International Journal of Parallel Programming

, Volume 40, Issue 1, pp 4–24 | Cite as

Data Layout Transformation Exploiting Memory-Level Parallelism in Structured Grid Many-Core Applications

  • I-Jui Sung
  • Nasser Anssari
  • John A. Stratton
  • Wen-Mei W. Hwu
Article
First Online:
Received:
Accepted:

Abstract

We present automatic data layout transformation as an effective compiler performance optimization for memory-bound structured grid applications. Structured grid applications include stencil codes and other code structures using a dense, regular grid as the primary data structure. Fluid dynamics and heat distribution, which both solve partial differential equations on a discretized representation of space, are representative of many important structured grid applications. Using the information available through variable-length array syntax, standardized in C99 and other modern languages, we enable automatic data layout transformations for structured grid codes with dynamically allocated arrays. We also present how a tool can guide these transformations to statically choose a good layout given a model of the memory system, using a modern GPU as an example. A transformed layout that distributes concurrent memory requests among parallel memory system components provides substantial speedup for structured grid applications by improving their achieved memory-level parallelism. Even with the overhead of more complex address calculations, we observe up to 10.94X speedup over the original layout, and a 1.16X performance gain in the worst case.

Keywords

GPU Parallel programming Data layout transformation 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anderson J.M., Amarasinghe S.P., Lam M.S.: Data and computation transformations for multiprocessors. SIGPLAN Not. 30(8), 166–178 (1995)CrossRefGoogle Scholar
  2. 2.
    Asanovic, K., Bodik, R., Catanzaro, B.C., Gebis, J.J., Husbands, P., Keutzer, K., Patterson, D.A., Plishker, W.L., Shalf, J., Williams, S.W., Yelick, K.A.: The landscape of parallel computing research: a view from berkeley. Technical report UCB/EECS-2006-183, EECS Department, University of California, Berkeley, Dec 2006Google Scholar
  3. 3.
    Bakhoda, A., Yuan, G.L., Fung, W.W.L., Wong, H., Aamodt, T.M.: Analyzing cuda workloads using a detailed gpu simulator. In: ISPASS, pp. 163–174. IEEE (2009)Google Scholar
  4. 4.
    Baskaran, M.M., Bondhugula, U., Krishnamoorthy, S., Ramanujam J., Rountev, A., Sadayappan, P.: A compiler framework for optimization of affine loop nests for gpgpus. In: ICS ’08: Proceedings of the 22nd annual international conference on Supercomputing, pp. 225–234. ACM, New York, NY, USA (2008)Google Scholar
  5. 5.
    Datta, K., Murphy, M., Volkov, V., Williams, S., Carter, J., Oliker, L., Patterson, D., Shalf, J., Yelick, K.: Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: SC08: Proceedings of the 2008 Conference on Supercomputing, pp. 1–12. Piscataway, NJ, USA (2008)Google Scholar
  6. 6.
    Demmel J.W.: Applied Numerical Linear Algebra. Society for Industrial and Applied Mathematics, Philadelphia, PA (1997)CrossRefMATHGoogle Scholar
  7. 7.
    Ferziger J.H., Peric M.: Computational Methods for Fluid Dynamics. Springer, Berlin (1999)MATHGoogle Scholar
  8. 8.
    Girbal S., Vasilache N., Bastoul C., Cohen A., Parello D., Sigler M., Temam O.: Semi-automatic composition of loop transformations for deep parallelism and memory hierarchies. Int. J. Parallel Prog. 34(3), 261–317 (2006)CrossRefMATHGoogle Scholar
  9. 9.
    Gundolf C.D., Douglas C.C., Haase G., Hu J., Kowarschik M., Weiss C.: Portable memory hierarchy techniques for PDE solvers, part II. SIAM News 33, 8–9 (2000)Google Scholar
  10. 10.
    Ipek E., Mutlu O., Martínez J.F., Caruana R.: Self-optimizing memory controllers: A reinforcement learning approach. Comp. Arch. News 36(3), 39–50 (2008)CrossRefGoogle Scholar
  11. 11.
    Jang, B., Mistry, P., Schaa, D., Dominguez, R., Kaeli, D.: Data transformations enabling loop vectorization on multithreaded data parallel architectures. In: PPoPP ’10: Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 353–354. ACM, New York, NY, USA (2010)Google Scholar
  12. 12.
