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
|
#pragma once
#ifdef __GNUC__
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wunused-parameter"
#endif
//===--- Cuda.h - Utilities for compiling CUDA code ------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_BASIC_CUDA_H
#define LLVM_CLANG_BASIC_CUDA_H
namespace llvm {
class StringRef;
class Twine;
class VersionTuple;
} // namespace llvm
namespace clang {
enum class CudaVersion {
UNKNOWN,
CUDA_70,
CUDA_75,
CUDA_80,
CUDA_90,
CUDA_91,
CUDA_92,
CUDA_100,
CUDA_101,
CUDA_102,
CUDA_110,
CUDA_111,
CUDA_112,
CUDA_113,
CUDA_114,
CUDA_115,
CUDA_116,
CUDA_117,
CUDA_118,
FULLY_SUPPORTED = CUDA_115,
PARTIALLY_SUPPORTED =
CUDA_118, // Partially supported. Proceed with a warning.
NEW = 10000, // Too new. Issue a warning, but allow using it.
};
const char *CudaVersionToString(CudaVersion V);
// Input is "Major.Minor"
CudaVersion CudaStringToVersion(const llvm::Twine &S);
enum class CudaArch {
UNUSED,
UNKNOWN,
SM_20,
SM_21,
SM_30,
SM_32,
SM_35,
SM_37,
SM_50,
SM_52,
SM_53,
SM_60,
SM_61,
SM_62,
SM_70,
SM_72,
SM_75,
SM_80,
SM_86,
SM_87,
SM_89,
SM_90,
GFX600,
GFX601,
GFX602,
GFX700,
GFX701,
GFX702,
GFX703,
GFX704,
GFX705,
GFX801,
GFX802,
GFX803,
GFX805,
GFX810,
GFX900,
GFX902,
GFX904,
GFX906,
GFX908,
GFX909,
GFX90a,
GFX90c,
GFX940,
GFX1010,
GFX1011,
GFX1012,
GFX1013,
GFX1030,
GFX1031,
GFX1032,
GFX1033,
GFX1034,
GFX1035,
GFX1036,
GFX1100,
GFX1101,
GFX1102,
GFX1103,
Generic, // A processor model named 'generic' if the target backend defines a
// public one.
LAST,
CudaDefault = CudaArch::SM_35,
HIPDefault = CudaArch::GFX803,
};
static inline bool IsNVIDIAGpuArch(CudaArch A) {
return A >= CudaArch::SM_20 && A < CudaArch::GFX600;
}
static inline bool IsAMDGpuArch(CudaArch A) {
// Generic processor model is for testing only.
return A >= CudaArch::GFX600 && A < CudaArch::Generic;
}
const char *CudaArchToString(CudaArch A);
const char *CudaArchToVirtualArchString(CudaArch A);
// The input should have the form "sm_20".
CudaArch StringToCudaArch(llvm::StringRef S);
/// Get the earliest CudaVersion that supports the given CudaArch.
CudaVersion MinVersionForCudaArch(CudaArch A);
/// Get the latest CudaVersion that supports the given CudaArch.
CudaVersion MaxVersionForCudaArch(CudaArch A);
// Various SDK-dependent features that affect CUDA compilation
enum class CudaFeature {
// CUDA-9.2+ uses a new API for launching kernels.
CUDA_USES_NEW_LAUNCH,
// CUDA-10.1+ needs explicit end of GPU binary registration.
CUDA_USES_FATBIN_REGISTER_END,
};
CudaVersion ToCudaVersion(llvm::VersionTuple);
bool CudaFeatureEnabled(llvm::VersionTuple, CudaFeature);
bool CudaFeatureEnabled(CudaVersion, CudaFeature);
} // namespace clang
#endif
#ifdef __GNUC__
#pragma GCC diagnostic pop
#endif
|
