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
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefix=RV32I
; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefix=RV64I
; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+zbb | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbNOZbt
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbNOZbt
; RUN: llc < %s -mtriple=riscv32 -mattr=+m,+zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV32IZbb,RV32IZbbZbt
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+experimental-zbt | FileCheck %s --check-prefixes=RV64IZbb,RV64IZbbZbt
declare i4 @llvm.ssub.sat.i4(i4, i4)
declare i8 @llvm.ssub.sat.i8(i8, i8)
declare i16 @llvm.ssub.sat.i16(i16, i16)
declare i32 @llvm.ssub.sat.i32(i32, i32)
declare i64 @llvm.ssub.sat.i64(i64, i64)
define signext i32 @func(i32 signext %x, i32 signext %y) nounwind {
; RV32I-LABEL: func:
; RV32I: # %bb.0:
; RV32I-NEXT: mv a2, a0
; RV32I-NEXT: sgtz a3, a1
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: slt a1, a0, a2
; RV32I-NEXT: beq a3, a1, .LBB0_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: srai a0, a0, 31
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: .LBB0_2:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func:
; RV64I: # %bb.0:
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: addiw a2, a1, -1
; RV64I-NEXT: bge a0, a2, .LBB0_3
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: bge a1, a0, .LBB0_4
; RV64I-NEXT: .LBB0_2:
; RV64I-NEXT: ret
; RV64I-NEXT: .LBB0_3:
; RV64I-NEXT: mv a0, a2
; RV64I-NEXT: blt a1, a0, .LBB0_2
; RV64I-NEXT: .LBB0_4:
; RV64I-NEXT: lui a0, 524288
; RV64I-NEXT: ret
;
; RV32IZbbNOZbt-LABEL: func:
; RV32IZbbNOZbt: # %bb.0:
; RV32IZbbNOZbt-NEXT: mv a2, a0
; RV32IZbbNOZbt-NEXT: sgtz a3, a1
; RV32IZbbNOZbt-NEXT: sub a0, a0, a1
; RV32IZbbNOZbt-NEXT: slt a1, a0, a2
; RV32IZbbNOZbt-NEXT: beq a3, a1, .LBB0_2
; RV32IZbbNOZbt-NEXT: # %bb.1:
; RV32IZbbNOZbt-NEXT: srai a0, a0, 31
; RV32IZbbNOZbt-NEXT: lui a1, 524288
; RV32IZbbNOZbt-NEXT: xor a0, a0, a1
; RV32IZbbNOZbt-NEXT: .LBB0_2:
; RV32IZbbNOZbt-NEXT: ret
;
; RV64IZbb-LABEL: func:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: lui a1, 524288
; RV64IZbb-NEXT: addiw a2, a1, -1
; RV64IZbb-NEXT: min a0, a0, a2
; RV64IZbb-NEXT: max a0, a0, a1
; RV64IZbb-NEXT: ret
;
; RV32IZbbZbt-LABEL: func:
; RV32IZbbZbt: # %bb.0:
; RV32IZbbZbt-NEXT: sgtz a2, a1
; RV32IZbbZbt-NEXT: sub a1, a0, a1
; RV32IZbbZbt-NEXT: slt a0, a1, a0
; RV32IZbbZbt-NEXT: xor a0, a2, a0
; RV32IZbbZbt-NEXT: srai a2, a1, 31
; RV32IZbbZbt-NEXT: lui a3, 524288
; RV32IZbbZbt-NEXT: xor a2, a2, a3
; RV32IZbbZbt-NEXT: cmov a0, a0, a2, a1
; RV32IZbbZbt-NEXT: ret
%tmp = call i32 @llvm.ssub.sat.i32(i32 %x, i32 %y);
ret i32 %tmp;
}
define i64 @func2(i64 %x, i64 %y) nounwind {
; RV32I-LABEL: func2:
; RV32I: # %bb.0:
; RV32I-NEXT: mv a4, a1
; RV32I-NEXT: sltu a1, a0, a2
; RV32I-NEXT: sub a5, a4, a3
; RV32I-NEXT: sub a1, a5, a1
; RV32I-NEXT: xor a5, a4, a1
; RV32I-NEXT: xor a3, a4, a3
; RV32I-NEXT: and a3, a3, a5
; RV32I-NEXT: bltz a3, .LBB1_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: sub a0, a0, a2
; RV32I-NEXT: ret
; RV32I-NEXT: .LBB1_2:
; RV32I-NEXT: srai a0, a1, 31
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a1, a0, a1
; RV32I-NEXT: ret
;
; RV64I-LABEL: func2:
; RV64I: # %bb.0:
; RV64I-NEXT: mv a2, a0
; RV64I-NEXT: sgtz a3, a1
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: slt a1, a0, a2
