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
|
; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s -check-prefix=CHECK -check-prefix=ENABLED
; RUN: llc --disable-x86-lea-opt < %s -mtriple=x86_64-linux | FileCheck %s -check-prefix=CHECK -check-prefix=DISABLED
%struct.anon1 = type { i32, i32, i32 }
%struct.anon2 = type { i32, [32 x i32], i32 }
@arr1 = external global [65 x %struct.anon1], align 16
@arr2 = external global [65 x %struct.anon2], align 16
define void @test1(i64 %x) nounwind {
entry:
%a = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 0
%tmp = load i32, i32* %a, align 4
%b = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 1
%tmp1 = load i32, i32* %b, align 4
%sub = sub i32 %tmp, %tmp1
%c = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 2
%tmp2 = load i32, i32* %c, align 4
%add = add nsw i32 %sub, %tmp2
switch i32 %add, label %sw.epilog [
i32 1, label %sw.bb.1
i32 2, label %sw.bb.2
]
sw.bb.1: ; preds = %entry
store i32 111, i32* %b, align 4
store i32 222, i32* %c, align 4
br label %sw.epilog
sw.bb.2: ; preds = %entry
store i32 333, i32* %b, align 4
store i32 444, i32* %c, align 4
br label %sw.epilog
sw.epilog: ; preds = %sw.bb.2, %sw.bb.1, %entry
ret void
; CHECK-LABEL: test1:
; CHECK: shlq $2, [[REG1:%[a-z]+]]
; CHECK: movl arr1([[REG1]],[[REG1]],2), {{.*}}
; CHECK: leaq arr1+4([[REG1]],[[REG1]],2), [[REG2:%[a-z]+]]
; CHECK: subl arr1+4([[REG1]],[[REG1]],2), {{.*}}
; DISABLED: leaq arr1+8([[REG1]],[[REG1]],2), [[REG3:%[a-z]+]]
; CHECK: addl arr1+8([[REG1]],[[REG1]],2), {{.*}}
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
}
define void @test2(i64 %x) nounwind optsize {
entry:
%a = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 0
%tmp = load i32, i32* %a, align 4
%b = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 1
%tmp1 = load i32, i32* %b, align 4
%sub = sub i32 %tmp, %tmp1
%c = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 2
%tmp2 = load i32, i32* %c, align 4
%add = add nsw i32 %sub, %tmp2
switch i32 %add, label %sw.epilog [
i32 1, label %sw.bb.1
i32 2, label %sw.bb.2
]
sw.bb.1: ; preds = %entry
store i32 111, i32* %b, align 4
store i32 222, i32* %c, align 4
br label %sw.epilog
sw.bb.2: ; preds = %entry
store i32 333, i32* %b, align 4
store i32 444, i32* %c, align 4
br label %sw.epilog
sw.epilog: ; preds = %sw.bb.2, %sw.bb.1, %entry
ret void
; CHECK-LABEL: test2:
; CHECK: shlq $2, [[REG1:%[a-z]+]]
; DISABLED: movl arr1([[REG1]],[[REG1]],2), {{.*}}
; CHECK: leaq arr1+4([[REG1]],[[REG1]],2), [[REG2:%[a-z]+]]
; ENABLED: movl -4([[REG2]]), {{.*}}
; ENABLED: subl ([[REG2]]), {{.*}}
; ENABLED: addl 4([[REG2]]), {{.*}}
; DISABLED: subl arr1+4([[REG1]],[[REG1]],2), {{.*}}
; DISABLED: leaq arr1+8([[REG1]],[[REG1]],2), [[REG3:%[a-z]+]]
; DISABLED: addl arr1+8([[REG1]],[[REG1]],2), {{.*}}
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
}
; Check that LEA optimization pass takes into account a resultant address
; displacement when choosing a LEA instruction for replacing a redundant
; address recalculation.
