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
|
// RUN: %clang_cc1 -no-opaque-pointers -triple csky -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -no-opaque-pointers -triple csky -target-feature +fpuv2_df -target-feature +fpuv2_sf \
// RUN: -target-feature +hard-float -target-feature +hard-float-abi -emit-llvm %s -o - | FileCheck %s
// This file contains test cases that will have the same output for the hard-float
// and soft-float ABIs.
#include <stddef.h>
#include <stdint.h>
// CHECK-LABEL: define{{.*}} void @f_void()
void f_void(void) {}
// Scalar arguments and return values smaller than the word size are extended
// according to the sign of their type, up to 32 bits
// CHECK-LABEL: define{{.*}} zeroext i1 @f_scalar_0(i1 noundef zeroext %x)
_Bool f_scalar_0(_Bool x) { return x; }
// CHECK-LABEL: define{{.*}} signext i8 @f_scalar_1(i8 noundef signext %x)
int8_t f_scalar_1(int8_t x) { return x; }
// CHECK-LABEL: define{{.*}} zeroext i8 @f_scalar_2(i8 noundef zeroext %x)
uint8_t f_scalar_2(uint8_t x) { return x; }
// CHECK-LABEL: define{{.*}} i32 @f_scalar_3(i32 noundef %x)
int32_t f_scalar_3(int32_t x) { return x; }
// CHECK-LABEL: define{{.*}} i64 @f_scalar_4(i64 noundef %x)
int64_t f_scalar_4(int64_t x) { return x; }
// CHECK-LABEL: define{{.*}} float @f_fp_scalar_1(float noundef %x)
float f_fp_scalar_1(float x) { return x; }
// CHECK-LABEL: define{{.*}} double @f_fp_scalar_2(double noundef %x)
double f_fp_scalar_2(double x) { return x; }
// CHECK-LABEL: define{{.*}} double @f_fp_scalar_3(double noundef %x)
long double f_fp_scalar_3(long double x) { return x; }
// Empty structs or unions are ignored.
struct empty_s {};
// CHECK-LABEL: define{{.*}} void @f_agg_empty_struct()
struct empty_s f_agg_empty_struct(struct empty_s x) {
return x;
}
union empty_u {};
// CHECK-LABEL: define{{.*}} void @f_agg_empty_union()
union empty_u f_agg_empty_union(union empty_u x) {
return x;
}
// Aggregates <= 4*xlen may be passed in registers, so will be coerced to
// integer arguments. The rules for return are <= 2*xlen.
struct tiny {
uint8_t a, b, c, d;
};
// CHECK-LABEL: define{{.*}} void @f_agg_tiny(i32 %x.coerce)
void f_agg_tiny(struct tiny x) {
x.a += x.b;
x.c += x.d;
}
// CHECK-LABEL: define{{.*}} i32 @f_agg_tiny_ret()
struct tiny f_agg_tiny_ret(void) {
return (struct tiny){1, 2, 3, 4};
}
struct small {
int32_t a, *b;
};
// CHECK-LABEL: define{{.*}} void @f_agg_small([2 x i32] %x.coerce)
void f_agg_small(struct small x) {
x.a += *x.b;
x.b = &x.a;
}
// CHECK-LABEL: define{{.*}} [2 x i32] @f_agg_small_ret()
struct small f_agg_small_ret(void) {
return (struct small){1, 0};
}
struct small_aligned {
int64_t a;
};
// CHECK-LABEL: define{{.*}} void @f_agg_small_aligned(i64 %x.coerce)
void f_agg_small_aligned(struct small_aligned x) {
x.a += x.a;
}
// CHECK-LABEL: define{{.*}} i64 @f_agg_small_aligned_ret(i64 %x.coerce)
struct small_aligned f_agg_small_aligned_ret(struct small_aligned x) {
return (struct small_aligned){10};
}
// For argument type, the first 4*XLen parts of aggregate will be passed
// in registers, and the rest will be passed in stack.
// So we can coerce to integers directly and let backend handle it correctly.
// For return type, aggregate which <= 2*XLen will be returned in registers.