; RV64I-NEXT: beq a3, a1, .LBB1_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: srai a0, a0, 63
; RV64I-NEXT: li a1, -1
; RV64I-NEXT: slli a1, a1, 63
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: .LBB1_2:
; RV64I-NEXT: ret
;
; RV32IZbbNOZbt-LABEL: func2:
; RV32IZbbNOZbt: # %bb.0:
; RV32IZbbNOZbt-NEXT: mv a4, a1
; RV32IZbbNOZbt-NEXT: sltu a1, a0, a2
; RV32IZbbNOZbt-NEXT: sub a5, a4, a3
; RV32IZbbNOZbt-NEXT: sub a1, a5, a1
; RV32IZbbNOZbt-NEXT: xor a5, a4, a1
; RV32IZbbNOZbt-NEXT: xor a3, a4, a3
; RV32IZbbNOZbt-NEXT: and a3, a3, a5
; RV32IZbbNOZbt-NEXT: bltz a3, .LBB1_2
; RV32IZbbNOZbt-NEXT: # %bb.1:
; RV32IZbbNOZbt-NEXT: sub a0, a0, a2
; RV32IZbbNOZbt-NEXT: ret
; RV32IZbbNOZbt-NEXT: .LBB1_2:
; RV32IZbbNOZbt-NEXT: srai a0, a1, 31
; RV32IZbbNOZbt-NEXT: lui a1, 524288
; RV32IZbbNOZbt-NEXT: xor a1, a0, a1
; RV32IZbbNOZbt-NEXT: ret
;
; RV64IZbbNOZbt-LABEL: func2:
; RV64IZbbNOZbt: # %bb.0:
; RV64IZbbNOZbt-NEXT: mv a2, a0
; RV64IZbbNOZbt-NEXT: sgtz a3, a1
; RV64IZbbNOZbt-NEXT: sub a0, a0, a1
; RV64IZbbNOZbt-NEXT: slt a1, a0, a2
; RV64IZbbNOZbt-NEXT: beq a3, a1, .LBB1_2
; RV64IZbbNOZbt-NEXT: # %bb.1:
; RV64IZbbNOZbt-NEXT: srai a0, a0, 63
; RV64IZbbNOZbt-NEXT: li a1, -1
; RV64IZbbNOZbt-NEXT: slli a1, a1, 63
; RV64IZbbNOZbt-NEXT: xor a0, a0, a1
; RV64IZbbNOZbt-NEXT: .LBB1_2:
; RV64IZbbNOZbt-NEXT: ret
;
; RV32IZbbZbt-LABEL: func2:
; RV32IZbbZbt: # %bb.0:
; RV32IZbbZbt-NEXT: sltu a4, a0, a2
; RV32IZbbZbt-NEXT: sub a5, a1, a3
; RV32IZbbZbt-NEXT: sub a4, a5, a4
; RV32IZbbZbt-NEXT: srai a5, a4, 31
; RV32IZbbZbt-NEXT: lui a6, 524288
; RV32IZbbZbt-NEXT: xor a6, a5, a6
; RV32IZbbZbt-NEXT: xor a7, a1, a4
; RV32IZbbZbt-NEXT: xor a1, a1, a3
; RV32IZbbZbt-NEXT: and a1, a1, a7
; RV32IZbbZbt-NEXT: slti a3, a1, 0
; RV32IZbbZbt-NEXT: cmov a1, a3, a6, a4
; RV32IZbbZbt-NEXT: sub a0, a0, a2
; RV32IZbbZbt-NEXT: cmov a0, a3, a5, a0
; RV32IZbbZbt-NEXT: ret
;
; RV64IZbbZbt-LABEL: func2:
; RV64IZbbZbt: # %bb.0:
; RV64IZbbZbt-NEXT: sgtz a2, a1
; RV64IZbbZbt-NEXT: sub a1, a0, a1
; RV64IZbbZbt-NEXT: slt a0, a1, a0
; RV64IZbbZbt-NEXT: xor a0, a2, a0
; RV64IZbbZbt-NEXT: srai a2, a1, 63
; RV64IZbbZbt-NEXT: li a3, -1
; RV64IZbbZbt-NEXT: slli a3, a3, 63
; RV64IZbbZbt-NEXT: xor a2, a2, a3
; RV64IZbbZbt-NEXT: cmov a0, a0, a2, a1
; RV64IZbbZbt-NEXT: ret
%tmp = call i64 @llvm.ssub.sat.i64(i64 %x, i64 %y);
ret i64 %tmp;
}
define signext i16 @func16(i16 signext %x, i16 signext %y) nounwind {
; RV32I-LABEL: func16:
; RV32I: # %bb.0:
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: lui a1, 8
; RV32I-NEXT: addi a1, a1, -1
; RV32I-NEXT: bge a0, a1, .LBB2_3
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: lui a1, 1048568
; RV32I-NEXT: bge a1, a0, .LBB2_4
; RV32I-NEXT: .LBB2_2:
; RV32I-NEXT: ret
; RV32I-NEXT: .LBB2_3:
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: lui a1, 1048568
; RV32I-NEXT: blt a1, a0, .LBB2_2
; RV32I-NEXT: .LBB2_4:
; RV32I-NEXT: lui a0, 1048568
; RV32I-NEXT: ret
;
; RV64I-LABEL: func16:
; RV64I: # %bb.0:
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: lui a1, 8
; RV64I-NEXT: addiw a1, a1, -1
; RV64I-NEXT: bge a0, a1, .LBB2_3
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: lui a1, 1048568
; RV64I-NEXT: bge a1, a0, .LBB2_4
; RV64I-NEXT: .LBB2_2:
; RV64I-NEXT: ret
; RV64I-NEXT: .LBB2_3:
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: lui a1, 1048568
; RV64I-NEXT: blt a1, a0, .LBB2_2
; RV64I-NEXT: .LBB2_4:
; RV64I-NEXT: lui a0, 1048568
