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
|J. Domke, T. Hoefler and W. Nagel:|
|Deadlock-Free Oblivious Routing for Arbitrary Topologies|
(. Vol , Nr. , In Proceedings of the 25th IEEE International Parallel \& Distributed Processing Symposium (IPDPS), presented in Anchorage, AL, USA, pages 613--624, IEEE Computer Society, ISSN: , ISBN: 0-7695-4385-7, May 2011, )
AbstractEfficient deadlock-free routing strategies are crucial to the performance of large-scale computing systems. Many specialized routing methods exist but remains a challenge to achieve lowest latency and highest bandwidth for irregular or unstructured high-performance networks. We investigate a novel routing strategy based on the single-source-shortest-path routing algorithm and extend it to use virtual channels to guarantee deadlock-freedom. We show that this algorithm achieves optimal latency, high-bandwidth with only a low number of virtual channels and can be implemented in practice. We show that the problem of finding the minimal number of virtual lanes needed to route a general network deadlock-free is NP-complete and propose different heuristics to solve the problem. We implemented all proposed algorithms in InfiniBand's Open Subnet Manager and compared the number of needed virtual channels and the bandwidth of multiple real and artificial network topologies to established practice. Our approach allows to use the existing virtual channels more effectively to guarantee deadlock-freedom and increase the effective bandwidth of up to a factor of two. Application benchmarks showed an improvement of up to 95%. Our routing scheme is not limited to InfiniBand but can be deployed on existing InfiniBand installations to increase network performance transparently without modifications to the user applications.