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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=avr -mcpu=avrtiny | FileCheck %s
; NOTE: Both %a(i8) and %b(i8) cost two registers.
define i8 @foo0(i8 %a, i8 %b) {
; CHECK-LABEL: foo0:
; CHECK: ; %bb.0:
; CHECK-NEXT: sub r24, r22
; CHECK-NEXT: ret
%c = sub i8 %a, %b
ret i8 %c
}
; NOTE: Both %a(i16) and %b(i16) cost two registers.
define i16 @foo1(i16 %a, i16 %b) {
; CHECK-LABEL: foo1:
; CHECK: ; %bb.0:
; CHECK-NEXT: sub r24, r22
; CHECK-NEXT: sbc r25, r23
; CHECK-NEXT: ret
%c = sub i16 %a, %b
ret i16 %c
}
; NOTE: %a(i16), %b(i16) and %c(i16) each costs two registers.
define i16 @foo2(i16 %a, i16 %b, i16 %c) {
; CHECK-LABEL: foo2:
; CHECK: ; %bb.0:
; CHECK-NEXT: sub r22, r24
; CHECK-NEXT: sbc r23, r25
; CHECK-NEXT: add r22, r20
; CHECK-NEXT: adc r23, r21
; CHECK-NEXT: mov r24, r22
; CHECK-NEXT: mov r25, r23
; CHECK-NEXT: ret
%d = sub i16 %a, %b
%e = sub i16 %c, %d
ret i16 %e
}
; NOTE: %a(i16), %b(i16) and %c(i16) each costs two registers,
; while %d(i16) is passed via the stack.
define i16 @foo3(i16 %a, i16 %b, i16 %c, i16 %d) {
; CHECK-LABEL: foo3:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: in r16, 63
; CHECK-NEXT: subi r28, 251
; CHECK-NEXT: sbci r29, 255
; CHECK-NEXT: ld r30, Y+
; CHECK-NEXT: ld r31, Y+
; CHECK-NEXT: subi r28, 2
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: subi r28, 5
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: out 63, r16
; CHECK-NEXT: sub r20, r30
; CHECK-NEXT: sbc r21, r31
; CHECK-NEXT: sub r24, r22
; CHECK-NEXT: sbc r25, r23
; CHECK-NEXT: add r24, r20
; CHECK-NEXT: adc r25, r21
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%e = sub i16 %a, %b
%g = sub i16 %c, %d
%h = add i16 %e, %g
ret i16 %h
}
; NOTE: %a(i32) costs four registers, while %b(i32) is passed via the stack.
define i32 @foo4(i32 %a, i32 %b) {
; CHECK-LABEL: foo4:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: in r16, 63
; CHECK-NEXT: subi r28, 251
; CHECK-NEXT: sbci r29, 255
; CHECK-NEXT: ld r20, Y+
; CHECK-NEXT: ld r21, Y+
; CHECK-NEXT: subi r28, 2
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: subi r28, 5
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: out 63, r16
; CHECK-NEXT: in r16, 63
; CHECK-NEXT: subi r28, 249
; CHECK-NEXT: sbci r29, 255
; CHECK-NEXT: ld r30, Y+
; CHECK-NEXT: ld r31, Y+
; CHECK-NEXT: subi r28, 2
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: subi r28, 7
; CHECK-NEXT: sbci r29, 0
; CHECK-NEXT: out 63, r16
; CHECK-NEXT: sub r20, r22
; CHECK-NEXT: sbc r21, r23
; CHECK-NEXT: sbc r30, r24
; CHECK-NEXT: sbc r31, r25
; CHECK-NEXT: mov r22, r20
; CHECK-NEXT: mov r23, r21
; CHECK-NEXT: mov r24, r30
; CHECK-NEXT: mov r25, r31
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%c = sub i32 %b, %a
ret i32 %c
}
; NOTE: %0 costs six registers, while %1 is passed via the stack.
define i8 @foo5([5 x i8] %0, i8 %1) {
; CHECK-LABEL: foo5:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 251
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r24, X
; CHECK-NEXT: add r24, r20
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%3 = extractvalue [5 x i8] %0, 0
%4 = add i8 %3, %1
ret i8 %4
}
; NOTE: %0 costs two registers and %1 costs four registers.
define i8 @foo6([2 x i8] %0, [4 x i8] %1) {
; CHECK-LABEL: foo6:
; CHECK: ; %bb.0:
; CHECK-NEXT: add r24, r20
; CHECK-NEXT: ret
%3 = extractvalue [2 x i8] %0, 0
%4 = extractvalue [4 x i8] %1, 0
%5 = add i8 %3, %4
ret i8 %5
}
; NOTE: %0 cost four registers, while %1 is passed via the stack,
; though there are two vacant registers.
define i8 @foo7([3 x i8] %0, [3 x i8] %1) {
; CHECK-LABEL: foo7:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 251
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r24, X
; CHECK-NEXT: add r24, r22
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%3 = extractvalue [3 x i8] %0, 0
%4 = extractvalue [3 x i8] %1, 0
%5 = add i8 %3, %4
ret i8 %5
}
; NOTE: %0 costs four registers, and %1 costs two registers, while %2 is
; passed via the stack, though there is one vacant register.
define i8 @foo8([3 x i8] %0, i8 %1, i8 %2) {
; CHECK-LABEL: foo8:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: add r22, r20
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 251
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r24, X
; CHECK-NEXT: sub r24, r22
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%4 = extractvalue [3 x i8] %0, 0
%5 = add i8 %4, %1
%6 = sub i8 %2, %5
ret i8 %6
}
; NOTE: %0 is passed via registers, though there are 6 vacant registers.
define i8 @foo9([7 x i8] %0) {
; CHECK-LABEL: foo9:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 250
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r25, X
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 251
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r24, X
; CHECK-NEXT: add r24, r25
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%2 = extractvalue [7 x i8] %0, 0
%3 = extractvalue [7 x i8] %0, 1
%4 = add i8 %2, %3
ret i8 %4
}
; NOTE: %0 costs six registers, while %1 and %2 are passed via the stack.
define i8 @fooa([6 x i8] %0, i8 %1, i8 %2) {
; CHECK-LABEL: fooa:
; CHECK: ; %bb.0:
; CHECK-NEXT: push r28
; CHECK-NEXT: push r29
; CHECK-NEXT: in r28, 61
; CHECK-NEXT: in r29, 62
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 251
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r25, X
; CHECK-NEXT: mov r26, r28
; CHECK-NEXT: mov r27, r29
; CHECK-NEXT: subi r26, 250
; CHECK-NEXT: sbci r27, 255
; CHECK-NEXT: ld r24, X
; CHECK-NEXT: sub r24, r25
; CHECK-NEXT: sub r24, r20
; CHECK-NEXT: pop r29
; CHECK-NEXT: pop r28
; CHECK-NEXT: ret
%4 = extractvalue [6 x i8] %0, 0
%5 = sub i8 %2, %1
%6 = sub i8 %5, %4
ret i8 %6
}
|
