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
|
; RUN: llc -march=x86 -enable-block-placement < %s | FileCheck %s
declare void @error(i32 %i, i32 %a, i32 %b)
define i32 @test_ifchains(i32 %i, i32* %a, i32 %b) {
; Test a chain of ifs, where the block guarded by the if is error handling code
; that is not expected to run.
; CHECK: test_ifchains:
; CHECK: %entry
; CHECK: %else1
; CHECK: %else2
; CHECK: %else3
; CHECK: %else4
; CHECK: %exit
; CHECK: %then1
; CHECK: %then2
; CHECK: %then3
; CHECK: %then4
; CHECK: %then5
entry:
%gep1 = getelementptr i32* %a, i32 1
%val1 = load i32* %gep1
%cond1 = icmp ugt i32 %val1, 1
br i1 %cond1, label %then1, label %else1, !prof !0
then1:
call void @error(i32 %i, i32 1, i32 %b)
br label %else1
else1:
%gep2 = getelementptr i32* %a, i32 2
%val2 = load i32* %gep2
%cond2 = icmp ugt i32 %val2, 2
br i1 %cond2, label %then2, label %else2, !prof !0
then2:
call void @error(i32 %i, i32 1, i32 %b)
br label %else2
else2:
%gep3 = getelementptr i32* %a, i32 3
%val3 = load i32* %gep3
%cond3 = icmp ugt i32 %val3, 3
br i1 %cond3, label %then3, label %else3, !prof !0
then3:
call void @error(i32 %i, i32 1, i32 %b)
br label %else3
else3:
%gep4 = getelementptr i32* %a, i32 4
%val4 = load i32* %gep4
%cond4 = icmp ugt i32 %val4, 4
br i1 %cond4, label %then4, label %else4, !prof !0
then4:
call void @error(i32 %i, i32 1, i32 %b)
br label %else4
else4:
%gep5 = getelementptr i32* %a, i32 3
%val5 = load i32* %gep5
%cond5 = icmp ugt i32 %val5, 3
br i1 %cond5, label %then5, label %exit, !prof !0
then5:
call void @error(i32 %i, i32 1, i32 %b)
br label %exit
exit:
ret i32 %b
}
define i32 @test_loop_cold_blocks(i32 %i, i32* %a) {
; Check that we sink cold loop blocks after the hot loop body.
; CHECK: test_loop_cold_blocks:
; CHECK: %entry
; CHECK: %body1
; CHECK: %body2
; CHECK: %body3
; CHECK: %unlikely1
; CHECK: %unlikely2
; CHECK: %exit
entry:
br label %body1
body1:
%iv = phi i32 [ 0, %entry ], [ %next, %body3 ]
%base = phi i32 [ 0, %entry ], [ %sum, %body3 ]
%unlikelycond1 = icmp slt i32 %base, 42
br i1 %unlikelycond1, label %unlikely1, label %body2, !prof !0
unlikely1:
call void @error(i32 %i, i32 1, i32 %base)
br label %body2
body2:
%unlikelycond2 = icmp sgt i32 %base, 21
br i1 %unlikelycond2, label %unlikely2, label %body3, !prof !0
unlikely2:
call void @error(i32 %i, i32 2, i32 %base)
br label %body3
body3:
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%0 = load i32* %arrayidx
%sum = add nsw i32 %0, %base
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %body1
exit:
ret i32 %sum
}
!0 = metadata !{metadata !"branch_weights", i32 4, i32 64}
define i32 @test_loop_early_exits(i32 %i, i32* %a) {
; Check that we sink early exit blocks out of loop bodies.
; CHECK: test_loop_early_exits:
; CHECK: %entry
; CHECK: %body1
; CHECK: %body2
; CHECK: %body3
; CHECK: %body4
; CHECK: %exit
; CHECK: %bail1
; CHECK: %bail2
; CHECK: %bail3
entry:
br label %body1
body1:
%iv = phi i32 [ 0, %entry ], [ %next, %body4 ]
%base = phi i32 [ 0, %entry ], [ %sum, %body4 ]
%bailcond1 = icmp eq i32 %base, 42
br i1 %bailcond1, label %bail1, label %body2
bail1:
ret i32 -1
body2:
%bailcond2 = icmp eq i32 %base, 43
br i1 %bailcond2, label %bail2, label %body3
bail2:
ret i32 -2
body3:
%bailcond3 = icmp eq i32 %base, 44
br i1 %bailcond3, label %bail3, label %body4
bail3:
ret i32 -3
body4:
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%0 = load i32* %arrayidx
%sum = add nsw i32 %0, %base
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %body1
exit:
ret i32 %sum
}
define i32 @test_loop_align(i32 %i, i32* %a) {
; Check that we provide basic loop body alignment with the block placement
; pass.
; CHECK: test_loop_align:
; CHECK: %entry
; CHECK: .align [[ALIGN:[0-9]+]],
; CHECK-NEXT: %body
; CHECK: %exit
entry:
br label %body
body:
%iv = phi i32 [ 0, %entry ], [ %next, %body ]
%base = phi i32 [ 0, %entry ], [ %sum, %body ]
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%0 = load i32* %arrayidx
%sum = add nsw i32 %0, %base
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %body
exit:
ret i32 %sum
}
define i32 @test_nested_loop_align(i32 %i, i32* %a, i32* %b) {
; Check that we provide nested loop body alignment.
; CHECK: test_nested_loop_align:
; CHECK: %entry
; CHECK: .align [[ALIGN]],
; CHECK-NEXT: %loop.body.1
; CHECK: .align [[ALIGN]],
; CHECK-NEXT: %inner.loop.body
; CHECK-NOT: .align
; CHECK: %exit
entry:
br label %loop.body.1
loop.body.1:
%iv = phi i32 [ 0, %entry ], [ %next, %loop.body.2 ]
%arrayidx = getelementptr inbounds i32* %a, i32 %iv
%bidx = load i32* %arrayidx
br label %inner.loop.body
inner.loop.body:
%inner.iv = phi i32 [ 0, %loop.body.1 ], [ %inner.next, %inner.loop.body ]
%base = phi i32 [ 0, %loop.body.1 ], [ %sum, %inner.loop.body ]
%scaled_idx = mul i32 %bidx, %iv
%inner.arrayidx = getelementptr inbounds i32* %b, i32 %scaled_idx
%0 = load i32* %inner.arrayidx
%sum = add nsw i32 %0, %base
%inner.next = add i32 %iv, 1
%inner.exitcond = icmp eq i32 %inner.next, %i
br i1 %inner.exitcond, label %loop.body.2, label %inner.loop.body
loop.body.2:
%next = add i32 %iv, 1
%exitcond = icmp eq i32 %next, %i
br i1 %exitcond, label %exit, label %loop.body.1
exit:
ret i32 %sum
}
|
