Specification and Performance Evaluation of Parallel I/O Interfaces for OpenMP

  • Kshitij Mehta
  • Edgar Gabriel
  • Barbara Chapman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7312)


One of the most severe performance limitations of parallel applications today stems from the performance of I/O operations. Numerous projects have shown, that parallel I/O in combination with parallel file systems can significantly improve the performance of I/O operations. However, as of today there is no support for parallel I/O operations for applications using shared-memory programming models such as OpenMP. This paper introduces parallel I/O interfaces for OpenMP. We discuss the rationale of our design decisions, present the interface specification and a prototype implementation with the OpenUH compiler. We evaluate the performance of our implementation for various benchmarks on different file systems and demonstrate the benefits of the new interfaces.


Message Passing Interface Prototype Implementation Parallel Region Private Variable Solid State Disk 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gabriel, E., Venkatesan, V., Shah, S.: Towards high performance cell segmentation in multispectral fine needle aspiration cytology of thyroid lesions. Computational Methods and Programs in Biomedicine 98(3), 231–240 (2009)CrossRefGoogle Scholar
  2. 2.
    OpenMP Application Review Board: OpenMP Application Program Interface, Draft 3.0 (October 2007)Google Scholar
  3. 3.
    Message Passing Interface Forum: MPI-2.2: Extensions to the Message Passing Interface (September 2009),
  4. 4.
    El-Ghazawi, T., Cantonnet, F., Saha, P., Thakur, R., Ross, R., Bonachea, D.: UPC-IO: A Parallel I/O API for UPC. V1.0 (2004)Google Scholar
  5. 5.
    Group, H.D.F.: HDF5 Reference Manual. Release 1.6.3, National Center for Supercomputing Application (NCSA), University of Illinois at Urbana-Champaign (September 2004)Google Scholar
  6. 6.
    Li, J., Liao, W.K., Choudhary, A., Ross, R., Thakur, R., Gropp, W., Latham, R., Siegel, A., Gallagher, B., Zingale, M.: Parallel netcdf: A high-performance scientific i/o interface. In: Proceedings of the 2003 ACM/IEEE Conference on Supercomputing, SC 2003, pp. 39–49. ACM, New York (2003)CrossRefGoogle Scholar
  7. 7.
    Ayguadé, E., Badia, R.M., Bellens, P., Cabrera, D., Duran, A., Ferrer, R., González, M., Igual, F.D., Jiménez-González, D., Labarta, J.: Extending openmp to survive the heterogeneous multi-core era. International Journal of Parallel Programming 38(5-6), 440–459 (2010)zbMATHCrossRefGoogle Scholar
  8. 8.
    Liao, C., Hernandez, O., Chapman, B., Chen, W., Zheng, W.: OpenUH: An optimizing, portable OpenMP compiler. In: 12th Workshop on Compilers for Parallel Computers (January 2006)Google Scholar
  9. 9.
    PVFS2 webpage: Parallel Virtual File System,
  10. 10.
    Wong, P., der Wijngaart, R.F.V.: NAS Parallel Benchmarks I/O Version 3.0. Technical Report NAS-03-002, Computer Sciences Corporation, NASA Advanced Supercomputing (NAS) DivisionGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Kshitij Mehta
    • 1
  • Edgar Gabriel
    • 1
  • Barbara Chapman
    • 1
  1. 1.Department of Computer ScienceUniversity of HoustonUSA

Personalised recommendations