    Ju Y.-L., Dietz, H.G.: Reduction of cache coherence overhead by compiler data layout and loop transformation. In: Proceedings of the Fourth International Workshop on Languages and Compilers for Parallel Computing, pp. 344–358. Springer, London, UK (1992)Google Scholar
  13. 13.
    Kennedy, K., Kremer, U.: Automatic data layout for high performance fortran. In: Supercomputing ’95: Proceedings of the 1995 ACM/IEEE conference on Supercomputing (CDROM), pp. 76. ACM, New York, NY, USA (1995)Google Scholar
  14. 14.
    Kindratenko, V., Enos, J., Shi, G.: Gpu clusters for high-performance computing. In: Proceedings of the Workshop on Parallel Programming on Accelerator Clusters. Jan 2009Google Scholar
  15. 15.
    Kwon, Y.-S., Koo, B.-T., Eum, N.-W.: Partial conflict-relieving programmable address shuffler for parallel memories in multi-core processor. In: ASP-DAC ’09: Proceedings of the 2009 Asia and South Pacific Design Automation Conference, pp. 329–334. IEEE Press, Piscataway, NJ, USA (2009)Google Scholar
  16. 16.
    Lu, Q., Alias, C., Bondhugula, U., Henretty, T., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P., Chen, Y., Lin, H., Ngai, T.-f.: Data layout transformation for enhancing data locality on nuca chip multiprocessors. In: Proceedings of the 18th International Conference on Parallel Architectures and Compilation Techniques, pp. 348–357 (2009)Google Scholar
  17. 17.
    Mace M.E.: Memory Storage Patterns in Parallel Processing. Kluwer, Boston (1987)CrossRefGoogle Scholar
  18. 18.
    Mahapatra N.R., Venkatrao B.: The processor-memory bottleneck: problems and solutions. Crossroads 5(3es), 2 (1999)CrossRefGoogle Scholar
  19. 19.
    McVoy, L., Staelin, C.: lmbench: portable tools for performance analysis. In: Proceedings of the 1996 USENIX Annual Technical Conference, pp. 23–23 (1996)Google Scholar
  20. 20.
    Morton K.W., Mayers D.F.: Numerical Solution of Partial Differential Equations: An Introduction. Cambridge University Press, New York, NY (2005)CrossRefMATHGoogle Scholar
  21. 21.
    Moscibroda, T., Mutlu, O.: Distributed order scheduling and its application to multi-core DRAM controllers. In: Proceedings of the 27th Symposium on Principles of Distributed Computing, pp. 365–374 (2008)Google Scholar
  22. 22.
    Mutlu O., Moscibroda T.: Parallelism-aware batch scheduling: enhancing both performance and fairness of shared DRAM systems. Comput. Arch. News 36(3), 63–74 (2008)CrossRefGoogle Scholar
  23. 23.
    nVIDIA: nvidia cuda programming guide 2.0 (2008)Google Scholar
  24. 24.
    Pohl T., Kowarschik M., Wilke J., Iglberger K., Rüde U.: Optimization and profiling of the cache performance of parallel lattice boltzmann codes. Parallel Process. Lett. 13(4), 549–560 (2003)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Qian Y.H., D’Humieres D., Lallemand P.: Lattice BGK models for Navier-Stokes equation. Europhys. Lett. 17(6), 479–484 (1992)CrossRefMATHGoogle Scholar
  26. 26.
    Rivera, G., Tseng, C.-W.: Tiling optimizations for 3D scientific computations. In: SC00: Proceedings of the 2000 conference on Supercomputing, p. 32 (2000)Google Scholar
  27. 27.
    Ryoo, S., Rodrigues, C.I., Baghsorkhi, S.S., Stone, S.S., Kirk, D.B., Hwu, W.-m.W.: Optimization principles and application performance evaluation of a multithreaded gpu using cuda. In: Proceedings of the 13th Symposium on Principles and Practice of Parallel Programming, pp. 73–82 (2008)Google Scholar
  28. 28.
    Sellappa S, Chatterjee S.: Cache-Efficient multigrid algorithms. Int. J. High Perform. Comput. Appl. 18(1), 115–133 (2004)CrossRefGoogle Scholar
  29. 29.
    Shao, J., Davis, B.T.: A burst scheduling access reordering mechanism. In: Proceedings of the 13th International Symposium on High Performance Computer Architecture, pp. 285–294 (2007)Google Scholar
  30. 30.
    Spradling C.D.: Spec cpu2006 benchmark tools. Comput. Arch. News 35(1), 130–134 (2007)CrossRefGoogle Scholar
  31. 31.
    Volkov, V., Demmel, J.W.: Benchmarking gpus to tune dense linear algebra. In: SC08: Proceedings of the 2008 Conference on Supercomputing, pp. 1–11 (2008)Google Scholar
  32. 32.
    Zhao Y.: Lattice Boltzmann based PDE solver on the GPU. Vis. Comput. 24(5), 323–333 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • I-Jui Sung
    • 1
  • Nasser Anssari
    • 1
  • John A. Stratton
    • 1
  • Wen-Mei W. Hwu
    • 1
  1. 1.University of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations