gemvgpu: gemvgpu

In yuanli22/RCUDA: GPU Enabled BLAS, LAPACK, Statistical Functions and Random Number Generators

Description

This function computes matrix-vector multipication y = a A x + b y by using CUDA cublas function cublasDgemv

Usage

gemvgpu(trans = 1, alpha = 1, A, x, beta = 0, y)

Arguments

trans	matrix A transpose operator, 1 (non-transpose), 2 (transpose), 3 (conjugate transpose); default at 1 (non-transpose)
alpha	scale factor a of matrix A; default 1
A	input matrix; list of R external GPU pointer and dimension
x	input vector; list of R external GPU pointer and dimension
beta	scale factor b of vector y; default 0
y	input/output vector; list of R external GPU pointer and dimension

Value

vector y, a list consisting of

• ptr: GPU pointer

• m: length of vector y

• n: 1

See Also

gergpu

Examples

A <- 1:12
x <- 1:3
y <- 1:4
A_gpu <- creategpu(A, 4, 3)
x_gpu <- creategpu(x)
y_gpu <- creategpu(y)
gemvgpu(trans = 1, alpha = 1, A_gpu, x_gpu, beta = 1, y_gpu)
gathergpu(y_gpu)

yuanli22/RCUDA documentation built on May 4, 2019, 6:35 p.m.