Compressing the Incompressible with ISABELA: In-situ Reduction of Spatio-temporal Data

  • Sriram Lakshminarasimhan
  • Neil Shah
  • Stephane Ethier
  • Scott Klasky
  • Rob Latham
  • Rob Ross
  • Nagiza F. Samatova
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6852)

Abstract

Modern large-scale scientific simulations running on HPC systems generate data in the order of terabytes during a single run. To lessen the I/O load during a simulation run, scientists are forced to capture data infrequently, thereby making data collection an inherently lossy process. Yet, lossless compression techniques are hardly suitable for scientific data due to its inherently random nature; for the applications used here, they offer less than 10% compression rate. They also impose significant overhead during decompression, making them unsuitable for data analysis and visualization that require repeated data access.

To address this problem, we propose an effective method for In-situ Sort-And-B-spline Error-bounded Lossy Abatement (ISABELA) of scientific data that is widely regarded as effectively incompressible. With ISABELA, we apply a preconditioner to seemingly random and noisy data along spatial resolution to achieve an accurate fitting model that guarantees a ≥ 0.99 correlation with the original data. We further take advantage of temporal patterns in scientific data to compress data by ≈ 85%, while introducing only a negligible overhead on simulations in terms of runtime. ISABELA  significantly outperforms existing lossy compression methods, such as Wavelet compression. Moreover, besides being a communication-free and scalable compression technique, ISABELA  is an inherently local decompression method, namely it does not decode the entire data, making it attractive for random access.

Keywords

Lossy Compression B-spline In-situ Processing Data-intensive Application High Performance Computing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abbasi, H., Lofstead, J., Zheng, F., Klasky, S., Schwan, K., Wolf, M.: Extending I/O through high performance data services. In: Cluster Computing, Austin, TX, IEEE International (September 2007)Google Scholar
  2. 2.
    De Boor, C.: A Practical Guide to Splines. Springer, Heidelberg (1978)CrossRefMATHGoogle Scholar
  3. 3.
    Burtscher, M., Ratanaworabhan, P.: FPC: A high-speed compressor for double-precision floating-point data (2009), http://www.csl.cornell.edu/~burtscher/research/FPC/
  4. 4.
    Chou, J., Piegl, L.: Data reduction using cubic rational B-splines. IEEE Comput. Graph. Appl. 12, 60–68 (1992)CrossRefGoogle Scholar
  5. 5.
    Cover, T.M., Thomas, J.: Elements of information theory. Wiley-Interscience, New York (1991)CrossRefMATHGoogle Scholar
  6. 6.
    Frazier, M.W.: An introduction to Wavelets through linear algebra, p. 501. Springer, Heidelberg (1999)MATHGoogle Scholar
  7. 7.
    He, X., Shi, P.: Monotone B-spline smoothing. Journal of the American Statistical Association 93(442), 643–650 (1998)MathSciNetMATHGoogle Scholar
  8. 8.
    Isenburg, M., Lindstrom, P., Snoeyink, J.: Lossless compression of predicted floating-point geometry. Computer-Aided Design 37(8), 869–877 (2005); CAD 2004 Special Issue: Modelling and Geometry Representations for CADCrossRefMATHGoogle Scholar
  9. 9.
    Lee, S., Wolberg, G., Shin, S.Y.: Scattered data interpolation with multilevel B-splines. IEEE Trans. on Viz. and Comp. Graphics 3(3), 228–244 (1997)CrossRefGoogle Scholar
  10. 10.
    Lindstrom, P., Isenburg, M.: Fast and efficient compression of floating-point data. IEEE Trans. on Viz. and Comp. Graphics 12(5), 1245–1250 (2006)CrossRefGoogle Scholar
  11. 11.
    Lofstead, J., Zheng, F., Klasky, S., Schwan, K.: Adaptable, metadata rich IO methods for portable high performance IO. In: IPDPS 2009, Rome, Italy (May 2009)Google Scholar
  12. 12.
    Ma, K., Wang, C., Yu, H., Tikhonova, A.: In-situ processing and visualization for ultrascale simulations. Journal of Physics: Conference Series 78(1), 012043 (2007)Google Scholar
  13. 13.
    Ratanaworabhan, P., Ke, J., Burtscher, M.: Fast lossless compression of scientific floating-point data. In: Proc. of the DCC (2006)Google Scholar
  14. 14.
    Sayood, K.: Introduction to data compression. Morgan Kaufmann Publishers Inc., San Francisco (1996)MATHGoogle Scholar
  15. 15.
    Wang, W.X., al, e.: Gyro-kinetic simulation of global turbulent transport properties in Tokamak experiments. Physics of Plasmas 13(9), 092505 (2006)CrossRefGoogle Scholar
  16. 16.
    Welch, T.A.: A technique for high-performance data compression. Computer 17, 8–19 (1984)CrossRefGoogle Scholar
  17. 17.
    Wold, S.: Spline functions in data analysis. American Statistical Association and American Society for Quality 16(1), 1–11 (1974)MathSciNetMATHGoogle Scholar
  18. 18.
    Zheng, F., al, e.: PreDatA–preparatory data analytics on peta-scale machines. In: IPDPS, Atlanta, GA (April 2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sriram Lakshminarasimhan
    • 1
    • 2
  • Neil Shah
    • 1
  • Stephane Ethier
    • 3
  • Scott Klasky
    • 2
  • Rob Latham
    • 4
  • Rob Ross
    • 4
  • Nagiza F. Samatova
    • 1
    • 2
  1. 1.North Carolina State UniversityRaleighUSA
  2. 2.Oak Ridge National LaboratoryOak RidgeUSA
  3. 3.Princeton Plasma Physics LaboratoryPrincetonUSA
  4. 4.Argonne National LaboratoryArgonneUSA

Personalised recommendations