Publication Date:
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 e ciently 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.
Iris type:
04.01 Contributo in Atti di convegno
Keywords:
Indexing web documents
List of contributors:
Orlando, Salvatore; Silvestri, Fabrizio; Perego, Raffaele
Book title:
ICCS 2004: 4th International Conference, (Kraków, Poland, June 6-9, 2004)