Skip to main content
View expanded cover

International Workshop on OpenMP

IWOMP 2019: OpenMP: Conquering the Full Hardware Spectrum pp 125–139Cite as

Design and Use of Loop-Transformation Pragmas

Part of the Lecture Notes in Computer Science book series (LNPSE,volume 11718)

Abstract

Adding a pragma directive into the source code is undoubtedly easier than rewriting it, for instance for loop unrolling. Moreover, if the application is maintained for multiple platforms, their difference in performance characteristics may require different code transformations. Code transformation directives allow replacing the directives depending on the platform, i.e. separation of code semantics and its performance optimization.

In this paper, we explore the design space (syntax and semantics) of adding such directive into a future OpenMP specification. Using a prototype implementation in Clang, we demonstrate the usefulness of such directives on a few benchmarks.

Keywords

  • OpenMP
  • Pragma
  • C/C++
  • Clang
  • Polly

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-28596-8_9
  • Chapter length: 15 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-28596-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   79.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 1.
Fig. 2.
Fig. 3.

Notes

  1. 1.

    Our previous paper [5] suggested to use safe semantics as the default, in conflict to the normal OpenMP behavior.

  2. 2.

    https://github.com/SOLLVE/clang/tree/pragma and

    https://github.com/SOLLVE/polly/tree/pragma.

References

  1. Bertolacci, I., Strout, M.M., de Supinski, B.R., Scogland, T.R.W., Davis, E.C., Olschanowsky, C.: Extending OpenMP to Facilitate loop optimization. In: de Supinski, B.R., Valero-Lara, P., Martorell, X., Mateo Bellido, S., Labarta, J. (eds.) IWOMP 2018. LNCS, vol. 11128, pp. 53–65. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98521-3_4

    CrossRef  Google Scholar 

  2. Donadio, S., et al.: A language for the compact representation of multiple program versions. In: Ayguadé, E., Baumgartner, G., Ramanujam, J., Sadayappan, P. (eds.) LCPC 2005. LNCS, vol. 4339, pp. 136–151. Springer, Heidelberg (2006). https://doi.org/10.1007/978-3-540-69330-7_10

    CrossRef  Google Scholar 

  3. Gareev, R., Grosser, T., Kruse, M.: High-performance generalized tensor operations: a compiler-oriented approach. ACM Trans. Archit. Code Optim. 15(3), 34:1–34:27 (2018). https://doi.org/10.1145/3235029

    CrossRef  Google Scholar 

  4. IBM: Product documentation for XL C/C++ for AIX, V13.1.3 (2015)

    Google Scholar 

  5. Kruse, M., Finkel, H.: A proposal for loop-transformation pragmas. In: de Supinski, B.R., Valero-Lara, P., Martorell, X., Mateo Bellido, S., Labarta, J. (eds.) IWOMP 2018. LNCS, vol. 11128, pp. 37–52. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98521-3_3

    CrossRef  Google Scholar 

  6. Kruse, M., Finkel, H.: User-directed loop-transformations in Clang. In: 2018 IEEE/ACM 5th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 49–58, November 2018. https://doi.org/10.1109/LLVM-HPC.2018.8639402

  7. OpenACC-Standard.org: The OpenACC Application Programming Interface Version 4.0, November 2017

    Google Scholar 

  8. Pouchet, L.N., Yuki, T.: Polybench 4.2.1 beta. https://sourceforge.net/projects/polybench

  9. Spiegel, J., Robie, J., Dyck, M.: XML Path Language (XPath) 3.1. W3C recommendation, W3C, March 2017. https://www.w3.org/TR/2017/REC-xpath-31-20170321/

Download references

Acknowledgments

This research was supported by the Exascale Computing Project (17-SC-20-SC), a collaborative effort of two U.S. Department of Energy organizations (Office of Science and the National Nuclear Security Administration) responsible for the planning and preparation of a capable exascale ecosystem, including software, applications, hardware, advanced system engineering, and early testbed platforms, in support of the nation’s exascale computing imperative.

This research used resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357.

Author information

Authors and Affiliations

  1. Argonne Leadership Computing Facility, Argonne National Laboratory, Lemont, IL, 60439, USA

    Michael Kruse & Hal Finkel

Authors
  1. Michael Kruse
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hal Finkel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Michael Kruse or Hal Finkel .

Editor information

Editors and Affiliations

  1. University of Auckland, Auckland, New Zealand

    Xing Fan

  2. Lawrence Livermore National Laboratory, Livermore, CA, USA

    Bronis R. de Supinski

  3. University of Auckland, Auckland, New Zealand

    Oliver Sinnen

  4. University of Auckland, Auckland, New Zealand

    Nasser Giacaman

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Kruse, M., Finkel, H. (2019). Design and Use of Loop-Transformation Pragmas. In: Fan, X., de Supinski, B., Sinnen, O., Giacaman, N. (eds) OpenMP: Conquering the Full Hardware Spectrum. IWOMP 2019. Lecture Notes in Computer Science(), vol 11718. Springer, Cham. https://doi.org/10.1007/978-3-030-28596-8_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-28596-8_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-28595-1

  • Online ISBN: 978-3-030-28596-8

  • eBook Packages: Computer ScienceComputer Science (R0)