In this paper we discuss the design of a parallel indexer for Web documents. By exploiting both data and pipeline parallelism, our prototype indexer efficiently builds a partitioned inverted compressed index, a suitable data structure commonly utilized by modern Web Search Engines. We discuss implementation issues and report the results of preliminary tests conducted on a SMP PCs. © Springer-Verlag 2004.
WINGS: A parallel indexer for Web contents / Silvestri, F.; Orlando, S.; Perego, R.. - 3036:(2004), pp. 263-270. (Intervento presentato al convegno International Conference on Computational Science tenutosi a Krakow, Poland) [10.1007/978-3-540-24685-5_33].
WINGS: A parallel indexer for Web contents
Silvestri F.;Orlando S.;
2004
Abstract
In this paper we discuss the design of a parallel indexer for Web documents. By exploiting both data and pipeline parallelism, our prototype indexer efficiently builds a partitioned inverted compressed index, a suitable data structure commonly utilized by modern Web Search Engines. We discuss implementation issues and report the results of preliminary tests conducted on a SMP PCs. © Springer-Verlag 2004.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.