@misc{10312,
  keywords = {Conference},
  author = {Bartosz Bogdanski and Bj{\o}rn Johnsen and Sven-Arne Reinemo and Frank Sem-Jacobsen},
  title = {Discovery and Routing of Degraded Fat-Trees},
  abstract = {The fat-tree topology has become a popular choice for InfiniBand enterprise systems due to its deadlock freedom, fault-tolerance and full bisection bandwidth. In the HPC domain, InfiniBand fabric is used in almost 42\% of the systems on the latest Top 500 list, and many of those systems are based on the fat-tree topology. Despite the popularity of the fat-tree topology, little research has been done to compare the behavior of InfiniBand routing algorithms on degraded fat-tree topologies. In this paper, we identify the weaknesses of the current fat-tree routing and propose enhancements that liberalize the restrictions imposed on the routed fabric. Furthermore, we present a thorough analysis of non-proprietary routing algorithms that are implemented in the InfiniBand Open Subnet Manager. Our results show that even though the performance of a fat-tree routed network deteriorates predictably with the number of failed links, fat-tree routing algorithm is still the best choice for severely degraded fat-tree fabrics.},
  year = {2012},
  journal = {2012 13th International Conference on Parallel and Distributed Computing, Applications and Technologies},
  pages = {689-694},
  month = {December},
  publisher = {IEEE Computer Society},
  address = {Los Alamitos},
  editor = {Hong Shen and Yingpeng Sang and Yidong Li and Depai Qian and Albert Zomaya},
}