TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ > Class Template Reference

SortedSegmentsBase serves as a base class for TNL::Algorithms::Segments::SortedSegments and TNL::Algorithms::Segments::SortedSegmentsView. More...

#include <TNL/Algorithms/Segments/SortedSegmentsBase.h>

Inheritance diagram for TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >:

Collaboration diagram for TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >:

Public Types
using	ConstPermutationView = typename Containers::VectorView< std::add_const_t< IndexType >, DeviceType, IndexType >
using	DeviceType = typename EmbeddedSegmentsView::DeviceType
	The device where the segments are operating.
using	EmbeddedSegmentsConstView = typename EmbeddedSegmentsView::ConstViewType
using	EmbeddedSegmentsView = EmbeddedSegmentsView_
using	IndexType = typename EmbeddedSegmentsView::IndexType
	The type used for indexing of segments elements.
using	PermutationView = typename Containers::VectorView< IndexType, DeviceType, IndexType >
using	SegmentViewType = typename EmbeddedSegmentsView::SegmentViewType
	Accessor type for one particular segment.

Public Member Functions
__cuda_callable__	SortedSegmentsBase ()=default
	Default constructor with no parameters to create empty segments view.
__cuda_callable__	SortedSegmentsBase (const SortedSegmentsBase &)=default
	Copy constructor.
__cuda_callable__	SortedSegmentsBase (SortedSegmentsBase &&) noexcept=default
	Move constructor.
__cuda_callable__ IndexType	getElementCount () const
	Returns the number of elements managed by all segments.
__cuda_callable__ EmbeddedSegmentsView	getEmbeddedSegmentsView ()
__cuda_callable__ EmbeddedSegmentsConstView	getEmbeddedSegmentsView () const
__cuda_callable__ IndexType	getGlobalIndex (IndexType segmentIdx, IndexType localIdx) const
	Computes the global index of an element managed by the segments.
__cuda_callable__ PermutationView	getInverseSegmentsPermutationView ()
	Returns a modifiable vector view with inverse segments permutation.
__cuda_callable__ ConstPermutationView	getInverseSegmentsPermutationView () const
	Returns a constant vector view with inverse segments permutation..
__cuda_callable__ IndexType	getSegmentCount () const
	Returns the number of segments.
__cuda_callable__ IndexType	getSegmentsCount () const
	Returns the number of segments. Deprecated, use getSegmentCount().
__cuda_callable__ IndexType	getSegmentSize (IndexType segmentIdx) const
	Returns the size of a particular segment denoted by segmentIdx.
__cuda_callable__ PermutationView	getSegmentsPermutationView ()
	Returns a modifiable vector view with segments permutation.
__cuda_callable__ ConstPermutationView	getSegmentsPermutationView () const
	Returns a constant vector view with segments permutation..
__cuda_callable__ SegmentViewType	getSegmentView (IndexType segmentIdx) const
	Returns a segment view (i.e., a segment accessor) for the specified segment index.
__cuda_callable__ IndexType	getSigma () const
	Gets the value of sigma.
__cuda_callable__ IndexType	getSize () const
	Returns the number of elements managed by all segments.
__cuda_callable__ IndexType	getStorageSize () const
	Returns number of elements that needs to be allocated by a container connected to this segments.
SortedSegmentsBase &	operator= (const SortedSegmentsBase &)=delete
	Copy-assignment operator.
SortedSegmentsBase &	operator= (SortedSegmentsBase &&)=delete
	Move-assignment operator.
__cuda_callable__ void	setSigma (IndexType value)
	Sets the value of sigma.

Static Public Member Functions
static constexpr ElementsOrganization	getOrganization ()
	Returns the data layout (it is always row-major order).
static std::string	getSegmentsType ()
	Returns string with the segments type.
static std::string	getSerializationType ()
	Returns string with the serialization type.
static constexpr bool	havePadding ()
	This function denotes if the underlying segments use the padding elements.

Protected Member Functions
__cuda_callable__ void	bind (const EmbeddedSegmentsView &embeddedSegmentsView, const PermutationView &segmentsPermutation, const PermutationView &inverseSegmentsPermutation)
	Re-initializes the internal attributes of the base class.

