Massive Parallelism on the Hybrid Text Retrieval Machine

The design of a high-performance, cost-effective, machine for retrieving textual data is discussed in this paper. High performance and cost effectiveness are achieved by a combination of low-cost hard disks, software filtering techniques, and a large amount of main memory. The discussion focuses on the signature processor, which is based on the partitioned signature file technique, and the mass storage system, which is based on a disk array. A performance evaluation on the individual system components, namely, the signature processor and the mass storage system, as well as the entire system is presented. *The author is on leave from the Department of Computer and Information Science, The Ohio State University, Columbus, OH 43210. 1 Introduction Information retrieval has been a very important application for computers. However, the massive amount of information handled by information retrieval applications such as library systems and office automation systems often overwhelms the lar..