Sparse Hamming Graph: A Customizable Network-on-Chip Topology
Patrick Iff, Maciej Besta, Matheus Cavalcante, Tim Fischer, Luca, Benini, Torsten Hoefler

TL;DR
This paper introduces the sparse Hamming graph, a customizable NoC topology that balances cost and performance, supported by a toolchain for efficient design optimization, outperforming existing topologies.
Contribution
The paper presents a novel sparse Hamming graph topology and a toolchain for rapid customization and optimization of NoC designs based on identified principles.
Findings
Achieves better cost-performance trade-offs than existing topologies
Provides a fast, accurate prediction toolchain for NoC design
Demonstrates flexibility in customizing NoC topologies
Abstract
Chips with hundreds to thousands of cores require scalable networks-on-chip (NoCs). Customization of the NoC topology is necessary to reach the diverse design goals of different chips. We introduce sparse Hamming graph, a novel NoC topology with an adjustable costperformance trade-off that is based on four NoC topology design principles we identified. To efficiently customize this topology, we develop a toolchain that leverages approximate floorplanning and link routing to deliver fast and accurate cost and performance predictions. We demonstrate how to use our methodology to achieve desired cost-performance trade-offs while outperforming established topologies in cost, performance, or both.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInterconnection Networks and Systems · Advancements in Battery Materials · Low-power high-performance VLSI design
