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
|
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp -x c -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -target-cpu core2 -fopenmp-simd -x c -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c -triple x86_64-apple-darwin10 -target-cpu core2 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c -triple x86_64-apple-darwin10 -target-cpu core2 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
#define HEADER
_Bool bv, bx;
char cv, cx;
unsigned char ucv, ucx;
short sv, sx;
unsigned short usv, usx;
int iv, ix;
unsigned int uiv, uix;
long lv, lx;
unsigned long ulv, ulx;
long long llv, llx;
unsigned long long ullv, ullx;
float fv, fx;
double dv, dx;
long double ldv, ldx;
_Complex int civ, cix;
_Complex float cfv, cfx;
_Complex double cdv, cdx;
typedef int int4 __attribute__((__vector_size__(16)));
int4 int4x;
struct BitFields {
int : 32;
int a : 31;
} bfx;
struct BitFields_packed {
int : 32;
int a : 31;
} __attribute__ ((__packed__)) bfx_packed;
struct BitFields2 {
int : 31;
int a : 1;
} bfx2;
struct BitFields2_packed {
int : 31;
int a : 1;
} __attribute__ ((__packed__)) bfx2_packed;
struct BitFields3 {
int : 11;
int a : 14;
} bfx3;
struct BitFields3_packed {
int : 11;
int a : 14;
} __attribute__ ((__packed__)) bfx3_packed;
struct BitFields4 {
short : 16;
int a: 1;
long b : 7;
} bfx4;
struct BitFields4_packed {
short : 16;
int a: 1;
long b : 7;
} __attribute__ ((__packed__)) bfx4_packed;
typedef float float2 __attribute__((ext_vector_type(2)));
float2 float2x;
// Register "0" is currently an invalid register for global register variables.
// Use "esp" instead of "0".
// register int rix __asm__("0");
register int rix __asm__("esp");
// CHECK-LABEL: @main(
int main(void) {
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store i8
#pragma omp atomic read
bv = bx;
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store i8
#pragma omp atomic read
cv = cx;
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store i8
#pragma omp atomic read
ucv = ucx;
// CHECK: load atomic i16, ptr {{.*}} monotonic, align 2
// CHECK: store i16
#pragma omp atomic read
sv = sx;
// CHECK: load atomic i16, ptr {{.*}} monotonic, align 2
// CHECK: store i16
#pragma omp atomic read
usv = usx;
// CHECK: load atomic i32, ptr {{.*}} monotonic, align 4
// CHECK: store i32
#pragma omp atomic read
iv = ix;
// CHECK: load atomic i32, ptr {{.*}} monotonic, align 4
// CHECK: store i32
#pragma omp atomic read
uiv = uix;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i64
#pragma omp atomic read
lv = lx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i64
#pragma omp atomic read
ulv = ulx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i64
#pragma omp atomic read
llv = llx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i64
#pragma omp atomic read
ullv = ullx;
// CHECK: load atomic float, ptr {{.*}} monotonic, align 4
// CHECK: store float
#pragma omp atomic read
fv = fx;
// CHECK: load atomic double, ptr {{.*}} monotonic, align 8
// CHECK: store double
#pragma omp atomic read
dv = dx;
// CHECK: [[LD:%.+]] = load atomic i128, ptr {{.*}} monotonic, align 16
// CHECK: store i128 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load x86_fp80, ptr [[LDTEMP]]
// CHECK: store x86_fp80 [[LD]]
#pragma omp atomic read
ldv = ldx;
// CHECK: call{{.*}} void @__atomic_load(i64 noundef 8,
// CHECK: store i32
// CHECK: store i32
#pragma omp atomic read
civ = cix;
// CHECK: call{{.*}} void @__atomic_load(i64 noundef 8,
// CHECK: store float
// CHECK: store float
#pragma omp atomic read
cfv = cfx;
// CHECK: call{{.*}} void @__atomic_load(i64 noundef 16,
// CHECK: call{{.*}} @__kmpc_flush(
// CHECK: store double
// CHECK: store double
#pragma omp atomic seq_cst read
cdv = cdx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i8
#pragma omp atomic read
bv = ulx;
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store i8
#pragma omp atomic read
cv = bx;
// CHECK: load atomic i8, ptr {{.*}} seq_cst, align 1
// CHECK: call{{.*}} @__kmpc_flush(
// CHECK: store i8
#pragma omp atomic read seq_cst
ucv = cx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i16
#pragma omp atomic read
sv = ulx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store i16
#pragma omp atomic read
usv = lx;
// CHECK: load atomic i32, ptr {{.*}} seq_cst, align 4
// CHECK: call{{.*}} @__kmpc_flush(
// CHECK: store i32
#pragma omp atomic seq_cst, read
iv = uix;
// CHECK: load atomic i32, ptr {{.*}} monotonic, align 4
// CHECK: store i32
#pragma omp atomic read
uiv = ix;
// CHECK: call{{.*}} void @__atomic_load(i64 noundef 8,
// CHECK: store i64
#pragma omp atomic read
lv = cix;
// CHECK: load atomic float, ptr {{.*}} monotonic, align 4
// CHECK: store i64
#pragma omp atomic read
ulv = fx;
// CHECK: load atomic double, ptr {{.*}} monotonic, align 8
// CHECK: store i64
#pragma omp atomic read
llv = dx;