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func16:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: lui a1, 8
; RV32IZbb-NEXT: addi a1, a1, -1
; RV32IZbb-NEXT: min a0, a0, a1
; RV32IZbb-NEXT: lui a1, 1048568
; RV32IZbb-NEXT: max a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func16:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: lui a1, 8
; RV64IZbb-NEXT: addiw a1, a1, -1
; RV64IZbb-NEXT: min a0, a0, a1
; RV64IZbb-NEXT: lui a1, 1048568
; RV64IZbb-NEXT: max a0, a0, a1
; RV64IZbb-NEXT: ret
%tmp = call i16 @llvm.ssub.sat.i16(i16 %x, i16 %y);
ret i16 %tmp;
}
define signext i8 @func8(i8 signext %x, i8 signext %y) nounwind {
; RV32I-LABEL: func8:
; RV32I: # %bb.0:
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: li a1, 127
; RV32I-NEXT: bge a0, a1, .LBB3_3
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: li a1, -128
; RV32I-NEXT: bge a1, a0, .LBB3_4
; RV32I-NEXT: .LBB3_2:
; RV32I-NEXT: ret
; RV32I-NEXT: .LBB3_3:
; RV32I-NEXT: li a0, 127
; RV32I-NEXT: li a1, -128
; RV32I-NEXT: blt a1, a0, .LBB3_2
; RV32I-NEXT: .LBB3_4:
; RV32I-NEXT: li a0, -128
; RV32I-NEXT: ret
;
; RV64I-LABEL: func8:
; RV64I: # %bb.0:
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: li a1, 127
; RV64I-NEXT: bge a0, a1, .LBB3_3
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: li a1, -128
; RV64I-NEXT: bge a1, a0, .LBB3_4
; RV64I-NEXT: .LBB3_2:
; RV64I-NEXT: ret
; RV64I-NEXT: .LBB3_3:
; RV64I-NEXT: li a0, 127
; RV64I-NEXT: li a1, -128
; RV64I-NEXT: blt a1, a0, .LBB3_2
; RV64I-NEXT: .LBB3_4:
; RV64I-NEXT: li a0, -128
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func8:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: li a1, 127
; RV32IZbb-NEXT: min a0, a0, a1
; RV32IZbb-NEXT: li a1, -128
; RV32IZbb-NEXT: max a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func8:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: li a1, 127
; RV64IZbb-NEXT: min a0, a0, a1
; RV64IZbb-NEXT: li a1, -128
; RV64IZbb-NEXT: max a0, a0, a1
; RV64IZbb-NEXT: ret
%tmp = call i8 @llvm.ssub.sat.i8(i8 %x, i8 %y);
ret i8 %tmp;
}
define signext i4 @func3(i4 signext %x, i4 signext %y) nounwind {
; RV32I-LABEL: func3:
; RV32I: # %bb.0:
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: li a1, 7
; RV32I-NEXT: bge a0, a1, .LBB4_3
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: li a1, -8
; RV32I-NEXT: bge a1, a0, .LBB4_4
; RV32I-NEXT: .LBB4_2:
; RV32I-NEXT: ret
; RV32I-NEXT: .LBB4_3:
; RV32I-NEXT: li a0, 7
; RV32I-NEXT: li a1, -8
; RV32I-NEXT: blt a1, a0, .LBB4_2
; RV32I-NEXT: .LBB4_4:
; RV32I-NEXT: li a0, -8
; RV32I-NEXT: ret
;
; RV64I-LABEL: func3:
; RV64I: # %bb.0:
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: li a1, 7
; RV64I-NEXT: bge a0, a1, .LBB4_3
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: li a1, -8
; RV64I-NEXT: bge a1, a0, .LBB4_4
; RV64I-NEXT: .LBB4_2:
; RV64I-NEXT: ret
; RV64I-NEXT: .LBB4_3:
; RV64I-NEXT: li a0, 7
; RV64I-NEXT: li a1, -8
; RV64I-NEXT: blt a1, a0, .LBB4_2
; RV64I-NEXT: .LBB4_4:
; RV64I-NEXT: li a0, -8
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func3:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: li a1, 7
; RV32IZbb-NEXT: min a0, a0, a1
; RV32IZbb-NEXT: li a1, -8
; RV32IZbb-NEXT: max a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func3:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: li a1, 7
; RV64IZbb-NEXT: min a0, a0, a1
; RV64IZbb-NEXT: li a1, -8
; RV64IZbb-NEXT: max a0, a0, a1
; RV64IZbb-NEXT: ret
%tmp = call i4 @llvm.ssub.sat.i4(i4 %x, i4 %y);
ret i4 %tmp;
}
|
