#include <cudpp_plan.h>
Inherited by CUDPPCompactPlan, CUDPPScanPlan, CUDPPSegmentedScanPlan, CUDPPSortPlan, and CUDPPSparseMatrixVectorMultiplyPlan.
Public Member Functions | |
| CUDPPPlan (CUDPPConfiguration config, size_t numElements, size_t numRows, size_t rowPitch) | |
| Plan base class constructor. | |
Public Attributes | |
| CUDPPConfiguration | m_config |
| size_t | m_numElements |
| size_t | m_numRows |
| size_t | m_rowPitch |
CUDPPPlan and its subclasses provide the internal (i.e. not visible to the library user) infrastructure for planning algorithm execution. They own intermediate storage for CUDPP algorithms as well as, in some cases, information about optimal execution configuration for the present hardware.
| CUDPPPlan::CUDPPPlan | ( | CUDPPConfiguration | config, | |
| size_t | numElements, | |||
| size_t | numRows, | |||
| size_t | rowPitch | |||
| ) |
Plan base class constructor.
| [in] | config | The configuration struct specifying algorithm and options |
| [in] | numElements | The maximum number of elements to be processed |
| [in] | numRows | The number of rows (for 2D operations) to be processed |
| [in] | rowPitch | The pitch of the rows of input data, in elements |
For internal use only.
Options structure
| size_t CUDPPPlan::m_numElements |
For internal use only.
Maximum number of input elements
| size_t CUDPPPlan::m_numRows |
For internal use only.
Maximum number of input rows
Reimplemented in CUDPPSparseMatrixVectorMultiplyPlan.
| size_t CUDPPPlan::m_rowPitch |
For internal use only.
Pitch of input rows in elements
1.5.5