Advertisement

Reconfigurable Many-Core Processor with Cache Coherence

  • Xing Han
  • Jiang Jiang
  • Yuzhuo Fu
  • Chang Wang
Part of the Communications in Computer and Information Science book series (CCIS, volume 396)

Abstract

As the number of cores integrated on one processor increases, the cost of on-chip communication becomes more expensive, including the latency and the load on links. This also limits the utilization of the many-core processor. This paper describes a virtual computing group(VCG) model to improve the utilization of the computing resources on NoC-based many-core processor. Each VCG can be reconfigured into different size and topology before the program starts. The token protocol for cache coherence is adopted to improve the performance of memory accessing. Modifications to Token protocol are made to support cache coherence in the local VCG only, which lightens the communication penalty on a large NoC. We implement this reconfigurable system in Gem5 simulator, and the simulation result proves the improvement of the performance.

Keywords

Reconfiguration Many-core Cache Coherence VCG Parallel Library 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baron, M.: The single-chip cloud computer - intel networks 48 pentiums on a chip. Microprocessor Report (2010)Google Scholar
  2. 2.
    Binkert, N.: The gem5 simulator. SIGARCH Computer Architecture News 39(2) (2011)Google Scholar
  3. 3.
    Dally, W., Seitz, C.: Deadlock free message routing in multiprocessor interconnection networks (1985)Google Scholar
  4. 4.
    David, W.: On-chip interconnection architecture of the tile processor. Micro 27(5) (2007)Google Scholar
  5. 5.
    Golub, G.H., Loan, C.F.V.: Matrix computations, 3rd edn. Johns Hopkins University Press (1996)Google Scholar
  6. 6.
    Guthaus, M.R.: MiBench: A free, commercially representative embedded benchmark suite. In: IEEE 4th Annual Workshop on Workload Characterization (2001)Google Scholar
  7. 7.
    ITRS2011, International technology roadmap for semiconductors: System drivers (2011)Google Scholar
  8. 8.
    Jiao, J., Fu, Y.: Multi-application specified link removal strategy for network on chip. In: Fourth International Joint Conference (2011)Google Scholar
  9. 9.
    Kumar, R., Mattson, T., Pokam, G., van der Wijngaart, R.: The case for message passing on many-core chipsGoogle Scholar
  10. 10.
    Lin, X., McKinley, P.K., Ni, L.M.: Deadlock-free multicast wormhole routing in 2d mesh multicomputers (1992)Google Scholar
  11. 11.
    Martin, M.: Token Coherence. University of Wisconsin-Madison (2003)Google Scholar
  12. 12.
    Ros, A.: A direct coherence protocol for many-core chip multiprocessors. IEEE Transactions on Parallel and Distributed Systems 21(12) (2010)Google Scholar
  13. 13.
    Sankaralingam, K.: The distributed microarchitecture of the trips prototype processor. In: 39th International Symposium on Microarchitecture (2006)Google Scholar
  14. 14.
    Vydyanathan, N., Krishnamoorthy, S., Sabin, G.: An integrated approach for processor allocation and scheduling of mixed-parallel applications. In: ICPP (2006)Google Scholar
  15. 15.
    Wu, C.: Design and simulation of a torus structure and route algorithm for network on chip. In: 7th International Conference (2007)Google Scholar
  16. 16.
    Xu, J., Wolf, W.: A design methodology for application-specific network-on-chip. ACM Transaction on Embedded Computing System 5(2) (2005)Google Scholar
  17. 17.
    Ye, Y., Xie, Y.: 3d optical networks-on-chip (noc) for multiprocessor systems-on-chip (mpsoc). In: 3D System Integration 2009, 3 DIC (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Xing Han
    • 1
  • Jiang Jiang
    • 1
  • Yuzhuo Fu
    • 1
  • Chang Wang
    • 1
  1. 1.School of MicroelectronicsShanghai Jiao Tong UniversityChina

Personalised recommendations