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
227
228
229
230
231
232
233
234
235
236
237
| ; RUN: opt -loop-simplify -loop-distribute -enable-loop-distribute -S < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=ALWAYS --check-prefix=NO_REMARKS
; RUN: opt -loop-simplify -loop-distribute -enable-loop-distribute -S \
; RUN: -pass-remarks-missed=loop-distribute < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=ALWAYS --check-prefix=MISSED_REMARKS
; RUN: opt -loop-simplify -loop-distribute -enable-loop-distribute -S \
; RUN: -pass-remarks-analysis=loop-distribute < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=ALWAYS --check-prefix=ANALYSIS_REMARKS
; RUN: opt -loop-simplify -loop-distribute -enable-loop-distribute -S \
; RUN: -pass-remarks=loop-distribute < %s 2>&1 \
; RUN: | FileCheck %s --check-prefix=ALWAYS --check-prefix=REMARKS
; This is the input program:
;
; 1 void forced (char *A, char *B, char *C, int N) {
; 2 #pragma clang loop distribute(enable)
; 3 for(int i = 0; i < N; i++) {
; 4 A[i] = B[i] * C[i];
; 5 }
; 6 }
; 7
; 8 void not_forced (char *A, char *B, char *C, int N) {
; 9 for(int i = 0; i < N; i++) {
; 10 A[i] = B[i] * C[i];
; 11 }
; 12 }
; 13
; 14 void success (char *A, char *B, char *C, char *D, char *E, int N) {
; 15 for(int i = 0; i < N; i++) {
; 16 A[i + 1] = A[i] + B[i];
; 17 C[i] = D[i] * E[i];
; 18 }
; 19 }
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.11.0"
; MISSED_REMARKS: remark: /tmp/t.c:3:3: loop not distributed: use -Rpass-analysis=loop-distribute for more info
; ALWAYS: remark: /tmp/t.c:3:3: loop not distributed: memory operations are safe for vectorization
; ALWAYS: warning: /tmp/t.c:3:3: loop not distributed: failed explicitly specified loop distribution
define void @forced(i8* %A, i8* %B, i8* %C, i32 %N) !dbg !7 {
entry:
%cmp12 = icmp sgt i32 %N, 0, !dbg !9
br i1 %cmp12, label %ph, label %for.cond.cleanup, !dbg !10
ph:
br label %for.body
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %ph ]
%arrayidx = getelementptr inbounds i8, i8* %B, i64 %indvars.iv, !dbg !12
%0 = load i8, i8* %arrayidx, align 1, !dbg !12, !tbaa !13
%arrayidx2 = getelementptr inbounds i8, i8* %C, i64 %indvars.iv, !dbg !16
%1 = load i8, i8* %arrayidx2, align 1, !dbg !16, !tbaa !13
%mul = mul i8 %1, %0, !dbg !17
%arrayidx6 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv, !dbg !18
store i8 %mul, i8* %arrayidx6, align 1, !dbg !19, !tbaa !13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !10
%lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !10
%exitcond = icmp eq i32 %lftr.wideiv, %N, !dbg !10
br i1 %exitcond, label %for.cond.cleanup, label %for.body, !dbg !10, !llvm.loop !20
for.cond.cleanup:
ret void, !dbg !11
}
; NO_REMARKS-NOT: remark: /tmp/t.c:9:3: loop not distributed: memory operations are safe for vectorization
; MISSED_REMARKS: remark: /tmp/t.c:9:3: loop not distributed: use -Rpass-analysis=loop-distribute for more info
; ANALYSIS_REMARKS: remark: /tmp/t.c:9:3: loop not distributed: memory operations are safe for vectorization
; ALWAYS-NOT: warning: /tmp/t.c:9:3: loop not distributed: failed explicitly specified loop distribution
define void @not_forced(i8* %A, i8* %B, i8* %C, i32 %N) !dbg !22 {
entry:
%cmp12 = icmp sgt i32 %N, 0, !dbg !23
br i1 %cmp12, label %ph, label %for.cond.cleanup, !dbg !24
ph:
br label %for.body
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %ph ]
%arrayidx = getelementptr inbounds i8, i8* %B, i64 %indvars.iv, !dbg !26
%0 = load i8, i8* %arrayidx, align 1, !dbg !26, !tbaa !13
%arrayidx2 = getelementptr inbounds i8, i8* %C, i64 %indvars.iv, !dbg !27
%1 = load i8, i8* %arrayidx2, align 1, !dbg !27, !tbaa !13
