An evaluation of document retrieval from serial files using the ICL Distributed Array Processor
- 1 June 1984
- journal article
- Published by Emerald Publishing in Online Review
- Vol. 8 (6) , 569-584
- https://doi.org/10.1108/eb024172
Abstract
The ICL Distributed Array Processor, or DAP, is a single instruction stream, multiple data stream computer in which instructions are broadcast for simultaneous execution in each of 4096 processing elements. Although originally developed for numeric computation, the DAP also provides a means for the rapid matching of the term lists representing documents and queries in information retrieval systems, and this paper presents an investigation of the use of the DAP for the parallel searching of large serial files of documents. Best match retrieval experiments with three collections of documents and queries show that the DAP is very much more efficient than a conventional mainframe computer in calculating a measure of similarity between a query and each of the documents in a large collection. It is suggested that the DAP, or machines with similar architectures, could form the basis for interactive bibliographic searching of serial files.Keywords
This publication has 17 references indexed in Scilit:
- The CAS ONLINE search system. 1. General system design and selection, generation, and use of search screensJournal of Chemical Information and Computer Sciences, 1983
- A review of the use of inverted files for best match searching in information retrieval systemsJournal of Information Science, 1983
- The DAP subroutine libraryComputer Physics Communications, 1982
- Using the ICL DAPComputer Physics Communications, 1982
- The nearest neighbour problem in information retrievalACM SIGIR Forum, 1981
- Influence of unlimited ranking on practical online search strategyOnline Review, 1980
- THE PROBABILITY RANKING PRINCIPLE IN IRJournal of Documentation, 1977
- Searching linear files on‐lineOnline Review, 1977
- Dynamic document processingCommunications of the ACM, 1972
- Inefficiency of the use of Boolean functions for information retrieval systemsCommunications of the ACM, 1961