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
|
// RUN: %clang_cc1 -triple arm64-apple-ios7 -target-abi darwinpcs -emit-llvm -o - %s | FileCheck %s
#include <stdarg.h>
typedef __attribute__(( ext_vector_type(3) )) char __char3;
typedef __attribute__(( ext_vector_type(4) )) char __char4;
typedef __attribute__(( ext_vector_type(5) )) char __char5;
typedef __attribute__(( ext_vector_type(9) )) char __char9;
typedef __attribute__(( ext_vector_type(19) )) char __char19;
typedef __attribute__(( ext_vector_type(3) )) short __short3;
typedef __attribute__(( ext_vector_type(5) )) short __short5;
typedef __attribute__(( ext_vector_type(3) )) int __int3;
typedef __attribute__(( ext_vector_type(5) )) int __int5;
typedef __attribute__(( ext_vector_type(3) )) double __double3;
double varargs_vec_3c(int fixed, ...) {
// CHECK: varargs_vec_3c
// CHECK: alloca <3 x i8>, align 4
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <3 x i8>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char3 c3 = va_arg(ap, __char3);
sum = sum + c3.x + c3.y;
va_end(ap);
return sum;
}
double test_3c(__char3 *in) {
// CHECK: test_3c
// CHECK: call double (i32, ...)* @varargs_vec_3c(i32 3, i32 {{%.*}})
return varargs_vec_3c(3, *in);
}
double varargs_vec_4c(int fixed, ...) {
// CHECK: varargs_vec_4c
// CHECK: alloca <4 x i8>, align 4
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <4 x i8>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char4 c4 = va_arg(ap, __char4);
sum = sum + c4.x + c4.y;
va_end(ap);
return sum;
}
double test_4c(__char4 *in) {
// CHECK: test_4c
// CHECK: call double (i32, ...)* @varargs_vec_4c(i32 4, i32 {{%.*}})
return varargs_vec_4c(4, *in);
}
double varargs_vec_5c(int fixed, ...) {
// CHECK: varargs_vec_5c
// CHECK: alloca <5 x i8>, align 8
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <5 x i8>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char5 c5 = va_arg(ap, __char5);
sum = sum + c5.x + c5.y;
va_end(ap);
return sum;
}
double test_5c(__char5 *in) {
// CHECK: test_5c
// CHECK: call double (i32, ...)* @varargs_vec_5c(i32 5, <2 x i32> {{%.*}})
return varargs_vec_5c(5, *in);
}
double varargs_vec_9c(int fixed, ...) {
// CHECK: varargs_vec_9c
// CHECK: alloca <9 x i8>, align 16
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <9 x i8>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char9 c9 = va_arg(ap, __char9);
sum = sum + c9.x + c9.y;
va_end(ap);
return sum;
}
double test_9c(__char9 *in) {
// CHECK: test_9c
// CHECK: call double (i32, ...)* @varargs_vec_9c(i32 9, <4 x i32> {{%.*}})
return varargs_vec_9c(9, *in);
}
double varargs_vec_19c(int fixed, ...) {
// CHECK: varargs_vec_19c
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <19 x i8>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char19 c19 = va_arg(ap, __char19);
sum = sum + c19.x + c19.y;
va_end(ap);
return sum;
}
double test_19c(__char19 *in) {
// CHECK: test_19c
// CHECK: call double (i32, ...)* @varargs_vec_19c(i32 19, <19 x i8>* {{%.*}})
return varargs_vec_19c(19, *in);
}
double varargs_vec_3s(int fixed, ...) {
// CHECK: varargs_vec_3s
// CHECK: alloca <3 x i16>, align 8
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <3 x i16>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__short3 c3 = va_arg(ap, __short3);
sum = sum + c3.x + c3.y;
va_end(ap);
return sum;
}
double test_3s(__short3 *in) {
// CHECK: test_3s
// CHECK: call double (i32, ...)* @varargs_vec_3s(i32 3, <2 x i32> {{%.*}})
return varargs_vec_3s(3, *in);
}
double varargs_vec_5s(int fixed, ...) {
// CHECK: varargs_vec_5s
// CHECK: alloca <5 x i16>, align 16
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <5 x i16>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__short5 c5 = va_arg(ap, __short5);
sum = sum + c5.x + c5.y;
va_end(ap);
return sum;
}
