TNL::Pointers::DevicePointer< Object, Device > Class Template Reference

The DevicePointer is like SharedPointer, except it takes an existing host object - there is no call to the ObjectType's constructor nor destructor. More...

#include <TNL/Pointers/DevicePointer.h>

Detailed Description

template<typename Object, typename Device = typename Object::DeviceType>
class TNL::Pointers::DevicePointer< Object, Device >

The DevicePointer is like SharedPointer, except it takes an existing host object - there is no call to the ObjectType's constructor nor destructor.

**NOTE: When using smart pointers to pass objects on GPU, one must call Pointers::synchronizeSmartPointersOnDevice< Devices::Cuda >() before calling a CUDA kernel working with smart pointers.**

Template Parameters

Object	is a type of object to be owned by the pointer.
Device	is device where the object is to be allocated. The object is always allocated on the host system as well for easier object manipulation.

See also UniquePointer and SharedPointer.

See also DevicePointer< Object, Devices::Host > and DevicePointer< Object, Devices::Cuda >.

Example

#include <iostream>
#include <cstdlib>
#include <TNL/Containers/Array.h>
#include <TNL/Pointers/DevicePointer.h>
 
using namespace TNL;
 
using ArrayCuda = Containers::Array< int, Devices::Cuda >;
 
struct Tuple
{
   Tuple( ArrayCuda& _a1, ArrayCuda& _a2 )
   : a1( _a1 ),
     a2( _a2 )
   {}
 
   Pointers::DevicePointer< ArrayCuda > a1, a2;
};
 
#ifdef __CUDACC__
__global__
void
printTuple( const Tuple t )
{
   printf( "Tuple size is: %d\n", t.a1->getSize() );
   for( int i = 0; i < t.a1->getSize(); i++ ) {
      printf( "a1[ %d ] = %d \n", i, ( *t.a1 )[ i ] );
      printf( "a2[ %d ] = %d \n", i, ( *t.a2 )[ i ] );
   }
}
#endif
 
int
main( int argc, char* argv[] )
{
   /***
    * Create a tuple of arrays and print them in CUDA kernel
    */
#ifdef __CUDACC__
   ArrayCuda a1( 3 ), a2( 3 );
   Tuple t( a1, a2 );
   a1 = 1;
   a2 = 2;
   Pointers::synchronizeSmartPointersOnDevice< Devices::Cuda >();
   printTuple<<< 1, 1 >>>( t );
 
   /***
    * Resize the arrays
    */
   a1.setSize( 5 );
   a2.setSize( 5 );
   a1 = 3;
   a2 = 4;
   Pointers::synchronizeSmartPointersOnDevice< Devices::Cuda >();
   printTuple<<< 1, 1 >>>( t );
#endif
   return EXIT_SUCCESS;
}

Output

Tuple size is: 3
a1[ 0 ] = 1 
a2[ 0 ] = 2 
a1[ 1 ] = 1 
a2[ 1 ] = 2 
a1[ 2 ] = 1 
a2[ 2 ] = 2 
Tuple size is: 3
a1[ 0 ] = 3 
a2[ 0 ] = 4 
a1[ 1 ] = 3 
a2[ 1 ] = 4 
a1[ 2 ] = 3 
a2[ 2 ] = 4 

---

The documentation for this class was generated from the following file:

• src/TNL/Pointers/DevicePointer.h