LAMA
lama::CUDADIAUtils Class Reference

This class provides CUDA parallelized routines needed for DIA format. More...

#include <CUDADIAUtils.hpp>

Static Public Member Functions

template<typename ValueType >
static void normalGEMV (ValueType result[], const ValueType alpha, const ValueType x[], const ValueType beta, const ValueType y[], const IndexType numRows, const IndexType numColumns, const IndexType numDiagonals, const IndexType diaOffsets[], const ValueType diaValues[], class SyncToken *syncToken)
 Implementation for DIAUtilsInterface::Mult:normalGEMV with CUDA on GPUs.
static void setInterface (struct DIAUtilsInterface &DIAUtils)
 Routine that registers all routines of this class at the LAMA interface.

Private Member Functions

 LAMA_LOG_DECL_STATIC_LOGGER (logger)

Detailed Description

This class provides CUDA parallelized routines needed for DIA format.


Member Function Documentation

template<typename ValueType >
static void lama::CUDADIAUtils::normalGEMV ( ValueType  result[],
const ValueType  alpha,
const ValueType  x[],
const ValueType  beta,
const ValueType  y[],
const IndexType  numRows,
const IndexType  numColumns,
const IndexType  numDiagonals,
const IndexType  diaOffsets[],
const ValueType  diaValues[],
class SyncToken syncToken 
) [static]

Implementation for DIAUtilsInterface::Mult:normalGEMV with CUDA on GPUs.

static void lama::CUDADIAUtils::setInterface ( struct DIAUtilsInterface DIAUtils) [static]

Routine that registers all routines of this class at the LAMA interface.

Referenced by lama::CUDAInterface::CUDAInterface().


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