Link to CALCM Home  

A Low-Radix and Low-Diameter 3D Interconnection Network Design

Tuesday November 4, 2008
Hamerschlag Hall D-210
4:30 pm



Jun Yang
University of Pittsburgh

The design of the network-on-chip (NoC) topologies for 3D integrated CMPs has important distinctions from 2D NoCs or off-chip interconnection networks. First, current 3D stacking technology allows only vertical inter-layer links. Hence, there cannot be direct connections between arbitrary nodes in different layers - the vertical connection topology is essentially fixed. Second, the 3D NoC is highly constrained by the complexity and power of routers and links. Hence, low-radix routers are preferred over high-radix routers for lower power and better heat dissipation. This implies long network latency due to high hop counts in network paths.

In this talk, I will introduce a low-diameter 3D network design using low-radix routers. Our topology leverages long wires to connect remote intra-layer nodes. We take the advantage of the state-of-the-art one-hop vertical communication design to utilize the long wires for shortening network paths. Effectively, we implement a small-to-medium sized clique network in different layers of a 3D chip. The resulting topology generates a diameter of 3-hop only network, using routers of less radix than that of a 3D mesh network. The proposed network shows up to 29% of network latency reduction, up to 10% throughput improvement, and up to 24% energy reduction, when compared to a 3D mesh network.


Jun Yang is an assistant professor of Electrical and Computer Engineering at University of Pittsburgh. She obtained her Ph.D. in CS from the University of Arizona in 2002. Prior to joining Pitt, she was an assistant professor in Computer Science and Engineering at University of California Riverside from 2002 to 2006. Her research interests include low power microprocessor design, thermal management, and 3D chip integration. She is a recipient of NSF CAREER award in 2008.

 

Department of Electrical and Computer EngineeringCarnegie Mellon UniversitySchool of Computer Science