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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=i686-unknown -verify-machineinstrs < %s | FileCheck %s
; RUN: opt < %s -codegenprepare -S -mtriple=x86_64-unknown-unknown | FileCheck --check-prefix=CHECK-CGP %s
@A = global i32 zeroinitializer
@B = global i32 zeroinitializer
@C = global i32 zeroinitializer
; Test that 'and' is sunk into bb0.
define i32 @and_sink1(i32 %a, i1 %c) {
; CHECK-LABEL: and_sink1:
; CHECK: # %bb.0:
; CHECK-NEXT: testb $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: je .LBB0_3
; CHECK-NEXT: # %bb.1: # %bb0
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: testb $4, %al
; CHECK-NEXT: movl $0, A
; CHECK-NEXT: jne .LBB0_3
; CHECK-NEXT: # %bb.2: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB0_3: # %bb2
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-CGP-LABEL: @and_sink1(
; CHECK-CGP-NOT: and i32
%and = and i32 %a, 4
br i1 %c, label %bb0, label %bb2
bb0:
; CHECK-CGP-LABEL: bb0:
; CHECK-CGP: and i32
; CHECK-CGP-NEXT: icmp eq i32
; CHECK-CGP-NEXT: store
; CHECK-CGP-NEXT: br
%cmp = icmp eq i32 %and, 0
store i32 0, i32* @A
br i1 %cmp, label %bb1, label %bb2
bb1:
ret i32 1
bb2:
ret i32 0
}
; Test that both 'and' and cmp get sunk to bb1.
define i32 @and_sink2(i32 %a, i1 %c, i1 %c2) {
; CHECK-LABEL: and_sink2:
; CHECK: # %bb.0:
; CHECK-NEXT: movl $0, A
; CHECK-NEXT: testb $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: je .LBB1_5
; CHECK-NEXT: # %bb.1: # %bb0.preheader
; CHECK-NEXT: movb {{[0-9]+}}(%esp), %al
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB1_2: # %bb0
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl $0, B
; CHECK-NEXT: testb $1, %al
; CHECK-NEXT: je .LBB1_5
; CHECK-NEXT: # %bb.3: # %bb1
; CHECK-NEXT: # in Loop: Header=BB1_2 Depth=1
; CHECK-NEXT: testb $4, %cl
; CHECK-NEXT: movl $0, C
; CHECK-NEXT: jne .LBB1_2
; CHECK-NEXT: # %bb.4: # %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB1_5: # %bb3
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-CGP-LABEL: @and_sink2(
; CHECK-CGP-NOT: and i32
%and = and i32 %a, 4
store i32 0, i32* @A
br i1 %c, label %bb0, label %bb3
bb0:
; CHECK-CGP-LABEL: bb0:
; CHECK-CGP-NOT: and i32
; CHECK-CGP-NOT: icmp
%cmp = icmp eq i32 %and, 0
store i32 0, i32* @B
br i1 %c2, label %bb1, label %bb3
bb1:
; CHECK-CGP-LABEL: bb1:
; CHECK-CGP: and i32
; CHECK-CGP-NEXT: icmp eq i32
; CHECK-CGP-NEXT: store
; CHECK-CGP-NEXT: br
store i32 0, i32* @C
br i1 %cmp, label %bb2, label %bb0
bb2:
ret i32 1
bb3:
ret i32 0
}
; Test that CodeGenPrepare doesn't get stuck in a loop sinking and hoisting a masked load.
define i32 @and_sink3(i1 %c, i32* %p) {
; CHECK-LABEL: and_sink3:
; CHECK: # %bb.0:
; CHECK-NEXT: testb $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: je .LBB2_3
; CHECK-NEXT: # %bb.1: # %bb0
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movzbl (%eax), %eax
; CHECK-NEXT: testl %eax, %eax
; CHECK-NEXT: movl $0, A
; CHECK-NEXT: je .LBB2_2
; CHECK-NEXT: .LBB2_3: # %bb2
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB2_2: # %bb1
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-CGP-LABEL: @and_sink3(
; CHECK-CGP: load i32
; CHECK-CGP-NEXT: and i32
%load = load i32, i32* %p
%and = and i32 %load, 255
br i1 %c, label %bb0, label %bb2
bb0:
; CHECK-CGP-LABEL: bb0:
; CHECK-CGP-NOT: and i32
; CHECK-CGP: icmp eq i32
%cmp = icmp eq i32 %and, 0
store i32 0, i32* @A
br i1 %cmp, label %bb1, label %bb2
bb1:
ret i32 1
bb2:
ret i32 0
}
; Test that CodeGenPrepare sinks/duplicates non-immediate 'and'.
