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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --include-generated-funcs
; RUN: opt -S -passes=verify,iroutliner -ir-outlining-no-cost < %s | FileCheck %s
; Here we have multiple exits, but the different sources, different outputs are
; needed, this checks that they are handled by separate switch statements.
define void @outline_outputs1() #0 {
entry:
%output = alloca i32, align 4
%result = alloca i32, align 4
%output2 = alloca i32, align 4
%result2 = alloca i32, align 4
%a = alloca i32, align 4
%b = alloca i32, align 4
br label %block_2
block_1:
%a2 = alloca i32, align 4
%b2 = alloca i32, align 4
br label %block_2
block_2:
%a2val = load i32, ptr %a
%b2val = load i32, ptr %b
%add2 = add i32 2, %a2val
%mul2 = mul i32 2, %b2val
br label %block_5
block_3:
%aval = load i32, ptr %a
%bval = load i32, ptr %b
%add = add i32 2, %aval
%mul = mul i32 2, %bval
br label %block_4
block_4:
store i32 %add, ptr %output, align 4
store i32 %mul, ptr %result, align 4
br label %block_6
block_5:
store i32 %add2, ptr %output, align 4
store i32 %mul2, ptr %result, align 4
br label %block_7
block_6:
%div = udiv i32 %aval, %bval
ret void
block_7:
%sub = sub i32 %a2val, %b2val
ret void
}
define void @outline_outputs2() #0 {
entry:
%output = alloca i32, align 4
%result = alloca i32, align 4
%output2 = alloca i32, align 4
%result2 = alloca i32, align 4
%a = alloca i32, align 4
%b = alloca i32, align 4
br label %block_2
block_1:
%a2 = alloca i32, align 4
%b2 = alloca i32, align 4
br label %block_2
block_2:
%a2val = load i32, ptr %a
%b2val = load i32, ptr %b
%add2 = add i32 2, %a2val
%mul2 = mul i32 2, %b2val
br label %block_5
block_3:
%aval = load i32, ptr %a
%bval = load i32, ptr %b
%add = add i32 2, %aval
%mul = mul i32 2, %bval
br label %block_4
block_4:
store i32 %add, ptr %output, align 4
store i32 %mul, ptr %result, align 4
br label %block_7
block_5:
store i32 %add2, ptr %output, align 4
store i32 %mul2, ptr %result, align 4
br label %block_6
block_6:
%diff = sub i32 %a2val, %b2val
ret void
block_7:
%quot = udiv i32 %add, %mul
ret void
}
; CHECK-LABEL: @outline_outputs1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[BVAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[AVAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2VAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A2VAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2:%.*]]
; CHECK: block_1:
; CHECK-NEXT: [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2]]
; CHECK: block_2:
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[A2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[B2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[AVAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[BVAL_LOC]])
; CHECK-NEXT: [[TMP0:%.*]] = call i1 @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[RESULT]], ptr [[A2VAL_LOC]], ptr [[B2VAL_LOC]], ptr [[AVAL_LOC]], ptr [[BVAL_LOC]], i32 0)
; CHECK-NEXT: [[A2VAL_RELOAD:%.*]] = load i32, ptr [[A2VAL_LOC]], align 4
; CHECK-NEXT: [[B2VAL_RELOAD:%.*]] = load i32, ptr [[B2VAL_LOC]], align 4
; CHECK-NEXT: [[AVAL_RELOAD:%.*]] = load i32, ptr [[AVAL_LOC]], align 4
; CHECK-NEXT: [[BVAL_RELOAD:%.*]] = load i32, ptr [[BVAL_LOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[A2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[B2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[AVAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[BVAL_LOC]])
; CHECK-NEXT: br i1 [[TMP0]], label [[BLOCK_6:%.*]], label [[BLOCK_7:%.*]]
; CHECK: block_6:
; CHECK-NEXT: [[DIV:%.*]] = udiv i32 [[AVAL_RELOAD]], [[BVAL_RELOAD]]
; CHECK-NEXT: ret void
; CHECK: block_7:
; CHECK-NEXT: [[SUB:%.*]] = sub i32 [[A2VAL_RELOAD]], [[B2VAL_RELOAD]]