define void @test3(i64 %x) nounwind optsize {
entry:
%a = getelementptr inbounds [65 x %struct.anon2], [65 x %struct.anon2]* @arr2, i64 0, i64 %x, i32 2
%tmp = load i32, i32* %a, align 4
%b = getelementptr inbounds [65 x %struct.anon2], [65 x %struct.anon2]* @arr2, i64 0, i64 %x, i32 0
%tmp1 = load i32, i32* %b, align 4
%add = add nsw i32 %tmp, %tmp1
switch i32 %add, label %sw.epilog [
i32 1, label %sw.bb.1
i32 2, label %sw.bb.2
]
sw.bb.1: ; preds = %entry
store i32 111, i32* %a, align 4
store i32 222, i32* %b, align 4
br label %sw.epilog
sw.bb.2: ; preds = %entry
store i32 333, i32* %a, align 4
; Make sure the REG3's definition LEA won't be removed as redundant.
%cvt = ptrtoint i32* %b to i32
store i32 %cvt, i32* %b, align 4
br label %sw.epilog
sw.epilog: ; preds = %sw.bb.2, %sw.bb.1, %entry
ret void
; CHECK-LABEL: test3:
; CHECK: imulq {{.*}}, [[REG1:%[a-z]+]]
; CHECK: leaq arr2+132([[REG1]]), [[REG2:%[a-z]+]]
; CHECK: leaq arr2([[REG1]]), [[REG3:%[a-z]+]]
; REG3's definition is closer to movl than REG2's, but the pass still chooses
; REG2 because it provides the resultant address displacement fitting 1 byte.
; ENABLED: movl ([[REG2]]), {{.*}}
; ENABLED: addl ([[REG3]]), {{.*}}
; DISABLED: movl arr2+132([[REG1]]), {{.*}}
; DISABLED: addl arr2([[REG1]]), {{.*}}
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; CHECK: movl ${{[1-4]+}}, ([[REG3]])
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; CHECK: movl {{.*}}, ([[REG3]])
}
define void @test4(i64 %x) nounwind minsize {
entry:
%a = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 0
%tmp = load i32, i32* %a, align 4
%b = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 1
%tmp1 = load i32, i32* %b, align 4
%sub = sub i32 %tmp, %tmp1
%c = getelementptr inbounds [65 x %struct.anon1], [65 x %struct.anon1]* @arr1, i64 0, i64 %x, i32 2
%tmp2 = load i32, i32* %c, align 4
%add = add nsw i32 %sub, %tmp2
switch i32 %add, label %sw.epilog [
i32 1, label %sw.bb.1
i32 2, label %sw.bb.2
]
sw.bb.1: ; preds = %entry
store i32 111, i32* %b, align 4
store i32 222, i32* %c, align 4
br label %sw.epilog
sw.bb.2: ; preds = %entry
store i32 333, i32* %b, align 4
store i32 444, i32* %c, align 4
br label %sw.epilog
sw.epilog: ; preds = %sw.bb.2, %sw.bb.1, %entry
ret void
; CHECK-LABEL: test4:
; CHECK: imulq {{.*}}, [[REG1:%[a-z]+]]
; DISABLED: movl arr1([[REG1]]), {{.*}}
; CHECK: leaq arr1+4([[REG1]]), [[REG2:%[a-z]+]]
; ENABLED: movl -4([[REG2]]), {{.*}}
; ENABLED: subl ([[REG2]]), {{.*}}
; ENABLED: addl 4([[REG2]]), {{.*}}
; DISABLED: subl arr1+4([[REG1]]), {{.*}}
; DISABLED: leaq arr1+8([[REG1]]), [[REG3:%[a-z]+]]
; DISABLED: addl arr1+8([[REG1]]), {{.*}}
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
; CHECK: movl ${{[1-4]+}}, ([[REG2]])
; ENABLED: movl ${{[1-4]+}}, 4([[REG2]])
; DISABLED: movl ${{[1-4]+}}, ([[REG3]])
}
|
