A database for on-line event analysis on a distributed memory machine

Parallel in-memory databases can enhance the structuring and parallelization of programs used in High Energy Physics (HEP). Efficient database access routines are used as communication primitives which hide the communication topology in contrast to the more explicit communications like PVM or MPI. A...

Descripción completa

Detalles Bibliográficos
Autores principales: Argante, E, Meesters, M R J, Van der Stok, P D V, Willers, Ian Malcolm
Lenguaje:eng
Publicado: 1995
Materias:
Detectors and Experimental Techniques
Acceso en línea:http://cds.cern.ch/record/294828
_version_ 1780888882340954112
author Argante, E
Meesters, M R J
Van der Stok, P D V
Willers, Ian Malcolm
author_facet Argante, E
Meesters, M R J
Van der Stok, P D V
Willers, Ian Malcolm
author_sort Argante, E
collection CERN
description Parallel in-memory databases can enhance the structuring and parallelization of programs used in High Energy Physics (HEP). Efficient database access routines are used as communication primitives which hide the communication topology in contrast to the more explicit communications like PVM or MPI. A parallel in-memory database, called SPIDER, has been implemented on a 32 node Meiko CS-2 distributed memory machine. The spider primitives generate a lower overhead than the one generated by PVM or PMI. The event reconstruction program, CPREAD of the CPLEAR experiment, has been used as a test case. Performance measurerate generated by CPLEAR.
id cern-294828
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 1995
record_format invenio
spelling cern-2948282019-09-30T06:29:59Zhttp://cds.cern.ch/record/294828engArgante, EMeesters, M R JVan der Stok, P D VWillers, Ian MalcolmA database for on-line event analysis on a distributed memory machineDetectors and Experimental TechniquesParallel in-memory databases can enhance the structuring and parallelization of programs used in High Energy Physics (HEP). Efficient database access routines are used as communication primitives which hide the communication topology in contrast to the more explicit communications like PVM or MPI. A parallel in-memory database, called SPIDER, has been implemented on a 32 node Meiko CS-2 distributed memory machine. The spider primitives generate a lower overhead than the one generated by PVM or PMI. The event reconstruction program, CPREAD of the CPLEAR experiment, has been used as a test case. Performance measurerate generated by CPLEAR.CERN-ECP-95-28CERN-ECP-95-028oai:cds.cern.ch:2948281995-12-11
spellingShingle Detectors and Experimental Techniques
Argante, E
Meesters, M R J
Van der Stok, P D V
Willers, Ian Malcolm
A database for on-line event analysis on a distributed memory machine
title A database for on-line event analysis on a distributed memory machine
title_full A database for on-line event analysis on a distributed memory machine
title_fullStr A database for on-line event analysis on a distributed memory machine
title_full_unstemmed A database for on-line event analysis on a distributed memory machine
title_short A database for on-line event analysis on a distributed memory machine
title_sort database for on-line event analysis on a distributed memory machine
topic Detectors and Experimental Techniques
url http://cds.cern.ch/record/294828
work_keys_str_mv AT argantee adatabaseforonlineeventanalysisonadistributedmemorymachine
AT meestersmrj adatabaseforonlineeventanalysisonadistributedmemorymachine
AT vanderstokpdv adatabaseforonlineeventanalysisonadistributedmemorymachine
AT willersianmalcolm adatabaseforonlineeventanalysisonadistributedmemorymachine
AT argantee databaseforonlineeventanalysisonadistributedmemorymachine
AT meestersmrj databaseforonlineeventanalysisonadistributedmemorymachine
AT vanderstokpdv databaseforonlineeventanalysisonadistributedmemorymachine
AT willersianmalcolm databaseforonlineeventanalysisonadistributedmemorymachine

Ejemplares similares