// Otherwise, aggregate will be returned indirectly.
struct large {
int32_t a, b, c, d;
};
// CHECK-LABEL: define{{.*}} void @f_agg_large([4 x i32] %x.coerce)
void f_agg_large(struct large x) {
x.a = x.b + x.c + x.d;
}
// The address where the struct should be written to will be the first
// argument
// CHECK-LABEL: define{{.*}} void @f_agg_large_ret(%struct.large* noalias sret(%struct.large) align 4 %agg.result, i32 noundef %i, i8 noundef signext %j)
struct large f_agg_large_ret(int32_t i, int8_t j) {
return (struct large){1, 2, 3, 4};
}
typedef unsigned char v16i8 __attribute__((vector_size(16)));
// CHECK-LABEL: define{{.*}} void @f_vec_large_v16i8(<16 x i8> noundef %x)
void f_vec_large_v16i8(v16i8 x) {
x[0] = x[7];
}
// CHECK-LABEL: define{{.*}} <16 x i8> @f_vec_large_v16i8_ret()
v16i8 f_vec_large_v16i8_ret(void) {
return (v16i8){1, 2, 3, 4, 5, 6, 7, 8};
}
// CHECK-LABEL: define{{.*}} i32 @f_scalar_stack_1(i32 %a.coerce, [2 x i32] %b.coerce, i64 %c.coerce, [4 x i32] %d.coerce, i8 noundef zeroext %e, i8 noundef signext %f, i8 noundef zeroext %g, i8 noundef signext %h)
int f_scalar_stack_1(struct tiny a, struct small b, struct small_aligned c,
struct large d, uint8_t e, int8_t f, uint8_t g, int8_t h) {
return g + h;
}
// Ensure that scalars passed on the stack are still determined correctly in
// the presence of large return values that consume a register due to the need
// to pass a pointer.
// CHECK-LABEL: define{{.*}} void @f_scalar_stack_2(%struct.large* noalias sret(%struct.large) align 4 %agg.result, i32 noundef %a, i64 noundef %b, i64 noundef %c, double noundef %d, i8 noundef zeroext %e, i8 noundef signext %f, i8 noundef zeroext %g)
struct large f_scalar_stack_2(int32_t a, int64_t b, int64_t c, long double d,
uint8_t e, int8_t f, uint8_t g) {
return (struct large){a, e, f, g};
}
// CHECK-LABEL: define{{.*}} double @f_scalar_stack_4(i32 noundef %a, i64 noundef %b, i64 noundef %c, double noundef %d, i8 noundef zeroext %e, i8 noundef signext %f, i8 noundef zeroext %g)
long double f_scalar_stack_4(int32_t a, int64_t b, int64_t c, long double d,
uint8_t e, int8_t f, uint8_t g) {
return d;
}
// Aggregates should be coerced integer arrary.
// CHECK-LABEL: define{{.*}} void @f_scalar_stack_5(double noundef %a, i64 noundef %b, double noundef %c, i64 noundef %d, i32 noundef %e, i64 noundef %f, float noundef %g, double noundef %h, double noundef %i)
void f_scalar_stack_5(double a, int64_t b, double c, int64_t d, int e,
int64_t f, float g, double h, long double i) {}
// CHECK-LABEL: define{{.*}} void @f_agg_stack(double noundef %a, i64 noundef %b, double noundef %c, i64 noundef %d, i32 %e.coerce, [2 x i32] %f.coerce, i64 %g.coerce, [4 x i32] %h.coerce)
void f_agg_stack(double a, int64_t b, double c, int64_t d, struct tiny e,
struct small f, struct small_aligned g, struct large h) {}
// Ensure that ABI lowering happens as expected for vararg calls. For CSKY
// with the base integer calling convention there will be no observable
// differences in the lowered IR for a call with varargs vs without.
