Home

Awesome

DBCSR: Distributed Block Compressed Sparse Row matrix library

Build Status Linux Build Status MacOS Build Status Latest GCC

codecov Licence GitHub Releases

DBCSR is a library designed to efficiently perform sparse matrix-matrix multiplication, among other operations. It is MPI and OpenMP parallel and can exploit Nvidia and AMD GPUs via CUDA and HIP.

<p align="center"> <img src="docs/media/logo/logo.png" width="500"> </p>

How to Install

Follow the installation guide.

Documentation

Documentation is available online for the latest release.

How to Cite

To cite DBCSR, use the following paper

@article{dbcsr,
	title = {{Sparse Matrix Multiplication: The Distributed Block-Compressed Sparse Row Library}},
	journal = {Parallel Computing},
	volume = {40},
	number = {5-6},
	year = {2014},
	issn = {0167-8191},
	author = {Urban Borstnik and Joost VandeVondele and Valery Weber and Juerg Hutter}
}

To cite the DBCSR software library, use:

@misc{dbcsr-software,
	author = {The CP2K Developers Group},
	title = {{DBCSR: Distributed Block Compressed Sparse Row matrix library}},
	publisher = {GitHub},
	journal = {GitHub repository},
	year = {2022},
	url = {https://github.com/cp2k/dbcsr}
}

Contributing to DBCSR

Your contribution to the project is welcome! Please see DBCSR's contribution guidelines and this wiki page. For any help, please notify the other developers.