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_cc_test_checks.py
// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// REQUIRES: aarch64-registered-target || arm-registered-target
#include <arm_mve.h>
// CHECK-LABEL: @test_asrl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.asrl(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]])
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
int64_t test_asrl(int64_t value, int32_t shift)
{
return asrl(value, shift);
}
// CHECK-LABEL: @test_lsll(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.lsll(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]])
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
uint64_t test_lsll(uint64_t value, int32_t shift)
{
return lsll(value, shift);
}
// CHECK-LABEL: @test_sqrshr(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.sqrshr(i32 [[VALUE:%.*]], i32 [[SHIFT:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
int32_t test_sqrshr(int32_t value, int32_t shift)
{
return sqrshr(value, shift);
}
// CHECK-LABEL: @test_sqrshrl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.sqrshrl(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]], i32 64)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
int64_t test_sqrshrl(int64_t value, int32_t shift)
{
return sqrshrl(value, shift);
}
// CHECK-LABEL: @test_sqrshrl_sat48(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.sqrshrl(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]], i32 48)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
int64_t test_sqrshrl_sat48(int64_t value, int32_t shift)
{
return sqrshrl_sat48(value, shift);
}
// CHECK-LABEL: @test_sqshl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.sqshl(i32 [[VALUE:%.*]], i32 2)
// CHECK-NEXT: ret i32 [[TMP0]]
//
int32_t test_sqshl(int32_t value)
{
return sqshl(value, 2);
}
// CHECK-LABEL: @test_sqshll(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.sqshll(i32 [[TMP2]], i32 [[TMP1]], i32 17)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
int64_t test_sqshll(int64_t value)
{
return sqshll(value, 17);
}
// CHECK-LABEL: @test_srshr(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.srshr(i32 [[VALUE:%.*]], i32 6)
// CHECK-NEXT: ret i32 [[TMP0]]
//
int32_t test_srshr(int32_t value)
{
return srshr(value, 6);
}
// CHECK-LABEL: @test_srshrl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.srshrl(i32 [[TMP2]], i32 [[TMP1]], i32 26)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
int64_t test_srshrl(int64_t value)
{
return srshrl(value, 26);
}
// CHECK-LABEL: @test_uqrshl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.uqrshl(i32 [[VALUE:%.*]], i32 [[SHIFT:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t test_uqrshl(uint32_t value, int32_t shift)
{
return uqrshl(value, shift);
}
// CHECK-LABEL: @test_uqrshll(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.uqrshll(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]], i32 64)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
uint64_t test_uqrshll(uint64_t value, int32_t shift)
{
return uqrshll(value, shift);
}
// CHECK-LABEL: @test_uqrshll_sat48(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.uqrshll(i32 [[TMP2]], i32 [[TMP1]], i32 [[SHIFT:%.*]], i32 48)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
uint64_t test_uqrshll_sat48(uint64_t value, int32_t shift)
{
return uqrshll_sat48(value, shift);
}
// CHECK-LABEL: @test_uqshl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.uqshl(i32 [[VALUE:%.*]], i32 21)
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t test_uqshl(uint32_t value)
{
return uqshl(value, 21);
}
// CHECK-LABEL: @test_uqshll(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.uqshll(i32 [[TMP2]], i32 [[TMP1]], i32 16)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
uint64_t test_uqshll(uint64_t value)
{
return uqshll(value, 16);
}
// CHECK-LABEL: @test_urshr(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.urshr(i32 [[VALUE:%.*]], i32 22)
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t test_urshr(uint32_t value)
{
return urshr(value, 22);
}
// CHECK-LABEL: @test_urshrl(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = lshr i64 [[VALUE:%.*]], 32
// CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[TMP0]] to i32
// CHECK-NEXT: [[TMP2:%.*]] = trunc i64 [[VALUE]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call { i32, i32 } @llvm.arm.mve.urshrl(i32 [[TMP2]], i32 [[TMP1]], i32 6)
// CHECK-NEXT: [[TMP4:%.*]] = extractvalue { i32, i32 } [[TMP3]], 1
// CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
// CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP5]], 32
// CHECK-NEXT: [[TMP7:%.*]] = extractvalue { i32, i32 } [[TMP3]], 0
// CHECK-NEXT: [[TMP8:%.*]] = zext i32 [[TMP7]] to i64
// CHECK-NEXT: [[TMP9:%.*]] = or i64 [[TMP6]], [[TMP8]]
// CHECK-NEXT: ret i64 [[TMP9]]
//
uint64_t test_urshrl(uint64_t value)
{
return urshrl(value, 6);
}
|
