A GALS Infrastructure for a Massively Parallel Multiprocessor
- 8 October 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test of Computers
- Vol. 24 (5) , 454-463
Abstract
This case study focuses on a massively parallel multiprocessor for real-time simulation of billions of neurons. Every node of the design comprises 20 ARM9 cores, a memory interface, a multicast router, and two NoC structures for communicating between internal cores and the environment. The NoCs are asynchronous; the cores and RAM interfaces are synchronous. This GALS approach decouples clocking concerns for different parts of the die, leading to greater power efficiency.Keywords
This publication has 4 references indexed in Scilit:
- Neural systems engineeringJournal of The Royal Society Interface, 2006
- Delay-insensitive, point-to-point interconnect using m-of-n codes2003
- Chain: a delay-insensitive chip area interconnectIEEE Micro, 2002
- Delay-insensitive codes — an overviewDistributed Computing, 1988