Merge branch 'JK/loops' into 'develop' (94531169) · Commits · TNL / tnl-dev

Documentation/Examples/Algorithms/CMakeLists.txt

+9 −7

Original line number	Diff line number	Diff line
		@@ -6,12 +6,14 @@ ELSE()
		ADD_CUSTOM_COMMAND( COMMAND ParallelForExample > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/ParallelForExample.out OUTPUT ParallelForExample.out )
		ENDIF()

		IF( BUILD_CUDA )
		ADD_CUSTOM_TARGET( RunAlgorithmsExamples-cuda ALL DEPENDS
		ParallelForExample.out
		)
		ELSE()
		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
		ParallelForExample.out
		unrolledForExample.out
		staticForExample.out
		)
		ENDIF()
		No newline at end of file

+6 −6

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <cstdlib>
		#include <TNL/Containers/Vector.h>
		#include <TNL/Algorithms/ParallelFor.h>

		@@ -13,10 +12,12 @@ void initMeshFunction( const int xSize,
		Vector< double, Device >& v,
		const double& c )
		{
		auto view = v1.getConstView();
		auto init = [=] __cuda_callable__ ( int i, int j, const int xSize, const double c ) mutable {
		view[ j * xSize + i ] = c; };
		ParallelFor2D< Device >::exec( 0, 0, xSize, ySize, init, xSize, c );
		auto view = v.getView();
		auto init = [=] __cuda_callable__ ( int i, int j ) mutable
		{
		view[ j * xSize + i ] = c;
		};
		ParallelFor2D< Device >::exec( 0, 0, xSize, ySize, init );
		}

		int main( int argc, char* argv[] )
		@@ -42,4 +43,3 @@ int main( int argc, char* argv[] )
		#endif
		return EXIT_SUCCESS;
		}

+7 −7

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <cstdlib>
		#include <TNL/Containers/Vector.h>
		#include <TNL/Algorithms/ParallelFor.h>

		@@ -14,16 +13,18 @@ void initMeshFunction( const int xSize,
		Vector< double, Device >& v,
		const double& c )
		{
		auto view = v1.getConstView();
		auto init = [=] __cuda_callable__ ( int i, int j, int k, const int xSize, const int ySize, const double c ) mutable {
		view[ ( k * ySize + j ) * xSize + i ] = c; };
		ParallelFor3D< Device >::exec( 0, 0, xSize, ySize, init, xSize, ySize, c );
		auto view = v.getView();
		auto init = [=] __cuda_callable__ ( int i, int j, int k ) mutable
		{
		view[ ( k * ySize + j ) * xSize + i ] = c;
		};
		ParallelFor3D< Device >::exec( 0, 0, 0, xSize, ySize, zSize, init );
		}

		int main( int argc, char* argv[] )
		{
		/***
		* Define dimensions of 2D mesh function.
		* Define dimensions of a 3D mesh function.
		*/
		const int xSize( 10 ), ySize( 10 ), zSize( 10 );
		const int size = xSize * ySize * zSize;
		@@ -43,4 +44,3 @@ int main( int argc, char* argv[] )
		#endif
		return EXIT_SUCCESS;
		}

+6 −6

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <cstdlib>
		#include <TNL/Containers/Vector.h>
		#include <TNL/Algorithms/ParallelFor.h>

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

		/****
		* Set all elements of the vector v to the constant c.
		@@ -14,10 +14,11 @@ void initVector( Vector< double, Device >& v,
		const double& c )
		{
		auto view = v.getView();
		auto init = [=] __cuda_callable__ ( int i, const double c ) mutable {
		view[ i ] = c; };

		Algorithms::ParallelFor< Device >::exec( 0, v.getSize(), init, c );
		auto init = [=] __cuda_callable__ ( int i ) mutable
		{
		view[ i ] = c;
		};
		ParallelFor< Device >::exec( 0, v.getSize(), init );
		}

		int main( int argc, char* argv[] )
		@@ -39,4 +40,3 @@ int main( int argc, char* argv[] )
		#endif
		return EXIT_SUCCESS;
		}

deleted100644 → 0

+0 −31

Original line number	Diff line number	Diff line
		#include <iostream>
		#include <cstdlib>
		#include <TNL/Containers/StaticVector.h>
		#include <TNL/Algorithms/TemplateStaticFor.h>

		using namespace TNL;
		using namespace TNL::Containers;

		const int Size( 5 );

		template< int I >
		struct LoopBody
		{
		static void exec( const StaticVector< Size, double >& v ) {
		std::cout << "v[ " << I << " ] = " << v[ I ] << std::endl;
		}
		};

		int main( int argc, char* argv[] )
		{
		/****
		* Initiate static vector
		*/
		StaticVector< Size, double > v{ 1.0, 2.0, 3.0, 4.0, 5.0 };

		/****
		* Print out the vector using template parameters for indexing.
		*/
		Algorithms::TemplateStaticFor< 0, Size, LoopBody >::exec( v );
		}