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

T. Hoefler, A. Hendel, D. Roweth:

 The Convergence of Hyperscale Data Center and High-Performance Computing Networks

(IEEE Computer. Vol 55, Nr. 7, pages 29-37, Jul. 2022)
Cover Feature Technology Predictions

Abstract

The emergence of large-scale distributed data processing and complex datacenter services led to an increase of intra-datacenter traffic. The characteristics of this emerging traffic are similar to those in high-performance supercomputers. However, network technologies used in supercomputers and datacenters are quite different and it is natural to ask whether they could be unified. We discuss the differences and commonalities between these two workload types and technologies and outline a path to convergence at multiple layers. We predict that emerging smart networking solutions will accelerate that convergence.

Documents

download article:
 

BibTeX

@article{hoefler-hpc-vs-mdc,
  author={Torsten Hoefler and Ariel Hendel and Duncan Roweth},
  title={{The Convergence of Hyperscale Data Center and High-Performance Computing Networks}},
  journal={IEEE Computer},
  year={2022},
  month={07},
  pages={29-37},
  volume={55},
  number={7},
}