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
|
// RUN: %clang_cc1 -triple armv7-apple-darwin -target-abi aapcs -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple armv7-apple-darwin -target-abi apcs-gnu -emit-llvm -o - %s | FileCheck -check-prefix=APCS-GNU %s
// RUN: %clang_cc1 -triple arm-linux-androideabi -emit-llvm -o - %s | FileCheck -check-prefix=ANDROID %s
#include <stdarg.h>
typedef __attribute__(( ext_vector_type(2) )) int __int2;
typedef __attribute__(( ext_vector_type(3) )) char __char3;
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;
// Passing legal vector types as varargs.
double varargs_vec_2i(int fixed, ...) {
// CHECK: varargs_vec_2i
// CHECK: [[VAR:%.*]] = alloca <2 x i32>, align 8
// CHECK: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// CHECK: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <2 x i32>*
// CHECK: [[VEC:%.*]] = load <2 x i32>, <2 x i32>* [[AP_CAST]], align 8
// CHECK: store <2 x i32> [[VEC]], <2 x i32>* [[VAR]], align 8
// APCS-GNU: varargs_vec_2i
// APCS-GNU: [[VAR:%.*]] = alloca <2 x i32>, align 8
// APCS-GNU: [[AP:%.*]] = load i8*,
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP]], i32 8
// APCS-GNU: [[AP_CAST:%.*]] = bitcast i8* [[AP]] to <2 x i32>*
// APCS-GNU: [[VEC:%.*]] = load <2 x i32>, <2 x i32>* [[AP_CAST]], align 4
// APCS-GNU: store <2 x i32> [[VEC]], <2 x i32>* [[VAR]], align 8
// ANDROID: varargs_vec_2i
// ANDROID: [[VAR:%.*]] = alloca <2 x i32>, align 8
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// ANDROID: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <2 x i32>*
// ANDROID: [[VEC:%.*]] = load <2 x i32>, <2 x i32>* [[AP_CAST]], align 8
// ANDROID: store <2 x i32> [[VEC]], <2 x i32>* [[VAR]], align 8
va_list ap;
double sum = fixed;
va_start(ap, fixed);
__int2 c3 = va_arg(ap, __int2);
sum = sum + c3.x + c3.y;
va_end(ap);
return sum;
}
double test_2i(__int2 *in) {
// CHECK: test_2i
// CHECK: call arm_aapcscc double (i32, ...) @varargs_vec_2i(i32 3, <2 x i32> {{%.*}})
// APCS-GNU: test_2i
// APCS-GNU: call double (i32, ...) @varargs_vec_2i(i32 3, <2 x i32> {{%.*}})
// ANDROID: test_2i
// ANDROID: call double (i32, ...) @varargs_vec_2i(i32 3, <2 x i32> {{%.*}})
return varargs_vec_2i(3, *in);
}
double varargs_vec_3c(int fixed, ...) {
// CHECK: varargs_vec_3c
// CHECK: alloca <3 x i8>, align 4
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP:%.*]], i32 4
// CHECK: bitcast i8* [[AP]] to <3 x i8>*
// APCS-GNU: varargs_vec_3c
// APCS-GNU: alloca <3 x i8>, align 4
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP:%.*]], i32 4
// APCS-GNU: bitcast i8* [[AP]] to <3 x i8>*
// ANDROID: varargs_vec_3c
// ANDROID: alloca <3 x i8>, align 4
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP:%.*]], i32 4
// ANDROID: bitcast i8* [[AP]] 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 arm_aapcscc double (i32, ...) @varargs_vec_3c(i32 3, i32 {{%.*}})
// APCS-GNU: test_3c
// APCS-GNU: call double (i32, ...) @varargs_vec_3c(i32 3, i32 {{%.*}})
// ANDROID: test_3c
// ANDROID: call double (i32, ...) @varargs_vec_3c(i32 3, <3 x i8> {{%.*}})
return varargs_vec_3c(3, *in);
}
double varargs_vec_5c(int fixed, ...) {
// CHECK: varargs_vec_5c
// CHECK: [[VAR:%.*]] = alloca <5 x i8>, align 8
// CHECK: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// CHECK: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <5 x i8>*
// CHECK: [[VEC:%.*]] = load <5 x i8>, <5 x i8>* [[AP_CAST]], align 8
// CHECK: store <5 x i8> [[VEC]], <5 x i8>* [[VAR]], align 8
// APCS-GNU: varargs_vec_5c
