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
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute -S -enable-mem-access-versioning=0 < %s | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
; PredicatedScalarEvolution decides it needs to insert a bounds check
; not based on memory access.
define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias %d, i32* noalias %e, i64 %N) {
; CHECK-LABEL: @f(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A2:%.*]] = ptrtoint i32* [[A:%.*]] to i64
; CHECK-NEXT: br label [[FOR_BODY_LVER_CHECK:%.*]]
; CHECK: for.body.lver.check:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N:%.*]], -1
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
; CHECK-NEXT: [[MUL1:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 2, i32 [[TMP1]])
; CHECK-NEXT: [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL1]], 0
; CHECK-NEXT: [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL1]], 1
; CHECK-NEXT: [[TMP2:%.*]] = add i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i32 0, [[MUL_RESULT]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[TMP3]], 0
; CHECK-NEXT: [[TMP5:%.*]] = icmp ult i32 [[TMP2]], 0
; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; CHECK-NEXT: [[MUL3:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]])
; CHECK-NEXT: [[MUL_RESULT4:%.*]] = extractvalue { i64, i1 } [[MUL3]], 0
; CHECK-NEXT: [[MUL_OVERFLOW5:%.*]] = extractvalue { i64, i1 } [[MUL3]], 1
; CHECK-NEXT: [[TMP11:%.*]] = add i64 [[A2]], [[MUL_RESULT4]]
; CHECK-NEXT: [[TMP12:%.*]] = sub i64 [[A2]], [[MUL_RESULT4]]
; CHECK-NEXT: [[TMP13:%.*]] = icmp ugt i64 [[TMP12]], [[A2]]
; CHECK-NEXT: [[TMP14:%.*]] = icmp ult i64 [[TMP11]], [[A2]]
; CHECK-NEXT: [[TMP15:%.*]] = select i1 false, i1 [[TMP13]], i1 [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = or i1 [[TMP15]], [[MUL_OVERFLOW5]]
; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP10]], [[TMP16]]
; CHECK-NEXT: br i1 [[TMP17]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]]
; CHECK: for.body.ph.lver.orig:
; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; CHECK: for.body.lver.orig:
; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXA_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXB_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADB_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXB_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULA_LVER_ORIG:%.*]] = mul i32 [[LOADB_LVER_ORIG]], [[LOADA_LVER_ORIG]]
; CHECK-NEXT: [[ADD_LVER_ORIG]] = add nuw nsw i64 [[IND_LVER_ORIG]], 1
; CHECK-NEXT: [[INC1_LVER_ORIG]] = add i32 [[IND1_LVER_ORIG]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULA_LVER_ORIG]], i32* [[ARRAYIDXA_PLUS_4_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXD_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[D:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADD_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXD_LVER_ORIG]], align 4
; CHECK-NEXT: [[ARRAYIDXE_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[E:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: [[LOADE_LVER_ORIG:%.*]] = load i32, i32* [[ARRAYIDXE_LVER_ORIG]], align 4
; CHECK-NEXT: [[MULC_LVER_ORIG:%.*]] = mul i32 [[LOADD_LVER_ORIG]], [[LOADE_LVER_ORIG]]
; CHECK-NEXT: [[ARRAYIDXC_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 [[MUL_EXT_LVER_ORIG]]
; CHECK-NEXT: store i32 [[MULC_LVER_ORIG]], i32* [[ARRAYIDXC_LVER_ORIG]], align 4
; CHECK-NEXT: [[EXITCOND_LVER_ORIG:%.*]] = icmp eq i64 [[ADD_LVER_ORIG]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_LVER_ORIG]], label [[FOR_END:%.*]], label [[FOR_BODY_LVER_ORIG]]
; CHECK: for.body.ph.ldist1:
; CHECK-NEXT: br label [[FOR_BODY_LDIST1:%.*]]
; CHECK: for.body.ldist1:
; CHECK-NEXT: [[IND_LDIST1:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[ADD_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[IND1_LDIST1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LDIST1]] ], [ [[INC1_LDIST1:%.*]], [[FOR_BODY_LDIST1]] ]
; CHECK-NEXT: [[MUL_LDIST1:%.*]] = mul i32 [[IND1_LDIST1]], 2
; CHECK-NEXT: [[MUL_EXT_LDIST1:%.*]] = zext i32 [[MUL_LDIST1]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LDIST1]]