double test_5s(__short5 *in) {
// CHECK: test_5s
// CHECK: call double (i32, ...)* @varargs_vec_5s(i32 5, <4 x i32> {{%.*}})
return varargs_vec_5s(5, *in);
}
double varargs_vec_3i(int fixed, ...) {
// CHECK: varargs_vec_3i
// CHECK: alloca <3 x i32>, align 16
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <3 x i32>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__int3 c3 = va_arg(ap, __int3);
sum = sum + c3.x + c3.y;
va_end(ap);
return sum;
}
double test_3i(__int3 *in) {
// CHECK: test_3i
// CHECK: call double (i32, ...)* @varargs_vec_3i(i32 3, <4 x i32> {{%.*}})
return varargs_vec_3i(3, *in);
}
double varargs_vec_5i(int fixed, ...) {
// CHECK: varargs_vec_5i
// CHECK: alloca <5 x i32>, align 16
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <5 x i32>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__int5 c5 = va_arg(ap, __int5);
sum = sum + c5.x + c5.y;
va_end(ap);
return sum;
}
double test_5i(__int5 *in) {
// CHECK: test_5i
// CHECK: call double (i32, ...)* @varargs_vec_5i(i32 5, <5 x i32>* {{%.*}})
return varargs_vec_5i(5, *in);
}
double varargs_vec_3d(int fixed, ...) {
// CHECK: varargs_vec_3d
// CHECK: alloca <3 x double>, align 16
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <3 x double>*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__double3 c3 = va_arg(ap, __double3);
sum = sum + c3.x + c3.y;
va_end(ap);
return sum;
}
double test_3d(__double3 *in) {
// CHECK: test_3d
// CHECK: call double (i32, ...)* @varargs_vec_3d(i32 3, <3 x double>* {{%.*}})
return varargs_vec_3d(3, *in);
}
double varargs_vec(int fixed, ...) {
// CHECK: varargs_vec
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__char3 c3 = va_arg(ap, __char3);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <3 x i8>*
sum = sum + c3.x + c3.y;
__char5 c5 = va_arg(ap, __char5);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <5 x i8>*
sum = sum + c5.x + c5.y;
__char9 c9 = va_arg(ap, __char9);
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <9 x i8>*
sum = sum + c9.x + c9.y;
__char19 c19 = va_arg(ap, __char19);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <19 x i8>*
sum = sum + c19.x + c19.y;
__short3 s3 = va_arg(ap, __short3);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: bitcast i8* [[AP_CUR]] to <3 x i16>*
sum = sum + s3.x + s3.y;
__short5 s5 = va_arg(ap, __short5);
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <5 x i16>*
sum = sum + s5.x + s5.y;
__int3 i3 = va_arg(ap, __int3);
// CHECK: [[ALIGN:%.*]] = and i64 {{%.*}}, -16
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i64 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to <3 x i32>*
sum = sum + i3.x + i3.y;
__int5 i5 = va_arg(ap, __int5);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <5 x i32>*
sum = sum + i5.x + i5.y;
__double3 d3 = va_arg(ap, __double3);
// CHECK: [[AP_NEXT:%.*]] = getelementptr i8* [[AP_CUR:%.*]], i32 8
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP_CUR]] to i8**
// CHECK: [[VAR2:%.*]] = load i8** [[VAR]]
// CHECK: bitcast i8* [[VAR2]] to <3 x double>*
sum = sum + d3.x + d3.y;
va_end(ap);
return sum;
}
double test(__char3 *c3, __char5 *c5, __char9 *c9, __char19 *c19,
__short3 *s3, __short5 *s5, __int3 *i3, __int5 *i5,
__double3 *d3) {
double ret = varargs_vec(3, *c3, *c5, *c9, *c19, *s3, *s5, *i3, *i5, *d3);
// CHECK: call double (i32, ...)* @varargs_vec(i32 3, i32 {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> {{%.*}}, <19 x i8>* {{%.*}}, <2 x i32> {{%.*}}, <4 x i32> {{%.*}}, <4 x i32> {{%.*}}, <5 x i32>* {{%.*}}, <3 x double>* {{%.*}})
return ret;
}
__attribute__((noinline)) double args_vec_3c(int fixed, __char3 c3) {
// CHECK: args_vec_3c
// CHECK: [[C3:%.*]] = alloca <3 x i8>, align 4
// CHECK: [[TMP:%.*]] = bitcast <3 x i8>* [[C3]] to i32*
// CHECK: store i32 {{%.*}}, i32* [[TMP]]