// CHECK: load atomic i128, ptr {{.*}} monotonic, align 16
// CHECK: store i64
#pragma omp atomic read
ullv = ldx;
// CHECK: call{{.*}} void @__atomic_load(i64 noundef 8,
// CHECK: store float
#pragma omp atomic read
fv = cix;
// CHECK: load atomic i16, ptr {{.*}} monotonic, align 2
// CHECK: store double
#pragma omp atomic read
dv = sx;
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bx;
// CHECK: load atomic i8, ptr {{.*}} monotonic, align 1
// CHECK: store i32
// CHECK: store i32
#pragma omp atomic read
civ = bx;
// CHECK: load atomic i16, ptr {{.*}} monotonic, align 2
// CHECK: store float
// CHECK: store float
#pragma omp atomic read
cfv = usx;
// CHECK: load atomic i64, ptr {{.*}} monotonic, align 8
// CHECK: store double
// CHECK: store double
#pragma omp atomic read
cdv = llx;
// CHECK: [[I128VAL:%.+]] = load atomic i128, ptr @{{.+}} monotonic, align 16
// CHECK: store i128 [[I128VAL]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load <4 x i32>, ptr [[LDTEMP]]
// CHECK: extractelement <4 x i32> [[LD]]
// CHECK: store i8
#pragma omp atomic read
bv = int4x[0];
// CHECK: [[LD:%.+]] = load atomic i32, ptr getelementptr (i8, ptr @{{.+}}, i64 4) monotonic, align 4
// CHECK: store i32 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i32, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i32 [[LD]], 1
// CHECK: ashr i32 [[SHL]], 1
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx.a;
// CHECK: call void @__atomic_load(i64 noundef 4, ptr noundef getelementptr (i8, ptr @bfx_packed, i64 4), ptr noundef [[LDTEMP:%.+]], i32 noundef 0)
// CHECK: [[LD:%.+]] = load i32, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i32 [[LD]], 1
// CHECK: ashr i32 [[SHL]], 1
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx_packed.a;
// CHECK: [[LD:%.+]] = load atomic i32, ptr @bfx2 monotonic, align 4
// CHECK: store i32 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i32, ptr [[LDTEMP]]
// CHECK: ashr i32 [[LD]], 31
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx2.a;
// CHECK: [[LD:%.+]] = load atomic i8, ptr getelementptr (i8, ptr @bfx2_packed, i64 3) monotonic, align 1
// CHECK: store i8 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i8, ptr [[LDTEMP]]
// CHECK: ashr i8 [[LD]], 7
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx2_packed.a;
// CHECK: [[LD:%.+]] = load atomic i32, ptr @bfx3 monotonic, align 4
// CHECK: store i32 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i32, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i32 [[LD]], 7
// CHECK: ashr i32 [[SHL]], 18
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx3.a;
// CHECK: call void @__atomic_load(i64 noundef 3, ptr noundef getelementptr (i8, ptr @bfx3_packed, i64 1), ptr noundef [[LDTEMP:%.+]], i32 noundef 0)
// CHECK: [[LD:%.+]] = load i24, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i24 [[LD]], 7
// CHECK: [[ASHR:%.+]] = ashr i24 [[SHL]], 10
// CHECK: sext i24 [[ASHR]] to i32
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx3_packed.a;
// CHECK: [[LD:%.+]] = load atomic i64, ptr @bfx4 monotonic, align 8
// CHECK: store i64 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i64, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i64 [[LD]], 47
// CHECK: [[ASHR:%.+]] = ashr i64 [[SHL]], 63
// CHECK: trunc i64 [[ASHR]] to i32
// CHECK: store x86_fp80
#pragma omp atomic read
ldv = bfx4.a;
// CHECK: [[LD:%.+]] = load atomic i8, ptr getelementptr (i8, ptr @bfx4_packed, i64 2) monotonic, align 1
// CHECK: store i8 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i8, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i8 [[LD]], 7
// CHECK: [[ASHR:%.+]] = ashr i8 [[SHL]], 7
// CHECK: sext i8 [[ASHR]] to i32
// CHECK: store x86_fp80
#pragma omp atomic relaxed read
ldv = bfx4_packed.a;
// CHECK: [[LD:%.+]] = load atomic i64, ptr @bfx4 monotonic, align 8
// CHECK: store i64 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i64, ptr [[LDTEMP]]
// CHECK: [[SHL:%.+]] = shl i64 [[LD]], 40
// CHECK: [[ASHR:%.+]] = ashr i64 [[SHL]], 57
// CHECK: store x86_fp80
#pragma omp atomic read relaxed
ldv = bfx4.b;
// CHECK: [[LD:%.+]] = load atomic i8, ptr getelementptr (i8, ptr @bfx4_packed, i64 2) acquire, align 1
// CHECK: store i8 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load i8, ptr [[LDTEMP]]
// CHECK: [[ASHR:%.+]] = ashr i8 [[LD]], 1
// CHECK: sext i8 [[ASHR]] to i64
// CHECK: call{{.*}} @__kmpc_flush(
// CHECK: store x86_fp80
#pragma omp atomic read acquire
ldv = bfx4_packed.b;
// CHECK: [[LD:%.+]] = load atomic i64, ptr @{{.+}} monotonic, align 8
// CHECK: store i64 [[LD]], ptr [[LDTEMP:%.+]]
// CHECK: [[LD:%.+]] = load <2 x float>, ptr [[LDTEMP]]
// CHECK: extractelement <2 x float> [[LD]]
// CHECK: store i64
#pragma omp atomic read
ulv = float2x.x;
// CHECK: call{{.*}} i{{[0-9]+}} @llvm.read_register
// CHECK: call{{.*}} @__kmpc_flush(
// CHECK: store double
#pragma omp atomic read seq_cst
dv = rix;
return 0;
}
#endif
|
