Commit 76a95d0b authored by Jakub Klinkovský's avatar Jakub Klinkovský
Browse files

Implemented 'outplace' variants of scan and distributed scan functions

parent 4f1dc3af

Documentation/Tutorials/ReductionAndScan/CMakeLists.txt

+2 −0
Original line number Diff line number Diff line
@@ -12,6 +12,8 @@ set( COMMON_EXAMPLES 
     MapReduceExample-3

     ReductionWithArgument

     ReductionWithArgumentWithFunctional

     inclusiveScanExample

     exclusiveScanExample

     inplaceInclusiveScanExample

     inplaceExclusiveScanExample

     SegmentedScanExample

Documentation/Tutorials/ReductionAndScan/exclusiveScanExample.cpp

0 → 100644
+31 −0
Original line number Diff line number Diff line 
#include <iostream>

#include <TNL/Containers/Array.h>

#include <TNL/Algorithms/scan.h>



using namespace TNL;

using namespace TNL::Containers;

using namespace TNL::Algorithms;



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

{

   /***

    * Firstly, test the prefix sum with an array allocated on CPU.

    */

   Array< double, Devices::Host > host_input( 10 ), host_output( 10 );

   host_input = 1.0;

   std::cout << "host_input = " << host_input << std::endl;

   exclusiveScan( host_input, host_output );

   std::cout << "host_output " << host_output << std::endl;



   /***

    * And then also on GPU.

    */

#ifdef HAVE_CUDA

   Array< double, Devices::Cuda > cuda_input( 10 ), cuda_output( 10 );

   cuda_input = 1.0;

   std::cout << "cuda_input = " << cuda_input << std::endl;

   exclusiveScan( cuda_input, cuda_output );

   std::cout << "cuda_output " << cuda_output << std::endl;

#endif

   return EXIT_SUCCESS;

}

Documentation/Tutorials/ReductionAndScan/exclusiveScanExample.cu

0 → 120000
+1 −0
Original line number Diff line number Diff line 
exclusiveScanExample.cpp
 
 No newline at end of file

Documentation/Tutorials/ReductionAndScan/inclusiveScanExample.cpp

0 → 100644
+31 −0
Original line number Diff line number Diff line 
#include <iostream>

#include <TNL/Containers/Array.h>

#include <TNL/Algorithms/scan.h>



using namespace TNL;

using namespace TNL::Containers;

using namespace TNL::Algorithms;



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

{

   /***

    * Firstly, test the prefix sum with an array allocated on CPU.

    */

   Array< double, Devices::Host > host_input( 10 ), host_output( 10 );

   host_input = 1.0;

   std::cout << "host_input = " << host_input << std::endl;

   inclusiveScan( host_input, host_output );

   std::cout << "host_output " << host_output << std::endl;



   /***

    * And then also on GPU.

    */

#ifdef HAVE_CUDA

   Array< double, Devices::Cuda > cuda_input( 10 ), cuda_output( 10 );

   cuda_input = 1.0;

   std::cout << "cuda_input = " << cuda_input << std::endl;

   inclusiveScan( cuda_input, cuda_output );

   std::cout << "cuda_output " << cuda_output << std::endl;

#endif

   return EXIT_SUCCESS;

}

Documentation/Tutorials/ReductionAndScan/inclusiveScanExample.cu

0 → 120000
+1 −0
Original line number Diff line number Diff line 
inclusiveScanExample.cpp
 
 No newline at end of file