Writting tutorial for segments. (1ac8fe84) · Commits · TNL / tnl-dev

Documentation/Examples/Algorithms/Segments/CMakeLists.txt

+6 −0

Original line number	Diff line number	Diff line
		set( COMMON_EXAMPLES
		SegmentsExample_General
		SegmentsPrintingExample-1
		SegmentsPrintingExample-2
		SegmentsExample_CSR_constructor_1
		SegmentsExample_CSR_constructor_2
		SegmentsExample_CSR_getSerializationType
		@@ -10,6 +12,10 @@ set( COMMON_EXAMPLES
		SegmentsExample_CSR_forSegments
		SegmentsExample_CSR_sequentialForSegments
		SegmentsExample_CSR_reduceSegments
		SegmentsExample_forElements
		SegmentsExample_forSegments-1
		SegmentsExample_forSegments-2
		SegmentsExample_reduceSegments
		)

		if( BUILD_CUDA )

Documentation/Examples/Algorithms/Segments/SegmentsExample_forElements.cpp

0 → 100644

+73 −0

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <TNL/Containers/Vector.h>
		#include <TNL/Algorithms/Segments/CSR.h>
		#include <TNL/Algorithms/Segments/Ellpack.h>
		#include <TNL/Devices/Host.h>
		#include <TNL/Devices/Cuda.h>

		template< typename Segments >
		void SegmentsExample()
		{
		using Device = typename Segments::DeviceType;

		/***
		* Create segments with given segments sizes.
		*/
		Segments segments{ 1, 2, 3, 4, 5 };

		/***
		* Allocate array for the segments;
		*/
		TNL::Containers::Array< double, Device > data( segments.getStorageSize(), 0.0 );

		/***
		* Insert data into particular segments with no check.
		*/
		auto data_view = data.getView();
		segments.forAllElements( [=] __cuda_callable__ ( int segmentIdx, int localIdx, int globalIdx ) mutable {
		data_view[ globalIdx ] = segmentIdx;
		} );

		/***
		* Print the data managed by the segments.
		*/
		std::cout << "Data setup with no check ... " << std::endl;
		std::cout << "Array: " << data << std::endl;
		auto fetch = [=] __cuda_callable__ ( int globalIdx ) -> double { return data_view[ globalIdx ]; };
		printSegments( segments, fetch, std::cout ) << std::endl;

		/***
		* Insert data into particular segments.
		*/
		data = 0.0;
		segments.forAllElements( [=] __cuda_callable__ ( int segmentIdx, int localIdx, int globalIdx ) mutable {
		if( localIdx <= segmentIdx )
		data_view[ globalIdx ] = segmentIdx;
		} );

		/***
		* Print the data managed by the segments.
		*/
		std::cout << "Data setup with check for padding elements..." << std::endl;
		std::cout << "Array: " << data << std::endl;
		printSegments( segments, fetch, std::cout ) << std::endl;
		}

		int main( int argc, char* argv[] )
		{
		std::cout << "Example of CSR segments on host: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Host, int > >();

		std::cout << "Example of Ellpack segments on host: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Host, int > >();


		#ifdef HAVE_CUDA
		std::cout << "Example of CSR segments on CUDA GPU: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Cuda, int > >();

		std::cout << "Example of Ellpack segments on CUDA GPU: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Cuda, int > >();
		#endif
		return EXIT_SUCCESS;
		}

Documentation/Examples/Algorithms/Segments/SegmentsExample_forElements.cu

0 → 120000

+1 −0

Original line number	Diff line number	Diff line
		SegmentsExample_forElements.cpp
		No newline at end of file

Documentation/Examples/Algorithms/Segments/SegmentsExample_forSegments-1.cpp

0 → 100644

+62 −0

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <TNL/Containers/Vector.h>
		#include <TNL/Algorithms/Segments/CSR.h>
		#include <TNL/Algorithms/Segments/Ellpack.h>
		#include <TNL/Devices/Host.h>
		#include <TNL/Devices/Cuda.h>

		template< typename Segments >
		void SegmentsExample()
		{
		using Device = typename Segments::DeviceType;

		/***
		* Create segments with given segments sizes.
		*/
		Segments segments{ 1, 2, 3, 4, 5 };

		/***
		* Allocate array for the segments;
		*/
		TNL::Containers::Array< double, Device > data( segments.getStorageSize(), 0.0 );

		/***
		* Insert data into particular segments.
		*/
		auto data_view = data.getView();
		using SegmentViewType = typename Segments::SegmentViewType;
		segments.forAllSegments( [=] __cuda_callable__ ( const SegmentViewType& segment ) mutable {
		double sum( 0.0 );
		for( auto element : segment )
		if( element.localIndex() <= element.segmentIndex() )
		{
		sum += element.localIndex() + 1;
		data_view[ element.globalIndex() ] = sum;
		}
		} );

		/***
		* Print the data managed by the segments.
		*/
		auto fetch = [=] __cuda_callable__ ( int globalIdx ) -> double { return data_view[ globalIdx ]; };
		printSegments( segments, fetch, std::cout );
		}

		int main( int argc, char* argv[] )
		{
		std::cout << "Example of CSR segments on host: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Host, int > >();

		std::cout << "Example of Ellpack segments on host: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Host, int > >();


		#ifdef HAVE_CUDA
		std::cout << "Example of CSR segments on CUDA GPU: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Cuda, int > >();

		std::cout << "Example of Ellpack segments on CUDA GPU: " << std::endl;
		SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Cuda, int > >();
		#endif
		return EXIT_SUCCESS;
		}

Documentation/Examples/Algorithms/Segments/SegmentsExample_forSegments-1.cu

0 → 120000

+1 −0

Original line number	Diff line number	Diff line
		SegmentsExample_forSegments-1.cpp
		No newline at end of file