Skip to Main Content (Press Enter)

Logo CNR
  • ×
  • Home
  • Persone
  • Pubblicazioni
  • Strutture
  • Competenze

UNI-FIND
Logo CNR

|

UNI-FIND

cnr.it
  • ×
  • Home
  • Persone
  • Pubblicazioni
  • Strutture
  • Competenze
  1. Pubblicazioni

AVES: A Computer Cluster System approach for INTEGRAL Scienti?c Analysis

Articolo
Data di Pubblicazione:
2012
Abstract:
Abstract. The AVES computing system, based on an Cluster architecture is a fully integrated, low cost computing facility dedicated to the archiving and analysis of the INTEGRAL data. AVES is a modular system that uses the software resource manager (SLURM) and allows almost unlimited expandibility (65,536 nodes and hundreds of thou- sands of processors); actually is composed by 30 Personal Computers with Quad-Cores CPU able to reach the computing power of 300 Giga Flops (300x109 Floating point Operations Per Second), with 120 GB of RAM and 7.5 Tera Bytes (TB) of storage mem- ory in UFS configuration plus 6 TB for users area. AVES was designed and built to solve growing problems raised from the analysis of the large data amount accumulated by the INTEGRAL mission (actually about 9 TB) and due to increase every year. The used analy- sis software is the OSA package, distributed by the ISDC in Geneva. This is a very complex package consisting of dozens of programs that can not be converted to parallel computing. To overcome this limitation we developed a series of programs to distribute the workload analysis on the various nodes making AVES automatically divide the analysis in N jobs sent to N cores. This solution thus produces a result similar to that obtained by the parallel computing configuration. In support of this we have developed tools that allow a flexible use of the scientific software and quality control of on-line data storing. The AVES software package is constituted by about 50 specific programs. Thus the whole computing time, com- pared to that provided by a Personal Computer with single processor, has been enhanced up to a factor 70.
Tipologia CRIS:
01.01 Articolo in rivista
Keywords:
aves; cluster; slurm; resources manager; osa; scientific software package
Elenco autori:
Martino, BRUNO LUIGI
Autori di Ateneo:
MARTINO BRUNO LUIGI
Link alla scheda completa:
https://iris.cnr.it/handle/20.500.14243/278860
Pubblicato in:
MEMORIE DELLA SOCIETÀ ASTRONOMICA ITALIANA (ONLINE)
Journal
  • Utilizzo dei cookie

Realizzato con VIVO | Designed by Cineca | 26.5.0.0 | Sorgente dati: PREPROD (Ribaltamento disabilitato)