Merge branch 'tutorials' into 'develop'

IF( BUILD_CUDA )

   CUDA_ADD_EXECUTABLE(ParallelForExampleCuda ParallelForExample.cu)

   ADD_CUSTOM_COMMAND( COMMAND ParallelForExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )

ELSE()

   ADD_EXECUTABLE(ParallelForExample ParallelForExample.cpp)

   ADD_CUSTOM_COMMAND( COMMAND ParallelForExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )

ENDIF()

IF( BUILD_CUDA )

ADD_CUSTOM_TARGET( RunAlgorithmsExamples-cuda ALL DEPENDS

   ParallelForExample.out

 )

ELSE()

ADD_CUSTOM_TARGET( RunAlgorithmsExamples ALL DEPENDS

   ParallelForExample.out

 )

ENDIF()

 No newline at end of file

#include <iostream>

#include <cstdlib>

#include <TNL/Containers/Vector.h>

#include <TNL/Algorithms/ParallelFor.h>

using namespace TNL;

using namespace TNL::Containers;

using namespace TNL::Algorithms;

template< typename Device >

void initMeshFunction( const int xSize,

                       const int ySize,

                       Vector< double, Device >& v,

                       const double& c )

{

   auto view = v1.getConstView();

   auto init = [=] __cuda_callable__  ( int i, int j, const int xSize, const double c ) mutable {

      view[ j * xSize + i ] =  c; };

   ParallelFor2D< Device >::exec( 0, 0, xSize, ySize, init, xSize, c );

}

int main( int argc, char* argv[] )

{

   /***

    * Define dimensions of 2D mesh function.

    */

   const int xSize( 10 ), ySize( 10 );

   const int size = xSize * ySize;

   /***

    * Firstly, test the mesh function initiation on CPU.

    */

   Vector< double, Devices::Host > host_v;

   initMeshFunction( xSize, ySize, host_v, 1.0 );

   /***

    * And then also on GPU.

    */

#ifdef HAVE_CUDA

   Vector< double, Devices::Cuda > cuda_v( size );

   initMeshFunction( xSize, ySize, cuda_v, 1.0 );

#endif

   return EXIT_SUCCESS;

}

ParallelForExample-2D.cpp

 No newline at end of file

#include <iostream>

#include <cstdlib>

#include <TNL/Containers/Vector.h>

#include <TNL/Algorithms/ParallelFor.h>

using namespace TNL;

using namespace TNL::Containers;

using namespace TNL::Algorithms;

template< typename Device >

void initMeshFunction( const int xSize,

                       const int ySize,

                       const int zSize,

                       Vector< double, Device >& v,

                       const double& c )

{

   auto view = v1.getConstView();

   auto init = [=] __cuda_callable__  ( int i, int j, int k, const int xSize, const int ySize, const double c ) mutable {

      view[ ( k * ySize + j ) * xSize + i ] =  c; };

   ParallelFor3D< Device >::exec( 0, 0, xSize, ySize, init, xSize, ySize, c );

}

int main( int argc, char* argv[] )

{

   /***

    * Define dimensions of 2D mesh function.

    */

   const int xSize( 10 ), ySize( 10 ), zSize( 10 );

   const int size = xSize * ySize * zSize;

   /***

    * Firstly, test the mesh function initiation on CPU.

    */

   Vector< double, Devices::Host > host_v;

   initMeshFunction( xSize, ySize, zSize, host_v, 1.0 );

   /***

    * And then also on GPU.

    */

#ifdef HAVE_CUDA

   Vector< double, Devices::Cuda > cuda_v( size );

   initMeshFunction( xSize, ySize, cuda_v, 1.0 );

#endif

   return EXIT_SUCCESS;

}

ParallelForExample-3D.cpp

 No newline at end of file