New icosahedral grid-point discretizations of the shallow water equations on the sphere
Journal of Computational Physics
The X architecture: not your father's diagonal wiring
SLIP '02 Proceedings of the 2002 international workshop on System-level interconnect prediction
Principles and Practices of Interconnection Networks
Principles and Practices of Interconnection Networks
The Y-architecture: yet another on-chip interconnect solution
ASP-DAC '03 Proceedings of the 2003 Asia and South Pacific Design Automation Conference
Blue Gene/L torus interconnection network
IBM Journal of Research and Development
The Y architecture for on-chip interconnect: analysis and methodology
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
| Hi-index | 0.00 |
The present paper is part of a larger effort to redesign, from the ground up, the best possible interconnect topologies for switchless multiprocessor computer systems. We focus here specifically on honeycomb graphs and their extension to problems on the sphere, as motivated by the design of special-purpose computational clusters for global weather forecasting. Eight families of efficient tiled layouts have been discovered which make such interconnects trivial to scale to large cluster sizes while incorporating no long wires. In the resulting switchless interconnect designs, the physical proximity of the cells created (in the PDE discretization of the physical domain) and the logical proximity of the nodes to which these cells are assigned (in the computational cluster) coincide perfectly, so all communication between physically adjacent cells during the PDE simulation require communication over just a single hop in the computational cluster.