symmgpu: symmgpu

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

Description

This function computes the symmetric matrix-matrix multiplication C = a A B + b C by using CUDA cublas function cublasDsymm

Usage

symmgpu(sidemode = 1, fillmode = 1, alpha = 1, A, B, beta = 0, C)

Arguments

sidemode	indicates whether the given matrix is on the left or right side in the matrix equation solved by a particular function. If sidemode == 1, the matrix is on the left side in the equation If sidemode == 2, the matrix is on the right side in the equation.
fillmode	indicates if matrix A lower or upper part is stored, the other part is not referenced and is inferred from the stored elements. if fillmode == 1 then the triagular banded matrix A is stored column by column, with the main diagonal of the matrix stored in row 1, the first subdiagonal in row 2 (starting at first position), the second subdiagonal in row 3 (starting at first position), etc. if fillmode == 2 then the triangular banded matrix A is stored column by column, with the main diagonal of the matrix stored in row k+1, the first superdiagonal in row k (starting at second position), the second superdiagonal in row k-1 (starting at third position), etc.
alpha	scale factor a of matrix AB; default 1
A	input matrix; list of R external GPU pointer and dimension
B	input matrix; list of R external GPU pointer and dimension
beta	scale factor b of matrix C; default 0
C	input/output matrix; list of R external GPU pointer and dimension

Value

updated matrix C, a list consisting of

• ptr: GPU pointer

• m: matrix C's number of rows

• n: matrix C's number of columns

See Also

gemmgpu

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