ABSTRACT
Recently proposed high-radix interconnection networks [10] require global adaptive routing to achieve optimum performance. Existing direct adaptive routing methods are slow to sense congestion remote from the source router and hence misroute many packets before such congestion is detected. This paper introduces indirect global adaptive routing (IAR) in which the adaptive routing decision uses information that is not directly available at the source router. We describe four IAR routing methods: credit round trip (CRT) [10], progressive adaptive routing (PAR), piggyback routing (PB), and reservation routing (RES). We evaluate each of these methods on the dragonfly topology under both steady-state and transient loads. Our results show that PB, PAR, and CRT all achieve good performance. PB provides the best absolute performance, with 2-7% lower latency on steady-state uniform random traffic at 70% load, while PAR provides the fastest response on transient loads. We also evaluate the implementation costs of the indirect adaptive routing methods and show that PB has the lowest implementation cost requiring <1% increase in the total storage of a typical high-radix router.
- R. V. Boppana and S. Chalasani. A comparison of adaptive wormhole routing algorithms. In Proc. of the International Symposium on Computer Architecture (ISCA), pages 351--360, San Diego, CA, 1993. ACM. Google ScholarDigital Library
- W. Choi and S. K. Das. Design and performance analysis of a proxy-based indirect routing scheme in ad hoc wireless networks. Mob. Netw. Appl., 8(5):499--515, 2003. Google ScholarDigital Library
- C. Clos. A study of non-blocking switching networks. Bell System Technical Journal, 32:406--424, 1953.Google ScholarCross Ref
- W. Dally and B. Towles. Principles and Practices of Interconnection Networks. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2003. Google ScholarDigital Library
- W. J. Dally. Virtual-channel flow control. In ISCA'90: Proceedings of the 17th annual international symposium on Computer Architecture, pages 60--68, New York, NY, USA, 1990. ACM. Google ScholarDigital Library
- P. T. Gaughan and S. Yalamanchili. Adaptive routing protocols for hypercube interconnection networks. Computer, 26(5):12--23, 1993. Google ScholarDigital Library
- P. Gratz, B. Grot, and S. W. Keckler. Regional congestion awareness for load balance in networks-on-chip. High Performance Computer Architecture, 2008. HPCA 2008. IEEE 14th International Symposium on, pages 203--214, Feb 2008.Google ScholarCross Ref
- L. Gravano, G. D. Pifarre, P. E. Berman, and J. L. C. Sanz. Adaptive deadlock- and livelock-free routing with all minimal paths in torus networks. IEEE Trans. Parallel Distrib. Syst., 5(12):1233--1251, 1994. Google ScholarDigital Library
- J. Kim, W. J. Dally, and D. Abts. Flattened butterfly: a cost-efficient topology for high-radix networks. In Proc. of the International Symposium on Computer Architecture (ISCA), pages 126--137, San Diego, CA, 2007. Google ScholarDigital Library
- J. Kim, W. J. Dally, S. Scott, and D. Abts. Technology-driven, highly-scalable dragonfly network. In Proc. of the International Symposium on Computer Architecture (ISCA), pages 77--88, Beijing, China, 2008. Google ScholarDigital Library
- J. Kim, W. J. Dally, S. Scott, and D. Abts. Cost-efficient dragonfly topology for large-scale system. IEEE Micro Top Picks, 29(1):33--40, Jan/Feb 2009. Google ScholarDigital Library
- J. Kim, W. J. Dally, B. Towles, and A. Gupta. Microarchitecture of a high-radix router. In Proc. of the International Symposium on Computer Architecture (ISCA), pages 420--431, Madison, WI, Jun. 2005. Google ScholarDigital Library
- A. Kumar, L.-S. Peh, and N. Jha. Token flow control. In IEEE/ACM International Symposium on Microarchitecture (MICRO), pages 342--353, Nov. 2008. Google ScholarDigital Library
- D. H. Linder and J. C. Harden. An adaptive and fault tolerant wormhole routing strategy for k-ary n-cubes. IEEE Trans. Comput., 40(1):2--12, 1991. Google ScholarDigital Library
- O. Lysne, S.-A. Reinemo, T. Skeie, A. G. Solheim, T. Sødring, L. P. Huse, and B. D. Johnsen. The interconnection network - architectural challenges for utility computing data centres. IEEE Computer, 41(9):62--69, 2008. Google ScholarDigital Library
- S. Scott, D. Abts, J. Kim, and W. J. Dally. The blackwidow high-radix clos network. In Proc. of the International Symposium on Computer Architecture (ISCA), pages 16--28, Boston, MA, 2006. Google ScholarDigital Library
- S. L. Scott and G. M. Thorson. The cray T3E network: Adaptive routing in a high performance 3D torus. In Hot Interconnects, pages 147--156, August 1996.Google Scholar
- A. Singh. Load-Balanced Routing in Interconnection Networks. PhD thesis, Stanford University, 2005.Google Scholar
- A. Singh, W. J. Dally, A. K. Gupta, and B. Towles. Adaptive channel queue routing on k-ary n-cubes. In SPAA '04: Proceedings of the sixteenth annual ACM symposium on Parallelism in algorithms and architectures, pages 11--19, New York, NY, USA, 2004. ACM. Google ScholarDigital Library
- L. G. Valiant. A scheme for fast parallel communication. SIAM Journal on Computing, 11(2):350--361, 1982.Google ScholarDigital Library
Index Terms
- Indirect adaptive routing on large scale interconnection networks
Recommendations
Indirect adaptive routing on large scale interconnection networks
Recently proposed high-radix interconnection networks [10] require global adaptive routing to achieve optimum performance. Existing direct adaptive routing methods are slow to sense congestion remote from the source router and hence misroute many ...
The k-ary n-direct s-indirect family of topologies for large-scale interconnection networks
In large-scale supercomputers, the interconnection network plays a key role in system performance. Network topology highly defines the performance and cost of the interconnection network. Direct topologies are sometimes used due to its reduced hardware ...
The Case for Chaotic Adaptive Routing
Chaotic routers are randomizing, nonminimal adaptive packet routers designed for use in the communication networks of parallel computers. Chaotic routers combine the flexibility found in adaptive routing with a design simple enough to be competitive ...
Comments