Merge branch 'TO/matrices-adaptive-csr' into 'develop' (499049d8) · Commits · TNL / tnl-dev

CMakeLists.txt

+31 −24

Original line number	Diff line number	Diff line
		@@ -309,30 +309,34 @@ if( ${WITH_GMP} )
		endif()
		endif()

		#if( BUILD_MPI )
		# FIND_PATH( PETSC_INCLUDE_DIR petsc.h
		# /usr/include/petsc
		# ${PETSC_DIR}/${PETSC_ARCH}/include
		# ${PETSC_DIR}/include
		# DOC "PETSC headers."
		# )
		# if( ${PETSC_INCLUDE_DIR} STREQUAL "PETSC_INCLUDE_DIR-NOTFOUND" )
		# message( "PETSC not found." )
		# else()
		# message( "PETSC headers found -- ${PETSC_INCLUDE_DIR}" )
		# FIND_LIBRARY(PETSC_LIBRARY petsc
		# ${PETSC_INCLUDE_DIR}/../lib
		# /usr/local/lib
		# /usr/lib)
		# if( PETSC_LIBRARY )
		# #string( REPLACE ";" " " MPI_LIBRARIES "${MPI_CXX_LIBRARIES}" )
		# #set( PETSC_LIBRARY "${MPI_LIBRARIES} ${PETSC_LIBRARY}")
		# message( "PETSC library found -- ${PETSC_LIBRARY}")
		####
		# Test for PETSc
		if( BUILD_MPI )
		FIND_PATH( PETSC_INCLUDE_DIR petsc.h
		/usr/include/petsc
		${PETSC_DIR}/${PETSC_ARCH}/include
		${PETSC_DIR}/include
		DOC "PETSC headers."
		)
		if( ${PETSC_INCLUDE_DIR} STREQUAL "PETSC_INCLUDE_DIR-NOTFOUND" )
		message( "PETSC not found." )
		else()
		message( "PETSC headers found -- ${PETSC_INCLUDE_DIR}" )
		FIND_LIBRARY(PETSC_LIBRARY petsc
		${PETSC_INCLUDE_DIR}/../lib
		/usr/local/lib
		/usr/lib)
		if( PETSC_LIBRARY )
		#string( REPLACE ";" " " MPI_LIBRARIES "${MPI_CXX_LIBRARIES}" )
		#set( PETSC_LIBRARY "${MPI_LIBRARIES} ${PETSC_LIBRARY}")
		message( "PETSC library found -- ${PETSC_LIBRARY}")
		#list( GET MPI_CXX_INCLUDE_PATH 0 MPI_CXX_PATH )
		#set(PETSC_CXX_FLAGS "-DHAVE_PETSC -I${PETSC_INCLUDE_DIR} -DHAVE_MPI -I${MPI_CXX_PATH}")
		# endif()
		# endif()
		#endif()
		set(PETSC_CXX_FLAGS -DHAVE_PETSC -I${PETSC_INCLUDE_DIR})
		set(PETSC_LINKER_FLAGS ${PETSC_LIBRARY})
		endif()
		endif()
		endif()

		# configure build paths
		set( CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_BINARY_DIR}/bin )
		@@ -413,6 +417,9 @@ message( " CMAKE_SHARED_LINKER_FLAGS_RELEASE = ${CMAKE_SHARED_LINKER_FLAGS_REL
		message( " CUDA_NVCC_FLAGS = ${CUDA_NVCC_FLAGS}" )
		message( " CUDA_SAMPLES_FLAGS = ${CUDA_SAMPLES_FLAGS}" )
		message( " GMP_LIBRARIES = ${GMP_LIBRARIES}" )
		message( " PETSC_CXX_FLAGS = ${PETSC_CXX_FLAGS}" )
		message( " PETSC_LINKER_FLAGS = ${PETSC_LINKER_FLAGS}" )

		if( MPI_CXX_FOUND AND ${WITH_MPI} )
		message( " MPI_CXX_COMPILE_OPTIONS = ${MPI_CXX_COMPILE_OPTIONS}" )
		message( " MPI_CXX_COMPILE_DEFINITIONS = ${MPI_CXX_COMPILE_DEFINITIONS}" )

