Optimal Global Interconnects for Networks-on-Chip in Many-Core Architectures
Authors:
- 25 February 2010
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Electron Device Letters
- Vol. 31 (4) , 290-292
Abstract
While integrated circuits are moving toward many-core architectures, no circuit-aware interconnect technology optimization methodology has been reported for such chips. To utilize a many-core chip to its full potential, low-latency ultrahigh-bandwidth intercore interconnects are needed. In this letter, for the first time, interconnect dimensions in a network-on-chip (NoC) are optimized to achieve large bandwidth density and small latency simultaneously. The optimal wire width for a NoC is found to be more than ten times smaller than the previously obtained optimal global interconnect width. For a 1000-core chip implemented in the technology year 2015, the optimal wire width is found to be minimum-dimension limited.Keywords
This publication has 14 references indexed in Scilit:
- Design and evaluation of a hierarchical on-chip interconnect for next-generation CMPs2009
- The Delay, Energy, and Bandwidth Comparisons between Copper, Carbon Nanotube, and Optical Interconnects for Local and Global Wiring Application2007
- A Delay Model for Networks-on-Chip Output-Queuing Router2006
- Comprehensive study of the resistivity of copper wires with lateral dimensions of 100 nm and smallerJournal of Applied Physics, 2004
- Comparisons of Conventional, 3-D, Optical, and RF Interconnects for On-Chip Clock DistributionIEEE Transactions on Electron Devices, 2004
- Compact distributed RLC interconnect models. IV. Unified models for time delay, crosstalk, and repeater insertionIEEE Transactions on Electron Devices, 2003
- Optimal global interconnects for GSIIEEE Transactions on Electron Devices, 2003
- A delay model and speculative architecture for pipelined routers2002
- The mean free path of electrons in metalsAdvances in Physics, 2001
- Route packets, net wires2001