; CHECK-NEXT: [[LOADA_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXA_LDIST1]], align 4
; CHECK-NEXT: [[ARRAYIDXB_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[MUL_EXT_LDIST1]]
; CHECK-NEXT: [[LOADB_LDIST1:%.*]] = load i32, i32* [[ARRAYIDXB_LDIST1]], align 4
; CHECK-NEXT: [[MULA_LDIST1:%.*]] = mul i32 [[LOADB_LDIST1]], [[LOADA_LDIST1]]
; CHECK-NEXT: [[ADD_LDIST1]] = add nuw nsw i64 [[IND_LDIST1]], 1
; CHECK-NEXT: [[INC1_LDIST1]] = add i32 [[IND1_LDIST1]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4_LDIST1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD_LDIST1]]
; CHECK-NEXT: store i32 [[MULA_LDIST1]], i32* [[ARRAYIDXA_PLUS_4_LDIST1]], align 4
; CHECK-NEXT: [[EXITCOND_LDIST1:%.*]] = icmp eq i64 [[ADD_LDIST1]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND_LDIST1]], label [[FOR_BODY_PH:%.*]], label [[FOR_BODY_LDIST1]]
; CHECK: for.body.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, [[FOR_BODY_PH]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[IND1:%.*]] = phi i32 [ 0, [[FOR_BODY_PH]] ], [ [[INC1:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[IND1]], 2
; CHECK-NEXT: [[MUL_EXT:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT: [[INC1]] = add i32 [[IND1]], 1
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%ind1 = phi i32 [ 0, %entry ], [ %inc1, %for.body ]
%mul = mul i32 %ind1, 2
%mul_ext = zext i32 %mul to i64
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %mul_ext
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %mul_ext
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%inc1 = add i32 %ind1, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %mul_ext
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %mul_ext
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %mul_ext
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Can't add control dependency with convergent in loop body.
define void @f_with_convergent(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias %d, i32* noalias %e, i64 %N) #1 {
; CHECK-LABEL: @f_with_convergent(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[IND:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[ADD:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[IND1:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INC1:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[IND1]], 2
; CHECK-NEXT: [[MUL_EXT:%.*]] = zext i32 [[MUL]] to i64
; CHECK-NEXT: [[ARRAYIDXA:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADA:%.*]] = load i32, i32* [[ARRAYIDXA]], align 4
; CHECK-NEXT: [[ARRAYIDXB:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADB:%.*]] = load i32, i32* [[ARRAYIDXB]], align 4
; CHECK-NEXT: [[MULA:%.*]] = mul i32 [[LOADB]], [[LOADA]]
; CHECK-NEXT: [[ADD]] = add nuw nsw i64 [[IND]], 1
; CHECK-NEXT: [[INC1]] = add i32 [[IND1]], 1
; CHECK-NEXT: [[ARRAYIDXA_PLUS_4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[ADD]]
; CHECK-NEXT: store i32 [[MULA]], i32* [[ARRAYIDXA_PLUS_4]], align 4
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[CONVERGENTD:%.*]] = call i32 @llvm.convergent(i32 [[LOADD]])
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[CONVERGENTD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N:%.*]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%ind1 = phi i32 [ 0, %entry ], [ %inc1, %for.body ]
%mul = mul i32 %ind1, 2
%mul_ext = zext i32 %mul to i64
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %mul_ext
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %mul_ext
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 1
%inc1 = add i32 %ind1, 1
%arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
store i32 %mulA, i32* %arrayidxA_plus_4, align 4
%arrayidxD = getelementptr inbounds i32, i32* %d, i64 %mul_ext
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %mul_ext
%loadE = load i32, i32* %arrayidxE, align 4
%convergentD = call i32 @llvm.convergent(i32 %loadD)
%mulC = mul i32 %convergentD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %mul_ext
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, %N
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
declare i32 @llvm.convergent(i32) #0
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind convergent }
|