Home Publications all years 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 theses techreports presentations edited volumes conferences Awards Research Teaching BLOG Miscellaneous Full CV [pdf]
Events
Past Events

Publications of Torsten Hoefler
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.
B. Prisacari, G. Rodriguez, P. Heidelberger, D. Chen, C. Minkenberg, T. Hoefler:
  Efficient Task Placement and Routing in Dragonfly Networks
(In Proceedings of the 23rd ACM International Symposium on HighPerformance Parallel and Distributed Computing (HPDC'14), presented in Vancouver, Canada, ACM, Jun. 2014)
AbstractDragonflies are recent network designs that are one of the
most promising topologies for the Exascale effort due to their
scalability and cost. While being able to achieve very high
throughput under random uniform alltoall traffic, other
widely used workloads in high performance computing, such
as the Cartesian nearest neighbor communication pattern,
experience a significant performance degradation, and have
been termed as â€˜pathologicalâ€™ patterns for Dragonfly networks.
Despite the importance of the Cartesian nearest neighbor
pattern as a basic building block for most scientific applications, there is as of now, no detailed theoretical model which
can predict its performance accurately on a dragonfly topology taking into account (i) the network parameters (number
of links and bandwidths per level) (ii) the routing function
used in the network (direct/indirect) and (iii) the placement on the network (random, hierarchical, etc.). Such a
theoretical model would establish the real performance expectation for this communication pattern, as well as help
determine the parameters that would lead to an optimum
performance.
In this work we present such a theoretical performance
analysis framework, which, taking as input (i) a network
specification, (ii) the domain decomposition parameters from
which the nearest neighbor communication pattern emerges,
and (iii) a task placement description, can predict the impact on the effective sustained injection bandwidth. Our
analysis is able to provide analytic bounds for the peformance of the neareat neighbor exchange across a multitude
of possible tasktonode maping strategies. Finally, using
a comprehensive set of simulations results, we validate the
correctness of the theoretical approach and in the process
address some misconceptions regarding Dragonfly network
behavior and evaluation, (such as the choice of throughput
maximization over workload completion time minimization
as optimization objective) and the question of whether the
standard notion of a balanced Dragonfly (topological parameters chosen for nearoptimum performance for uniform
random alltoall traffic) can be extended to workloads other
than uniform random traffic. To this end we conclude that
the optimal performance/cost Dragonfly network design for
uniform random alltoall traffic is different to the optimal
performance/cost Dragonfly network design for the Cartesian nearest neighbor pattern.
Documentsdownload article:   BibTeX  @inproceedings{prisacaridragonflymapping, author={B. Prisacari and G. Rodriguez and P. Heidelberger and D. Chen and C. Minkenberg and T. Hoefler}, title={{Efficient Task Placement and Routing in Dragonfly Networks }}, year={2014}, month={Jun.}, booktitle={Proceedings of the 23rd ACM International Symposium on HighPerformance Parallel and Distributed Computing (HPDC'14)}, location={Vancouver, Canada}, publisher={ACM}, source={http://www.unixer.de/~htor/publications/}, } 

