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
| ; RUN: opt -loop-vectorize -enable-arm-maskedldst < %s -S -o - | FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1-m.main-none-eabi"
; CHECK-LABEL: test_i32_align4
; CHECK: call void @llvm.masked.store.v4i32.p0v4i32
define void @test_i32_align4(i32* nocapture %A, i32 %n) #0 {
entry:
%cmp12 = icmp sgt i32 %n, 0
br i1 %cmp12, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.inc
%i.013 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.013
%0 = load i32, i32* %arrayidx, align 4
%.off = add i32 %0, 9
%1 = icmp ult i32 %.off, 19
br i1 %1, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i32 0, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i.013, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
for.cond.cleanup.loopexit: ; preds = %for.inc
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
; CHECK-LABEL: test_i32_align2
; CHECK-NOT: call void @llvm.masked.store
define void @test_i32_align2(i32* nocapture %A, i32 %n) #0 {
entry:
%cmp12 = icmp sgt i32 %n, 0
br i1 %cmp12, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.inc
%i.013 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.013
%0 = load i32, i32* %arrayidx, align 2
%.off = add i32 %0, 9
%1 = icmp ult i32 %.off, 19
br i1 %1, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i32 0, i32* %arrayidx, align 2
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i.013, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
for.cond.cleanup.loopexit: ; preds = %for.inc
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
; CHECK-LABEL: test_i32_noalign
; CHECK: call void @llvm.masked.store.v4i32.p0v4i32
define void @test_i32_noalign(i32* nocapture %A, i32 %n) #0 {
entry:
%cmp12 = icmp sgt i32 %n, 0
br i1 %cmp12, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.inc
%i.013 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.013
%0 = load i32, i32* %arrayidx
%.off = add i32 %0, 9
%1 = icmp ult i32 %.off, 19
br i1 %1, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i32 0, i32* %arrayidx
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i.013, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
for.cond.cleanup.loopexit: ; preds = %for.inc
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
; CHECK-LABEL: test_i16_align2
; CHECK: call void @llvm.masked.store.v8i16.p0v8i16
define void @test_i16_align2(i16* nocapture %A, i32 %n) #0 {
entry:
%cmp12 = icmp sgt i32 %n, 0
br i1 %cmp12, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.inc
%i.013 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %A, i32 %i.013
%0 = load i16, i16* %arrayidx, align 2
%.off = add i16 %0, 9
%1 = icmp ult i16 %.off, 19
br i1 %1, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i16 0, i16* %arrayidx, align 2
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i.013, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
for.cond.cleanup.loopexit: ; preds = %for.inc
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
; CHECK-LABEL: test_i16_align1
; CHECK-NOT: call void @llvm.masked.store
define void @test_i16_align1(i16* nocapture %A, i32 %n) #0 {
entry:
%cmp12 = icmp sgt i32 %n, 0
br i1 %cmp12, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.inc
%i.013 = phi i32 [ %inc, %for.inc ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i16, i16* %A, i32 %i.013
%0 = load i16, i16* %arrayidx, align 1
%.off = add i16 %0, 9
%1 = icmp ult i16 %.off, 19
br i1 %1, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i16 0, i16* %arrayidx, align 1
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%inc = add nuw nsw i32 %i.013, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
for.cond.cleanup.loopexit: ; preds = %for.inc
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
}
attributes #0 = { "target-features"="+mve" }
|