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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=i386-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=32-ALL,32-GOOD-RA
; RUN: llc -mtriple=i386-linux-gnu -verify-machineinstrs -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=32-ALL,32-FAST-RA
; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA
; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA
; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mattr=+sahf %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mattr=+sahf -pre-RA-sched=fast %s -o - | FileCheck %s --check-prefixes=64-ALL,64-FAST-RA-SAHF
; RUN: llc -mtriple=x86_64-linux-gnu -verify-machineinstrs -mcpu=corei7 %s -o - | FileCheck %s --check-prefixes=64-ALL,64-GOOD-RA-SAHF
declare i32 @foo()
declare i32 @bar(i64)
; In the following case when using fast scheduling we get a long chain of
; EFLAGS save/restore due to a sequence of:
; cmpxchg8b (implicit-def eflags)
; eax = copy eflags
; adjcallstackdown32
; ...
; use of eax
; During PEI the adjcallstackdown32 is replaced with the subl which
; clobbers eflags, effectively interfering in the liveness interval. However,
; we then promote these copies into independent conditions in GPRs that avoids
; repeated saving and restoring logic and can be trivially managed by the
; register allocator.
define i64 @test_intervening_call(i64* %foo, i64 %bar, i64 %baz) nounwind {
; 32-GOOD-RA-LABEL: test_intervening_call:
; 32-GOOD-RA: # %bb.0: # %entry
; 32-GOOD-RA-NEXT: pushl %ebx
; 32-GOOD-RA-NEXT: pushl %esi
; 32-GOOD-RA-NEXT: pushl %eax
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %eax
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %edx
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %ebx
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %ecx
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %esi
; 32-GOOD-RA-NEXT: lock cmpxchg8b (%esi)
; 32-GOOD-RA-NEXT: setne %bl
; 32-GOOD-RA-NEXT: subl $8, %esp
; 32-GOOD-RA-NEXT: pushl %edx
; 32-GOOD-RA-NEXT: pushl %eax
; 32-GOOD-RA-NEXT: calll bar
; 32-GOOD-RA-NEXT: addl $16, %esp
; 32-GOOD-RA-NEXT: testb %bl, %bl
; 32-GOOD-RA-NEXT: jne .LBB0_3
; 32-GOOD-RA-NEXT: # %bb.1: # %t
; 32-GOOD-RA-NEXT: movl $42, %eax
; 32-GOOD-RA-NEXT: jmp .LBB0_2
; 32-GOOD-RA-NEXT: .LBB0_3: # %f
; 32-GOOD-RA-NEXT: xorl %eax, %eax
; 32-GOOD-RA-NEXT: .LBB0_2: # %t
; 32-GOOD-RA-NEXT: xorl %edx, %edx
; 32-GOOD-RA-NEXT: addl $4, %esp
; 32-GOOD-RA-NEXT: popl %esi
; 32-GOOD-RA-NEXT: popl %ebx
; 32-GOOD-RA-NEXT: retl
;
; 32-FAST-RA-LABEL: test_intervening_call:
; 32-FAST-RA: # %bb.0: # %entry
; 32-FAST-RA-NEXT: pushl %ebx
; 32-FAST-RA-NEXT: pushl %esi
; 32-FAST-RA-NEXT: pushl %eax
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %esi
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %ebx
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %ecx
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %eax
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %edx
; 32-FAST-RA-NEXT: lock cmpxchg8b (%esi)
; 32-FAST-RA-NEXT: setne %bl
; 32-FAST-RA-NEXT: subl $8, %esp
; 32-FAST-RA-NEXT: pushl %edx
; 32-FAST-RA-NEXT: pushl %eax
; 32-FAST-RA-NEXT: calll bar
; 32-FAST-RA-NEXT: addl $16, %esp
; 32-FAST-RA-NEXT: testb %bl, %bl
; 32-FAST-RA-NEXT: jne .LBB0_3
; 32-FAST-RA-NEXT: # %bb.1: # %t
; 32-FAST-RA-NEXT: movl $42, %eax
; 32-FAST-RA-NEXT: jmp .LBB0_2
; 32-FAST-RA-NEXT: .LBB0_3: # %f
; 32-FAST-RA-NEXT: xorl %eax, %eax
; 32-FAST-RA-NEXT: .LBB0_2: # %t
; 32-FAST-RA-NEXT: xorl %edx, %edx
; 32-FAST-RA-NEXT: addl $4, %esp
; 32-FAST-RA-NEXT: popl %esi
; 32-FAST-RA-NEXT: popl %ebx
; 32-FAST-RA-NEXT: retl
;
; 64-ALL-LABEL: test_intervening_call:
; 64-ALL: # %bb.0: # %entry
; 64-ALL-NEXT: pushq %rbx
; 64-ALL-NEXT: movq %rsi, %rax
; 64-ALL-NEXT: lock cmpxchgq %rdx, (%rdi)
; 64-ALL-NEXT: setne %bl
; 64-ALL-NEXT: movq %rax, %rdi
; 64-ALL-NEXT: callq bar
; 64-ALL-NEXT: testb %bl, %bl
; 64-ALL-NEXT: jne .LBB0_2
; 64-ALL-NEXT: # %bb.1: # %t
; 64-ALL-NEXT: movl $42, %eax
; 64-ALL-NEXT: popq %rbx
; 64-ALL-NEXT: retq
; 64-ALL-NEXT: .LBB0_2: # %f
; 64-ALL-NEXT: xorl %eax, %eax
; 64-ALL-NEXT: popq %rbx
; 64-ALL-NEXT: retq
entry:
%cx = cmpxchg i64* %foo, i64 %bar, i64 %baz seq_cst seq_cst
%v = extractvalue { i64, i1 } %cx, 0
%p = extractvalue { i64, i1 } %cx, 1
call i32 @bar(i64 %v)
br i1 %p, label %t, label %f
t:
ret i64 42
f:
ret i64 0
}
; Interesting in producing a clobber without any function calls.