int f_va_callee(int, ...);
// CHECK-LABEL: define{{.*}} void @f_va_caller()
// CHECK: call i32 (i32, ...) @f_va_callee(i32 noundef 1, i32 noundef 2, i64 noundef 3, double noundef 4.000000e+00, double noundef 5.000000e+00, i32 {{%.*}}, [2 x i32] {{%.*}}, i64 {{%.*}}, [4 x i32] {{%.*}})
void f_va_caller(void) {
f_va_callee(1, 2, 3LL, 4.0f, 5.0, (struct tiny){6, 7, 8, 9},
(struct small){10, NULL}, (struct small_aligned){11},
(struct large){12, 13, 14, 15});
}
// CHECK-LABEL: define{{.*}} i32 @f_va_1(i8* noundef %fmt, ...) {{.*}} {
// CHECK: [[FMT_ADDR:%.*]] = alloca i8*, align 4
// CHECK: [[VA:%.*]] = alloca i8*, align 4
// CHECK: [[V:%.*]] = alloca i32, align 4
// CHECK: store i8* %fmt, i8** [[FMT_ADDR]], align 4
// CHECK: [[VA1:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK: call void @llvm.va_start(i8* [[VA1]])
// CHECK: [[ARGP_CUR:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR]], i32 4
// CHECK: store i8* [[ARGP_NEXT]], i8** [[VA]], align 4
// CHECK: [[TMP0:%.*]] = bitcast i8* [[ARGP_CUR]] to i32*
// CHECK: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK: store i32 [[TMP1]], i32* [[V]], align 4
// CHECK: [[VA2:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK: call void @llvm.va_end(i8* [[VA2]])
// CHECK: [[TMP2:%.*]] = load i32, i32* [[V]], align 4
// CHECK: ret i32 [[TMP2]]
// CHECK: }
int f_va_1(char *fmt, ...) {
__builtin_va_list va;
__builtin_va_start(va, fmt);
int v = __builtin_va_arg(va, int);
__builtin_va_end(va);
return v;
}
// CHECK-LABEL: @f_va_2(
// CHECK: [[FMT_ADDR:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[VA:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[V:%.*]] = alloca double, align 4
// CHECK-NEXT: store i8* [[FMT:%.*]], i8** [[FMT_ADDR]], align 4
// CHECK-NEXT: [[VA1:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_start(i8* [[VA1]])
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR]], i32 8
// CHECK-NEXT: store i8* [[ARGP_NEXT]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[ARGP_CUR]] to double*
// CHECK-NEXT: [[TMP4:%.*]] = load double, double* [[TMP3]], align 4
// CHECK-NEXT: store double [[TMP4]], double* [[V]], align 4
// CHECK-NEXT: [[VA2:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_end(i8* [[VA2]])
// CHECK-NEXT: [[TMP5:%.*]] = load double, double* [[V]], align 4
// CHECK-NEXT: ret double [[TMP5]]
double f_va_2(char *fmt, ...) {
__builtin_va_list va;
__builtin_va_start(va, fmt);
double v = __builtin_va_arg(va, double);
__builtin_va_end(va);
return v;
}
// CHECK-LABEL: @f_va_3(
// CHECK: [[FMT_ADDR:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[VA:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[V:%.*]] = alloca double, align 4
// CHECK-NEXT: [[W:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[X:%.*]] = alloca double, align 4
// CHECK-NEXT: store i8* [[FMT:%.*]], i8** [[FMT_ADDR]], align 4
// CHECK-NEXT: [[VA1:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_start(i8* [[VA1]])
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR]], i32 8
// CHECK-NEXT: store i8* [[ARGP_NEXT]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[ARGP_CUR]] to double*
// CHECK-NEXT: [[TMP4:%.*]] = load double, double* [[TMP3]], align 4
// CHECK-NEXT: store double [[TMP4]], double* [[V]], align 4
// CHECK-NEXT: [[ARGP_CUR2:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT3:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR2]], i32 4
// CHECK-NEXT: store i8* [[ARGP_NEXT3]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = bitcast i8* [[ARGP_CUR2]] to i32*
// CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4
// CHECK-NEXT: store i32 [[TMP6]], i32* [[W]], align 4
// CHECK-NEXT: [[ARGP_CUR4:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT5:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR4]], i32 8
// CHECK-NEXT: store i8* [[ARGP_NEXT5]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP10:%.*]] = bitcast i8* [[ARGP_CUR4]] to double*
// CHECK-NEXT: [[TMP11:%.*]] = load double, double* [[TMP10]], align 4
// CHECK-NEXT: store double [[TMP11]], double* [[X]], align 4
