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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s
; No overflow flags, same type width.
define i32 @test_01(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_01:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addq $-4, %rdi
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB0_1: # %loop
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: subq $1, %rsi
; CHECK-NEXT: jb .LBB0_4
; CHECK-NEXT: # %bb.2: # %backedge
; CHECK-NEXT: # in Loop: Header=BB0_1 Depth=1
; CHECK-NEXT: cmpl %edx, (%rdi)
; CHECK-NEXT: leaq 4(%rdi), %rdi
; CHECK-NEXT: jne .LBB0_1
; CHECK-NEXT: # %bb.3: # %failure
; CHECK-NEXT: .LBB0_4: # %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nsw flag, same type width.
define i32 @test_02(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_02:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addq $-4, %rdi
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB1_1: # %loop
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: subq $1, %rsi
; CHECK-NEXT: jb .LBB1_4
; CHECK-NEXT: # %bb.2: # %backedge
; CHECK-NEXT: # in Loop: Header=BB1_1 Depth=1
; CHECK-NEXT: cmpl %edx, (%rdi)
; CHECK-NEXT: leaq 4(%rdi), %rdi
; CHECK-NEXT: jne .LBB1_1
; CHECK-NEXT: # %bb.3: # %failure
; CHECK-NEXT: .LBB1_4: # %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nsw i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nsw flag, optimization is possible because memory instruction is dominated by loop-exiting check against iv.next.
define i32 @test_02_nopoison(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_02_nopoison:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addq $-4, %rdi
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB2_1: # %loop
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: subq $1, %rsi
; CHECK-NEXT: jb .LBB2_4
; CHECK-NEXT: # %bb.2: # %backedge
; CHECK-NEXT: # in Loop: Header=BB2_1 Depth=1
; CHECK-NEXT: cmpl %edx, (%rdi)
; CHECK-NEXT: leaq 4(%rdi), %rdi
; CHECK-NEXT: jne .LBB2_1
; CHECK-NEXT: # %bb.3: # %failure
; CHECK-NEXT: .LBB2_4: # %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%len.plus.1 = add i64 %len, 1
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nsw i64 %iv, 1
%cond_1 = icmp eq i64 %iv.next, %len.plus.1
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nuw flag, same type width.
define i32 @test_03(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_03:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addq $-4, %rdi
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB3_1: # %loop
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: subq $1, %rsi
; CHECK-NEXT: jb .LBB3_4
; CHECK-NEXT: # %bb.2: # %backedge
; CHECK-NEXT: # in Loop: Header=BB3_1 Depth=1
; CHECK-NEXT: cmpl %edx, (%rdi)
; CHECK-NEXT: leaq 4(%rdi), %rdi
; CHECK-NEXT: jne .LBB3_1
; CHECK-NEXT: # %bb.3: # %failure
; CHECK-NEXT: .LBB3_4: # %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nuw i64 %iv, 1
%cond_1 = icmp eq i64 %iv, %len
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
; nuw flag, optimization is possible because memory instruction is dominated by loop-exiting check against iv.next.
define i32 @test_03_nopoison(ptr %p, i64 %len, i32 %x) {
; CHECK-LABEL: test_03_nopoison:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addq $-4, %rdi
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB4_1: # %loop
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: subq $1, %rsi
; CHECK-NEXT: jb .LBB4_4
; CHECK-NEXT: # %bb.2: # %backedge
; CHECK-NEXT: # in Loop: Header=BB4_1 Depth=1
; CHECK-NEXT: cmpl %edx, (%rdi)
; CHECK-NEXT: leaq 4(%rdi), %rdi
; CHECK-NEXT: jne .LBB4_1
; CHECK-NEXT: # %bb.3: # %failure
; CHECK-NEXT: .LBB4_4: # %exit
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: retq
entry:
%len.plus.1 = add i64 %len, 1
%scevgep = getelementptr i32, ptr %p, i64 -1
br label %loop
loop: ; preds = %backedge, %entry
%iv = phi i64 [ %iv.next, %backedge ], [ 0, %entry ]
%iv.next = add nuw i64 %iv, 1
%cond_1 = icmp eq i64 %iv.next, %len.plus.1
br i1 %cond_1, label %exit, label %backedge
backedge: ; preds = %loop
%scevgep1 = getelementptr i32, ptr %scevgep, i64 %iv
%loaded = load atomic i32, ptr %scevgep1 unordered, align 4
%cond_2 = icmp eq i32 %loaded, %x
br i1 %cond_2, label %failure, label %loop
exit: ; preds = %loop
ret i32 -1
failure: ; preds = %backedge
unreachable
}
|
