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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-linux-generic -verify-machineinstrs -mattr=sse2 | FileCheck %s --check-prefix=X86 --check-prefix=X86-SSE
; RUN: llc < %s -mtriple=i386-linux-generic -verify-machineinstrs | FileCheck %s --check-prefix=X86 --check-prefix=X86-NOSSE
; RUN: llc < %s -mtriple=x86_64-linux-generic -verify-machineinstrs -mattr=sse2 | FileCheck %s --check-prefix=X64
; Note: This test is testing that the lowering for atomics matches what we
; currently emit for non-atomics + the atomic restriction. The presence of
; particular lowering detail in these tests should not be read as requiring
; that detail for correctness unless it's related to the atomicity itself.
; (Specifically, there were reviewer questions about the lowering for halfs
; and their calling convention which remain unresolved.)
define void @store_half(half* %fptr, half %v) {
; X86-SSE-LABEL: store_half:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pushl %esi
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: subl $8, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: .cfi_offset %esi, -8
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SSE-NEXT: calll __gnu_f2h_ieee
; X86-SSE-NEXT: movw %ax, (%esi)
; X86-SSE-NEXT: addl $8, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; X86-NOSSE-LABEL: store_half:
; X86-NOSSE: # %bb.0:
; X86-NOSSE-NEXT: pushl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: subl $8, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 16
; X86-NOSSE-NEXT: .cfi_offset %esi, -8
; X86-NOSSE-NEXT: flds {{[0-9]+}}(%esp)
; X86-NOSSE-NEXT: fstps (%esp)
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NOSSE-NEXT: calll __gnu_f2h_ieee
; X86-NOSSE-NEXT: movw %ax, (%esi)
; X86-NOSSE-NEXT: addl $8, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: popl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X64-LABEL: store_half:
; X64: # %bb.0:
; X64-NEXT: pushq %rbx
; X64-NEXT: .cfi_def_cfa_offset 16
; X64-NEXT: .cfi_offset %rbx, -16
; X64-NEXT: movq %rdi, %rbx
; X64-NEXT: callq __gnu_f2h_ieee
; X64-NEXT: movw %ax, (%rbx)
; X64-NEXT: popq %rbx
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
store atomic half %v, half* %fptr unordered, align 2
ret void
}
define void @store_float(float* %fptr, float %v) {
; X86-LABEL: store_float:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: store_float:
; X64: # %bb.0:
; X64-NEXT: movd %xmm0, %eax
; X64-NEXT: movl %eax, (%rdi)
; X64-NEXT: retq
store atomic float %v, float* %fptr unordered, align 4
ret void
}
define void @store_double(double* %fptr, double %v) {
; X86-LABEL: store_double:
; X86: # %bb.0:
; X86-NEXT: pushl %ebx
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: .cfi_offset %esi, -12
; X86-NEXT: .cfi_offset %ebx, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl 4(%esi), %edx
; X86-NEXT: .p2align 4, 0x90
; X86-NEXT: .LBB2_1: # %atomicrmw.start
; X86-NEXT: # =>This Inner Loop Header: Depth=1
; X86-NEXT: lock cmpxchg8b (%esi)
; X86-NEXT: jne .LBB2_1
; X86-NEXT: # %bb.2: # %atomicrmw.end
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: popl %ebx
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
;
; X64-LABEL: store_double:
; X64: # %bb.0:
; X64-NEXT: movq %xmm0, %rax
; X64-NEXT: movq %rax, (%rdi)
; X64-NEXT: retq
store atomic double %v, double* %fptr unordered, align 8
ret void
}
define void @store_fp128(fp128* %fptr, fp128 %v) {
; X86-LABEL: store_fp128:
; X86: # %bb.0:
; X86-NEXT: subl $36, %esp
; X86-NEXT: .cfi_adjust_cfa_offset 36
; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl %eax
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: calll __sync_lock_test_and_set_16
; X86-NEXT: .cfi_adjust_cfa_offset -4
; X86-NEXT: addl $56, %esp
; X86-NEXT: .cfi_adjust_cfa_offset -56
; X86-NEXT: retl
;
; X64-LABEL: store_fp128:
; X64: # %bb.0:
; X64-NEXT: pushq %rax
; X64-NEXT: .cfi_def_cfa_offset 16
; X64-NEXT: callq __sync_lock_test_and_set_16
; X64-NEXT: popq %rax
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
store atomic fp128 %v, fp128* %fptr unordered, align 16
ret void
}
define half @load_half(half* %fptr) {
; X86-LABEL: load_half:
; X86: # %bb.0:
; X86-NEXT: subl $12, %esp
