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
|
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute -verify-loop-info -verify-dom-info -S \
; RUN: < %s | FileCheck %s
; RUN: opt -basicaa -loop-distribute -enable-loop-distribute -loop-vectorize -force-vector-width=4 \
; RUN: -verify-loop-info -verify-dom-info -S < %s | \
; RUN: FileCheck --check-prefix=VECTORIZE %s
; The memcheck version of basic.ll. We should distribute and vectorize the
; second part of this loop with 5 memchecks (A+1 x {C, D, E} + C x {A, B})
;
; for (i = 0; i < n; i++) {
; A[i + 1] = A[i] * B[i];
; -------------------------------
; C[i] = D[i] * E[i];
; }
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
@B = common global i32* null, align 8
@A = common global i32* null, align 8
@C = common global i32* null, align 8
@D = common global i32* null, align 8
@E = common global i32* null, align 8
; CHECK-LABEL: @f(
define void @f() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
; We have two compares for each array overlap check.
; Since the checks to A and A + 4 get merged, this will give us a
; total of 8 compares.
;
; CHECK: for.body.lver.check:
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK: = icmp
; CHECK-NOT: = icmp
; CHECK: br i1 %memcheck.conflict, label %for.body.ph.lver.orig, label %for.body.ph.ldist1
; The non-distributed loop that the memchecks fall back on.
; CHECK: for.body.ph.lver.orig:
; CHECK: br label %for.body.lver.orig
; CHECK: for.body.lver.orig:
; CHECK: br i1 %exitcond.lver.orig, label %for.end, label %for.body.lver.orig
; Verify the two distributed loops.
; CHECK: for.body.ph.ldist1:
; CHECK: br label %for.body.ldist1
; CHECK: for.body.ldist1:
; CHECK: %mulA.ldist1 = mul i32 %loadB.ldist1, %loadA.ldist1
; CHECK: br i1 %exitcond.ldist1, label %for.body.ph, label %for.body.ldist1
; CHECK: for.body.ph:
; CHECK: br label %for.body
; CHECK: for.body:
; CHECK: %mulC = mul i32 %loadD, %loadE
; CHECK: for.end:
; VECTORIZE: mul <4 x i32>
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 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 %ind
%loadD = load i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Make sure there's no "Multiple reports generated" assert with a
; volatile load, and no distribution
; TODO: Distribution of volatile may be possible under some
; circumstance, but the current implementation does not touch them.
; CHECK-LABEL: @f_volatile_load(
; CHECK: br label %for.body{{$}}
; CHECK-NOT: load
; CHECK: {{^}}for.body:
; CHECK: load i32
; CHECK: load i32
; CHECK: load volatile i32
; CHECK: load i32
; CHECK: br i1 %exitcond, label %for.end, label %for.body{{$}}
; CHECK-NOT: load
; VECTORIZE-NOT: load <4 x i32>
; VECTORIZE-NOT: mul <4 x i32>
define void @f_volatile_load() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
%c = load i32*, i32** @C, align 8
%d = load i32*, i32** @D, align 8
%e = load i32*, i32** @E, align 8
br label %for.body
for.body:
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulA = mul i32 %loadB, %loadA
%add = add nuw nsw i64 %ind, 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 %ind
%loadD = load volatile i32, i32* %arrayidxD, align 4
%arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
%loadE = load i32, i32* %arrayidxE, align 4
%mulC = mul i32 %loadD, %loadE
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
|
