Copyright Notice:

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

K. Lakhotia, L. Monroe, K. Isham, M. Besta, N. Blach, T. Hoefler, F. Petrini:

 PolarStar: Expanding the Horizon of Diameter-3 Networks

(In Proceedings of the 36th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA'24), presented in Nantes, France, Association for Computing Machinery, Jun. 2024)


In this paper, we present PolarStar, a novel family of diameter-3 network topologies derived from the star product of two low-diameter factor graphs. The proposed PolarStar construction gives the largest known diameter-3 network topologies for almost all radixes. When compared to state-of-the-art diameter-3 networks, PolarStar achieves 31% geometric mean increase in scale over Bundlefly, 91% over Dragonfly, and 690% over 3-D HyperX. PolarStar has many other desirable properties including a modular layout, large bisection, high resilience to link failures and a large number of feasible sizes for every radix. Our evaluation shows that it exhibits comparable or better performance than other diameter-3 networks under various traffic patterns.


download article:
access preprint on arxiv:


  author={Kartik Lakhotia and Laura Monroe and Kelly Isham and Maciej Besta and Nils Blach and Torsten Hoefler and Fabrizio Petrini},
  title={{PolarStar: Expanding the Horizon of Diameter-3 Networks}},
  booktitle={Proceedings of the 36th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA'24)},
  location={Nantes, France},
  publisher={Association for Computing Machinery},