aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clang16/lib/CodeGen/CGCUDARuntime.h
blob: 9a9c6d26cc63c40c4d74c39337afb77563fa4daa (plain) (blame)
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
//===----- CGCUDARuntime.h - Interface to CUDA Runtimes ---------*- 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
//
//===----------------------------------------------------------------------===//
//
// This provides an abstract class for CUDA code generation.  Concrete
// subclasses of this implement code generation for specific CUDA
// runtime libraries.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_LIB_CODEGEN_CGCUDARUNTIME_H
#define LLVM_CLANG_LIB_CODEGEN_CGCUDARUNTIME_H

#include "clang/AST/GlobalDecl.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/GlobalValue.h"

namespace llvm {
class Function;
class GlobalVariable;
}

namespace clang {

class CUDAKernelCallExpr;
class NamedDecl;
class VarDecl;

namespace CodeGen {

class CodeGenFunction;
class CodeGenModule;
class FunctionArgList;
class ReturnValueSlot;
class RValue;

class CGCUDARuntime {
protected:
  CodeGenModule &CGM;

public:
  // Global variable properties that must be passed to CUDA runtime.
  class DeviceVarFlags {
  public:
    enum DeviceVarKind {
      Variable, // Variable
      Surface,  // Builtin surface
      Texture,  // Builtin texture
    };

    /// The kind flag for an offloading entry.
    enum OffloadEntryKindFlag : uint32_t {
      /// Mark the entry as a global entry. This indicates the presense of a
      /// kernel if the size field is zero and a variable otherwise.
      OffloadGlobalEntry = 0x0,
      /// Mark the entry as a managed global variable.
      OffloadGlobalManagedEntry = 0x1,
      /// Mark the entry as a surface variable.
      OffloadGlobalSurfaceEntry = 0x2,
      /// Mark the entry as a texture variable.
      OffloadGlobalTextureEntry = 0x3,
    };

  private:
    unsigned Kind : 2;
    unsigned Extern : 1;
    unsigned Constant : 1;   // Constant variable.
    unsigned Managed : 1;    // Managed variable.
    unsigned Normalized : 1; // Normalized texture.
    int SurfTexType;         // Type of surface/texutre.

  public:
    DeviceVarFlags(DeviceVarKind K, bool E, bool C, bool M, bool N, int T)
        : Kind(K), Extern(E), Constant(C), Managed(M), Normalized(N),
          SurfTexType(T) {}

    DeviceVarKind getKind() const { return static_cast<DeviceVarKind>(Kind); }
    bool isExtern() const { return Extern; }
    bool isConstant() const { return Constant; }
    bool isManaged() const { return Managed; }
    bool isNormalized() const { return Normalized; }
    int getSurfTexType() const { return SurfTexType; }
  };

  CGCUDARuntime(CodeGenModule &CGM) : CGM(CGM) {}
  virtual ~CGCUDARuntime();

  virtual RValue EmitCUDAKernelCallExpr(CodeGenFunction &CGF,
                                        const CUDAKernelCallExpr *E,
                                        ReturnValueSlot ReturnValue);

  /// Emits a kernel launch stub.
  virtual void emitDeviceStub(CodeGenFunction &CGF, FunctionArgList &Args) = 0;

  /// Check whether a variable is a device variable and register it if true.
  virtual void handleVarRegistration(const VarDecl *VD,
                                     llvm::GlobalVariable &Var) = 0;

  /// Finalize generated LLVM module. Returns a module constructor function
  /// to be added or a null pointer.
  virtual llvm::Function *finalizeModule() = 0;

  /// Returns function or variable name on device side even if the current
  /// compilation is for host.
  virtual std::string getDeviceSideName(const NamedDecl *ND) = 0;

  /// Get kernel handle by stub function.
  virtual llvm::GlobalValue *getKernelHandle(llvm::Function *Stub,
                                             GlobalDecl GD) = 0;

  /// Get kernel stub by kernel handle.
  virtual llvm::Function *getKernelStub(llvm::GlobalValue *Handle) = 0;

  /// Adjust linkage of shadow variables in host compilation.
  virtual void
  internalizeDeviceSideVar(const VarDecl *D,
                           llvm::GlobalValue::LinkageTypes &Linkage) = 0;
};

/// Creates an instance of a CUDA runtime class.
CGCUDARuntime *CreateNVCUDARuntime(CodeGenModule &CGM);

}
}

#endif