = __builtin_va_arg(list, one_char_t);
}
// Typical edge cases, none hit special handling in VAArg lowering.
typedef struct {
int x[16];
double y[8];
} large_value_t;
// CHECK-LABEL: @large_value(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT:%.*]], ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[TMP0]], ptr align 8 [[TMP1]], i32 128, i1 false)
// CHECK-NEXT: ret void
//
void large_value(__builtin_va_list list, large_value_t *out) {
*out = __builtin_va_arg(list, large_value_t);
}
typedef int v128_t __attribute__((__vector_size__(16), __aligned__(16)));
// CHECK-LABEL: @vector(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT:%.*]], ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 15
// CHECK-NEXT: [[ARGP_CUR_ALIGNED:%.*]] = call ptr @llvm.ptrmask.p0.i32(ptr [[TMP0]], i32 -16)
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR_ALIGNED]], i32 16
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, ptr [[ARGP_CUR_ALIGNED]], align 16
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: store <4 x i32> [[TMP1]], ptr [[TMP2]], align 16
// CHECK-NEXT: ret void
//
void vector(__builtin_va_list list, v128_t *out) {
*out = __builtin_va_arg(list, v128_t);
}
typedef struct BF {
float not_an_i32[2];
int A : 1;
char B;
int C : 13;
} BF;
// CHECK-LABEL: @bitfield(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LIST_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: [[OUT_ADDR:%.*]] = alloca ptr, align 4
// CHECK-NEXT: store ptr [[LIST:%.*]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: store ptr [[OUT:%.*]], ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[OUT_ADDR]], align 4
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load ptr, ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, ptr [[ARGP_CUR]], i32 4
// CHECK-NEXT: store ptr [[ARGP_NEXT]], ptr [[LIST_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARGP_CUR]], align 4
// CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr align 4 [[TMP0]], ptr align 4 [[TMP1]], i32 12, i1 false)
// CHECK-NEXT: ret void
//
void bitfield(__builtin_va_list list, BF *out) {
*out = __builtin_va_arg(list, BF);
}
|
