Concurrent Non-deferred Reference Counting on the Microgrid: First Experiences

  • Stephan Herhut
  • Carl Joslin
  • Sven-Bodo Scholz
  • Raphael Poss
  • Clemens Grelck
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6647)

Abstract

We present a first evaluation of our novel approach for non-deferred reference counting on the Microgrid many-core architecture. Non-deferred reference counting is a fundamental building block of implicit heap management of functional array languages in general and Single Assignment C in particular. Existing lock-free approaches for multi-core and SMP settings do not scale well for large numbers of cores in emerging many-core platforms. We, instead, employ a dedicated core for reference counting and use asynchronous messaging to emit reference counting operations. This novel approach decouples computational workload from reference-counting overhead. Experiments using cycle-accurate simulation of a realistic Microgrid show that, by exploiting asynchronism, we are able to tolerate even worst-case reference counting loads reasonably well. Scalability is essentially limited only by the combined sequential runtime of all reference counting operations, in accordance with Amdahl’s law. Even though developed in the context of Single Assignment C and the Microgrid, our approach is applicable to a wide range of languages and platforms.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bailey, D., et al.: The NAS Parallel Benchmarks. International Journal of Supercomputer Applications 5(3), 63–73 (1991)CrossRefGoogle Scholar
  2. 2.
    Baumann, A., Barham, P., Dagand, P.E., et al.: The multikernel: a new OS architecture for scalable multicore systems. In: 22nd Symposium on Operating Systems Principles (SOSP 2009), pp. 29–44. ACM, New York (2009)CrossRefGoogle Scholar
  3. 3.
    Bousias, K., Guang, L., Jesshope, C., Lankamp, M.: Implementation and Evaluation of a Microthread Architecture. J. Systems Architecture 55(3), 149–161 (2009)CrossRefGoogle Scholar
  4. 4.
    Collins, G.E.: A Method for Overlapping and Erasure of Lists. Communications of the ACM 3(12), 655–657 (1960)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Doligez, D., Leroy, X.: A Concurrent, Generational Garbage Collector for a Multithreaded Implementation of ML. In: POPL 1993: 20th Symposium on Principles of Programming Languages, pp. 113–123. ACM, New York (1993)Google Scholar
  6. 6.
    Ghemawat, S., Gobioff, H., Leung, S.T.: The Google file system. SIGOPS Oper. Syst. Rev. 37(5), 29–43 (2003)CrossRefGoogle Scholar
  7. 7.
    Grelck, C., Scholz, S.B.: Towards an Efficient Functional Implementation of the NAS Benchmark FT. In: Malyshkin, V.E. (ed.) PaCT 2003. LNCS, vol. 2763, pp. 230–235. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    Grelck, C.: Shared memory multiprocessor support for functional array processing in SAC. Journal of Functional Programming 15(3), 353–401 (2005)CrossRefMATHGoogle Scholar
  9. 9.
    Grelck, C., Kreye, D., Scholz, S.B.: On Code Generation for Multi-Generator WITH-Loops in SAC. In: Koopman, P., Clack, C. (eds.) IFL 1999. LNCS, vol. 1868, pp. 77–94. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Grelck, C., Scholz, S.B.: Merging compositions of array skeletons in SAC. Journal of Parallel Computing 32(7+8), 507–522 (2006)CrossRefGoogle Scholar
  11. 11.
    Grelck, C., Scholz, S.B.: SAC: A Functional Array Language for Efficient Multithreaded Execution. Int. Journal of Parallel Programming 34(4), 383–427 (2006)CrossRefMATHGoogle Scholar
  12. 12.
    Grelck, C., Scholz, S.B.: Efficient Heap Management for Declarative Data Parallel Programming on Multicores. In: 3rd Workshop on Declarative Aspects of Multicore Programming (DAMP 2008), San Francisco, USA, pp. 17–31. ACM Press, New York (2008)Google Scholar
  13. 13.
    Grelck, C., Trojahner, K.: Implicit Memory Management for SaC. In: Grelck, C., Huch, F. (eds.) IFL 2004, pp. 335–348 (2004); University of Kiel, Institute of Computer Science and Applied Mathematics technical report 0408Google Scholar
  14. 14.
    Jesshope, C.: A model for the design and programming of multi-cores. Advances in Parallel Computing, High Performance Computing and Grids in Action (16), 37–55 (2008)Google Scholar
  15. 15.
    Joisha, P.G.: A principled approach to nondeferred reference-counting garbage collection. In: 4th International Conference on Virtual Execution Environments (VEE 2008), pp. 131–140. ACM, New York (2008)Google Scholar
  16. 16.
    Marlow, S., Harris, T., James, R.P., Peyton Jones, S.: Parallel Generational-Copying Garbage Collection with a Block-Structured Heap. In: ISMM 2008: 7th International Symposium on Memory Management, pp. 11–20. ACM, New York (2008)Google Scholar
  17. 17.
    Scholz, S.B.: Single Assignment C: Efficient Support for High-Level Array Operations in a Functional Setting. J. Functional Programming 13(6), 1005–1059 (2003)MathSciNetCrossRefMATHGoogle Scholar
  18. 18.
    Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The Hadoop distributed file system. In: 26th Symposium on Massive Storage Systems and Technologies (MSST 2010). IEEE Press, Incline Village, USA (May 2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Stephan Herhut
    • 1
  • Carl Joslin
    • 1
  • Sven-Bodo Scholz
    • 1
  • Raphael Poss
    • 2
  • Clemens Grelck
    • 2
  1. 1.University of HertfordshireUnited Kingdom
  2. 2.University of AmsterdamNetherlands

Personalised recommendations