Abstract | ||
---|---|---|
Parallel computing is a promising way to achieve high performance in a database system. The disk access speed has been a well known bottleneck for database machines, and the data intensive nature and the random communication patterns of databases make the interconnection network in a database machine difficult to design.This article describes the design of a highly parallel, high throughput database machine based on the new T9000 transputer family and a large number of relatively inexpensive disks. The database machine is designed to achieve a throughput of more than 10,000 elementary transactions per second and a total size in the range of terabytes. The Semantic Binary Database Model is employed by the system. Besides its logical aspects, this model's implementation facilitates the utilization of the parallel processing power and improves the reliability of the system. |
Year | DOI | Venue |
---|---|---|
1993 | 10.1145/165660.165672 | SIGARCH Computer Architecture News |
Field | DocType | Volume |
Database tuning,Computer architecture,Database model,Parallel database,Computer science,Transputer,Parallel computing,Transactions per second,Database machine,Distributed database,Distributed computing,Semantic data model | Journal | 21 |
Issue | Citations | PageRank |
5 | 0 | 0.34 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qiang Li | 1 | 84 | 19.63 |
Naphtali Rishe | 2 | 1178 | 398.80 |