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
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; REQUIRES: asserts
; RUN: opt < %s -S -debug -passes=loop-idiom 2>&1 | FileCheck %s
; The C code to generate this testcase:
; void test(int *ar, int n, int m)
; {
; long i;
; for (i=0; i<n; ++i) {
; int *arr = ar + i * m;
; memset(arr, 0, i + m * sizeof(int));
; }
; }
; Check on debug outputs...
; CHECK: loop-idiom Scanning: F[MemsetSize_LoopVariant] Countable Loop %for.body
; CHECK-NEXT: memset size is non-constant
; CHECK-NEXT: memset size is not a loop-invariant, abort
; CHECK: loop-idiom Scanning: F[MemsetSize_Stride_Mismatch] Countable Loop %for.body
; CHECK-NEXT: memset size is non-constant
; CHECK-NEXT: MemsetSizeSCEV: (4 * (sext i32 %m to i64))<nsw>
; CHECK-NEXT: PositiveStrideSCEV: (4 + (4 * (sext i32 %m to i64))<nsw>)<nsw>
; CHECK-NEXT: Try to fold SCEV based on loop guard
; CHECK-NEXT: FoldedMemsetSize: (4 * (sext i32 %m to i64))<nsw>
; CHECK-NEXT: FoldedPositiveStride: (4 + (4 * (sext i32 %m to i64))<nsw>)<nsw>
; CHECK-NEXT: SCEV don't match, abort
; CHECK: loop-idiom Scanning: F[NonZeroAddressSpace] Countable Loop %for.cond1.preheader
; CHECK-NEXT: memset size is non-constant
; CHECK-NEXT: pointer is not in address space zero, abort
; CHECK: loop-idiom Scanning: F[NonAffinePointer] Countable Loop %for.body
; CHECK-NEXT: Pointer is not affine, abort
define void @MemsetSize_LoopVariant(ptr %ar, i32 %n, i32 %m) {
; CHECK-LABEL: @MemsetSize_LoopVariant(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CONV:%.*]] = sext i32 [[N:%.*]] to i64
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i64 0, [[CONV]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[CONV1:%.*]] = sext i32 [[M:%.*]] to i64
; CHECK-NEXT: [[CONV2:%.*]] = sext i32 [[M]] to i64
; CHECK-NEXT: [[MUL3:%.*]] = mul i64 [[CONV2]], 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_02:%.*]] = phi i64 [ 0, [[FOR_BODY_LR_PH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i64 [[I_02]], [[CONV1]]
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[AR:%.*]], i64 [[MUL]]
; CHECK-NEXT: [[ADD:%.*]] = add nsw i64 [[I_02]], [[MUL3]]
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ADD_PTR]], i8 0, i64 [[ADD]], i1 false)
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_02]], 1
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[INC]], [[CONV]]
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%conv = sext i32 %n to i64
%cmp1 = icmp slt i64 0, %conv
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%conv1 = sext i32 %m to i64
%conv2 = sext i32 %m to i64
%mul3 = mul i64 %conv2, 4
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i64 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%mul = mul nsw i64 %i.02, %conv1
%add.ptr = getelementptr inbounds i32, ptr %ar, i64 %mul
%add = add nsw i64 %i.02, %mul3
call void @llvm.memset.p0.i64(ptr align 4 %add.ptr, i8 0, i64 %add, i1 false)
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nuw nsw i64 %i.02, 1
%cmp = icmp slt i64 %inc, %conv
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
ret void
}
; void test(int *ar, int n, int m)
; {
; long i;
; for (i=0; i<n; ++i) {
; int *arr = ar + i + i * m;
; memset(arr, 0, m * sizeof(int));
; }
; }
define void @MemsetSize_Stride_Mismatch(ptr %ar, i32 %n, i32 %m) {
; CHECK-LABEL: @MemsetSize_Stride_Mismatch(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CONV:%.*]] = sext i32 [[N:%.*]] to i64
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i64 0, [[CONV]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[CONV1:%.*]] = sext i32 [[M:%.*]] to i64
; CHECK-NEXT: [[CONV3:%.*]] = sext i32 [[M]] to i64
; CHECK-NEXT: [[MUL4:%.*]] = mul i64 [[CONV3]], 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_02:%.*]] = phi i64 [ 0, [[FOR_BODY_LR_PH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[AR:%.*]], i64 [[I_02]]
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i64 [[I_02]], [[CONV1]]
; CHECK-NEXT: [[ADD_PTR2:%.*]] = getelementptr inbounds i32, ptr [[ADD_PTR]], i64 [[MUL]]
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ADD_PTR2]], i8 0, i64 [[MUL4]], i1 false)
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_02]], 1
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[INC]], [[CONV]]
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%conv = sext i32 %n to i64
%cmp1 = icmp slt i64 0, %conv
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%conv1 = sext i32 %m to i64
%conv3 = sext i32 %m to i64
%mul4 = mul i64 %conv3, 4