; X86-NEXT: .cfi_def_cfa_offset 16
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movzwl (%eax), %eax
; X86-NEXT: movl %eax, (%esp)
; X86-NEXT: calll __gnu_h2f_ieee
; X86-NEXT: addl $12, %esp
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
;
; X64-LABEL: load_half:
; X64: # %bb.0:
; X64-NEXT: pushq %rax
; X64-NEXT: .cfi_def_cfa_offset 16
; X64-NEXT: movzwl (%rdi), %edi
; X64-NEXT: callq __gnu_h2f_ieee
; X64-NEXT: popq %rax
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
%v = load atomic half, half* %fptr unordered, align 2
ret half %v
}
define float @load_float(float* %fptr) {
; X86-SSE-LABEL: load_float:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movd (%eax), %xmm0
; X86-SSE-NEXT: movd %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; X86-NOSSE-LABEL: load_float:
; X86-NOSSE: # %bb.0:
; X86-NOSSE-NEXT: pushl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NOSSE-NEXT: movl (%eax), %eax
; X86-NOSSE-NEXT: movl %eax, (%esp)
; X86-NOSSE-NEXT: flds (%esp)
; X86-NOSSE-NEXT: popl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X64-LABEL: load_float:
; X64: # %bb.0:
; X64-NEXT: movd (%rdi), %xmm0
; X64-NEXT: retq
%v = load atomic float, float* %fptr unordered, align 4
ret float %v
}
define double @load_double(double* %fptr) {
; X86-SSE-LABEL: load_double:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movlps %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; X86-NOSSE-LABEL: load_double:
; X86-NOSSE: # %bb.0:
; X86-NOSSE-NEXT: pushl %ebx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: pushl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 12
; X86-NOSSE-NEXT: subl $12, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 24
; X86-NOSSE-NEXT: .cfi_offset %esi, -12
; X86-NOSSE-NEXT: .cfi_offset %ebx, -8
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NOSSE-NEXT: xorl %eax, %eax
; X86-NOSSE-NEXT: xorl %edx, %edx
; X86-NOSSE-NEXT: xorl %ecx, %ecx
; X86-NOSSE-NEXT: xorl %ebx, %ebx
; X86-NOSSE-NEXT: lock cmpxchg8b (%esi)
; X86-NOSSE-NEXT: movl %edx, {{[0-9]+}}(%esp)
; X86-NOSSE-NEXT: movl %eax, (%esp)
; X86-NOSSE-NEXT: fldl (%esp)
; X86-NOSSE-NEXT: addl $12, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 12
; X86-NOSSE-NEXT: popl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: popl %ebx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X64-LABEL: load_double:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %xmm0
; X64-NEXT: retq
%v = load atomic double, double* %fptr unordered, align 8
ret double %v
}
define fp128 @load_fp128(fp128* %fptr) {
; X86-LABEL: load_fp128:
; X86: # %bb.0:
; X86-NEXT: pushl %edi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: subl $20, %esp
; X86-NEXT: .cfi_def_cfa_offset 32
; X86-NEXT: .cfi_offset %esi, -12
; X86-NEXT: .cfi_offset %edi, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: subl $8, %esp
; X86-NEXT: .cfi_adjust_cfa_offset 8
; X86-NEXT: leal {{[0-9]+}}(%esp), %eax
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl $0
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl {{[0-9]+}}(%esp)
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: pushl %eax
; X86-NEXT: .cfi_adjust_cfa_offset 4
; X86-NEXT: calll __sync_val_compare_and_swap_16
; X86-NEXT: .cfi_adjust_cfa_offset -4
; X86-NEXT: addl $44, %esp
; X86-NEXT: .cfi_adjust_cfa_offset -44
; X86-NEXT: movl (%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl %edi, 8(%esi)
; X86-NEXT: movl %edx, 12(%esi)
; X86-NEXT: movl %eax, (%esi)
; X86-NEXT: movl %ecx, 4(%esi)
; X86-NEXT: movl %esi, %eax
; X86-NEXT: addl $20, %esp
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: popl %edi
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl $4
;
; X64-LABEL: load_fp128:
; X64: # %bb.0:
; X64-NEXT: pushq %rax
; X64-NEXT: .cfi_def_cfa_offset 16
; X64-NEXT: xorl %esi, %esi
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: xorl %ecx, %ecx
; X64-NEXT: xorl %r8d, %r8d
; X64-NEXT: callq __sync_val_compare_and_swap_16
; X64-NEXT: popq %rcx
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
%v = load atomic fp128, fp128* %fptr unordered, align 16
ret fp128 %v
}
; sanity check the seq_cst lowering since that's the
; interesting one from an ordering perspective on x86.
