Cargando…

Parallelizing TTree::Draw functionality with PROOF

In ROOT, the software context of this project, multi-threading is not currently an easy option, because ROOT is not by construction thread-aware and thread-safeness can only be achieved with heavy locking. Therefore, for a ROOT task, multi-processing is currently the most eective way to achieve cunc...

Descripción completa

Detalles Bibliográficos
Autor principal: Marinaci, Stefano
Lenguaje:eng
Publicado: 2014
Materias:
Acceso en línea:http://cds.cern.ch/record/1756818
_version_ 1780943353740787712
author Marinaci, Stefano
author_facet Marinaci, Stefano
author_sort Marinaci, Stefano
collection CERN
description In ROOT, the software context of this project, multi-threading is not currently an easy option, because ROOT is not by construction thread-aware and thread-safeness can only be achieved with heavy locking. Therefore, for a ROOT task, multi-processing is currently the most eective way to achieve cuncurrency. Multi-processing in ROOT is done via PROOF. PROOF is used to enable interactive analysis of large sets of ROOT les in parallel on clusters of computers or many-core machines. More generally PROOF can parallelize tasks that can be formulated as a set of independent sub-tasks. The PROOF technology is rather ecient to exploit all the CPU's provided by many-core processors. A dedicated version of PROOF, PROOF-Lite, provides an out-of-the-box solution to take full advantage of the additional cores available in today desktops or laptops. One of the items on the PROOF plan of work is to improve the inte- gration of PROOF-Lite for local processing of ROOT trees. In this project we investigate the case of the Draw functionality and its implementation via PROOF.
id cern-1756818
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2014
record_format invenio
spelling cern-17568182019-09-30T06:29:59Zhttp://cds.cern.ch/record/1756818engMarinaci, StefanoParallelizing TTree::Draw functionality with PROOFComputing and ComputersIn ROOT, the software context of this project, multi-threading is not currently an easy option, because ROOT is not by construction thread-aware and thread-safeness can only be achieved with heavy locking. Therefore, for a ROOT task, multi-processing is currently the most eective way to achieve cuncurrency. Multi-processing in ROOT is done via PROOF. PROOF is used to enable interactive analysis of large sets of ROOT les in parallel on clusters of computers or many-core machines. More generally PROOF can parallelize tasks that can be formulated as a set of independent sub-tasks. The PROOF technology is rather ecient to exploit all the CPU's provided by many-core processors. A dedicated version of PROOF, PROOF-Lite, provides an out-of-the-box solution to take full advantage of the additional cores available in today desktops or laptops. One of the items on the PROOF plan of work is to improve the inte- gration of PROOF-Lite for local processing of ROOT trees. In this project we investigate the case of the Draw functionality and its implementation via PROOF.CERN-STUDENTS-Note-2014-205oai:cds.cern.ch:17568182014-09-19
spellingShingle Computing and Computers
Marinaci, Stefano
Parallelizing TTree::Draw functionality with PROOF
title Parallelizing TTree::Draw functionality with PROOF
title_full Parallelizing TTree::Draw functionality with PROOF
title_fullStr Parallelizing TTree::Draw functionality with PROOF
title_full_unstemmed Parallelizing TTree::Draw functionality with PROOF
title_short Parallelizing TTree::Draw functionality with PROOF
title_sort parallelizing ttree::draw functionality with proof
topic Computing and Computers
url http://cds.cern.ch/record/1756818
work_keys_str_mv AT marinacistefano parallelizingttreedrawfunctionalitywithproof