Seiichi Yoshizumi

Accelerating non-numerical processing by an extended vector processor

The problems of utilizing an extended vector processor called IDP (Integrated Database Processor) for nonnumerical processing are discussed. IDP has highly pipelined merge and search vector facilities in addition to conventional vector facilities. This extended vector processor can be utilized not only for primitive relational operations but also for the following applications: (1) complex relational query using multiple indexes; (2) multiway merge/sort utility, and (3) generation and test processing. Vectorization methods and performance improvements are described and analyzed.<<ETX>>

IDP — A Main Storage Based Vector Database Processor —

A new relational database machine called an Integrated Database Processor (IDP) is presented. IDP is a main storage based database machine attached to the CPU of a general purpose computer. A database stored in a secondary storage area is dynamically rearranged into a simple vector form and placed in main storage. IDP collectively processes this vectorized database in a pipelined manner. Architecturally, IDP is regarded as an extension of a conventional pipelined vector processor. Using the extended facilities, important primitive functions in relational operations such as searching, sorting, joining, and set operations, to which conventional vector processors are difficult to apply, can be vectorized. According to measurement, IDP is more than 10 times faster than a corresponding scalar program. In this paper, we describe the design concept, architecture, hardware implementation, and performance evaluation of IDP.

A relational database system architecture based on a vector processing method

A new relational database system architecture based on a vector processing method is presented. The similarity between table and vector structures was studied. This similarity implies that vector processors have high potential for the improvement of Relational Data Base Management System (RDBMS) performance. In commercial RDBMSs, however, data records are internally organized in complex pointer structures, to which vector processing is not directly applicable. We propose a new vectorization method by which data in the pointer structures are dynamically rearranged into vector form, and collectively processed using a pipelined vector processor. A new pipelined vector processor called an Integrated Database Processor (IDP) which is particularly suitable for our vectorization strategy was developed. IDP is designed as an optional hardware for a general purpose computer. The vectorization method and IDP are applied to Hitachis new, recently-announced, commercial RDBMS (called RDB1/IDP). In this paper, the vectorization method and the architecture of IDP are described. The performance improvement is also described and analyzed.

A relational database system architecture based on a vector-processing method

A new relational database system architecture based on a vector processing method is presented. The similarity between table and vector structures was studied. This similarity implies that vector processors have high potential for the improvement of Relational Data Base Management System (RDBMS) performance. In commercial RDBMSs, however, data records are internally organized in complex pointer structures, to which vector processing is not directly applicable. We propose a new vectorization method by which data in the pointer structures are dynamically rearranged into vector form, and collectively processed using a pipelined vector processor. A new pipelined vector processor called an Integrated Database Processor (IDP) which is particularly suitable for our vectorization strategy was developed. IDP is designed as an optional hardware for a general purpose computer. The vectorization method and IDP are applied to Hitachis new, recently-announced, commercial RDBMS (called RDB1/IDP). In this paper, the vectorization method and the architecture of IDP are described. The performance improvement is also described and analyzed.