Advertisement

Tulipse: A Visualization Framework for User-Guided Parallelization

  • Yi Wen Wong
  • Tomasz Dubrownik
  • Wai Teng Tang
  • Wen Jun Tan
  • Rubing Duan
  • Rick Siow Mong Goh
  • Shyh-hao Kuo
  • Stephen John Turner
  • Weng-Fai Wong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7484)

Abstract

Parallelization of existing code for modern multicore processors is tedious as the person performing these tasks must understand the algorithms, data structures and data dependencies in order to do a good job. Current options available to the programmer include either automatic parallelization or a complete rewrite in a parallel programming language. However, there are limitations with these options. In this paper, we propose a framework that enables the programmer to visualize information critical for semi-automated parallelization. The framework, called Tulipse, offers a program structure view that is augmented with key performance information, and a loop-nest dependency view that can be used to visualize data dependencies gathered from static or dynamic analyses. Our paper will demonstrate how these two new perspectives aid in the parallelization of code.

Keywords

Data Dependency Iteration Space Statement Instance Speech Recognition System Code Section 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bluemke, I., Fugas, J.: A tool supporting C code parallelization. Innovations Comput. Sci. Soft. Eng., 259–264 (2010)Google Scholar
  2. 2.
    Dave, C., Bae, H., Min, S.J., Lee, S., Eigenmann, R., Midkiff, S.: Cetus: A source-to-source compiler infrastructure for multicores. Computer 42, 36–42 (2009)CrossRefGoogle Scholar
  3. 3.
    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 Program. 34, 261–317 (2006)zbMATHCrossRefGoogle Scholar
  4. 4.
  5. 5.
    Intel Parallel Advisor, http://software.intel.com/en-us/
  6. 6.
    Kennedy, K., McKinley, K.S., Tseng, C.W.: Interactive parallel programming using the ParaScope editor. IEEE Trans. Parallel Distrib. Syst. 2, 329–341 (1991)CrossRefGoogle Scholar
  7. 7.
    Kim, S.W., Park, I., Eigenmann, R.: A Performance Advisor Tool for Shared-Memory Parallel Programming. In: Midkiff, S.P., Moreira, J.E., Gupta, M., Chatterjee, S., Ferrante, J., Prins, J.F., Pugh, B., Tseng, C.-W. (eds.) LCPC 2000. LNCS, vol. 2017, pp. 274–288. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Liao, S.W., Diwan, A., Bosch Jr., R.P., Ghuloum, A., Lam, M.S.: SUIF Explorer: an interactive and interprocedural parallelizer. In: PPoPP, pp. 37–48 (1999)Google Scholar
  9. 9.
  10. 10.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 12, 629–639 (1990)CrossRefGoogle Scholar
  11. 11.
    Sasakura, M., Joe, K., Kunieda, Y., Araki, K.: Naraview: An interactive 3D visualization system for parallelization of programs. Int. J. Parallel Program. 27, 111–129 (1999)CrossRefGoogle Scholar
  12. 12.
    SPEC CPU 2006 v1.1, http://www.spec.org
  13. 13.
  14. 14.
  15. 15.
    Yu, Y., D’Hollander, E.H.: Loop parallelization using the 3D iteration space visualizer. J. Visual Lang. Comput. 12, 163–181 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yi Wen Wong
    • 1
  • Tomasz Dubrownik
    • 2
  • Wai Teng Tang
    • 3
  • Wen Jun Tan
    • 3
  • Rubing Duan
    • 4
  • Rick Siow Mong Goh
    • 4
  • Shyh-hao Kuo
    • 4
  • Stephen John Turner
    • 3
  • Weng-Fai Wong
    • 1
  1. 1.National University of SingaporeSingapore
  2. 2.University of WarsawPoland
  3. 3.Nanyang Technological UniversitySingapore
  4. 4.Institute of High Performance ComputingA*StarSingapore

Personalised recommendations