Documentation/Examples/Algorithms/CMakeLists.txt

+30 −51

Original line number	Diff line number	Diff line
		IF( BUILD_CUDA )
		CUDA_ADD_EXECUTABLE( SortingExampleCuda SortingExample.cu)
		ADD_CUSTOM_COMMAND( COMMAND SortingExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample.out OUTPUT SortingExample.out )

		CUDA_ADD_EXECUTABLE( SortingExample2Cuda SortingExample2.cu)
		ADD_CUSTOM_COMMAND( COMMAND SortingExample2Cuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample2.out OUTPUT SortingExample2.out )

		CUDA_ADD_EXECUTABLE( SortingExample3Cuda SortingExample3.cu)
		ADD_CUSTOM_COMMAND( COMMAND SortingExample3Cuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample3.out OUTPUT SortingExample3.out )

		CUDA_ADD_EXECUTABLE(ParallelForExampleCuda ParallelForExample.cu)
		ADD_CUSTOM_COMMAND( COMMAND ParallelForExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )
		ADD_SUBDIRECTORY( Segments )

		set( COMMON_EXAMPLES
		SortingExample
		SortingExample2
		SortingExample3
		ParallelForExample
		SequentialForExample
		)

		CUDA_ADD_EXECUTABLE(reduceArrayExampleCuda reduceArrayExample.cu)
		ADD_CUSTOM_COMMAND( COMMAND reduceArrayExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceArrayExample.out OUTPUT reduceArrayExample.out )
		set( HOST_EXAMPLES
		staticForExample
		unrolledForExample
		)
		if( BUILD_CUDA )
		foreach( target IN ITEMS ${COMMON_EXAMPLES} )
		cuda_add_executable( ${target}-cuda ${target}.cu OPTIONS )
		add_custom_command( COMMAND ${target}-cuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/${target}.out OUTPUT ${target}.out )
		set( CUDA_OUTPUTS ${CUDA_OUTPUTS} ${target}.out )
		endforeach()
		else()
		foreach( target IN ITEMS ${COMMON_EXAMPLES} ${HOST_EXAMPLES})
		add_executable( ${target} ${target}.cpp )
		add_custom_command( COMMAND ${target} > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/${target}.out OUTPUT ${target}.out )
		set( HOST_OUTPUTS ${HOST_OUTPUTS} ${target}.out )
		endforeach()
		endif()

		CUDA_ADD_EXECUTABLE(reduceWithArgumentArrayExampleCuda reduceWithArgumentArrayExample.cu)
		ADD_CUSTOM_COMMAND( COMMAND reduceWithArgumentArrayExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceWithArgumentArrayExample.out OUTPUT reduceWithArgumentArrayExample.out )
		IF( BUILD_CUDA )
		ADD_CUSTOM_TARGET( RunAlgorithmsExamples-cuda ALL DEPENDS ${CUDA_OUTPUTS} )
		ELSE()
		ADD_EXECUTABLE( SortingExample SortingExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND SortingExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample.out OUTPUT SortingExample.out )

		ADD_EXECUTABLE( SortingExample2 SortingExample2.cpp)
		ADD_CUSTOM_COMMAND( COMMAND SortingExample2 > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample2.out OUTPUT SortingExample2.out )

		ADD_EXECUTABLE( SortingExample3 SortingExample3.cpp)
		ADD_CUSTOM_COMMAND( COMMAND SortingExample3 > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/SortingExample3.out OUTPUT SortingExample3.out )

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

		ADD_EXECUTABLE(reduceArrayExample reduceArrayExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND reduceArrayExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceArrayExample.out OUTPUT reduceArrayExample.out )

