An on-chip network fabric supporting coarse-grained processor array

Authors:
Phi-Hung Pham;Phuong Mau;Jungmoon Kim;Chulwoo Kim
Affiliations:
School of Electrical Engineering, Korea University, Seoul, South Korea;School of Electrical Engineering, Korea University, Seoul, South Korea;School of Electrical Engineering, Korea University, Seoul, South Korea;School of Electrical Engineering, Korea University, Seoul, South Korea
Venue:
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Year:
2013

Citing 7
Cited 0

A Family of Fault-Tolerant Routing Protocols for Direct Multiprocessor Networks

IEEE Transactions on Parallel and Distributed Systems
A decade of reconfigurable computing: a visionary retrospective

Proceedings of the conference on Design, automation and test in Europe
Route packets, not wires: on-chip inteconnection networks

Proceedings of the 38th annual Design Automation Conference
When reconfigurable architecture meets network-on-chip

SBCCI '04 Proceedings of the 17th symposium on Integrated circuits and system design
Towards software defined radios using coarse-grained reconfigurable hardware

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Dynamically Reconfigurable Systems: Architectures, Design Methods and Applications

Dynamically Reconfigurable Systems: Architectures, Design Methods and Applications
Design and Implementation of Backtracking Wave-Pipeline Switch to Support Guaranteed Throughput in Network-on-Chip

IEEE Transactions on Very Large Scale Integration (VLSI) Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Coarse grained arrays (CGAs) with run-time reconfigurability play an important role in accelerating reconfigurable computing applications. It is challenging to design on-chip communication networks (OCNs) for such CGAs with dynamic run-time reconfigurability whilst satisfying the tight budgets of power and area for an embedded system. This paper presents a silicon-proven design of a 64-PE circuit-switched OCN fabric with a dynamic path-setup scheme capable of supporting an embedded coarse-grained processor array. A proof-of-concept test chip fabricated in a 0.13 µm CMOS process occupies a silicon area of 23 mm2 and consumes a peak power of 200 mW @ 128 MHz and 1.2 Vcc, at room temperature. The OCN overhead consumes 9.4% of the area and 18% of the power of the total chip. Experimental results and analysis show that the proposed OCN fabric with its dynamic path-setup is suitable for use in an embedded CGA supporting fast run-time reconfigurability.