define void @store_float_seq_cst(float* %fptr, float %v) {
; X86-LABEL: store_float_seq_cst:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: xchgl %ecx, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: store_float_seq_cst:
; X64: # %bb.0:
; X64-NEXT: movd %xmm0, %eax
; X64-NEXT: xchgl %eax, (%rdi)
; X64-NEXT: retq
store atomic float %v, float* %fptr seq_cst, align 4
ret void
}
define void @store_double_seq_cst(double* %fptr, double %v) {
; X86-LABEL: store_double_seq_cst:
; X86: # %bb.0:
; X86-NEXT: pushl %ebx
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: .cfi_offset %esi, -12
; X86-NEXT: .cfi_offset %ebx, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl (%esi), %eax
; X86-NEXT: movl 4(%esi), %edx
; X86-NEXT: .p2align 4, 0x90
; X86-NEXT: .LBB9_1: # %atomicrmw.start
; X86-NEXT: # =>This Inner Loop Header: Depth=1
; X86-NEXT: lock cmpxchg8b (%esi)
; X86-NEXT: jne .LBB9_1
; X86-NEXT: # %bb.2: # %atomicrmw.end
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: popl %ebx
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
;
; X64-LABEL: store_double_seq_cst:
; X64: # %bb.0:
; X64-NEXT: movq %xmm0, %rax
; X64-NEXT: xchgq %rax, (%rdi)
; X64-NEXT: retq
store atomic double %v, double* %fptr seq_cst, align 8
ret void
}
define float @load_float_seq_cst(float* %fptr) {
; X86-SSE-LABEL: load_float_seq_cst:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl (%eax), %eax
; X86-SSE-NEXT: movd %eax, %xmm0
; X86-SSE-NEXT: movd %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; X86-NOSSE-LABEL: load_float_seq_cst:
; X86-NOSSE: # %bb.0:
; X86-NOSSE-NEXT: pushl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NOSSE-NEXT: movl (%eax), %eax
; X86-NOSSE-NEXT: movl %eax, (%esp)
; X86-NOSSE-NEXT: flds (%esp)
; X86-NOSSE-NEXT: popl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X64-LABEL: load_float_seq_cst:
; X64: # %bb.0:
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: movd %eax, %xmm0
; X64-NEXT: retq
%v = load atomic float, float* %fptr seq_cst, align 4
ret float %v
}
define double @load_double_seq_cst(double* %fptr) {
; X86-SSE-LABEL: load_double_seq_cst:
; X86-SSE: # %bb.0:
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movlps %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; X86-NOSSE-LABEL: load_double_seq_cst:
; X86-NOSSE: # %bb.0:
; X86-NOSSE-NEXT: pushl %ebx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: pushl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 12
; X86-NOSSE-NEXT: subl $12, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 24
; X86-NOSSE-NEXT: .cfi_offset %esi, -12
; X86-NOSSE-NEXT: .cfi_offset %ebx, -8
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NOSSE-NEXT: xorl %eax, %eax
; X86-NOSSE-NEXT: xorl %edx, %edx
; X86-NOSSE-NEXT: xorl %ecx, %ecx
; X86-NOSSE-NEXT: xorl %ebx, %ebx
; X86-NOSSE-NEXT: lock cmpxchg8b (%esi)
; X86-NOSSE-NEXT: movl %edx, {{[0-9]+}}(%esp)
; X86-NOSSE-NEXT: movl %eax, (%esp)
; X86-NOSSE-NEXT: fldl (%esp)
; X86-NOSSE-NEXT: addl $12, %esp
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 12
; X86-NOSSE-NEXT: popl %esi
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: popl %ebx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X64-LABEL: load_double_seq_cst:
; X64: # %bb.0:
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: movq %rax, %xmm0
; X64-NEXT: retq
%v = load atomic double, double* %fptr seq_cst, align 8
ret double %v
}
|
