This file is indexed.

/usr/include/trilinos/Kokkos_Cuda.hpp is in libtrilinos-kokkos-dev 12.10.1-3.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
/*
//@HEADER
// ************************************************************************
//
//                        Kokkos v. 2.0
//              Copyright (2014) Sandia Corporation
//
// Under the terms of Contract DE-AC04-94AL85000 with Sandia Corporation,
// the U.S. Government retains certain rights in this software.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// 1. Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//
// 2. Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
//
// 3. Neither the name of the Corporation nor the names of the
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY SANDIA CORPORATION "AS IS" AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL SANDIA CORPORATION OR THE
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Questions? Contact  H. Carter Edwards (hcedwar@sandia.gov)
//
// ************************************************************************
//@HEADER
*/

#ifndef KOKKOS_CUDA_HPP
#define KOKKOS_CUDA_HPP

#include <Kokkos_Core_fwd.hpp>

// If CUDA execution space is enabled then use this header file.

#if defined( KOKKOS_HAVE_CUDA )

#include <iosfwd>
#include <vector>

#include <Kokkos_CudaSpace.hpp>

#include <Kokkos_Parallel.hpp>
#include <Kokkos_TaskScheduler.hpp>
#include <Kokkos_Layout.hpp>
#include <Kokkos_ScratchSpace.hpp>
#include <Kokkos_MemoryTraits.hpp>
#include <impl/Kokkos_Tags.hpp>

#include <KokkosExp_MDRangePolicy.hpp>

/*--------------------------------------------------------------------------*/

namespace Kokkos {
namespace Impl {
class CudaExec ;
} // namespace Impl
} // namespace Kokkos

/*--------------------------------------------------------------------------*/

namespace Kokkos {

/// \class Cuda
/// \brief Kokkos Execution Space that uses CUDA to run on GPUs.
///
/// An "execution space" represents a parallel execution model.  It tells Kokkos
/// how to parallelize the execution of kernels in a parallel_for or
/// parallel_reduce.  For example, the Threads execution space uses Pthreads or
/// C++11 threads on a CPU, the OpenMP execution space uses the OpenMP language
/// extensions, and the Serial execution space executes "parallel" kernels
/// sequentially.  The Cuda execution space uses NVIDIA's CUDA programming
/// model to execute kernels in parallel on GPUs.
class Cuda {
public:
  //! \name Type declarations that all Kokkos execution spaces must provide.
  //@{

  //! Tag this class as a kokkos execution space
  typedef Cuda                  execution_space ;

#if defined( KOKKOS_USE_CUDA_UVM )
  //! This execution space's preferred memory space.
  typedef CudaUVMSpace          memory_space ;
#else
  //! This execution space's preferred memory space.
  typedef CudaSpace             memory_space ;
#endif

  //! This execution space preferred device_type
  typedef Kokkos::Device<execution_space,memory_space> device_type;

  //! The size_type best suited for this execution space.
  typedef memory_space::size_type  size_type ;

  //! This execution space's preferred array layout.
  typedef LayoutLeft            array_layout ;

  //!
  typedef ScratchMemorySpace< Cuda >  scratch_memory_space ;

  //@}
  //--------------------------------------------------
  //! \name Functions that all Kokkos devices must implement.
  //@{

  /// \brief True if and only if this method is being called in a
  ///   thread-parallel function.
  KOKKOS_INLINE_FUNCTION static int in_parallel() {
#if defined( __CUDA_ARCH__ )
    return true;
#else
    return false;
#endif
  }

  /** \brief  Set the device in a "sleep" state.
   *
   * This function sets the device in a "sleep" state in which it is
   * not ready for work.  This may consume less resources than if the
   * device were in an "awake" state, but it may also take time to
   * bring the device from a sleep state to be ready for work.
   *
   * \return True if the device is in the "sleep" state, else false if
   *   the device is actively working and could not enter the "sleep"
   *   state.
   */
  static bool sleep();

  /// \brief Wake the device from the 'sleep' state so it is ready for work.
  ///
  /// \return True if the device is in the "ready" state, else "false"
  ///  if the device is actively working (which also means that it's
  ///  awake).
  static bool wake();

  /// \brief Wait until all dispatched functors complete.
  ///
  /// The parallel_for or parallel_reduce dispatch of a functor may
  /// return asynchronously, before the functor completes.  This
  /// method does not return until all dispatched functors on this
  /// device have completed.
  static void fence();

  //! Free any resources being consumed by the device.
  static void finalize();

  //! Has been initialized
  static int is_initialized();

  /** \brief  Return the maximum amount of concurrency.  */
  static int concurrency();

  //! Print configuration information to the given output stream.
  static void print_configuration( std::ostream & , const bool detail = false );

  //@}
  //--------------------------------------------------
  //! \name  Cuda space instances

  ~Cuda() {}
  Cuda();
  explicit Cuda( const int instance_id );

  Cuda( Cuda && ) = default ;
  Cuda( const Cuda & ) = default ;
  Cuda & operator = ( Cuda && ) = default ;
  Cuda & operator = ( const Cuda & ) = default ;

  //--------------------------------------------------------------------------
  //! \name Device-specific functions
  //@{

  struct SelectDevice {
    int cuda_device_id ;
    SelectDevice() : cuda_device_id(0) {}
    explicit SelectDevice( int id ) : cuda_device_id( id ) {}
  };

  //! Initialize, telling the CUDA run-time library which device to use.
  static void initialize( const SelectDevice = SelectDevice()
                        , const size_t num_instances = 1 );

  /// \brief Cuda device architecture of the selected device.
  ///
  /// This matches the __CUDA_ARCH__ specification.
  static size_type device_arch();

  //! Query device count.
  static size_type detect_device_count();

  /** \brief  Detect the available devices and their architecture
   *          as defined by the __CUDA_ARCH__ specification.
   */
  static std::vector<unsigned> detect_device_arch();

  cudaStream_t cuda_stream() const { return m_stream ; }
  int          cuda_device() const { return m_device ; }

  //@}
  //--------------------------------------------------------------------------

private:

  cudaStream_t m_stream ;
  int          m_device ;
};

} // namespace Kokkos

/*--------------------------------------------------------------------------*/
/*--------------------------------------------------------------------------*/

namespace Kokkos {
namespace Impl {

template<>
struct VerifyExecutionCanAccessMemorySpace
  < Kokkos::CudaSpace
  , Kokkos::Cuda::scratch_memory_space
  >
{
  enum { value = true };
  KOKKOS_INLINE_FUNCTION static void verify( void ) { }
  KOKKOS_INLINE_FUNCTION static void verify( const void * ) { }
};

template<>
struct VerifyExecutionCanAccessMemorySpace
  < Kokkos::HostSpace
  , Kokkos::Cuda::scratch_memory_space
  >
{
  enum { value = false };
  inline static void verify( void ) { CudaSpace::access_error(); }
  inline static void verify( const void * p ) { CudaSpace::access_error(p); }
};

} // namespace Impl
} // namespace Kokkos

/*--------------------------------------------------------------------------*/
/*--------------------------------------------------------------------------*/

#include <Cuda/Kokkos_CudaExec.hpp>
#include <Cuda/Kokkos_Cuda_View.hpp>
#include <Cuda/Kokkos_Cuda_Parallel.hpp>
#include <Cuda/Kokkos_Cuda_Task.hpp>

//----------------------------------------------------------------------------

#endif /* #if defined( KOKKOS_HAVE_CUDA ) */
#endif /* #ifndef KOKKOS_CUDA_HPP */