hclhkbu / gcoospdm

Sparse-dense matrix-matrix multiplication on GPUs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

GCOOSpDM

Efficient sparse-dense matrix-matrix multiplication on GPUs using the customized sparse storage format

Quick Install

git clone https://github.com/hclhkbu/gcoospdm.git 
cd gcoospdm
git submodule update --init --recursive
cd src
make

Example

After sucessfully compiled, one can try the following example:

./main -sparsity=0.900000 -nRowsA=800 -nRowsB=800 -nColsA=800 -nColsB=800 -algo=gcoospdm

About

Sparse-dense matrix-matrix multiplication on GPUs

License:MIT License


Languages

Language:Python 40.0%Language:Cuda 23.7%Language:C++ 21.5%Language:Makefile 8.9%Language:Shell 5.2%Language:C 0.6%Language:Perl 6 0.1%