Merge branch 'TO/sorting' into 'develop' (d37bcd8c) · Commits · TNL / tnl-dev

CMakeLists.txt

+5 −0

Original line number	Diff line number	Diff line
		@@ -32,6 +32,7 @@ option(BUILD_TESTS "Build tests" OFF)
		option(BUILD_MATRIX_TESTS "Build tests for matrix formats" OFF)
		option(BUILD_PYTHON "Compile the Python bindings" OFF)
		option(BUILD_DOC "Build examples included in the documentation" OFF)
		set(CUDA_SAMPLES_PATH "none" CACHE STRING "Path to CUDA Samples - it is used only for some benchmarking.")

		# install paths relative to the cmake's prefix
		set( TNL_TARGET_INCLUDE_DIRECTORY "include/TNL" )
		@@ -253,6 +254,9 @@ if( ${WITH_CUDA} )
		endif()
		set( CMAKE_EXECUTABLE_SUFFIX "${executable_suffix_backup}" )
		endif()
		if( NOT CUDA_SAMPLES_DIR STREQUAL "none" )
		set( CUDA_SAMPLES_FLAGS "-I${CUDA_SAMPLES_DIR} -DHAVE_CUDA_SAMPLES")
		endif()
		endif()


		@@ -407,6 +411,7 @@ message( " CMAKE_SHARED_LINKER_FLAGS = ${CMAKE_SHARED_LINKER_FLAGS}" )
		message( " CMAKE_SHARED_LINKER_FLAGS_DEBUG = ${CMAKE_SHARED_LINKER_FLAGS_DEBUG}" )
		message( " CMAKE_SHARED_LINKER_FLAGS_RELEASE = ${CMAKE_SHARED_LINKER_FLAGS_RELEASE}" )
		message( " CUDA_NVCC_FLAGS = ${CUDA_NVCC_FLAGS}" )
		message( " CUDA_SAMPLES_FLAGS = ${CUDA_SAMPLES_FLAGS}" )
		message( " GMP_LIBRARIES = ${GMP_LIBRARIES}" )
		if( MPI_CXX_FOUND AND ${WITH_MPI} )
		message( " MPI_CXX_COMPILE_OPTIONS = ${MPI_CXX_COMPILE_OPTIONS}" )

Documentation/Examples/Algorithms/CMakeLists.txt

+15 −0

Original line number	Diff line number	Diff line
		IF( BUILD_CUDA )
		CUDA_ADD_EXECUTABLE(ParallelForExampleCuda ParallelForExample.cu)
		ADD_CUSTOM_COMMAND( COMMAND ParallelForExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )
		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 )
		ELSE()
		ADD_EXECUTABLE(ParallelForExample ParallelForExample.cpp)
		ADD_CUSTOM_COMMAND( COMMAND ParallelForExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )
		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 )
		ENDIF()

		ADD_EXECUTABLE(staticForExample staticForExample.cpp)
		@@ -13,6 +25,9 @@ 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
		unrolledForExample.out
		staticForExample.out

Documentation/Examples/Algorithms/SortingExample.cpp

0 → 100644

+55 −0

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <TNL/Containers/Array.h>
		#include <TNL/Algorithms/sort.h>

		using namespace TNL;
		using namespace TNL::Containers;
		using namespace TNL::Algorithms;

		template< typename ArrayT >
		void sort( ArrayT& array )
		{
		const int size = 10;

		/****
		* Fill the array with random integers.
		*/
		Array< int > aux_array( size );
		srand( size + 2021 );
		aux_array.forAllElements( [=] __cuda_callable__ ( int i, int& value ) { value = std::rand() % (2*size); } );
		array = aux_array;

		std::cout << "Random array: " << array << std::endl;

		/****
		* Sort the array in ascending order.
		*/
		ascendingSort( array );
		std::cout << "Array sorted in ascending order:" << array << std::endl;

		/***
		* Sort the array in descending order.
		*/
		descendingSort( array );
		std::cout << "Array sorted in descending order:" << array << std::endl;
		}

		int main( int argc, char* argv[] )
		{
		/***
		* Firstly, test the sorting on CPU.
		*/
		std::cout << "Sorting on CPU ... " << std::endl;
		Array< int, Devices::Host > host_array;
		sort( host_array );

		#ifdef HAVE_CUDA
		/***
		* And then also on GPU.
		*/
		std::cout << "Sorting on GPU ... " << std::endl;
		Array< int, Devices::Cuda > cuda_array;
		sort( cuda_array );
		#endif
		return EXIT_SUCCESS;
		}

Documentation/Examples/Algorithms/SortingExample.cu

0 → 120000

+1 −0

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

Documentation/Examples/Algorithms/SortingExample2.cpp

0 → 100644

+55 −0

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <TNL/Containers/Array.h>
		#include <TNL/Algorithms/sort.h>

		using namespace TNL;
		using namespace TNL::Containers;
		using namespace TNL::Algorithms;

		template< typename ArrayT >
		void sort( ArrayT& array )
		{
		const int size = 10;

		/****
		* Fill the array with random integers.
		*/
		Array< int > aux_array( size );
		srand( size + 2021 );
		aux_array.forAllElements( [=] __cuda_callable__ ( int i, int& value ) { value = std::rand() % (2*size); } );
		array = aux_array;

		std::cout << "Random array: " << array << std::endl;

		/****
		* Sort the array in ascending order.
		*/
		sort( array, [] __cuda_callable__ ( int a, int b ) { return a < b; } );
		std::cout << "Array sorted in ascending order:" << array << std::endl;

		/***
		* Sort the array in descending order.
		*/
		sort( array, [] __cuda_callable__ ( int a, int b ) { return a > b; } );
		std::cout << "Array sorted in descending order:" << array << std::endl;
		}

		int main( int argc, char* argv[] )
		{
		/***
		* Firstly, test the sorting on CPU.
		*/
		std::cout << "Sorting on CPU ... " << std::endl;
		Array< int, Devices::Host > host_array;
		sort( host_array );

		#ifdef HAVE_CUDA
		/***
		* And then also on GPU.
		*/
		std::cout << "Sorting on GPU ... " << std::endl;
		Array< int, Devices::Cuda > cuda_array;
		sort( cuda_array );
		#endif
		return EXIT_SUCCESS;
		}