A simulation-based evaluation of a disk I/O subsystem for a massively parallel computer: JUMP-1

JUMP-1 is a distributed shared-memory massively parallel computer and is composed of multiple clusters of inter-connected network called RDT (Recursive Diagonal Torus). Each cluster in JUMP-1 consists of 4 element processors, secondary cache memories, and 2 MBP (Memory Based Processor) for high-spee...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the 16th International Conference on Distributed Computing Systems pp. 562 - 569
Main Authors: Nakajo, H., Ohtani, S., Kaneda, Y.
Format: Conference Proceeding
Language:English
Japanese
Published: IEEE 23.12.2002
Subjects:
Application software
Cache memory
Computational modeling
Computer networks
Computer simulation
Concurrent computing
Distributed computing
High performance computing
Research and development
Systems engineering and theory
ISBN:9780818673993, 0818673990
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:JUMP-1 is a distributed shared-memory massively parallel computer and is composed of multiple clusters of inter-connected network called RDT (Recursive Diagonal Torus). Each cluster in JUMP-1 consists of 4 element processors, secondary cache memories, and 2 MBP (Memory Based Processor) for high-speed synchronization and communication among clusters. The I/O subsystem is connected to a cluster via a high-speed serial link called STAFF-Link. The I/O buffer memory is mapped onto the JUMP-1 global shared-memory to permit each I/O access operation as memory access. In this paper we describe evaluation of the fundamental performance of the disk I/O subsystem using event-driven simulation, and estimated performance with a Video On Demand (VOD) application.
ISBN:9780818673993
0818673990
DOI:10.1109/ICDCS.1996.508006