Synthetic traffic generation as a tool for dynamic interconnect evaluation

ABSTRACT

Run-time reconfigurable interconnection networks can provide significant performance gains in shared-memory multiprocessor systems. However, designing such networks is hard, requiring detailed but slow execution-driven simulations, since faster methods are currently not suitable for use with dynamic network topologies. In this paper, we extend one of these methods, synthetic traffic generation, to incorporate the dynamic traffic behavior necessary to accurately determine the performance of a reconfigurable network. Our synthetic traffic flow has the same characteristics as the flow resulting from an execution driven simulation, but can be much shorter: we can gain a reduction in simulation time of up to 100x at only a limited expense in accuracy. This way, it is possible to quickly analyze the dynamic interconnect requirements of an application and evaluate various aspects of a proposed reconfigurable interconnect implementation.

REFERENCES

• 1: I. Artundo, L. Desmet, W. Heirman, C. Debaes, J. Dambre, J. Van Campenhout, and H. Thienpont. Selective optical broadcast component for reconfigurable multiprocessor interconnects. IEEE Journal on Selected Topics in Quantum Electronics: Special Issue on Optical Communication, 12(4):828--837, July 2006.
• 2: K. Beyls and E. D`Hollander. Reuse distance as a metric for cache behavior. In TGonzalez, editor, Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems, pages 617--622, Anaheim, California, USA, Aug. 2001.
• 3: David E. Culler , Anoop Gupta , Jaswinder Pal Singh, Parallel Computer Architecture: A Hardware/Software Approach, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1997
• 4: W. Heirman, J. Dambre, I. Artundo, C. Debaes, H. Thienpont, D. Stroobandt, and J. VanCampenhout. Predicting reconfigurable interconnect performance in distributed shared-memory systems. Integration, the VLSI Journal: Special Issue on SLIP`05, 2007. To appear.
• 5: W. Heirman , J. Dambre , J. Van Campenhout , C. Debaes , H. Thienpont, Traffic Temporal Analysis for Reconfigurable Interconnects in Shared-Memory Systems, Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 3, p.150.1, April 04-08, 2005 [doi>10.1109/IPDPS.2005.442]
• 6: Peter S. Magnusson , Magnus Christensson , Jesper Eskilson , Daniel Forsgren , Gustav Hållberg , Johan Högberg , Fredrik Larsson , Andreas Moestedt , Bengt Werner, Simics: A Full System Simulation Platform, Computer, v.35 n.2, p.50-58, February 2002 [doi>10.1109/2.982916]
• 7: F. Ridruejo, A. Gonzalez, and J. Miguel-Alonso. TrGen: a traffic generation system for interconnection network simulators. In 1st. Int. Workshop on Performance Evaluation of Networks for Parallel, Cluster and Grid Computing Systems (PEN-PCGCS'05), Olso, Norway, June 2005.
• 8: F. Vandeputte, L. Eeckhout, and K. De Bosschere. An analysis of program phase behavior and its predictability. In DDubois, editor, Proceedings of the 7th International Conference on Computing Anticipatory Systems (CASYS), volume 839, pages 361--370, Melville, New York, June 2006. American Institute of Physics.
• 9: Steven Cameron Woo , Moriyoshi Ohara , Evan Torrie , Jaswinder Pal Singh , Anoop Gupta, The SPLASH-2 programs: characterization and methodological considerations, Proceedings of the 22nd annual international symposium on Computer architecture, p.24-36, June 22-24, 1995, S. Margherita Ligure, Italy

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.4 Parallel Architectures
          Subjects: Distributed architectures

General Terms:
Algorithms, Design, Measurement, Performance

Keywords:
dynamic interconnect requirements, reconfigurable interconnect, synthetic traffic generation