Protected Attributes
EmbeddedSegmentsView	embeddedSegmentsView
PermutationView	inverseSegmentsPermutationView
PermutationView	segmentsPermutationView
	Vector view with the segments permutation.
IndexType	sigma = -1

Detailed Description

template<typename EmbeddedSegmentsView_>
class TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >

SortedSegmentsBase serves as a base class for TNL::Algorithms::Segments::SortedSegments and TNL::Algorithms::Segments::SortedSegmentsView.

The sorted segments are inspired by SELL-C-sigma sparse matrix storage format:

Kreutzer, Moritz, et al. "A unified sparse matrix data format for efficient general sparse matrix-vector multiplication on modern processors with wide SIMD units." SIAM Journal on Scientific Computing 36.5 (2014): C401-C423.

Template Parameters

EmbeddedSegments

is a type of segments used to manage the data.

Member Function Documentation

bind()

template<typename EmbeddedSegmentsView_>

__cuda_callable__ void TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >::bind ( const EmbeddedSegmentsView & embeddedSegmentsView, const PermutationView & segmentsPermutation, const PermutationView & inverseSegmentsPermutation )

protected

Re-initializes the internal attributes of the base class.

Note that this function is protected to ensure that the user cannot modify the base class of segments. For the same reason, in future code development we also need to make sure that all non-const functions in the base class return by value and not by reference.

getGlobalIndex()

template<typename EmbeddedSegmentsView_>

__cuda_callable__ IndexType TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >::getGlobalIndex ( IndexType segmentIdx, IndexType localIdx ) const

nodiscard

Computes the global index of an element managed by the segments.

The global index serves as a reference to the element within its container.

Parameters

segmentIdx	The index of the segment containing the element.
localIdx	The local index of the element within the segment.

Returns

The global index of the element.

getSegmentsType()

template<typename EmbeddedSegmentsView_>

std::string TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >::getSegmentsType ( )

staticnodiscard

Returns string with the segments type.

Example

#include <iostream>
#include <functional>
#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()
{
   /***
    * Create segments and print the segments type.
    */
   Segments segments;
   std::cout << "The segments type is: " << segments.getSegmentsType() << '\n';
}
 
int
main( int argc, char* argv[] )
{
   std::cout << "Example of CSR segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Host, int > >();
 
   std::cout << "Example of Ellpack segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Host, int > >();
 
#ifdef __CUDACC__
   std::cout << "Example of CSR segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Cuda, int > >();
 
   std::cout << "Example of Ellpack segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Cuda, int > >();
#endif
   return EXIT_SUCCESS;
}

Output

Example of CSR segments on host:
The segments type is: CSR
Example of Ellpack segments on host:
The segments type is: Ellpack
Example of CSR segments on CUDA GPU:
The segments type is: CSR
Example of Ellpack segments on CUDA GPU:
The segments type is: Ellpack

getSegmentView()

template<typename EmbeddedSegmentsView_>

__cuda_callable__ SegmentViewType TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >::getSegmentView ( IndexType segmentIdx ) const

nodiscard

Returns a segment view (i.e., a segment accessor) for the specified segment index.

Parameters

segmentIdx

The index of the requested segment.

Returns

The segment view of the specified segment.

Example

#include <iostream>
#include <TNL/Containers/Vector.h>
#include <TNL/Algorithms/Segments/CSR.h>
#include <TNL/Algorithms/Segments/Ellpack.h>
#include <TNL/Algorithms/SequentialFor.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.
    */
   const int size( 5 );
   Segments segments{ 1, 2, 3, 4, 5 };
   auto view = segments.getView();
 
   /***
    * Print the elements mapping using segment view.
    */
   std::cout << "Mapping of local indexes to global indexes:\n";
 
   auto f = [ = ] __cuda_callable__( int segmentIdx )
   {
      printf( "Segment idx. %d: ", segmentIdx );  // printf works even in GPU kernels
      auto segment = view.getSegmentView( segmentIdx );
      for( auto element : segment )
         printf( "%d -> %d \t", element.localIndex(), element.globalIndex() );
      printf( "\n" );
   };
   TNL::Algorithms::SequentialFor< Device >::exec( 0, size, f );
}
 
int
main( int argc, char* argv[] )
{
   std::cout << "Example of CSR segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Host, int > >();
 
   std::cout << "Example of Ellpack segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Host, int > >();
 
