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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-unroll -mtriple=thumbv7a-unknown-linux-gnueabihf -S %s | FileCheck %s
; Check we unroll even with optsize, if the result is smaller, either because
; we have single iteration loops or bodies with constant folding opportunities
; after fully unrolling.
; TODO: Looks like we should enable some unrolling for M-class, even when
; optimising for size.
declare i32 @get()
define void @fully_unrolled_single_iteration(i32* %src) #0 {
; CHECK-LABEL: @fully_unrolled_single_iteration(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARR:%.*]] = alloca [4 x i32], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[V:%.*]] = load i32, i32* [[SRC:%.*]]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
; CHECK-NEXT: store i32 [[V]], i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
; CHECK-NEXT: call void @use(i32* nonnull [[PTR]])
; CHECK-NEXT: ret void
;
entry:
%arr = alloca [4 x i32], align 4
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%src.idx = getelementptr inbounds i32, i32* %src, i64 %indvars.iv
%v = load i32, i32* %src.idx
%arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
store i32 %v, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%ptr = bitcast [4 x i32]* %arr to i32*
call void @use(i32* nonnull %ptr) #4
ret void
}
define void @fully_unrolled_smaller() #0 {
; CHECK-LABEL: @fully_unrolled_smaller(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARR:%.*]] = alloca [4 x i32], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
; CHECK-NEXT: store i32 16, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 1
; CHECK-NEXT: store i32 4104, i32* [[ARRAYIDX_1]], align 4
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 2
; CHECK-NEXT: store i32 1048592, i32* [[ARRAYIDX_2]], align 4
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 3
; CHECK-NEXT: store i32 268435480, i32* [[ARRAYIDX_3]], align 4
; CHECK-NEXT: [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
; CHECK-NEXT: call void @use(i32* nonnull [[PTR]])
; CHECK-NEXT: ret void
;
entry:
%arr = alloca [4 x i32], align 4
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%indvars.iv.tr = trunc i64 %indvars.iv to i32
%shl.0 = shl i32 %indvars.iv.tr, 3
%shl.1 = shl i32 16, %shl.0
%or = or i32 %shl.1, %shl.0
%arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
store i32 %or, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv, 3
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%ptr = bitcast [4 x i32]* %arr to i32*
call void @use(i32* nonnull %ptr) #4
ret void
}
define void @fully_unrolled_smaller_Oz() #1 {
; CHECK-LABEL: @fully_unrolled_smaller_Oz(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARR:%.*]] = alloca [4 x i32], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
; CHECK-NEXT: store i32 16, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 1
; CHECK-NEXT: store i32 4104, i32* [[ARRAYIDX_1]], align 4
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 2
; CHECK-NEXT: store i32 1048592, i32* [[ARRAYIDX_2]], align 4
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 3
; CHECK-NEXT: store i32 268435480, i32* [[ARRAYIDX_3]], align 4
; CHECK-NEXT: [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
; CHECK-NEXT: call void @use(i32* nonnull [[PTR]])
; CHECK-NEXT: ret void
;
entry:
%arr = alloca [4 x i32], align 4
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%indvars.iv.tr = trunc i64 %indvars.iv to i32
%shl.0 = shl i32 %indvars.iv.tr, 3
%shl.1 = shl i32 16, %shl.0
%or = or i32 %shl.1, %shl.0
%arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
store i32 %or, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv, 3
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%ptr = bitcast [4 x i32]* %arr to i32*
call void @use(i32* nonnull %ptr) #4
ret void
}
define void @fully_unrolled_bigger() #0 {
; CHECK-LABEL: @fully_unrolled_bigger(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARR:%.*]] = alloca [4 x i32], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[INDVARS_IV_TR:%.*]] = trunc i64 [[INDVARS_IV]] to i32
; CHECK-NEXT: [[SHL_0:%.*]] = shl i32 [[INDVARS_IV_TR]], 3
; CHECK-NEXT: [[SHL_1:%.*]] = shl i32 16, [[SHL_0]]
; CHECK-NEXT: [[OR:%.*]] = or i32 [[SHL_1]], [[SHL_0]]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: store i32 [[OR]], i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV]], 7
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
; CHECK-NEXT: call void @use(i32* nonnull [[PTR]])
; CHECK-NEXT: ret void
;
entry:
%arr = alloca [4 x i32], align 4
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%indvars.iv.tr = trunc i64 %indvars.iv to i32
%shl.0 = shl i32 %indvars.iv.tr, 3
%shl.1 = shl i32 16, %shl.0
%or = or i32 %shl.1, %shl.0
%arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
store i32 %or, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv, 7
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%ptr = bitcast [4 x i32]* %arr to i32*
call void @use(i32* nonnull %ptr) #4
ret void
}
declare void @use(i32*)
attributes #0 = { optsize }
attributes #1 = { minsize optsize }
|