// CHECK-NEXT: [[VA6:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_end(i8* [[VA6]])
// CHECK-NEXT: [[TMP12:%.*]] = load double, double* [[V]], align 4
// CHECK-NEXT: [[TMP13:%.*]] = load double, double* [[X]], align 4
// CHECK-NEXT: [[ADD:%.*]] = fadd double [[TMP12]], [[TMP13]]
// CHECK-NEXT: ret double [[ADD]]
double f_va_3(char *fmt, ...) {
__builtin_va_list va;
__builtin_va_start(va, fmt);
double v = __builtin_va_arg(va, double);
int w = __builtin_va_arg(va, int);
double x = __builtin_va_arg(va, double);
__builtin_va_end(va);
return v + x;
}
// CHECK-LABEL: define{{.*}} i32 @f_va_4(i8* noundef %fmt, ...) {{.*}} {
// CHECK: [[FMT_ADDR:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[VA:%.*]] = alloca i8*, align 4
// CHECK-NEXT: [[V:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[LD:%.*]] = alloca double, align 4
// CHECK-NEXT: [[TS:%.*]] = alloca [[STRUCT_TINY:%.*]], align 1
// CHECK-NEXT: [[SS:%.*]] = alloca [[STRUCT_SMALL:%.*]], align 4
// CHECK-NEXT: [[LS:%.*]] = alloca [[STRUCT_LARGE:%.*]], align 4
// CHECK-NEXT: [[RET:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i8* [[FMT:%.*]], i8** [[FMT_ADDR]], align 4
// CHECK-NEXT: [[VA1:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_start(i8* [[VA1]])
// CHECK-NEXT: [[ARGP_CUR:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR]], i32 4
// CHECK-NEXT: store i8* [[ARGP_NEXT]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i8* [[ARGP_CUR]] to i32*
// CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK-NEXT: store i32 [[TMP1]], i32* [[V]], align 4
// CHECK-NEXT: [[ARGP_CUR2:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT3:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR2]], i32 8
// CHECK-NEXT: store i8* [[ARGP_NEXT3]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[ARGP_CUR2]] to double*
// CHECK-NEXT: [[TMP4:%.*]] = load double, double* [[TMP2]], align 4
// CHECK-NEXT: store double [[TMP4]], double* [[LD]], align 4
// CHECK-NEXT: [[ARGP_CUR4:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT5:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR4]], i32 4
// CHECK-NEXT: store i8* [[ARGP_NEXT5]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = bitcast i8* [[ARGP_CUR4]] to %struct.tiny*
// CHECK-NEXT: [[TMP6:%.*]] = bitcast %struct.tiny* [[TS]] to i8*
// CHECK-NEXT: [[TMP7:%.*]] = bitcast %struct.tiny* [[TMP5]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[TMP6]], i8* align 4 [[TMP7]], i32 4, i1 false)
// CHECK-NEXT: [[ARGP_CUR6:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT7:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR6]], i32 8
// CHECK-NEXT: store i8* [[ARGP_NEXT7]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP8:%.*]] = bitcast i8* [[ARGP_CUR6]] to %struct.small*
// CHECK-NEXT: [[TMP9:%.*]] = bitcast %struct.small* [[SS]] to i8*
// CHECK-NEXT: [[TMP10:%.*]] = bitcast %struct.small* [[TMP8]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP9]], i8* align 4 [[TMP10]], i32 8, i1 false)
// CHECK-NEXT: [[ARGP_CUR8:%.*]] = load i8*, i8** [[VA]], align 4
// CHECK-NEXT: [[ARGP_NEXT9:%.*]] = getelementptr inbounds i8, i8* [[ARGP_CUR8]], i32 16
// CHECK-NEXT: store i8* [[ARGP_NEXT9]], i8** [[VA]], align 4
// CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[ARGP_CUR8]] to %struct.large*
// CHECK-NEXT: [[TMP13:%.*]] = bitcast %struct.large* [[LS]] to i8*
// CHECK-NEXT: [[TMP14:%.*]] = bitcast %struct.large* [[TMP11]] to i8*
// CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP13]], i8* align 4 [[TMP14]], i32 16, i1 false)
// CHECK-NEXT: [[VA10:%.*]] = bitcast i8** [[VA]] to i8*
// CHECK-NEXT: call void @llvm.va_end(i8* [[VA10]])
int f_va_4(char *fmt, ...) {
__builtin_va_list va;
__builtin_va_start(va, fmt);
int v = __builtin_va_arg(va, int);
long double ld = __builtin_va_arg(va, long double);
struct tiny ts = __builtin_va_arg(va, struct tiny);
struct small ss = __builtin_va_arg(va, struct small);
struct large ls = __builtin_va_arg(va, struct large);
__builtin_va_end(va);
int ret = (int)((long double)v + ld);
ret = ret + ts.a + ts.b + ts.c + ts.d;
ret = ret + ss.a + (int)ss.b;
ret = ret + ls.a + ls.b + ls.c + ls.d;
return ret;
}
|
