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
|
; RUN: opt -S -codegenprepare < %s | FileCheck %s
target datalayout =
"e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
target triple = "x86_64-unknown-linux-gnu"
; Can we sink single addressing mode computation to use?
define void @test1(i1 %cond, i64* %base) {
; CHECK-LABEL: @test1
; CHECK: add i64 {{.+}}, 40
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
%v = load i32, i32* %casted, align 4
br label %fallthrough
fallthrough:
ret void
}
declare void @foo(i32)
; Make sure sinking two copies of addressing mode into different blocks works
define void @test2(i1 %cond, i64* %base) {
; CHECK-LABEL: @test2
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
%cmp = icmp eq i32 %v1, 0
br i1 %cmp, label %next, label %fallthrough
next:
; CHECK-LABEL: next:
; CHECK: add i64 {{.+}}, 40
%v2 = load i32, i32* %casted, align 4
call void @foo(i32 %v2)
br label %fallthrough
fallthrough:
ret void
}
; If we have two loads in the same block, only need one copy of addressing mode
; - instruction selection will duplicate if needed
define void @test3(i1 %cond, i64* %base) {
; CHECK-LABEL: @test3
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
; CHECK-NOT: add i64 {{.+}}, 40
%v2 = load i32, i32* %casted, align 4
call void @foo(i32 %v2)
br label %fallthrough
fallthrough:
ret void
}
; Can we still sink addressing mode if there's a cold use of the
; address itself?
define void @test4(i1 %cond, i64* %base) {
; CHECK-LABEL: @test4
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
%cmp = icmp eq i32 %v1, 0
br i1 %cmp, label %rare.1, label %fallthrough
fallthrough:
ret void
rare.1:
; CHECK-LABEL: rare.1:
; CHECK: add i64 {{.+}}, 40
call void @slowpath(i32 %v1, i32* %casted) cold
br label %fallthrough
}
; Negative test - don't want to duplicate addressing into hot path
define void @test5(i1 %cond, i64* %base) {
; CHECK-LABEL: @test5
entry:
; CHECK: %addr = getelementptr
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK-NOT: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
%cmp = icmp eq i32 %v1, 0
br i1 %cmp, label %rare.1, label %fallthrough
fallthrough:
ret void
rare.1:
call void @slowpath(i32 %v1, i32* %casted) ;; NOT COLD
br label %fallthrough
}
; Negative test - opt for size
define void @test6(i1 %cond, i64* %base) minsize {
; CHECK-LABEL: @test6
entry:
; CHECK: %addr = getelementptr
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK-NOT: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
%cmp = icmp eq i32 %v1, 0
br i1 %cmp, label %rare.1, label %fallthrough
fallthrough:
ret void
rare.1:
call void @slowpath(i32 %v1, i32* %casted) cold
br label %fallthrough
}
; Make sure sinking two copies of addressing mode into different blocks works
; when there are cold paths for each.
define void @test7(i1 %cond, i64* %base) {
; CHECK-LABEL: @test7
entry:
%addr = getelementptr inbounds i64, i64* %base, i64 5
%casted = bitcast i64* %addr to i32*
br i1 %cond, label %if.then, label %fallthrough
if.then:
; CHECK-LABEL: if.then:
; CHECK: add i64 {{.+}}, 40
%v1 = load i32, i32* %casted, align 4
call void @foo(i32 %v1)
%cmp = icmp eq i32 %v1, 0
br i1 %cmp, label %rare.1, label %next
next:
; CHECK-LABEL: next:
; CHECK: add i64 {{.+}}, 40
%v2 = load i32, i32* %casted, align 4
call void @foo(i32 %v2)
%cmp2 = icmp eq i32 %v2, 0
br i1 %cmp2, label %rare.1, label %fallthrough
fallthrough:
ret void
rare.1:
; CHECK-LABEL: rare.1:
; CHECK: add i64 {{.+}}, 40
call void @slowpath(i32 %v1, i32* %casted) cold
br label %next
rare.2:
; CHECK-LABEL: rare.2:
; CHECK: add i64 {{.+}}, 40
call void @slowpath(i32 %v2, i32* %casted) cold
br label %fallthrough
}
declare void @slowpath(i32, i32*)
|