#ifdef __CUDACC__
   std::cout << "Example of CSR segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Cuda, int > >();
 
   std::cout << "Example of Ellpack segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Cuda, int > >();
#endif
   return EXIT_SUCCESS;
}

Output

Example of CSR segments on host:
Mapping of local indexes to global indexes:
Segment idx. 0: 0 -> 0  
Segment idx. 1: 0 -> 1  1 -> 2  
Segment idx. 2: 0 -> 3  1 -> 4  2 -> 5  
Segment idx. 3: 0 -> 6  1 -> 7  2 -> 8  3 -> 9  
Segment idx. 4: 0 -> 10     1 -> 11     2 -> 12     3 -> 13     4 -> 14     
Example of Ellpack segments on host:
Mapping of local indexes to global indexes:
Segment idx. 0: 0 -> 0  1 -> 1  2 -> 2  3 -> 3  4 -> 4  
Segment idx. 1: 0 -> 5  1 -> 6  2 -> 7  3 -> 8  4 -> 9  
Segment idx. 2: 0 -> 10     1 -> 11     2 -> 12     3 -> 13     4 -> 14     
Segment idx. 3: 0 -> 15     1 -> 16     2 -> 17     3 -> 18     4 -> 19     
Segment idx. 4: 0 -> 20     1 -> 21     2 -> 22     3 -> 23     4 -> 24     
Example of CSR segments on CUDA GPU:
Mapping of local indexes to global indexes:
Segment idx. 0: 0 -> 0  
Segment idx. 1: 0 -> 1  1 -> 2  
Segment idx. 2: 0 -> 3  1 -> 4  2 -> 5  
Segment idx. 3: 0 -> 6  1 -> 7  2 -> 8  3 -> 9  
Segment idx. 4: 0 -> 10     1 -> 11     2 -> 12     3 -> 13     4 -> 14     
Example of Ellpack segments on CUDA GPU:
Mapping of local indexes to global indexes:
Segment idx. 0: 0 -> 0  1 -> 32     2 -> 64     3 -> 96     4 -> 128    
Segment idx. 1: 0 -> 1  1 -> 33     2 -> 65     3 -> 97     4 -> 129    
Segment idx. 2: 0 -> 2  1 -> 34     2 -> 66     3 -> 98     4 -> 130    
Segment idx. 3: 0 -> 3  1 -> 35     2 -> 67     3 -> 99     4 -> 131    
Segment idx. 4: 0 -> 4  1 -> 36     2 -> 68     3 -> 100    4 -> 132    

getSerializationType()

template<typename EmbeddedSegmentsView_>

std::string TNL::Algorithms::Segments::SortedSegmentsBase< EmbeddedSegmentsView_ >::getSerializationType ( )

staticnodiscard

Returns string with the serialization type.

Example

#include <iostream>
#include <functional>
#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()
{
   /***
    * Create segments and print the serialization type.
    */
   Segments segments;
   std::cout << "The serialization type is: " << segments.getSerializationType() << '\n';
}
 
int
main( int argc, char* argv[] )
{
   std::cout << "Example of CSR segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Host, int > >();
 
   std::cout << "Example of Ellpack segments on host:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Host, int > >();
 
#ifdef __CUDACC__
   std::cout << "Example of CSR segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::CSR< TNL::Devices::Cuda, int > >();
 
   std::cout << "Example of Ellpack segments on CUDA GPU:\n";
   SegmentsExample< TNL::Algorithms::Segments::Ellpack< TNL::Devices::Cuda, int > >();
#endif
   return EXIT_SUCCESS;
}

Output

Example of CSR segments on host:
The serialization type is: CSR< int >
Example of Ellpack segments on host:
The serialization type is: Ellpack< int, RowMajorOrder, 32 >
Example of CSR segments on CUDA GPU:
The serialization type is: CSR< int >
Example of Ellpack segments on CUDA GPU:
The serialization type is: Ellpack< int, ColumnMajorOrder, 32 >

---

The documentation for this class was generated from the following file:

• src/TNL/Algorithms/Segments/SortedSegmentsBase.h