{"title":"Message-passing database machines","authors":"L. Bic","doi":"10.1109/PARBSE.1990.77197","DOIUrl":null,"url":null,"abstract":"The development of message-passing database machines is briefly examined, with emphasis on the Active Graph Model (AGM). The AGM, developed specifically to exploit massive parallelism, is based on the principles of purely message-driven computation, where the entire database is represented as a graph of communicating nodes. Unlike object-oriented models, however, where the programmer must provide the methods for message handling, in AGM, generic methods are an inherent part of the model. This results in a much finer grain of parallelism than is obtained with object-oriented systems. Since both memory and control are encapsulated within each node, the database is capable of exploiting an architecture consisting of a very large number of loosely coupled processors and disk units. A hardware prototype consisting of 16 processors and 16 disks is now operational.<<ETX>>","PeriodicalId":389644,"journal":{"name":"Proceedings. PARBASE-90: International Conference on Databases, Parallel Architectures, and Their Applications","volume":"81 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. PARBASE-90: International Conference on Databases, Parallel Architectures, and Their Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PARBSE.1990.77197","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The development of message-passing database machines is briefly examined, with emphasis on the Active Graph Model (AGM). The AGM, developed specifically to exploit massive parallelism, is based on the principles of purely message-driven computation, where the entire database is represented as a graph of communicating nodes. Unlike object-oriented models, however, where the programmer must provide the methods for message handling, in AGM, generic methods are an inherent part of the model. This results in a much finer grain of parallelism than is obtained with object-oriented systems. Since both memory and control are encapsulated within each node, the database is capable of exploiting an architecture consisting of a very large number of loosely coupled processors and disk units. A hardware prototype consisting of 16 processors and 16 disks is now operational.<>