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
|
; 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-prefix=RV32IZbb
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb | FileCheck %s --check-prefix=RV64IZbb
declare i4 @llvm.usub.sat.i4(i4, i4)
declare i8 @llvm.usub.sat.i8(i8, i8)
declare i16 @llvm.usub.sat.i16(i16, i16)
declare i32 @llvm.usub.sat.i32(i32, i32)
declare i64 @llvm.usub.sat.i64(i64, i64)
define i32 @func32(i32 %x, i32 %y, i32 %z) nounwind {
; RV32I-LABEL: func32:
; RV32I: # %bb.0:
; RV32I-NEXT: mv a3, a0
; RV32I-NEXT: mul a0, a1, a2
; RV32I-NEXT: sub a1, a3, a0
; RV32I-NEXT: li a0, 0
; RV32I-NEXT: bltu a3, a1, .LBB0_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: .LBB0_2:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func32:
; RV64I: # %bb.0:
; RV64I-NEXT: mulw a1, a1, a2
; RV64I-NEXT: subw a1, a0, a1
; RV64I-NEXT: sext.w a2, a0
; RV64I-NEXT: li a0, 0
; RV64I-NEXT: bltu a2, a1, .LBB0_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: .LBB0_2:
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func32:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: mul a1, a1, a2
; RV32IZbb-NEXT: maxu a0, a0, a1
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func32:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: mulw a1, a1, a2
; RV64IZbb-NEXT: sext.w a0, a0
; RV64IZbb-NEXT: maxu a0, a0, a1
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: ret
%a = mul i32 %y, %z
%tmp = call i32 @llvm.usub.sat.i32(i32 %x, i32 %a)
ret i32 %tmp
}
define i64 @func64(i64 %x, i64 %y, i64 %z) nounwind {
; RV32I-LABEL: func64:
; RV32I: # %bb.0:
; RV32I-NEXT: sltu a2, a0, a4
; RV32I-NEXT: sub a3, a1, a5
; RV32I-NEXT: sub a2, a3, a2
; RV32I-NEXT: sub a3, a0, a4
; RV32I-NEXT: beq a2, a1, .LBB1_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: sltu a4, a1, a2
; RV32I-NEXT: j .LBB1_3
; RV32I-NEXT: .LBB1_2:
; RV32I-NEXT: sltu a4, a0, a3
; RV32I-NEXT: .LBB1_3:
; RV32I-NEXT: li a0, 0
; RV32I-NEXT: li a1, 0
; RV32I-NEXT: bnez a4, .LBB1_5
; RV32I-NEXT: # %bb.4:
; RV32I-NEXT: mv a0, a3
; RV32I-NEXT: mv a1, a2
; RV32I-NEXT: .LBB1_5:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func64:
; RV64I: # %bb.0:
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: sub a2, a0, a2
; RV64I-NEXT: li a0, 0
; RV64I-NEXT: bltu a1, a2, .LBB1_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: mv a0, a2
; RV64I-NEXT: .LBB1_2:
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func64:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: sltu a2, a0, a4
; RV32IZbb-NEXT: sub a3, a1, a5
; RV32IZbb-NEXT: sub a2, a3, a2
; RV32IZbb-NEXT: sub a3, a0, a4
; RV32IZbb-NEXT: beq a2, a1, .LBB1_2
; RV32IZbb-NEXT: # %bb.1:
; RV32IZbb-NEXT: sltu a4, a1, a2
; RV32IZbb-NEXT: j .LBB1_3
; RV32IZbb-NEXT: .LBB1_2:
; RV32IZbb-NEXT: sltu a4, a0, a3
; RV32IZbb-NEXT: .LBB1_3:
; RV32IZbb-NEXT: li a0, 0
; RV32IZbb-NEXT: li a1, 0
; RV32IZbb-NEXT: bnez a4, .LBB1_5
; RV32IZbb-NEXT: # %bb.4:
; RV32IZbb-NEXT: mv a0, a3
; RV32IZbb-NEXT: mv a1, a2
; RV32IZbb-NEXT: .LBB1_5:
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func64:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: maxu a0, a0, a2
; RV64IZbb-NEXT: sub a0, a0, a2
; RV64IZbb-NEXT: ret
%a = mul i64 %y, %z
%tmp = call i64 @llvm.usub.sat.i64(i64 %x, i64 %z)
ret i64 %tmp
}
define i16 @func16(i16 %x, i16 %y, i16 %z) nounwind {
; RV32I-LABEL: func16:
; RV32I: # %bb.0:
; RV32I-NEXT: lui a3, 16
; RV32I-NEXT: addi a3, a3, -1
; RV32I-NEXT: and a4, a0, a3
; RV32I-NEXT: mul a0, a1, a2
; RV32I-NEXT: and a0, a0, a3
; RV32I-NEXT: sub a1, a4, a0
