umul-sign-check.ll
7.53 KB
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
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -instcombine -S %s | FileCheck %s
; Check that we simplify llvm.umul.with.overflow, if the overflow check is
; weakened by or (icmp ne %res, 0) %overflow. This is generated by code using
; __builtin_mul_overflow with negative integer constants, e.g.
; bool test(unsigned long long v, unsigned long long *res) {
; return __builtin_mul_overflow(v, -4775807LL, res);
; }
declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) #0
define i1 @test1(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test1(
; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: store i64 [[MUL]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
store i64 %mul, i64* %ptr, align 8
ret i1 %overflow.1
}
define i1 @test1_or_ops_swapped(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test1_or_ops_swapped(
; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: store i64 [[MUL]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %cmp, %overflow
store i64 %mul, i64* %ptr, align 8
ret i1 %overflow.1
}
define i1 @test2(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test2(
; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[NEG:%.*]] = sub i64 0, [[MUL]]
; CHECK-NEXT: store i64 [[NEG]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
%neg = sub i64 0, %mul
store i64 %neg, i64* %ptr, align 8
ret i1 %overflow.1
}
declare void @use(i1)
define i1 @test3_multiple_overflow_users(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test3_multiple_overflow_users(
; CHECK-NEXT: [[RES:%.*]] = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[A:%.*]], i64 [[B:%.*]])
; CHECK-NEXT: [[OVERFLOW:%.*]] = extractvalue { i64, i1 } [[RES]], 1
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: call void @use(i1 [[OVERFLOW]])
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
call void @use(i1 %overflow)
ret i1 %overflow.1
}
; Do not simplify if %overflow and %mul have multiple uses.
define i1 @test3_multiple_overflow_and_mul_users(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test3_multiple_overflow_and_mul_users(
; CHECK-NEXT: [[RES:%.*]] = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[A:%.*]], i64 [[B:%.*]])
; CHECK-NEXT: [[OVERFLOW:%.*]] = extractvalue { i64, i1 } [[RES]], 1
; CHECK-NEXT: [[MUL:%.*]] = extractvalue { i64, i1 } [[RES]], 0
; CHECK-NEXT: [[CMP:%.*]] = icmp ne i64 [[MUL]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = or i1 [[OVERFLOW]], [[CMP]]
; CHECK-NEXT: [[NEG:%.*]] = sub i64 0, [[MUL]]
; CHECK-NEXT: store i64 [[NEG]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: call void @use(i1 [[OVERFLOW]])
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
%neg = sub i64 0, %mul
store i64 %neg, i64* %ptr, align 8
call void @use(i1 %overflow)
ret i1 %overflow.1
}
declare void @use.2({ i64, i1 })
define i1 @test3_multiple_res_users(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test3_multiple_res_users(
; CHECK-NEXT: [[RES:%.*]] = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[A:%.*]], i64 [[B:%.*]])
; CHECK-NEXT: [[MUL:%.*]] = extractvalue { i64, i1 } [[RES]], 0
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[NEG:%.*]] = sub i64 0, [[MUL]]
; CHECK-NEXT: store i64 [[NEG]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: call void @use.2({ i64, i1 } [[RES]])
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
%neg = sub i64 0, %mul
store i64 %neg, i64* %ptr, align 8
call void @use.2({ i64, i1 } %res)
ret i1 %overflow.1
}
declare void @use.3(i64)
; Simplify if %mul has multiple uses.
define i1 @test3_multiple_mul_users(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test3_multiple_mul_users(
; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp ne i64 [[A]], 0
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[B]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = and i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[NEG:%.*]] = sub i64 0, [[MUL]]
; CHECK-NEXT: store i64 [[NEG]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: call void @use.3(i64 [[MUL]])
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp ne i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
%neg = sub i64 0, %mul
store i64 %neg, i64* %ptr, align 8
call void @use.3(i64 %mul)
ret i1 %overflow.1
}
define i1 @test4_no_icmp_ne(i64 %a, i64 %b, i64* %ptr) {
; CHECK-LABEL: @test4_no_icmp_ne(
; CHECK-NEXT: [[RES:%.*]] = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[A:%.*]], i64 [[B:%.*]])
; CHECK-NEXT: [[OVERFLOW:%.*]] = extractvalue { i64, i1 } [[RES]], 1
; CHECK-NEXT: [[MUL:%.*]] = extractvalue { i64, i1 } [[RES]], 0
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i64 [[MUL]], 0
; CHECK-NEXT: [[OVERFLOW_1:%.*]] = or i1 [[OVERFLOW]], [[CMP]]
; CHECK-NEXT: [[NEG:%.*]] = sub i64 0, [[MUL]]
; CHECK-NEXT: store i64 [[NEG]], i64* [[PTR:%.*]], align 8
; CHECK-NEXT: ret i1 [[OVERFLOW_1]]
;
%res = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
%overflow = extractvalue { i64, i1 } %res, 1
%mul = extractvalue { i64, i1 } %res, 0
%cmp = icmp sgt i64 %mul, 0
%overflow.1 = or i1 %overflow, %cmp
%neg = sub i64 0, %mul
store i64 %neg, i64* %ptr, align 8
ret i1 %overflow.1
}
attributes #0 = { nounwind readnone speculatable willreturn }