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i64 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%add.ptr = getelementptr inbounds i32, ptr %ar, i64 %i.02
%mul = mul nsw i64 %i.02, %conv1
%add.ptr2 = getelementptr inbounds i32, ptr %add.ptr, i64 %mul
call void @llvm.memset.p0.i64(ptr align 4 %add.ptr2, i8 0, i64 %mul4, i1 false)
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nuw nsw i64 %i.02, 1
%cmp = icmp slt i64 %inc, %conv
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
ret void
}
define void @NonZeroAddressSpace(ptr addrspace(2) nocapture %ar, i64 %n, i64 %m) {
; CHECK-LABEL: @NonZeroAddressSpace(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = shl nuw i64 [[M:%.*]], 2
; CHECK-NEXT: br label [[FOR_COND1_PREHEADER:%.*]]
; CHECK: for.cond1.preheader:
; CHECK-NEXT: [[I_017:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC5:%.*]], [[FOR_INC4:%.*]] ]
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[M]], [[I_017]]
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, ptr addrspace(2) [[AR:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i64 [[I_017]], [[M]]
; CHECK-NEXT: call void @llvm.memset.p2.i64(ptr addrspace(2) align 4 [[SCEVGEP]], i8 0, i64 [[TMP0]], i1 false)
; CHECK-NEXT: br label [[FOR_INC4]]
; CHECK: for.inc4:
; CHECK-NEXT: [[INC5]] = add nuw nsw i64 [[I_017]], 1
; CHECK-NEXT: [[EXITCOND18_NOT:%.*]] = icmp eq i64 [[INC5]], [[N:%.*]]
; CHECK-NEXT: br i1 [[EXITCOND18_NOT]], label [[FOR_END6:%.*]], label [[FOR_COND1_PREHEADER]]
; CHECK: for.end6:
; CHECK-NEXT: ret void
;
entry:
%0 = shl nuw i64 %m, 2
br label %for.cond1.preheader
for.cond1.preheader: ; preds = %for.inc4, %entry
%i.017 = phi i64 [ 0, %entry ], [ %inc5, %for.inc4 ]
%1 = mul i64 %m, %i.017
%scevgep = getelementptr i32, ptr addrspace(2) %ar, i64 %1
%mul = mul nsw i64 %i.017, %m
call void @llvm.memset.p2.i64(ptr addrspace(2) align 4 %scevgep, i8 0, i64 %0, i1 false)
br label %for.inc4
for.inc4: ; preds = %for.cond1.preheader
%inc5 = add nuw nsw i64 %i.017, 1
%exitcond18.not = icmp eq i64 %inc5, %n
br i1 %exitcond18.not, label %for.end6, label %for.cond1.preheader
for.end6: ; preds = %for.inc4
ret void
}
; void test(int *ar, int n, int m)
; {
; long i;
; for (i=0; i<n; ++i) {
; int *arr = ar + i * m;
; memset(arr, 0, m * sizeof(int));
; ar = ar + i;
; }
; }
define void @NonAffinePointer(ptr %ar, i32 %n, i32 %m) {
; CHECK-LABEL: @NonAffinePointer(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CONV:%.*]] = sext i32 [[N:%.*]] to i64
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i64 0, [[CONV]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[CONV1:%.*]] = sext i32 [[M:%.*]] to i64
; CHECK-NEXT: [[CONV2:%.*]] = sext i32 [[M]] to i64
; CHECK-NEXT: [[MUL3:%.*]] = mul i64 [[CONV2]], 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[AR_ADDR_03:%.*]] = phi ptr [ [[AR:%.*]], [[FOR_BODY_LR_PH]] ], [ [[ADD_PTR4:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT: [[I_02:%.*]] = phi i64 [ 0, [[FOR_BODY_LR_PH]] ], [ [[INC:%.*]], [[FOR_INC]] ]
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i64 [[I_02]], [[CONV1]]
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[AR_ADDR_03]], i64 [[MUL]]
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ADD_PTR]], i8 0, i64 [[MUL3]], i1 false)
; CHECK-NEXT: [[ADD_PTR4]] = getelementptr inbounds i32, ptr [[AR_ADDR_03]], i64 [[I_02]]
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_02]], 1
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[INC]], [[CONV]]
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%conv = sext i32 %n to i64
%cmp1 = icmp slt i64 0, %conv
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
%conv1 = sext i32 %m to i64
%conv2 = sext i32 %m to i64
%mul3 = mul i64 %conv2, 4
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%ar.addr.03 = phi ptr [ %ar, %for.body.lr.ph ], [ %add.ptr4, %for.inc ]
%i.02 = phi i64 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%mul = mul nsw i64 %i.02, %conv1
%add.ptr = getelementptr inbounds i32, ptr %ar.addr.03, i64 %mul
call void @llvm.memset.p0.i64(ptr align 4 %add.ptr, i8 0, i64 %mul3, i1 false)
%add.ptr4 = getelementptr inbounds i32, ptr %ar.addr.03, i64 %i.02
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nuw nsw i64 %i.02, 1
%cmp = icmp slt i64 %inc, %conv
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
ret void
}
declare void @llvm.memset.p0.i64(ptr nocapture writeonly, i8, i64, i1 immarg)
declare void @llvm.memset.p2.i64(ptr addrspace(2) nocapture writeonly, i8, i64, i1 immarg)
|