%mul = mul i8 %1, %0, !dbg !28
%arrayidx6 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv, !dbg !29
store i8 %mul, i8* %arrayidx6, align 1, !dbg !30, !tbaa !13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !24
%lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !24
%exitcond = icmp eq i32 %lftr.wideiv, %N, !dbg !24
br i1 %exitcond, label %for.cond.cleanup, label %for.body, !dbg !24
for.cond.cleanup:
ret void, !dbg !25
}
; REMARKS: remark: /tmp/t.c:15:3: distributed loop
define void @success(i8* %A, i8* %B, i8* %C, i8* %D, i8* %E, i32 %N) !dbg !31 {
entry:
%cmp28 = icmp sgt i32 %N, 0, !dbg !32
br i1 %cmp28, label %ph, label %for.cond.cleanup, !dbg !33
ph:
br label %for.body
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %ph ]
%arrayidx = getelementptr inbounds i8, i8* %A, i64 %indvars.iv, !dbg !35
%0 = load i8, i8* %arrayidx, align 1, !dbg !35, !tbaa !13
%arrayidx2 = getelementptr inbounds i8, i8* %B, i64 %indvars.iv, !dbg !36
%1 = load i8, i8* %arrayidx2, align 1, !dbg !36, !tbaa !13
%add = add i8 %1, %0, !dbg !37
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !33
%arrayidx7 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv.next, !dbg !38
store i8 %add, i8* %arrayidx7, align 1, !dbg !39, !tbaa !13
%arrayidx9 = getelementptr inbounds i8, i8* %D, i64 %indvars.iv, !dbg !40
%2 = load i8, i8* %arrayidx9, align 1, !dbg !40, !tbaa !13
%arrayidx12 = getelementptr inbounds i8, i8* %E, i64 %indvars.iv, !dbg !41
%3 = load i8, i8* %arrayidx12, align 1, !dbg !41, !tbaa !13
%mul = mul i8 %3, %2, !dbg !42
%arrayidx16 = getelementptr inbounds i8, i8* %C, i64 %indvars.iv, !dbg !43
store i8 %mul, i8* %arrayidx16, align 1, !dbg !44, !tbaa !13
%lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !33
%exitcond = icmp eq i32 %lftr.wideiv, %N, !dbg !33
br i1 %exitcond, label %for.cond.cleanup, label %for.body, !dbg !33
for.cond.cleanup:
ret void, !dbg !34
}
; MISSED_REMARKS: /tmp/t.c:27:5: loop not distributed: use -Rpass-analysis=loop-distribute for more info
; ANALYSIS_REMARKS: /tmp/t.c:27:5: loop not distributed: may not insert runtime check with convergent operation
; ALWAYS: warning: /tmp/t.c:27:5: loop not distributed: failed explicitly specified loop distribution
define void @convergent(i8* %A, i8* %B, i8* %C, i8* %D, i8* %E, i32 %N) #1 !dbg !45 {
entry:
%cmp28 = icmp sgt i32 %N, 0, !dbg !46
br i1 %cmp28, label %ph, label %for.cond.cleanup, !dbg !47
ph:
br label %for.body
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %ph ]
%arrayidx = getelementptr inbounds i8, i8* %A, i64 %indvars.iv, !dbg !49
%0 = load i8, i8* %arrayidx, align 1, !dbg !49, !tbaa !13
%arrayidx2 = getelementptr inbounds i8, i8* %B, i64 %indvars.iv, !dbg !50
%1 = load i8, i8* %arrayidx2, align 1, !dbg !50, !tbaa !13
%add = add i8 %1, %0, !dbg !51
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1, !dbg !57
%arrayidx7 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv.next, !dbg !52
store i8 %add, i8* %arrayidx7, align 1, !dbg !53, !tbaa !13
%arrayidx9 = getelementptr inbounds i8, i8* %D, i64 %indvars.iv, !dbg !54
%2 = load i8, i8* %arrayidx9, align 1, !dbg !54, !tbaa !13
%arrayidx12 = getelementptr inbounds i8, i8* %E, i64 %indvars.iv, !dbg !55
%3 = load i8, i8* %arrayidx12, align 1, !dbg !55, !tbaa !13
%mul = mul i8 %3, %2, !dbg !56
%arrayidx16 = getelementptr inbounds i8, i8* %C, i64 %indvars.iv, !dbg !57
store i8 %mul, i8* %arrayidx16, align 1, !dbg !58, !tbaa !13
call void @llvm.convergent()
%lftr.wideiv = trunc i64 %indvars.iv.next to i32, !dbg !57
%exitcond = icmp eq i32 %lftr.wideiv, %N, !dbg !57
br i1 %exitcond, label %for.cond.cleanup, label %for.body, !llvm.loop !20, !dbg !57
