• DocumentCode
    2693287
  • Title

    H.264/AVC decoder parallelization and optimization on asymetric multicore platform using dynamic load balancing

  • Author

    Kim, Yun-il ; Kim, Jong-Tae ; Bae, Sehyun ; Baik, Hyunki ; Song, Hyo Jung

  • Author_Institution
    Software Labs., Samsung Electron. Co., Ltd., Suwon
  • fYear
    2008
  • fDate
    June 23 2008-April 26 2008
  • Firstpage
    1001
  • Lastpage
    1004
  • Abstract
    We propose a new method for H.264/AVC parallel decoder implementation on the CELL Broadband Engine processor. To decode the full HD H.264 stream in real time, the high performance processing is required due to the high computation and complexity. Our decoder exploits the functional partition method to parallelize the H.264 decoder on multicore platform. The load of performance critical module is dynamically balanced with less computational module to fully utilize of the multicore processors. The experimental results of proposed load balancing method show that it runs about 1.4 times faster than the normal parallel decoder with same hardware requirement - 1 PPE and 3 SPEs. This result is more than 4 times faster performance than that of the single core decoder - PPE only.
  • Keywords
    microprocessor chips; parallel architectures; resource allocation; video coding; CELL Broadband Engine processor; H.264/AVC decoder parallelization; H.264/AVC parallel decoder implementation; asymetric multicore platform; computational module; dynamic load balancing; functional partition method; hardware requirement; high performance processing; multicore processors; performance critical module; Automatic voltage control; Decoding; Engines; Hardware; High definition video; Load management; Motion compensation; Multicore processing; Process design; Streaming media; Cell Broadband Engine Architecture; Dynamic load balance; H.264; Multi-core; parallelization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Multimedia and Expo, 2008 IEEE International Conference on
  • Conference_Location
    Hannover
  • Print_ISBN
    978-1-4244-2570-9
  • Electronic_ISBN
    978-1-4244-2571-6
  • Type

    conf

  • DOI
    10.1109/ICME.2008.4607606
  • Filename
    4607606