define i32 @test_control_flow(i32* %p, i32 %i, i32 %j) nounwind {
; 32-ALL-LABEL: test_control_flow:
; 32-ALL: # %bb.0: # %entry
; 32-ALL-NEXT: movl {{[0-9]+}}(%esp), %eax
; 32-ALL-NEXT: cmpl {{[0-9]+}}(%esp), %eax
; 32-ALL-NEXT: jle .LBB1_6
; 32-ALL-NEXT: # %bb.1: # %loop_start
; 32-ALL-NEXT: movl {{[0-9]+}}(%esp), %ecx
; 32-ALL-NEXT: .p2align 4, 0x90
; 32-ALL-NEXT: .LBB1_2: # %while.condthread-pre-split.i
; 32-ALL-NEXT: # =>This Loop Header: Depth=1
; 32-ALL-NEXT: # Child Loop BB1_3 Depth 2
; 32-ALL-NEXT: movl (%ecx), %edx
; 32-ALL-NEXT: .p2align 4, 0x90
; 32-ALL-NEXT: .LBB1_3: # %while.cond.i
; 32-ALL-NEXT: # Parent Loop BB1_2 Depth=1
; 32-ALL-NEXT: # => This Inner Loop Header: Depth=2
; 32-ALL-NEXT: movl %edx, %eax
; 32-ALL-NEXT: xorl %edx, %edx
; 32-ALL-NEXT: testl %eax, %eax
; 32-ALL-NEXT: je .LBB1_3
; 32-ALL-NEXT: # %bb.4: # %while.body.i
; 32-ALL-NEXT: # in Loop: Header=BB1_2 Depth=1
; 32-ALL-NEXT: lock cmpxchgl %eax, (%ecx)
; 32-ALL-NEXT: jne .LBB1_2
; 32-ALL-NEXT: # %bb.5:
; 32-ALL-NEXT: xorl %eax, %eax
; 32-ALL-NEXT: .LBB1_6: # %cond.end
; 32-ALL-NEXT: retl
;
; 64-ALL-LABEL: test_control_flow:
; 64-ALL: # %bb.0: # %entry
; 64-ALL-NEXT: movl %esi, %eax
; 64-ALL-NEXT: cmpl %edx, %esi
; 64-ALL-NEXT: jle .LBB1_5
; 64-ALL-NEXT: .p2align 4, 0x90
; 64-ALL-NEXT: .LBB1_1: # %while.condthread-pre-split.i
; 64-ALL-NEXT: # =>This Loop Header: Depth=1
; 64-ALL-NEXT: # Child Loop BB1_2 Depth 2
; 64-ALL-NEXT: movl (%rdi), %ecx
; 64-ALL-NEXT: .p2align 4, 0x90
; 64-ALL-NEXT: .LBB1_2: # %while.cond.i
; 64-ALL-NEXT: # Parent Loop BB1_1 Depth=1
; 64-ALL-NEXT: # => This Inner Loop Header: Depth=2
; 64-ALL-NEXT: movl %ecx, %eax
; 64-ALL-NEXT: xorl %ecx, %ecx
; 64-ALL-NEXT: testl %eax, %eax
; 64-ALL-NEXT: je .LBB1_2
; 64-ALL-NEXT: # %bb.3: # %while.body.i
; 64-ALL-NEXT: # in Loop: Header=BB1_1 Depth=1
; 64-ALL-NEXT: lock cmpxchgl %eax, (%rdi)
; 64-ALL-NEXT: jne .LBB1_1
; 64-ALL-NEXT: # %bb.4:
; 64-ALL-NEXT: xorl %eax, %eax
; 64-ALL-NEXT: .LBB1_5: # %cond.end
; 64-ALL-NEXT: retq
entry:
%cmp = icmp sgt i32 %i, %j
br i1 %cmp, label %loop_start, label %cond.end
loop_start:
br label %while.condthread-pre-split.i
while.condthread-pre-split.i:
%.pr.i = load i32, i32* %p, align 4
br label %while.cond.i
while.cond.i:
%0 = phi i32 [ %.pr.i, %while.condthread-pre-split.i ], [ 0, %while.cond.i ]
%tobool.i = icmp eq i32 %0, 0
br i1 %tobool.i, label %while.cond.i, label %while.body.i
while.body.i:
%.lcssa = phi i32 [ %0, %while.cond.i ]
%1 = cmpxchg i32* %p, i32 %.lcssa, i32 %.lcssa seq_cst seq_cst
%2 = extractvalue { i32, i1 } %1, 1
br i1 %2, label %cond.end.loopexit, label %while.condthread-pre-split.i
cond.end.loopexit:
br label %cond.end
cond.end:
%cond = phi i32 [ %i, %entry ], [ 0, %cond.end.loopexit ]
ret i32 %cond
}
; This one is an interesting case because CMOV doesn't have a chain
; operand. Naive attempts to limit cmpxchg EFLAGS use are likely to fail here.