double sum = fixed;
sum = sum + c3.x + c3.y;
return sum;
}
double fixed_3c(__char3 *in) {
// CHECK: fixed_3c
// CHECK: call double @args_vec_3c(i32 3, i32 {{%.*}})
return args_vec_3c(3, *in);
}
__attribute__((noinline)) double args_vec_5c(int fixed, __char5 c5) {
// CHECK: args_vec_5c
// CHECK: [[C5:%.*]] = alloca <5 x i8>, align 8
// CHECK: [[TMP:%.*]] = bitcast <5 x i8>* [[C5]] to <2 x i32>*
// CHECK: store <2 x i32> {{%.*}}, <2 x i32>* [[TMP]], align 1
double sum = fixed;
sum = sum + c5.x + c5.y;
return sum;
}
double fixed_5c(__char5 *in) {
// CHECK: fixed_5c
// CHECK: call double @args_vec_5c(i32 5, <2 x i32> {{%.*}})
return args_vec_5c(5, *in);
}
__attribute__((noinline)) double args_vec_9c(int fixed, __char9 c9) {
// CHECK: args_vec_9c
// CHECK: [[C9:%.*]] = alloca <9 x i8>, align 16
// CHECK: [[TMP:%.*]] = bitcast <9 x i8>* [[C9]] to <4 x i32>*
// CHECK: store <4 x i32> {{%.*}}, <4 x i32>* [[TMP]], align 1
double sum = fixed;
sum = sum + c9.x + c9.y;
return sum;
}
double fixed_9c(__char9 *in) {
// CHECK: fixed_9c
// CHECK: call double @args_vec_9c(i32 9, <4 x i32> {{%.*}})
return args_vec_9c(9, *in);
}
__attribute__((noinline)) double args_vec_19c(int fixed, __char19 c19) {
// CHECK: args_vec_19c
// CHECK: [[C19:%.*]] = load <19 x i8>* {{.*}}, align 16
double sum = fixed;
sum = sum + c19.x + c19.y;
return sum;
}
double fixed_19c(__char19 *in) {
// CHECK: fixed_19c
// CHECK: call double @args_vec_19c(i32 19, <19 x i8>* {{%.*}})
return args_vec_19c(19, *in);
}
__attribute__((noinline)) double args_vec_3s(int fixed, __short3 c3) {
// CHECK: args_vec_3s
// CHECK: [[C3:%.*]] = alloca <3 x i16>, align 8
// CHECK: [[TMP:%.*]] = bitcast <3 x i16>* [[C3]] to <2 x i32>*
// CHECK: store <2 x i32> {{%.*}}, <2 x i32>* [[TMP]], align 1
double sum = fixed;
sum = sum + c3.x + c3.y;
return sum;
}
double fixed_3s(__short3 *in) {
// CHECK: fixed_3s
// CHECK: call double @args_vec_3s(i32 3, <2 x i32> {{%.*}})
return args_vec_3s(3, *in);
}
__attribute__((noinline)) double args_vec_5s(int fixed, __short5 c5) {
// CHECK: args_vec_5s
// CHECK: [[C5:%.*]] = alloca <5 x i16>, align 16
// CHECK: [[TMP:%.*]] = bitcast <5 x i16>* [[C5]] to <4 x i32>*
// CHECK: store <4 x i32> {{%.*}}, <4 x i32>* [[TMP]], align 1
double sum = fixed;
sum = sum + c5.x + c5.y;
return sum;
}
double fixed_5s(__short5 *in) {
// CHECK: fixed_5s
// CHECK: call double @args_vec_5s(i32 5, <4 x i32> {{%.*}})
return args_vec_5s(5, *in);
}
__attribute__((noinline)) double args_vec_3i(int fixed, __int3 c3) {
// CHECK: args_vec_3i
// CHECK: [[C3:%.*]] = alloca <3 x i32>, align 16
// CHECK: [[TMP:%.*]] = bitcast <3 x i32>* [[C3]] to <4 x i32>*
// CHECK: store <4 x i32> {{%.*}}, <4 x i32>* [[TMP]], align 1
double sum = fixed;
sum = sum + c3.x + c3.y;
return sum;
}
double fixed_3i(__int3 *in) {
// CHECK: fixed_3i
// CHECK: call double @args_vec_3i(i32 3, <4 x i32> {{%.*}})
return args_vec_3i(3, *in);
}
__attribute__((noinline)) double args_vec_5i(int fixed, __int5 c5) {
// CHECK: args_vec_5i
// CHECK: [[C5:%.*]] = load <5 x i32>* {{%.*}}, align 16
double sum = fixed;
sum = sum + c5.x + c5.y;
return sum;
}
double fixed_5i(__int5 *in) {
// CHECK: fixed_5i
// CHECK: call double @args_vec_5i(i32 5, <5 x i32>* {{%.*}})
return args_vec_5i(5, *in);
}
__attribute__((noinline)) double args_vec_3d(int fixed, __double3 c3) {
// CHECK: args_vec_3d
// CHECK: [[CAST:%.*]] = bitcast <3 x double>* {{%.*}} to <4 x double>*
// CHECK: [[LOAD:%.*]] = load <4 x double>* [[CAST]]
// CHECK: shufflevector <4 x double> [[LOAD]], <4 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
double sum = fixed;
sum = sum + c3.x + c3.y;
return sum;
}
double fixed_3d(__double3 *in) {
// CHECK: fixed_3d
// CHECK: call double @args_vec_3d(i32 3, <3 x double>* {{%.*}})
return args_vec_3d(3, *in);
}
|