		ADD_EXECUTABLE(reduceWithArgumentArrayExample reduceWithArgumentArrayExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND reduceWithArgumentArrayExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceWithArgumentArrayExample.out OUTPUT reduceWithArgumentArrayExample.out )
		ADD_CUSTOM_TARGET( RunAlgorithmsExamples ALL DEPENDS ${HOST_OUTPUTS} )
		ENDIF()
		No newline at end of file

		ADD_EXECUTABLE(staticForExample staticForExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND staticForExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/staticForExample.out OUTPUT staticForExample.out )

		ADD_EXECUTABLE(unrolledForExample unrolledForExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND unrolledForExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/unrolledForExample.out OUTPUT unrolledForExample.out )

		ADD_CUSTOM_TARGET( RunAlgorithmsExamples ALL DEPENDS
		SortingExample.out
		SortingExample2.out
		SortingExample3.out
		ParallelForExample.out
		reduceArrayExample.out
		reduceWithArgumentArrayExample.out
		unrolledForExample.out
		staticForExample.out
		)

Documentation/Examples/Algorithms/Segments/CMakeLists.txt

0 → 100644

+39 −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
		SegmentsExample_CSR_getSegmentsType
		SegmentsExample_CSR_setSegmentsSizes
		SegmentsExample_CSR_getSegmentView
		SegmentsExample_CSR_forElements
		SegmentsExample_CSR_forSegments
		SegmentsExample_CSR_sequentialForSegments
		SegmentsExample_CSR_reduceSegments
		SegmentsExample_forElements
		SegmentsExample_forSegments-1
		SegmentsExample_forSegments-2
		SegmentsExample_reduceSegments
		)

		if( BUILD_CUDA )
		foreach( target IN ITEMS ${COMMON_EXAMPLES} )
		cuda_add_executable( ${target}-cuda ${target}.cu OPTIONS )
		add_custom_command( COMMAND ${target}-cuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/${target}.out OUTPUT ${target}.out )
		set( CUDA_OUTPUTS ${CUDA_OUTPUTS} ${target}.out )
		endforeach()
		else()
		foreach( target IN ITEMS ${COMMON_EXAMPLES} )
		add_executable( ${target} ${target}.cpp )
		add_custom_command( COMMAND ${target} > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/${target}.out OUTPUT ${target}.out )
		set( HOST_OUTPUTS ${HOST_OUTPUTS} ${target}.out )
		endforeach()
		endif()

		IF( BUILD_CUDA )
		ADD_CUSTOM_TARGET( RunSegmentsExamples-cuda ALL DEPENDS ${CUDA_OUTPUTS} )
		ELSE()
		ADD_CUSTOM_TARGET( RunSegmentsExamples ALL DEPENDS ${HOST_OUTPUTS} )
		ENDIF()
		No newline at end of file

Documentation/Examples/Algorithms/Segments/SegmentsExample_CSR_constructor_1.cpp

0 → 100644

+51 −0

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

		template< typename Device >
		void SegmentsExample()
		{
		using SegmentsType = typename TNL::Algorithms::Segments::CSR< Device, int >;

		/***
		* Create segments with given segments sizes.
		*/
		TNL::Containers::Vector< int, Device > segmentsSizes{ 1, 2, 3, 4, 5 };
		SegmentsType segments( segmentsSizes );
		std::cout << "Segments sizes are: " << segments << std::endl;

		/***
		* 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();
		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.
		*/
		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::Devices::Host >();

		#ifdef HAVE_CUDA
		std::cout << "Example of CSR segments on CUDA GPU: " << std::endl;
		SegmentsExample< TNL::Devices::Cuda >();
		#endif
		return EXIT_SUCCESS;
		}

Documentation/Examples/Algorithms/Segments/SegmentsExample_CSR_constructor_1.cu

0 → 120000

+1 −0

Original line number	Diff line number	Diff line
		SegmentsExample_CSR_constructor_1.cpp
		No newline at end of file