// APCS-GNU: [[VAR:%.*]] = alloca <5 x i8>, align 8
// APCS-GNU: [[AP:%.*]] = load i8*,
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP]], i32 8
// APCS-GNU: [[AP_CAST:%.*]] = bitcast i8* [[AP]] to <5 x i8>*
// APCS-GNU: [[VEC:%.*]] = load <5 x i8>, <5 x i8>* [[AP_CAST]], align 4
// APCS-GNU: store <5 x i8> [[VEC]], <5 x i8>* [[VAR]], align 8
// ANDROID: varargs_vec_5c
// ANDROID: [[VAR:%.*]] = alloca <5 x i8>, align 8
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// ANDROID: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <5 x i8>*
// ANDROID: [[VEC:%.*]] = load <5 x i8>, <5 x i8>* [[AP_CAST]], align 8
// ANDROID: store <5 x i8> [[VEC]], <5 x i8>* [[VAR]], align 8
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 arm_aapcscc double (i32, ...) @varargs_vec_5c(i32 5, <2 x i32> {{%.*}})
// APCS-GNU: test_5c
// APCS-GNU: call double (i32, ...) @varargs_vec_5c(i32 5, <2 x i32> {{%.*}})
// ANDROID: test_5c
// ANDROID: 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: [[VAR:%.*]] = alloca <9 x i8>, align 16
// CHECK: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// CHECK: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <9 x i8>*
// CHECK: [[T0:%.*]] = load <9 x i8>, <9 x i8>* [[AP_CAST]], align 8
// CHECK: store <9 x i8> [[T0]], <9 x i8>* [[VAR]], align 16
// APCS-GNU: varargs_vec_9c
// APCS-GNU: [[VAR:%.*]] = alloca <9 x i8>, align 16
// APCS-GNU: [[AP:%.*]] = load i8*,
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP]], i32 16
// APCS-GNU: [[AP_CAST:%.*]] = bitcast i8* [[AP]] to <9 x i8>*
// APCS-GNU: [[VEC:%.*]] = load <9 x i8>, <9 x i8>* [[AP_CAST]], align 4
// APCS-GNU: store <9 x i8> [[VEC]], <9 x i8>* [[VAR]], align 16
// ANDROID: varargs_vec_9c
// ANDROID: [[VAR:%.*]] = alloca <9 x i8>, align 16
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// ANDROID: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <9 x i8>*
// ANDROID: [[T0:%.*]] = load <9 x i8>, <9 x i8>* [[AP_CAST]], align 8
// ANDROID: store <9 x i8> [[T0]], <9 x i8>* [[VAR]], align 16
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 arm_aapcscc double (i32, ...) @varargs_vec_9c(i32 9, <4 x i32> {{%.*}})
// APCS-GNU: test_9c
// APCS-GNU: call double (i32, ...) @varargs_vec_9c(i32 9, <4 x i32> {{%.*}})
// ANDROID: test_9c
// ANDROID: 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 inbounds i8, i8* [[AP:%.*]], i32 4
// CHECK: [[VAR:%.*]] = bitcast i8* [[AP]] to <19 x i8>**
// CHECK: [[VAR2:%.*]] = load <19 x i8>*, <19 x i8>** [[VAR]]
// APCS-GNU: varargs_vec_19c
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP:%.*]], i32 4
// APCS-GNU: [[VAR:%.*]] = bitcast i8* [[AP]] to <19 x i8>**
// APCS-GNU: [[VAR2:%.*]] = load <19 x i8>*, <19 x i8>** [[VAR]]
// ANDROID: varargs_vec_19c
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP:%.*]], i32 4
// ANDROID: [[VAR:%.*]] = bitcast i8* [[AP]] to <19 x i8>**
// ANDROID: [[VAR2:%.*]] = load <19 x i8>*, <19 x i8>** [[VAR]]
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 arm_aapcscc double (i32, ...) @varargs_vec_19c(i32 19, <19 x i8>* {{%.*}})
// APCS-GNU: test_19c
// APCS-GNU: call double (i32, ...) @varargs_vec_19c(i32 19, <19 x i8>* {{%.*}})
// ANDROID: test_19c
// ANDROID: 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: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// CHECK: bitcast i8* [[AP_ALIGN]] to <3 x i16>*
// APCS-GNU: varargs_vec_3s
// APCS-GNU: [[VAR:%.*]] = alloca <3 x i16>, align 8
// APCS-GNU: [[AP:%.*]] = load i8*,
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP]], i32 8
// APCS-GNU: [[AP_CAST:%.*]] = bitcast i8* [[AP]] to <3 x i16>*