define i32 @and_sink4(i32 %a, i32 %b, i1 %c) {
; CHECK-LABEL: and_sink4:
; CHECK: # %bb.0:
; CHECK-NEXT: testb $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: je .LBB3_4
; CHECK-NEXT: # %bb.1: # %bb0
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: testl %eax, %ecx
; CHECK-NEXT: movl $0, A
; CHECK-NEXT: jne .LBB3_4
; CHECK-NEXT: # %bb.2: # %bb1
; CHECK-NEXT: leal (%ecx,%eax), %edx
; CHECK-NEXT: testl %eax, %ecx
; CHECK-NEXT: movl %edx, B
; CHECK-NEXT: je .LBB3_3
; CHECK-NEXT: .LBB3_4: # %bb3
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB3_3: # %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-CGP-LABEL: @and_sink4(
; CHECK-CGP-NOT: and i32
; CHECK-CGP-NOT: icmp
%and = and i32 %a, %b
%cmp = icmp eq i32 %and, 0
br i1 %c, label %bb0, label %bb3
bb0:
; CHECK-CGP-LABEL: bb0:
; CHECK-CGP: and i32
; CHECK-CGP-NEXT: icmp eq i32
store i32 0, i32* @A
br i1 %cmp, label %bb1, label %bb3
bb1:
; CHECK-CGP-LABEL: bb1:
; CHECK-CGP: and i32
; CHECK-CGP-NEXT: icmp eq i32
%add = add i32 %a, %b
store i32 %add, i32* @B
br i1 %cmp, label %bb2, label %bb3
bb2:
ret i32 1
bb3:
ret i32 0
}
; Test that CodeGenPrepare doesn't sink/duplicate non-immediate 'and'
; when it would increase register pressure.
define i32 @and_sink5(i32 %a, i32 %b, i32 %a2, i32 %b2, i1 %c) {
; CHECK-LABEL: and_sink5:
; CHECK: # %bb.0:
; CHECK-NEXT: testb $1, {{[0-9]+}}(%esp)
; CHECK-NEXT: je .LBB4_4
; CHECK-NEXT: # %bb.1: # %bb0
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: andl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movl $0, A
; CHECK-NEXT: jne .LBB4_4
; CHECK-NEXT: # %bb.2: # %bb1
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: addl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: testl %eax, %eax
; CHECK-NEXT: movl %ecx, B
; CHECK-NEXT: je .LBB4_3
; CHECK-NEXT: .LBB4_4: # %bb3
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: retl
; CHECK-NEXT: .LBB4_3: # %bb2
; CHECK-NEXT: movl $1, %eax
; CHECK-NEXT: retl
; CHECK-CGP-LABEL: @and_sink5(
; CHECK-CGP: and i32
; CHECK-CGP-NOT: icmp
%and = and i32 %a, %b
%cmp = icmp eq i32 %and, 0
br i1 %c, label %bb0, label %bb3
bb0:
; CHECK-CGP-LABEL: bb0:
; CHECK-CGP-NOT: and i32
; CHECK-CGP: icmp eq i32
store i32 0, i32* @A
br i1 %cmp, label %bb1, label %bb3
bb1:
; CHECK-CGP-LABEL: bb1:
; CHECK-CGP-NOT: and i32
; CHECK-CGP: icmp eq i32
%add = add i32 %a2, %b2
store i32 %add, i32* @B
br i1 %cmp, label %bb2, label %bb3
bb2:
ret i32 1
bb3:
ret i32 0
}
|