define i32 @test_feed_cmov(i32* %addr, i32 %desired, i32 %new) nounwind {
; 32-GOOD-RA-LABEL: test_feed_cmov:
; 32-GOOD-RA: # %bb.0: # %entry
; 32-GOOD-RA-NEXT: pushl %ebx
; 32-GOOD-RA-NEXT: pushl %esi
; 32-GOOD-RA-NEXT: pushl %eax
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %eax
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %esi
; 32-GOOD-RA-NEXT: movl {{[0-9]+}}(%esp), %ecx
; 32-GOOD-RA-NEXT: lock cmpxchgl %esi, (%ecx)
; 32-GOOD-RA-NEXT: sete %bl
; 32-GOOD-RA-NEXT: calll foo
; 32-GOOD-RA-NEXT: testb %bl, %bl
; 32-GOOD-RA-NEXT: jne .LBB2_2
; 32-GOOD-RA-NEXT: # %bb.1: # %entry
; 32-GOOD-RA-NEXT: movl %eax, %esi
; 32-GOOD-RA-NEXT: .LBB2_2: # %entry
; 32-GOOD-RA-NEXT: movl %esi, %eax
; 32-GOOD-RA-NEXT: addl $4, %esp
; 32-GOOD-RA-NEXT: popl %esi
; 32-GOOD-RA-NEXT: popl %ebx
; 32-GOOD-RA-NEXT: retl
;
; 32-FAST-RA-LABEL: test_feed_cmov:
; 32-FAST-RA: # %bb.0: # %entry
; 32-FAST-RA-NEXT: pushl %ebx
; 32-FAST-RA-NEXT: pushl %esi
; 32-FAST-RA-NEXT: pushl %eax
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %ecx
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %esi
; 32-FAST-RA-NEXT: movl {{[0-9]+}}(%esp), %eax
; 32-FAST-RA-NEXT: lock cmpxchgl %esi, (%ecx)
; 32-FAST-RA-NEXT: sete %bl
; 32-FAST-RA-NEXT: calll foo
; 32-FAST-RA-NEXT: testb %bl, %bl
; 32-FAST-RA-NEXT: jne .LBB2_2
; 32-FAST-RA-NEXT: # %bb.1: # %entry
; 32-FAST-RA-NEXT: movl %eax, %esi
; 32-FAST-RA-NEXT: .LBB2_2: # %entry
; 32-FAST-RA-NEXT: movl %esi, %eax
; 32-FAST-RA-NEXT: addl $4, %esp
; 32-FAST-RA-NEXT: popl %esi
; 32-FAST-RA-NEXT: popl %ebx
; 32-FAST-RA-NEXT: retl
;
; 64-ALL-LABEL: test_feed_cmov:
; 64-ALL: # %bb.0: # %entry
; 64-ALL-NEXT: pushq %rbp
; 64-ALL-NEXT: pushq %rbx
; 64-ALL-NEXT: pushq %rax
; 64-ALL-NEXT: movl %edx, %ebx
; 64-ALL-NEXT: movl %esi, %eax
; 64-ALL-NEXT: lock cmpxchgl %edx, (%rdi)
; 64-ALL-NEXT: sete %bpl
; 64-ALL-NEXT: callq foo
; 64-ALL-NEXT: testb %bpl, %bpl
; 64-ALL-NEXT: cmovnel %ebx, %eax
; 64-ALL-NEXT: addq $8, %rsp
; 64-ALL-NEXT: popq %rbx
; 64-ALL-NEXT: popq %rbp
; 64-ALL-NEXT: retq
entry:
%res = cmpxchg i32* %addr, i32 %desired, i32 %new seq_cst seq_cst
%success = extractvalue { i32, i1 } %res, 1
%rhs = call i32 @foo()
%ret = select i1 %success, i32 %new, i32 %rhs
ret i32 %ret
}
|