A case for random shortcut topologies for HPC interconnects

Authors:
Michihiro Koibuchi;Hiroki Matsutani;Hideharu Amano;D. Frank Hsu;Henri Casanova
Affiliations:
National Institute of Informatics/SOKENDAI, Hitotsubashi, Chiyoda-ku, Tokyo, JAPAN;Keio University, Hiyoshi, Kohoku-ku, Yokohama, Japan;Keio University, Hiyoshi, Kohoku-ku, Yokohama, Japan;Fordham University, New York, NY;University of Hawai'i at Manoa, Honolulu, HI
Venue:
Proceedings of the 39th Annual International Symposium on Computer Architecture
Year:
2012

Citing 19
Cited 1

The diameter of a cycle plus a random matching

SIAM Journal on Discrete Mathematics
The de Bruijn Multiprocessor Network: A Versatile Parallel Processing and Sorting Network for VLSI

IEEE Transactions on Computers
A Variation on the Hypercube with Lower Diameter

IEEE Transactions on Computers
Distributed loop computer networks: a survey

Journal of Parallel and Distributed Computing
High-Performance Routing in Networks of Workstations with Irregular Topology

IEEE Transactions on Parallel and Distributed Systems
Properties and Performance of Folded Hypercubes

IEEE Transactions on Parallel and Distributed Systems
A Necessary and Sufficient Condition for Deadlock-Free Adaptive Routing in Wormhole Networks

IEEE Transactions on Parallel and Distributed Systems
Deadlock-Free Dynamic Reconfiguration Schemes for Increased Network Dependability

IEEE Transactions on Parallel and Distributed Systems
Principles and Practices of Interconnection Networks

Principles and Practices of Interconnection Networks
On the Feasibility of Optical Circuit Switching for High Performance Computing Systems

SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
The BlackWidow High-Radix Clos Network

Proceedings of the 33rd annual international symposium on Computer Architecture
Flattened butterfly: a cost-efficient topology for high-radix networks

Proceedings of the 34th annual international symposium on Computer architecture
An Effective Design of Deadlock-Free Routing Algorithms Based on 2D Turn Model for Irregular Networks

IEEE Transactions on Parallel and Distributed Systems
Technology-Driven, Highly-Scalable Dragonfly Topology

ISCA '08 Proceedings of the 35th Annual International Symposium on Computer Architecture
Region-based routing: a mechanism to support efficient routing algorithms in NoCs

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Packaging the Blue Gene/L supercomputer

IBM Journal of Research and Development
Tofu: A 6D Mesh/Torus Interconnect for Exascale Computers

Computer
Small-world networks: from theoretical bounds to practical systems

OPODIS'07 Proceedings of the 11th international conference on Principles of distributed systems
A Survey and Evaluation of Topology-Agnostic Deterministic Routing Algorithms

IEEE Transactions on Parallel and Distributed Systems

Characterization and cost-efficient selection of NoC topologies for general purpose CMPs

Proceedings of the 2013 Interconnection Network Architecture: On-Chip, Multi-Chip

Quantified Score

Hi-index	0.00

Visualization

Abstract

As the scales of parallel applications and platforms increase the negative impact of communication latencies on performance becomes large. Fortunately, modern High Performance Computing (HPC) systems can exploit low-latency topologies of high-radix switches. In this context, we propose the use of random shortcut topologies, which are generated by augmenting classical topologies with random links. Using graph analysis we find that these topologies, when compared to non-random topologies of the same degree, lead to drastically reduced diameter and average shortest path length. The best results are obtained when adding random links to a ring topology, meaning that good random shortcut topologies can easily be generated for arbitrary numbers of switches. Using flit-level discrete event simulation we find that random shortcut topologies achieve throughput comparable to and latency lower than that of existing non-random topologies such as hypercubes and tori. Finally, we discuss and quantify practical challenges for random shortcut topologies, including routing scalability and larger physical cable lengths.