Grant-in-Aid for Developmental Scientific Research (B)
|Allocation Type||Single-year Grants|
|Research Institution||Utsunomiya University|
BABA Takanobu Utsunomiya University, Faculty of Engineering, Professor, 工学部, 教授 (70092616)
MAEDA Akira Information & Communication Systems Laboratory, Toshiba Corporation, Chief Speci, 情報・通信システム技術研究所・開発第1部, 研究主幹
KOIKE Nobuhiko C & C Research Laboratories, NEC Europe Ltd., General Manager, コンピュータシステム研究部, 部長
BANDO Tadaaki Systems Development Laboratory, Hitachi Ltd., Deputy General Manager, システム開発研究所, 副所長
YONAZAWA Akinori University of Tokyo, Faculty of Science, Professor, 理学部, 教授 (00133116)
YOSHINAGA Tsutomu Utsunomiya University, Faculty of Engineering, Research Associate, 工学部, 助手 (60210738)
坂東 忠秋 (株)日立製作所, 日立研究所, 部長
熊谷 毅 宇都宮大学, 工学部, 助教授 (90125815)
|Project Period (FY)
1992 – 1994
Completed(Fiscal Year 1994)
|Budget Amount *help
¥16,200,000 (Direct Cost : ¥16,200,000)
Fiscal Year 1994 : ¥1,500,000 (Direct Cost : ¥1,500,000)
Fiscal Year 1993 : ¥5,100,000 (Direct Cost : ¥5,100,000)
Fiscal Year 1992 : ¥9,600,000 (Direct Cost : ¥9,600,000)
|Keywords||parallel processing / object-oriented / total architecture / actor model / multicomputer / programming language / 高並列 / ノードプロセッサ / ルータ / ネットワークトポロジ / メッセージ / VLSI / メッセージ交換|
We have developed a parallel object-oriented total architecture A-NET (Actors NET work). The development includes the design and implementation of a programming language, and a multicomputer hardware, and their applications.
(1) 8-node Prototype Multicomputer
We developed a 2-node prototype in 1994, and debugged its hardware. Based on that experience, we scaled it up to 8 nodes and put them into an originally designed 20-slot cabinet at the beginning of 1995. We also developed its device driver on the host workstation and connected the prototype and the host via VME interface.
(2) Parallel Object-Oriented Language
We have designed a parallel object-oriented language A-NETL.In 1994, we added some file access functions to A-NETL.We also improved the reliability and portability of the langage processors.
(3) Future Work
We have to adjust the 8-node prototype hardware. Then we will extend it to the 16-node one. We also need to modify the software environment in order to replace the simulator with the real machine.
Now, we are planning to implement A-NETL both on AP1000 and on workstation clusters to extend its available environment.