OpenCL based high-quality HEVC motion estimation on GPU

Fan Wang, Dajiang Zhou, Satoshi Goto

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    9 Citations (Scopus)

    Abstract

    This paper presents a high quality H.265/HEVC motion estimation implementation with the cooperation of CPU and GPU. The data dependency from MVP (Motion Vector Predictor) restricts the degree of parallelism on GPU. To overcome the constraint from MVP, we propose to use an estimated MVP on GPU and the accurate MVP to refine the motion vector on CPU. GPU fully utilizes its tremendous parallel computing ability without the restriction from MVP. CPU makes up for the deviation from GPU with a small range refinement. Encoding speed benefits from the high degree of parallelism and compression performance is maintained by the CPU refinement. Experimental result shows that the speedup achieves 2.39 times and 32.77 times in the whole ×265 encoder with CPU SIMD (Single Instruction Multiple Data) on and off, respectively. On the other hand, the quality degradation is negligible with only 0.05% increase of BD-rate.

    Original languageEnglish
    Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1263-1267
    Number of pages5
    ISBN (Electronic)9781479957514
    DOIs
    Publication statusPublished - 2014 Jan 28

    Fingerprint

    Motion estimation
    Program processors
    Parallel processing systems
    Graphics processing unit
    Degradation

    Keywords

    • GPU
    • H.265
    • HEVC
    • motion estimation
    • parallel computing

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Wang, F., Zhou, D., & Goto, S. (2014). OpenCL based high-quality HEVC motion estimation on GPU. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 1263-1267). [7025252] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025252

    OpenCL based high-quality HEVC motion estimation on GPU. / Wang, Fan; Zhou, Dajiang; Goto, Satoshi.

    2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1263-1267 7025252.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Wang, F, Zhou, D & Goto, S 2014, OpenCL based high-quality HEVC motion estimation on GPU. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025252, Institute of Electrical and Electronics Engineers Inc., pp. 1263-1267. https://doi.org/10.1109/ICIP.2014.7025252
    Wang F, Zhou D, Goto S. OpenCL based high-quality HEVC motion estimation on GPU. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1263-1267. 7025252 https://doi.org/10.1109/ICIP.2014.7025252
    Wang, Fan ; Zhou, Dajiang ; Goto, Satoshi. / OpenCL based high-quality HEVC motion estimation on GPU. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1263-1267
    @inproceedings{0a0ef2ee016840578fb74a4778ff60e1,
    title = "OpenCL based high-quality HEVC motion estimation on GPU",
    abstract = "This paper presents a high quality H.265/HEVC motion estimation implementation with the cooperation of CPU and GPU. The data dependency from MVP (Motion Vector Predictor) restricts the degree of parallelism on GPU. To overcome the constraint from MVP, we propose to use an estimated MVP on GPU and the accurate MVP to refine the motion vector on CPU. GPU fully utilizes its tremendous parallel computing ability without the restriction from MVP. CPU makes up for the deviation from GPU with a small range refinement. Encoding speed benefits from the high degree of parallelism and compression performance is maintained by the CPU refinement. Experimental result shows that the speedup achieves 2.39 times and 32.77 times in the whole ×265 encoder with CPU SIMD (Single Instruction Multiple Data) on and off, respectively. On the other hand, the quality degradation is negligible with only 0.05{\%} increase of BD-rate.",
    keywords = "GPU, H.265, HEVC, motion estimation, parallel computing",
    author = "Fan Wang and Dajiang Zhou and Satoshi Goto",
    year = "2014",
    month = "1",
    day = "28",
    doi = "10.1109/ICIP.2014.7025252",
    language = "English",
    pages = "1263--1267",
    booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    address = "United States",

    }

    TY - GEN

    T1 - OpenCL based high-quality HEVC motion estimation on GPU

    AU - Wang, Fan

    AU - Zhou, Dajiang

    AU - Goto, Satoshi

    PY - 2014/1/28

    Y1 - 2014/1/28

    N2 - This paper presents a high quality H.265/HEVC motion estimation implementation with the cooperation of CPU and GPU. The data dependency from MVP (Motion Vector Predictor) restricts the degree of parallelism on GPU. To overcome the constraint from MVP, we propose to use an estimated MVP on GPU and the accurate MVP to refine the motion vector on CPU. GPU fully utilizes its tremendous parallel computing ability without the restriction from MVP. CPU makes up for the deviation from GPU with a small range refinement. Encoding speed benefits from the high degree of parallelism and compression performance is maintained by the CPU refinement. Experimental result shows that the speedup achieves 2.39 times and 32.77 times in the whole ×265 encoder with CPU SIMD (Single Instruction Multiple Data) on and off, respectively. On the other hand, the quality degradation is negligible with only 0.05% increase of BD-rate.

    AB - This paper presents a high quality H.265/HEVC motion estimation implementation with the cooperation of CPU and GPU. The data dependency from MVP (Motion Vector Predictor) restricts the degree of parallelism on GPU. To overcome the constraint from MVP, we propose to use an estimated MVP on GPU and the accurate MVP to refine the motion vector on CPU. GPU fully utilizes its tremendous parallel computing ability without the restriction from MVP. CPU makes up for the deviation from GPU with a small range refinement. Encoding speed benefits from the high degree of parallelism and compression performance is maintained by the CPU refinement. Experimental result shows that the speedup achieves 2.39 times and 32.77 times in the whole ×265 encoder with CPU SIMD (Single Instruction Multiple Data) on and off, respectively. On the other hand, the quality degradation is negligible with only 0.05% increase of BD-rate.

    KW - GPU

    KW - H.265

    KW - HEVC

    KW - motion estimation

    KW - parallel computing

    UR - http://www.scopus.com/inward/record.url?scp=84983121573&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84983121573&partnerID=8YFLogxK

    U2 - 10.1109/ICIP.2014.7025252

    DO - 10.1109/ICIP.2014.7025252

    M3 - Conference contribution

    AN - SCOPUS:84983121573

    SP - 1263

    EP - 1267

    BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -