User Tools

Site Tools


dbcsr

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
dbcsr [2018/01/18 20:24]
oschuett moved from dbcsr.cp2k.org
dbcsr [2018/07/17 07:48] (current)
alazzaro
Line 1: Line 1:
-libDBCSR ​(or DBCSR for short) is a sparse matrix library designed to efficiently perform sparse matrix matrix multiplication,​ among other operations. It is MPI and OpenMP parallel, and can exploit accelerators. It is developed as part of [[ http://​www.cp2k.org/​ | CP2K ]], where it provides core functionality for [[ doi>​10.1021/​ct200897x | linear scaling electronic structure theory ]]. general overview of the library [[ doi>​10.1016/​j.parco.2014.03.012 | has been published ]]. A discussion of recent developments,​ in particular GPU work, [[ doi>​10.1002/​9781118670712.ch8 | has appeared as a chapter]] in '​Electronic Structure Calculations on Graphics Processing Units',​ John Wiley and Sons, ISBN 9781118661789,​ and is available as a [[ http://​dbcsr.cp2k.org/​_media/​gpu_book_chapter_submitted.pdf | preprint ]]. The use of one-sided MPI and a 2.5D algorithm to reduce communication is shown to be effective for sparse matrix matrix multiplication in [[https://​arxiv.org/​abs/​1705.10218 | this manuscript ]].+====== ​libDBCSR ​Sparse Matrix Library ======
  
-libDBCSR is made available for integration in other projects, the latest tarball (nightly update) can be downloaded here: +libDBCSR (or DBCSR for short) is a sparse matrix library designed to efficiently perform sparse matrix matrix multiplication,​ among other operations. It is MPI and OpenMP parallel, and can exploit accelerators. It is developed as part of [[ http://​www.cp2k.org/​ | CP2K ]], where it provides core functionality for [[ doi>​10.1021/​ct200897x | linear scaling electronic structure theory ]]. A general overview of the library [[ doi>​10.1016/​j.parco.2014.03.012 | has been published ]]. A discussion of recent developments,​ in particular GPU work, [[ doi>​10.1002/​9781118670712.ch8 | has appeared as a chapter]] in '​Electronic Structure Calculations on Graphics Processing Units',​ John Wiley and Sons, ISBN 9781118661789,​ and is available as a {{ :​gpu_book_chapter_submitted.pdf |preprint }}. The use of one-sided MPI and a 2.5D algorithm to reduce communication is shown to be effective for sparse matrix matrix multiplication in [[https://​arxiv.org/​abs/​1705.10218 | this manuscript ]]. 
-[[http://dbcsr.cp2k.org/downloads/​libdbcsr_latest.tgz|{{ :​download-big.png?​direct |Download the latest version}}]]+libDBCSR is made available for integration in other projects, ​see the [[https://​github.com/​cp2k/​dbcsr|github webpage]]. 
 + 
 +{{ :​dbcsr_logo.png?​nolink&​300 |}} 
 + 
 +<!--- 
 +the latest tarball (nightly update) can be downloaded here:) 
 +[[ https://www.cp2k.org/static/​dbcsr/​libdbcsr_latest.tgz|{{ :​download-big.png?​direct |Download the latest version}}]]
  
 A good overview of the provided functionality is provided by the API documentation:​ A good overview of the provided functionality is provided by the API documentation:​
Line 9: Line 15:
 As part of a [[ http://​www.pasc-ch.org/​ | PASC ]] project, we will refactor the code to provide a more streamlined API and further performance improvements. As part of a [[ http://​www.pasc-ch.org/​ | PASC ]] project, we will refactor the code to provide a more streamlined API and further performance improvements.
  
-Developments take place in the [[ http://​www.cp2k.org/​download | CP2K svn repository ]], where all version of the library can be found.+Developments take place in the [[ download | CP2K svn repository ]], where all version of the library can be found. 
 +-->
dbcsr.1516307050.txt.gz · Last modified: 2018/01/18 20:24 by oschuett