Design of an application-dependent static-based shared memory network

Authors:
Yoshimasa Ohnishi;Takaichi Yoshida
Affiliations:
Kyushu Institute of Technology, Iizuka, Fukuoka, Japan;Kyushu Institute of Technology, Iizuka, Fukuoka, Japan
Venue:
ICA3PP'12 Proceedings of the 12th international conference on Algorithms and Architectures for Parallel Processing - Volume Part II
Year:
2012

Citing 6
Cited 0

Architecture and implementation of MEMORY CHANNEL 2

Digital Technical Journal
Low Latency High Bandwidth Message Transfer Mechanisms for a Network Interface Plugged into a Memory Slot

Cluster Computing
Communication Optimizations for Fine-Grained UPC Applications

Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques
Reconfigurable hybrid interconnection for static and dynamic scientific applications

Proceedings of the 4th international conference on Computing frontiers
Design and Evaluation of a Distributed Shared Memory Network for Application-Specific PC Cluster Systems

WAINA '11 Proceedings of the 2011 IEEE Workshops of International Conference on Advanced Information Networking and Applications
INAM - a scalable infiniband network analysis and monitoring tool

Euro-Par'11 Proceedings of the 2011 international conference on Parallel Processing - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

The latency of network switching is of particular importance for fine-grained communication processes such as memory access. We propose a specialized network switch that reduces communication latency because many scientific computing applications have specific access patterns. In this paper, we describe the basic concept and design of our reconfigurable shared memory network. Our evaluation results show that there is no significant difference between the port-to-port latency of our network switch and that of an 8-port InfiniBand network switch. Furthermore, the hardware size of the routing stack in the network switch does not increase with the number of nodes.