diff --git a/Documentation/Examples/Algorithms/CMakeLists.txt b/Documentation/Examples/Algorithms/CMakeLists.txt
index 8afdc50cc9771126ecbebe1f64c57d3aa1fd1807..c200642f526cb84e06601b1c0a57c823cc885102 100644
--- a/Documentation/Examples/Algorithms/CMakeLists.txt
+++ b/Documentation/Examples/Algorithms/CMakeLists.txt
@@ -1,56 +1,35 @@
ADD_SUBDIRECTORY( Segments )
-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 )
-
- CUDA_ADD_EXECUTABLE(reduceArrayExampleCuda reduceArrayExample.cu)
- ADD_CUSTOM_COMMAND( COMMAND reduceArrayExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceArrayExample.out OUTPUT reduceArrayExample.out )
-
- CUDA_ADD_EXECUTABLE(reduceWithArgumentArrayExampleCuda reduceWithArgumentArrayExample.cu)
- ADD_CUSTOM_COMMAND( COMMAND reduceWithArgumentArrayExampleCuda > ${TNL_DOCUMENTATION_OUTPUT_SNIPPETS_PATH}/reduceWithArgumentArrayExample.out OUTPUT reduceWithArgumentArrayExample.out )
-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 )
-ENDIF()
-
-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
+set( COMMON_EXAMPLES
+ SortingExample
+ SortingExample2
+ SortingExample3
+ ParallelForExample
+ SequentialForExample
unrolledForExample.out
staticForExample.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()
+
+IF( BUILD_CUDA )
+ ADD_CUSTOM_TARGET( RunAlgorithmsExamples-cuda ALL DEPENDS ${CUDA_OUTPUTS} )
+ELSE()
+ ADD_CUSTOM_TARGET( RunAlgorithmsExamples ALL DEPENDS ${HOST_OUTPUTS} )
+ENDIF()
\ No newline at end of file
diff --git a/Documentation/Examples/Algorithms/SequentialForExample.cpp b/Documentation/Examples/Algorithms/SequentialForExample.cpp
new file mode 100644
index 0000000000000000000000000000000000000000..d127a33a973f6c7ab9482680dd70bd6c321b7999
--- /dev/null
+++ b/Documentation/Examples/Algorithms/SequentialForExample.cpp
@@ -0,0 +1,37 @@
+#include <iostream>
+#include <cstdlib>
+#include <TNL/Containers/Vector.h>
+#include <TNL/Algorithms/ParallelFor.h>
+#include <TNL/Algorithms/SequentialFor.h>
+
+using namespace TNL;
+using namespace TNL::Containers;
+
+template< typename Device >
+void printVector()
+{
+ const int size( 36 );
+ TNL::Containers::Vector< float, Device > v( size, 1.0 );
+ auto view = v.getView();
+ auto print = [=] __cuda_callable__ ( int i ) mutable {
+ printf( "v[ %d ] = %f \n", i, view[ i ] ); // we use printf because of compatibility with GPU kernels
+ };
+ std::cout << "Printing vector using parallel for: " << std::endl;
+ Algorithms::ParallelFor< Device >::exec( 0, v.getSize(), print );
+
+ std::cout << "Printing vector using sequential for: " << std::endl;
+ Algorithms::SequentialFor< Device >::exec( 0, v.getSize(), print );
+}
+
+int main( int argc, char* argv[] )
+{
+ std::cout << "Example on the host:" << std::endl;
+ printVector< TNL::Devices::Host >();
+
+#ifdef HAVE_CUDA
+ std::cout << "Example on CUDA GPU:" << std::endl;
+ printVector< TNL::Devices::Cuda >();
+#endif
+ return EXIT_SUCCESS;
+}
+
diff --git a/Documentation/Examples/Algorithms/SequentialForExample.cu b/Documentation/Examples/Algorithms/SequentialForExample.cu
new file mode 120000
index 0000000000000000000000000000000000000000..ac78b379b6e3ed91150ba91d3c7c465a41f70501
--- /dev/null
+++ b/Documentation/Examples/Algorithms/SequentialForExample.cu
@@ -0,0 +1 @@
+SequentialForExample.cpp
\ No newline at end of file
diff --git a/src/TNL/Algorithms/SequentialFor.h b/src/TNL/Algorithms/SequentialFor.h
new file mode 100644
index 0000000000000000000000000000000000000000..ea783ca33dbfb875c15b55be12fe3c0aa2480c0e
--- /dev/null
+++ b/src/TNL/Algorithms/SequentialFor.h
@@ -0,0 +1,54 @@
+/***************************************************************************
+ SequentialFor.h - description
+ -------------------
+ begin : Apr 5, 2021
+ copyright : (C) 2021 by Tomas Oberhuber et al.
+ email : tomas.oberhuber@fjfi.cvut.cz
+ ***************************************************************************/
+
+/* See Copyright Notice in tnl/Copyright */
+
+#pragma once
+
+#include <TNL/Algorithms/ParallelFor.h>
+
+
+namespace TNL {
+ namespace Algorithms {
+
+/**
+ * \brief Wrapper to ParallelFor which makes it run sequentially.
+ *
+ * It is helpfull for debuging or just sequential for loops on GPUs.
+ */
+template< typename Device = Devices::Sequential >
+struct SequentialFor
+{
+ /**
+ * \brief Static method for execution of the loop.
+ *
+ * \tparam Index defines the type of indexes over which the loop iterates.
+ * \tparam Function is the type of function to be called in each iteration.
+ *
+ * \param start the for-loop iterates over index interval [start, end).
+ * \param end the for-loop iterates over index interval [start, end).
+ * \param f is the function to be called in each iteration
+ *
+ * \par Example
+ * \include Algorithms/SequentialForExample.cpp
+ * \par Output
+ * \include SequentialForExample.out
+ *
+ */
+ template< typename Index,
+ typename Function >
+ static void exec( Index start, Index end, Function f )
+ {
+ for( Index i = start; i < end; i++ )
+ ParallelFor< Device >::exec( i, i + 1, f );
+ }
+};
+
+
+ } // namespace Algorithms
+} // namespace TNL
\ No newline at end of file