for.cond.cleanup:
ret void, !dbg !58
}
declare void @llvm.convergent() #0
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind convergent }
!llvm.dbg.cu = !{!0}
!llvm.module.flags = !{!3, !4}
!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 3.9.0 (trunk 267633) (llvm/trunk 267675)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2)
!1 = !DIFile(filename: "/tmp/t.c", directory: "/tmp")
!2 = !{}
!3 = !{i32 2, !"Dwarf Version", i32 2}
!4 = !{i32 2, !"Debug Info Version", i32 3}
!7 = distinct !DISubprogram(name: "forced", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, flags: DIFlagPrototyped, isOptimized: true, unit: !0, retainedNodes: !2)
!8 = !DISubroutineType(types: !2)
!9 = !DILocation(line: 3, column: 20, scope: !7)
!10 = !DILocation(line: 3, column: 3, scope: !7)
!11 = !DILocation(line: 6, column: 1, scope: !7)
!12 = !DILocation(line: 4, column: 12, scope: !7)
!13 = !{!14, !14, i64 0}
!14 = !{!"omnipotent char", !15, i64 0}
!15 = !{!"Simple C/C++ TBAA"}
!16 = !DILocation(line: 4, column: 19, scope: !7)
!17 = !DILocation(line: 4, column: 17, scope: !7)
!18 = !DILocation(line: 4, column: 5, scope: !7)
!19 = !DILocation(line: 4, column: 10, scope: !7)
!20 = distinct !{!20, !21}
!21 = !{!"llvm.loop.distribute.enable", i1 true}
!22 = distinct !DISubprogram(name: "not_forced", scope: !1, file: !1, line: 8, type: !8, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, unit: !0, retainedNodes: !2)
!23 = !DILocation(line: 9, column: 20, scope: !22)
!24 = !DILocation(line: 9, column: 3, scope: !22)
!25 = !DILocation(line: 12, column: 1, scope: !22)
!26 = !DILocation(line: 10, column: 12, scope: !22)
!27 = !DILocation(line: 10, column: 19, scope: !22)
!28 = !DILocation(line: 10, column: 17, scope: !22)
!29 = !DILocation(line: 10, column: 5, scope: !22)
!30 = !DILocation(line: 10, column: 10, scope: !22)
!31 = distinct !DISubprogram(name: "success", scope: !1, file: !1, line: 14, type: !8, isLocal: false, isDefinition: true, scopeLine: 14, flags: DIFlagPrototyped, isOptimized: true, unit: !0, retainedNodes: !2)
!32 = !DILocation(line: 15, column: 20, scope: !31)
!33 = !DILocation(line: 15, column: 3, scope: !31)
!34 = !DILocation(line: 19, column: 1, scope: !31)
!35 = !DILocation(line: 16, column: 16, scope: !31)
!36 = !DILocation(line: 16, column: 23, scope: !31)
!37 = !DILocation(line: 16, column: 21, scope: !31)
!38 = !DILocation(line: 16, column: 5, scope: !31)
!39 = !DILocation(line: 16, column: 14, scope: !31)
!40 = !DILocation(line: 17, column: 12, scope: !31)
!41 = !DILocation(line: 17, column: 19, scope: !31)
!42 = !DILocation(line: 17, column: 17, scope: !31)
!43 = !DILocation(line: 17, column: 5, scope: !31)
!44 = !DILocation(line: 17, column: 10, scope: !31)
!45 = distinct !DISubprogram(name: "convergent", scope: !1, file: !1, line: 24, type: !8, isLocal: false, isDefinition: true, scopeLine: 24, flags: DIFlagPrototyped, isOptimized: true, unit: !0, retainedNodes: !2)
!46 = !DILocation(line: 25, column: 20, scope: !45)
!47 = !DILocation(line: 25, column: 3, scope: !45)
!48 = !DILocation(line: 29, column: 1, scope: !45)
!49 = !DILocation(line: 26, column: 16, scope: !45)
!50 = !DILocation(line: 26, column: 23, scope: !45)
!51 = !DILocation(line: 26, column: 21, scope: !45)
!52 = !DILocation(line: 26, column: 5, scope: !45)
!53 = !DILocation(line: 26, column: 14, scope: !45)
!54 = !DILocation(line: 27, column: 12, scope: !45)
!55 = !DILocation(line: 27, column: 19, scope: !45)
!56 = !DILocation(line: 27, column: 17, scope: !45)
!57 = !DILocation(line: 27, column: 5, scope: !45)
!58 = !DILocation(line: 27, column: 10, scope: !45)
|