; RV32I-NEXT: li a0, 0
; RV32I-NEXT: bltu a4, a1, .LBB2_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: .LBB2_2:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func16:
; RV64I: # %bb.0:
; RV64I-NEXT: lui a3, 16
; RV64I-NEXT: addiw a3, a3, -1
; RV64I-NEXT: and a4, a0, a3
; RV64I-NEXT: mul a0, a1, a2
; RV64I-NEXT: and a0, a0, a3
; RV64I-NEXT: sub a1, a4, a0
; RV64I-NEXT: li a0, 0
; RV64I-NEXT: bltu a4, a1, .LBB2_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: .LBB2_2:
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func16:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: zext.h a0, a0
; RV32IZbb-NEXT: mul a1, a1, a2
; RV32IZbb-NEXT: zext.h a1, a1
; RV32IZbb-NEXT: maxu a0, a0, a1
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func16:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: zext.h a0, a0
; RV64IZbb-NEXT: mulw a1, a1, a2
; RV64IZbb-NEXT: zext.h a1, a1
; RV64IZbb-NEXT: maxu a0, a0, a1
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: ret
%a = mul i16 %y, %z
%tmp = call i16 @llvm.usub.sat.i16(i16 %x, i16 %a)
ret i16 %tmp
}
define i8 @func8(i8 %x, i8 %y, i8 %z) nounwind {
; RV32I-LABEL: func8:
; RV32I: # %bb.0:
; RV32I-NEXT: andi a3, a0, 255
; RV32I-NEXT: mul a0, a1, a2
; RV32I-NEXT: andi a0, a0, 255
; RV32I-NEXT: sub a1, a3, a0
; RV32I-NEXT: li a0, 0
; RV32I-NEXT: bltu a3, a1, .LBB3_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: .LBB3_2:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func8:
; RV64I: # %bb.0:
; RV64I-NEXT: andi a3, a0, 255
; RV64I-NEXT: mulw a0, a1, a2
; RV64I-NEXT: andi a0, a0, 255
; RV64I-NEXT: sub a1, a3, a0
; RV64I-NEXT: li a0, 0
; RV64I-NEXT: bltu a3, a1, .LBB3_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: .LBB3_2:
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func8:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: andi a0, a0, 255
; RV32IZbb-NEXT: mul a1, a1, a2
; RV32IZbb-NEXT: andi a1, a1, 255
; RV32IZbb-NEXT: maxu a0, a0, a1
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func8:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: andi a0, a0, 255
; RV64IZbb-NEXT: mulw a1, a1, a2
; RV64IZbb-NEXT: andi a1, a1, 255
; RV64IZbb-NEXT: maxu a0, a0, a1
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: ret
%a = mul i8 %y, %z
%tmp = call i8 @llvm.usub.sat.i8(i8 %x, i8 %a)
ret i8 %tmp
}
define i4 @func4(i4 %x, i4 %y, i4 %z) nounwind {
; RV32I-LABEL: func4:
; RV32I: # %bb.0:
; RV32I-NEXT: andi a3, a0, 15
; RV32I-NEXT: mul a0, a1, a2
; RV32I-NEXT: andi a0, a0, 15
; RV32I-NEXT: sub a1, a3, a0
; RV32I-NEXT: li a0, 0
; RV32I-NEXT: bltu a3, a1, .LBB4_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: .LBB4_2:
; RV32I-NEXT: ret
;
; RV64I-LABEL: func4:
; RV64I: # %bb.0:
; RV64I-NEXT: andi a3, a0, 15
; RV64I-NEXT: mulw a0, a1, a2
; RV64I-NEXT: andi a0, a0, 15
; RV64I-NEXT: sub a1, a3, a0
; RV64I-NEXT: li a0, 0
; RV64I-NEXT: bltu a3, a1, .LBB4_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: .LBB4_2:
; RV64I-NEXT: ret
;
; RV32IZbb-LABEL: func4:
; RV32IZbb: # %bb.0:
; RV32IZbb-NEXT: andi a0, a0, 15
; RV32IZbb-NEXT: mul a1, a1, a2
; RV32IZbb-NEXT: andi a1, a1, 15
; RV32IZbb-NEXT: maxu a0, a0, a1
; RV32IZbb-NEXT: sub a0, a0, a1
; RV32IZbb-NEXT: ret
;
; RV64IZbb-LABEL: func4:
; RV64IZbb: # %bb.0:
; RV64IZbb-NEXT: andi a0, a0, 15
; RV64IZbb-NEXT: mulw a1, a1, a2
; RV64IZbb-NEXT: andi a1, a1, 15
; RV64IZbb-NEXT: maxu a0, a0, a1
; RV64IZbb-NEXT: sub a0, a0, a1
; RV64IZbb-NEXT: ret
%a = mul i4 %y, %z
%tmp = call i4 @llvm.usub.sat.i4(i4 %x, i4 %a)
ret i4 %tmp
}
|
