dg::exblas::gpu Namespace Reference

gpu (CUDA) versions of primitive functions More...

Functions
__device__ void	Accumulate (int64_t *accumulator, double x, int stride=1)
	Accumulate a double to the superaccumulator (GPU version)
__device__ int	Normalize (int64_t *accumulator, int &imin, int &imax, int stride=1)
	Normalize a superaccumulator (GPU version)
__device__ double	Round (int64_t *accumulator)
	Convert a superaccumulator to the nearest double precision number (GPU version)

Detailed Description

gpu (CUDA) versions of primitive functions

Function Documentation

Accumulate()

__device__ void dg::exblas::gpu::Accumulate ( int64_t * accumulator, double x, int stride = 1 )

inline

Accumulate a double to the superaccumulator (GPU version)

Parameters

accumulator	a pointer to at least BIN_COUNT 64 bit integers on the GPU (representing the superaccumulator)
x	the double to add to the superaccumulator
stride	stride in which accumulator is to be accessed

Normalize()

__device__ int dg::exblas::gpu::Normalize ( int64_t * accumulator, int & imin, int & imax, int stride = 1 )

inline

Normalize a superaccumulator (GPU version)

Parameters

accumulator	a pointer to at least BIN_COUNT 64 bit integers on the GPU (representing the superaccumulator)
imin	the first index in the accumulator
imax	the last index in the accumulator
stride	strid in which the superaccumulator is accessed

Returns

carry in bit (sign)

Round()

__device__ double dg::exblas::gpu::Round ( int64_t * accumulator )

inline

Convert a superaccumulator to the nearest double precision number (GPU version)

Parameters

accumulator

a pointer to at least BIN_COUNT 64 bit integers on the GPU (representing the superaccumulator)

Returns

the double precision number nearest to the superaccumulator