reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    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
//===--- AMDGPUMachineModuleInfo.h ------------------------------*- 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
//
//===----------------------------------------------------------------------===//
//
/// \file
/// AMDGPU Machine Module Info.
///
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEMODULEINFO_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEMODULEINFO_H

#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachineModuleInfoImpls.h"
#include "llvm/IR/LLVMContext.h"

namespace llvm {

class AMDGPUMachineModuleInfo final : public MachineModuleInfoELF {
private:

  // All supported memory/synchronization scopes can be found here:
  //   http://llvm.org/docs/AMDGPUUsage.html#memory-scopes

  /// Agent synchronization scope ID (cross address space).
  SyncScope::ID AgentSSID;
  /// Workgroup synchronization scope ID (cross address space).
  SyncScope::ID WorkgroupSSID;
  /// Wavefront synchronization scope ID (cross address space).
  SyncScope::ID WavefrontSSID;
  /// System synchronization scope ID (single address space).
  SyncScope::ID SystemOneAddressSpaceSSID;
  /// Agent synchronization scope ID (single address space).
  SyncScope::ID AgentOneAddressSpaceSSID;
  /// Workgroup synchronization scope ID (single address space).
  SyncScope::ID WorkgroupOneAddressSpaceSSID;
  /// Wavefront synchronization scope ID (single address space).
  SyncScope::ID WavefrontOneAddressSpaceSSID;
  /// Single thread synchronization scope ID (single address space).
  SyncScope::ID SingleThreadOneAddressSpaceSSID;

  /// In AMDGPU target synchronization scopes are inclusive, meaning a
  /// larger synchronization scope is inclusive of a smaller synchronization
  /// scope.
  ///
  /// \returns \p SSID's inclusion ordering, or "None" if \p SSID is not
  /// supported by the AMDGPU target.
  Optional<uint8_t> getSyncScopeInclusionOrdering(SyncScope::ID SSID) const {
    if (SSID == SyncScope::SingleThread ||
        SSID == getSingleThreadOneAddressSpaceSSID())
      return 0;
    else if (SSID == getWavefrontSSID() ||
             SSID == getWavefrontOneAddressSpaceSSID())
      return 1;
    else if (SSID == getWorkgroupSSID() ||
             SSID == getWorkgroupOneAddressSpaceSSID())
      return 2;
    else if (SSID == getAgentSSID() ||
             SSID == getAgentOneAddressSpaceSSID())
      return 3;
    else if (SSID == SyncScope::System ||
             SSID == getSystemOneAddressSpaceSSID())
      return 4;

    return None;
  }

  /// \returns True if \p SSID is restricted to single address space, false
  /// otherwise
  bool isOneAddressSpace(SyncScope::ID SSID) const {
    return SSID == getSingleThreadOneAddressSpaceSSID() ||
        SSID == getWavefrontOneAddressSpaceSSID() ||
        SSID == getWorkgroupOneAddressSpaceSSID() ||
        SSID == getAgentOneAddressSpaceSSID() ||
        SSID == getSystemOneAddressSpaceSSID();
  }

public:
  AMDGPUMachineModuleInfo(const MachineModuleInfo &MMI);

  /// \returns Agent synchronization scope ID (cross address space).
  SyncScope::ID getAgentSSID() const {
    return AgentSSID;
  }
  /// \returns Workgroup synchronization scope ID (cross address space).
  SyncScope::ID getWorkgroupSSID() const {
    return WorkgroupSSID;
  }
  /// \returns Wavefront synchronization scope ID (cross address space).
  SyncScope::ID getWavefrontSSID() const {
    return WavefrontSSID;
  }
  /// \returns System synchronization scope ID (single address space).
  SyncScope::ID getSystemOneAddressSpaceSSID() const {
    return SystemOneAddressSpaceSSID;
  }
  /// \returns Agent synchronization scope ID (single address space).
  SyncScope::ID getAgentOneAddressSpaceSSID() const {
    return AgentOneAddressSpaceSSID;
  }
  /// \returns Workgroup synchronization scope ID (single address space).
  SyncScope::ID getWorkgroupOneAddressSpaceSSID() const {
    return WorkgroupOneAddressSpaceSSID;
  }
  /// \returns Wavefront synchronization scope ID (single address space).
  SyncScope::ID getWavefrontOneAddressSpaceSSID() const {
    return WavefrontOneAddressSpaceSSID;
  }
  /// \returns Single thread synchronization scope ID (single address space).
  SyncScope::ID getSingleThreadOneAddressSpaceSSID() const {
    return SingleThreadOneAddressSpaceSSID;
  }

  /// In AMDGPU target synchronization scopes are inclusive, meaning a
  /// larger synchronization scope is inclusive of a smaller synchronization
  /// scope.
  ///
  /// \returns True if synchronization scope \p A is larger than or equal to
  /// synchronization scope \p B, false if synchronization scope \p A is smaller
  /// than synchronization scope \p B, or "None" if either synchronization scope
  /// \p A or \p B is not supported by the AMDGPU target.
  Optional<bool> isSyncScopeInclusion(SyncScope::ID A, SyncScope::ID B) const {
    const auto &AIO = getSyncScopeInclusionOrdering(A);
    const auto &BIO = getSyncScopeInclusionOrdering(B);
    if (!AIO || !BIO)
      return None;

    bool IsAOneAddressSpace = isOneAddressSpace(A);
    bool IsBOneAddressSpace = isOneAddressSpace(B);

    return AIO.getValue() >= BIO.getValue() &&
        (IsAOneAddressSpace == IsBOneAddressSpace || !IsAOneAddressSpace);
  }
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEMODULEINFO_H