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: @outline_outputs2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[MUL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[ADD_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2VAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A2VAL_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2:%.*]]
; CHECK: block_1:
; CHECK-NEXT: [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2]]
; CHECK: block_2:
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[A2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[B2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 -1, ptr [[MUL_LOC]])
; CHECK-NEXT: [[TMP0:%.*]] = call i1 @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[RESULT]], ptr [[A2VAL_LOC]], ptr [[B2VAL_LOC]], ptr [[ADD_LOC]], ptr [[MUL_LOC]], i32 1)
; CHECK-NEXT: [[A2VAL_RELOAD:%.*]] = load i32, ptr [[A2VAL_LOC]], align 4
; CHECK-NEXT: [[B2VAL_RELOAD:%.*]] = load i32, ptr [[B2VAL_LOC]], align 4
; CHECK-NEXT: [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
; CHECK-NEXT: [[MUL_RELOAD:%.*]] = load i32, ptr [[MUL_LOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[A2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[B2VAL_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 -1, ptr [[MUL_LOC]])
; CHECK-NEXT: br i1 [[TMP0]], label [[BLOCK_7:%.*]], label [[BLOCK_6:%.*]]
; CHECK: block_6:
; CHECK-NEXT: [[DIFF:%.*]] = sub i32 [[A2VAL_RELOAD]], [[B2VAL_RELOAD]]
; CHECK-NEXT: ret void
; CHECK: block_7:
; CHECK-NEXT: [[QUOT:%.*]] = udiv i32 [[ADD_RELOAD]], [[MUL_RELOAD]]
; CHECK-NEXT: ret void
;
;
; CHECK: define internal i1 @outlined_ir_func_0(
; CHECK-NEXT: newFuncRoot:
; CHECK-NEXT: br label [[BLOCK_2_TO_OUTLINE:%.*]]
; CHECK: block_2_to_outline:
; CHECK-NEXT: [[A2VAL:%.*]] = load i32, ptr [[TMP0:%.*]], align 4
; CHECK-NEXT: [[B2VAL:%.*]] = load i32, ptr [[TMP1:%.*]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = add i32 2, [[A2VAL]]
; CHECK-NEXT: [[MUL2:%.*]] = mul i32 2, [[B2VAL]]
; CHECK-NEXT: br label [[BLOCK_5:%.*]]
; CHECK: block_3:
; CHECK-NEXT: [[AVAL:%.*]] = load i32, ptr [[TMP0]], align 4
; CHECK-NEXT: [[BVAL:%.*]] = load i32, ptr [[TMP1]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add i32 2, [[AVAL]]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 2, [[BVAL]]
; CHECK-NEXT: br label [[BLOCK_4:%.*]]
; CHECK: block_4:
; CHECK-NEXT: store i32 [[ADD]], ptr [[TMP2:%.*]], align 4
; CHECK-NEXT: store i32 [[MUL]], ptr [[TMP3:%.*]], align 4
; CHECK-NEXT: br label [[BLOCK_6_EXITSTUB:%.*]]
; CHECK: block_5:
; CHECK-NEXT: store i32 [[ADD2]], ptr [[TMP2]], align 4
; CHECK-NEXT: store i32 [[MUL2]], ptr [[TMP3]], align 4
; CHECK-NEXT: br label [[BLOCK_7_EXITSTUB:%.*]]
; CHECK: block_6.exitStub:
; CHECK-NEXT: switch i32 [[TMP8:%.*]], label [[FINAL_BLOCK_1:%.*]] [
; CHECK-NEXT: i32 0, label [[OUTPUT_BLOCK_0_1:%.*]]
; CHECK-NEXT: i32 1, label [[OUTPUT_BLOCK_1_1:%.*]]
; CHECK-NEXT: ]
; CHECK: block_7.exitStub:
; CHECK-NEXT: switch i32 [[TMP8]], label [[FINAL_BLOCK_0:%.*]] [
; CHECK-NEXT: i32 0, label [[OUTPUT_BLOCK_0_0:%.*]]
; CHECK-NEXT: i32 1, label [[OUTPUT_BLOCK_1_0:%.*]]
; CHECK-NEXT: ]
; CHECK: output_block_0_0:
; CHECK-NEXT: store i32 [[A2VAL]], ptr [[TMP4:%.*]], align 4
; CHECK-NEXT: store i32 [[B2VAL]], ptr [[TMP5:%.*]], align 4
; CHECK-NEXT: br label [[FINAL_BLOCK_0]]
; CHECK: output_block_0_1:
; CHECK-NEXT: store i32 [[AVAL]], ptr [[TMP6:%.*]], align 4
; CHECK-NEXT: store i32 [[BVAL]], ptr [[TMP7:%.*]], align 4
; CHECK-NEXT: br label [[FINAL_BLOCK_1]]
; CHECK: output_block_1_0:
; CHECK-NEXT: store i32 [[A2VAL]], ptr [[TMP4]], align 4
; CHECK-NEXT: store i32 [[B2VAL]], ptr [[TMP5]], align 4
; CHECK-NEXT: br label [[FINAL_BLOCK_0]]
; CHECK: output_block_1_1:
; CHECK-NEXT: store i32 [[ADD]], ptr [[TMP6]], align 4
; CHECK-NEXT: store i32 [[MUL]], ptr [[TMP7]], align 4
; CHECK-NEXT: br label [[FINAL_BLOCK_1]]
; CHECK: final_block_0:
; CHECK-NEXT: ret i1 false
; CHECK: final_block_1:
; CHECK-NEXT: ret i1 true
;
|
