Parallel Hardware/Software Architecture for the BWT and LZ77 Lossless Data Compression Algorithms

Arquitectura Hardware/Software Paralela para los Algoritmos de Compresión de Datos sin Pérdida BWT y LZ77

Virgilio Zuñiga Grajeda, Claudia Feregrino Uribe and Rene Cumplido Parra

National Institute for Astrophysics, Optics and Electronics Luis Enrique Erro No. 1. Tonantzintla, Puebla, Mexico. Postal Code: 72840 virgilio@inaoep.mx ; cferegrino@inaoep.mx ; rcumplido@inaoep.mx

Article received on july 25, 2006
Accepted on october 2, 2006

Abstract.

Nowadays, the use of digital communication systems has increased in such a way that network bandwidth is affected. This problem can be solved by implementing data compression algorithms in communication devices to reduce the amount of data to be transmitted. However, the design of large hardware data compression models implies to consider an efficient use of the silicon area. This work proposes the conjunction of two different hardware lossless data compression approaches which share common hardware elements. The project also involves the design of a hardware/software architecture to exploit parallelism increasing execution speed while keeping flexibility. A custom coprocessor unit executes the compute–intense tasks of the Burrows–Wheeler Transform and the Lempel–Ziv lossless data compression schemes. This coprocessor unit is controlled by a SPARC V8 compatible general purpose microprocessor called LEON2.

Keywords: Data compression, Burrows–Wheeler Transform, Lempel–Ziv, Coprocessor, LEON2.

Resumen.

Hoy en día, el uso de sistemas de comunicación digitales ha aumentado de tal forma que el ancho de banda en las redes resulta afectado. Este problema puede solucionarse implementando algoritmos de compresión de datos en dispositivos de comunicación reduciendo la cantidad de datos a transmitir. Sin embargo, el diseño de modelos complejos de compresión de datos en hardware implica considerar el uso eficiente de la superficie de silicio. Este trabajo propone la combinación de dos esquemas diferentes de compresión de datos sin pérdida que compartan elementos comunes. Este proyecto también trata el diseño de una arquitectura hardware/software que explote el paralelismo e incremente la velocidad de ejecución manteniendo su flexibilidad. Un coprocesador ejecuta las tareas computacionalmente intensas de los esquemas de compresión Burrows–Wheeler Transform y Lempel–Ziv. El coprocesador es controlado por un microprocesador de propósito general compatible con la arquitectura SPARC V8 llamado LEON2.

Palabras clave: Compresión de Datos, Transformada de Burrows–Wheeler, Lempel–Ziv, Coprocesador, LEON2.

DESCARGAR ARTÍCULO EN FORMATO PDF

Acknowledgments

The authors acknowledge the financial support from the Mexican National Council for Science and Technology (CONACyT), grant number 181512.

References

1. N. Abramson. Information Theory and Coding. McGraw–Hill, New York, 1963.        [ Links ]

2. M. Burrows and D. J. Wheeler. A block–sorting lossless data compression algorithm. Technical Report 124, SRC (digital, Palo Alto), May 1994.        [ Links ]

3. J. G. Cleary and I. H. Witten. Data compression using adaptive coding and partial string matching. IEEE Transactions on Communications, 32(4):396–402, Apr. 1984.        [ Links ]

4. T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to Algorithms. The MIT Press and McGraw–Hill Book Company, second edition, 2001.        [ Links ]

5. C. Ebeling, D. C. Cronquist, and P. Franklin. RaPiD – reconfigurable pipelined datapath. In R. Hartenstein and M. Glesner, editors, th International Workshop on Field–Programmable Logic and Compilers, pages 126–135. Springer–Verlag, Apr. 1996.        [ Links ]

6. Gaisler Research. http://www.gaisler.com/. (Accessed September, 2005).        [ Links ]

7. Gaisler Research. LEON2 Processor User's Manual, 1.0.30 edition, July 2005. http://www.gaisler.com/, (Accessed September, 2005).        [ Links ]

8. GNU Lesser General Public License. http://www.gnu.org/copyleft/, Feb. 1999. (Accessed September, 2005).        [ Links ]

9. S. Goldstein, H. Schmit, M. Budiu, S. Cadambi, M. Moe, R. Taylor, and R. Laufer. PipeRench: A co–processor for streaming multimedia acceleration. In D. DeGroot, editor, Proceedings of the 26th Annual International Symposium on Computer Architecture, Computer Architecture News, pages 28–41, New York, N.Y., May 1999. ACM Press.        [ Links ]

10. J. R. Hauser and J. Wawrzynek. Garp: A MIPS processor with a reconfigurable coprocessor. In K. L. C. S. Press, editor, IEEE Symposium on FPGAs for Custom Computing Machines, pages 12–21, Los Alamitos, CA, Apr. 1997. IEEE Computer Society Press.        [ Links ]

11. D. A. Huffman. A method for the construction of minimum redundancy codes. Proceedings of the Institute of Electronics and Radio Engineers, 4(9):1098–1101, Sept. 1952.        [ Links ]

12. S. Jones. 100 Mbit/s adaptive data compressor design using selectively shiftable content–addressable memory. IEE Proceedings–G, 139(4):498–502, Aug. 1992.        [ Links ]

13. A. Mukherjee, N. Motgi, J. Becker, A. Friebe, C. Habermann, and M. Glesner. Prototyping of efficient hardware algorithms for data compression in future communication systems. In IEEE International Workshop on Rapid System Prototyping, pages 58–63, June 2001.        [ Links ]

14. M. Nelson and J.–L. Gailly. The Data Compression Book. M & T Books, second edition, 1996.        [ Links ]

15. D. Salomon. Data Compression: The Complete Reference. Springer–Verlag, third edition, 2004.        [ Links ]

16. J. Seward. http://www.bzip.org/. (Accessed September, 2005).        [ Links ]

17. SPARC International Inc. The SPARC Architecture Manual, Version 8, 1992. http://www.sparc.org/, (Accessed September, 2005).        [ Links ]

18. Sun Microsystems. http://www.sun.com/. (Accessed September, 2005).        [ Links ]

19. Sun Microsystems, Inc. SPARC Assembly Language Reference Manual, May 2002. http://docs.sun.com/, (Accessed September, 2005).        [ Links ]

20. R.–Y. Yang and C.–Y. Lee. High–throughput data compressor designs using content addressable memory. In International Symposium on Circuits and Systems, pages 147–150, 1994.        [ Links ]

21. J. Ziv and A. Lempel. A universal algorithm for sequential data compression. IEEE Transactions on Information Theory, 23(3):337–343, May 1977.        [ Links ]