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
266
267
268
269
270
271
272
273
|
; RUN: opt < %s -gvn -enable-load-pre -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
define i32 @test1(i32* %p, i1 %C) {
; CHECK: @test1
block1:
br i1 %C, label %block2, label %block3
block2:
br label %block4
; CHECK: block2:
; CHECK-NEXT: load i32* %p
block3:
store i32 0, i32* %p
br label %block4
block4:
%PRE = load i32* %p
ret i32 %PRE
; CHECK: block4:
; CHECK-NEXT: phi i32
; CHECK-NEXT: ret i32
}
; This is a simple phi translation case.
define i32 @test2(i32* %p, i32* %q, i1 %C) {
; CHECK: @test2
block1:
br i1 %C, label %block2, label %block3
block2:
br label %block4
; CHECK: block2:
; CHECK-NEXT: load i32* %q
block3:
store i32 0, i32* %p
br label %block4
block4:
%P2 = phi i32* [%p, %block3], [%q, %block2]
%PRE = load i32* %P2
ret i32 %PRE
; CHECK: block4:
; CHECK-NEXT: phi i32 [
; CHECK-NOT: load
; CHECK: ret i32
}
; This is a PRE case that requires phi translation through a GEP.
define i32 @test3(i32* %p, i32* %q, i32** %Hack, i1 %C) {
; CHECK: @test3
block1:
%B = getelementptr i32* %q, i32 1
store i32* %B, i32** %Hack
br i1 %C, label %block2, label %block3
block2:
br label %block4
; CHECK: block2:
; CHECK-NEXT: load i32* %B
block3:
%A = getelementptr i32* %p, i32 1
store i32 0, i32* %A
br label %block4
block4:
%P2 = phi i32* [%p, %block3], [%q, %block2]
%P3 = getelementptr i32* %P2, i32 1
%PRE = load i32* %P3
ret i32 %PRE
; CHECK: block4:
; CHECK-NEXT: phi i32 [
; CHECK-NOT: load
; CHECK: ret i32
}
;; Here the loaded address is available, but the computation is in 'block3'
;; which does not dominate 'block2'.
define i32 @test4(i32* %p, i32* %q, i32** %Hack, i1 %C) {
; CHECK: @test4
block1:
br i1 %C, label %block2, label %block3
block2:
br label %block4
; CHECK: block2:
; CHECK: load i32*
; CHECK: br label %block4
block3:
%B = getelementptr i32* %q, i32 1
store i32* %B, i32** %Hack
%A = getelementptr i32* %p, i32 1
store i32 0, i32* %A
br label %block4
block4:
%P2 = phi i32* [%p, %block3], [%q, %block2]
%P3 = getelementptr i32* %P2, i32 1
%PRE = load i32* %P3
ret i32 %PRE
; CHECK: block4:
; CHECK-NEXT: phi i32 [
; CHECK-NOT: load
; CHECK: ret i32
}
;void test5(int N, double *G) {
; int j;
; for (j = 0; j < N - 1; j++)
; G[j] = G[j] + G[j+1];
;}
define void @test5(i32 %N, double* nocapture %G) nounwind ssp {
; CHECK: @test5
entry:
%0 = add i32 %N, -1
%1 = icmp sgt i32 %0, 0
br i1 %1, label %bb.nph, label %return
bb.nph:
%tmp = zext i32 %0 to i64
br label %bb
; CHECK: bb.nph:
; CHECK: load double*
; CHECK: br label %bb
bb:
%indvar = phi i64 [ 0, %bb.nph ], [ %tmp6, %bb ]
%tmp6 = add i64 %indvar, 1
%scevgep = getelementptr double* %G, i64 %tmp6
%scevgep7 = getelementptr double* %G, i64 %indvar
%2 = load double* %scevgep7, align 8
%3 = load double* %scevgep, align 8
%4 = fadd double %2, %3
store double %4, double* %scevgep7, align 8
%exitcond = icmp eq i64 %tmp6, %tmp
br i1 %exitcond, label %return, label %bb
; Should only be one load in the loop.
; CHECK: bb:
; CHECK: load double*
; CHECK-NOT: load double*
; CHECK: br i1 %exitcond
return:
ret void
}
;void test6(int N, double *G) {
; int j;
; for (j = 0; j < N - 1; j++)
; G[j+1] = G[j] + G[j+1];
;}
define void @test6(i32 %N, double* nocapture %G) nounwind ssp {
; CHECK: @test6
entry:
%0 = add i32 %N, -1
%1 = icmp sgt i32 %0, 0
br i1 %1, label %bb.nph, label %return
bb.nph:
%tmp = zext i32 %0 to i64
br label %bb
; CHECK: bb.nph:
; CHECK: load double*
; CHECK: br label %bb
bb:
%indvar = phi i64 [ 0, %bb.nph ], [ %tmp6, %bb ]
%tmp6 = add i64 %indvar, 1
%scevgep = getelementptr double* %G, i64 %tmp6
%scevgep7 = getelementptr double* %G, i64 %indvar
%2 = load double* %scevgep7, align 8
%3 = load double* %scevgep, align 8
%4 = fadd double %2, %3
store double %4, double* %scevgep, align 8
%exitcond = icmp eq i64 %tmp6, %tmp
br i1 %exitcond, label %return, label %bb
; Should only be one load in the loop.
; CHECK: bb:
; CHECK: load double*
; CHECK-NOT: load double*
; CHECK: br i1 %exitcond
return:
ret void
}
;void test7(int N, double* G) {
; long j;
; G[1] = 1;
; for (j = 1; j < N - 1; j++)
; G[j+1] = G[j] + G[j+1];
;}
; This requires phi translation of the adds.
define void @test7(i32 %N, double* nocapture %G) nounwind ssp {
entry:
%0 = getelementptr inbounds double* %G, i64 1
store double 1.000000e+00, double* %0, align 8
%1 = add i32 %N, -1
%2 = icmp sgt i32 %1, 1
br i1 %2, label %bb.nph, label %return
bb.nph:
%tmp = sext i32 %1 to i64
%tmp7 = add i64 %tmp, -1
br label %bb
bb:
%indvar = phi i64 [ 0, %bb.nph ], [ %tmp9, %bb ]
%tmp8 = add i64 %indvar, 2
%scevgep = getelementptr double* %G, i64 %tmp8
%tmp9 = add i64 %indvar, 1
%scevgep10 = getelementptr double* %G, i64 %tmp9
%3 = load double* %scevgep10, align 8
%4 = load double* %scevgep, align 8
%5 = fadd double %3, %4
store double %5, double* %scevgep, align 8
%exitcond = icmp eq i64 %tmp9, %tmp7
br i1 %exitcond, label %return, label %bb
; Should only be one load in the loop.
; CHECK: bb:
; CHECK: load double*
; CHECK-NOT: load double*
; CHECK: br i1 %exitcond
return:
ret void
}
;;; --- todo
;; Here the loaded address isn't available in 'block2' at all.
define i32 @testX(i32* %p, i32* %q, i32** %Hack, i1 %C) {
; CHECK: @testX
block1:
br i1 %C, label %block2, label %block3
block2:
br label %block4
; HECK: block2:
; HECK: load i32*
; HECK: br label %block4
block3:
%A = getelementptr i32* %p, i32 1
store i32 0, i32* %A
br label %block4
block4:
%P2 = phi i32* [%p, %block3], [%q, %block2]
%P3 = getelementptr i32* %P2, i32 1
%PRE = load i32* %P3
ret i32 %PRE
; HECK: block4:
; HECK-NEXT: phi i32 [
; HECK-NOT: load
; HECK: ret i32
}
|