// APCS-GNU: [[VEC:%.*]] = load <3 x i16>, <3 x i16>* [[AP_CAST]], align 4
// ANDROID: varargs_vec_3s
// ANDROID: alloca <3 x i16>, align 8
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 8
// ANDROID: bitcast i8* [[AP_ALIGN]] 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 arm_aapcscc double (i32, ...) @varargs_vec_3s(i32 3, <2 x i32> {{%.*}})
// APCS-GNU: test_3s
// APCS-GNU: call double (i32, ...) @varargs_vec_3s(i32 3, <2 x i32> {{%.*}})
// ANDROID: test_3s
// ANDROID: call double (i32, ...) @varargs_vec_3s(i32 3, <3 x i16> {{%.*}})
return varargs_vec_3s(3, *in);
}
double varargs_vec_5s(int fixed, ...) {
// CHECK: varargs_vec_5s
// CHECK: [[VAR_ALIGN:%.*]] = alloca <5 x i16>, align 16
// CHECK: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// CHECK: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <5 x i16>*
// CHECK: [[VEC:%.*]] = load <5 x i16>, <5 x i16>* [[AP_CAST]], align 8
// CHECK: store <5 x i16> [[VEC]], <5 x i16>* [[VAR_ALIGN]], align 16
// APCS-GNU: varargs_vec_5s
// APCS-GNU: [[VAR:%.*]] = alloca <5 x i16>, align 16
// APCS-GNU: [[AP:%.*]] = load i8*,
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP]], i32 16
// APCS-GNU: [[AP_CAST:%.*]] = bitcast i8* [[AP]] to <5 x i16>*
// APCS-GNU: [[VEC:%.*]] = load <5 x i16>, <5 x i16>* [[AP_CAST]], align 4
// ANDROID: varargs_vec_5s
// ANDROID: [[VAR_ALIGN:%.*]] = alloca <5 x i16>, align 16
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// ANDROID: [[AP_CAST:%.*]] = bitcast i8* [[AP_ALIGN]] to <5 x i16>*
// ANDROID: [[VEC:%.*]] = load <5 x i16>, <5 x i16>* [[AP_CAST]], align 8
// ANDROID: store <5 x i16> [[VEC]], <5 x i16>* [[VAR_ALIGN]], align 16
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 arm_aapcscc double (i32, ...) @varargs_vec_5s(i32 5, <4 x i32> {{%.*}})
// APCS-GNU: test_5s
// APCS-GNU: call double (i32, ...) @varargs_vec_5s(i32 5, <4 x i32> {{%.*}})
// ANDROID: test_5s
// ANDROID: call double (i32, ...) @varargs_vec_5s(i32 5, <4 x i32> {{%.*}})
return varargs_vec_5s(5, *in);
}
// Pass struct as varargs.
typedef struct
{
__int2 i2;
float f;
} StructWithVec;
double varargs_struct(int fixed, ...) {
// CHECK: varargs_struct
// CHECK: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// CHECK: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// CHECK: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// CHECK: bitcast i8* [[AP_ALIGN]] to %struct.StructWithVec*
// APCS-GNU: varargs_struct
// APCS-GNU: [[VAR_ALIGN:%.*]] = alloca %struct.StructWithVec
// APCS-GNU: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* {{%.*}}, i32 16
// APCS-GNU: bitcast %struct.StructWithVec* [[VAR_ALIGN]] to i8*
// APCS-GNU: call void @llvm.memcpy
// ANDROID: varargs_struct
// ANDROID: [[ALIGN:%.*]] = and i32 {{%.*}}, -8
// ANDROID: [[AP_ALIGN:%.*]] = inttoptr i32 [[ALIGN]] to i8*
// ANDROID: [[AP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[AP_ALIGN]], i32 16
// ANDROID: bitcast i8* [[AP_ALIGN]] to %struct.StructWithVec*
va_list ap;
double sum = fixed;
va_start(ap, fixed);
StructWithVec c3 = va_arg(ap, StructWithVec);
sum = sum + c3.i2.x + c3.i2.y + c3.f;
va_end(ap);
return sum;
}
double test_struct(StructWithVec* d) {
// CHECK: test_struct
// CHECK: call arm_aapcscc double (i32, ...) @varargs_struct(i32 3, [2 x i64] {{%.*}})
// APCS-GNU: test_struct
// APCS-GNU: call double (i32, ...) @varargs_struct(i32 3, [2 x i64] {{%.*}})
// ANDROID: test_struct
// ANDROID: call double (i32, ...) @varargs_struct(i32 3, [2 x i64] {{%.*}})
return varargs_struct(3, *d);
}
|
