Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation

Stefan  Radicke; Jens-Uwe  Hahn; Qi Wang; Christos  Grecos

doi:10.1007/978-3-319-25915-4_21

Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation

Stefan Radicke, Jens-Uwe Hahn, Qi Wang, Christos Grecos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

The High Efficiency Video Coding (HEVC) standard provides an outstanding compression performance and is thus ideally suited for Ultra High Definition (UHD) content. However, the complexity of the encoder is substantial and therefore highly optimized implementations are required to achieve reasonable speeds. For this purpose, high-level parallelization mechanisms like Wavefront Parallel Processing (WPP), can be used to leverage modern multi-core hardware. In this work, the WPP mechanism is theoretically analyzed and a non-intrusive implementation of it based on the reference test model HM-13.0 is presented. Furthermore, a novel extension for heterogeneous computing platforms called Heterogeneous WPP (HWPP) is proposed which largely increases the achievable speedups. To demonstrate the power of HWPP, a Graphics Processing Unit (GPU) accelerated Motion Estimation (ME) algorithm is integrated. Based on a large amount of experimental data, it is shown that the speedups achieved with WPP and HWPP reach up to 8.9 and 17.9 times, respectively.

Original language	English
Title of host publication	E-Business and Telecommunications
Subtitle of host publication	11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers
Editors	M. Obaidat , A. Holzinger , J. Filipe
Publisher	Springer
Pages	393-417
Volume	554
ISBN (Electronic)	978-3-319-25915-4
ISBN (Print)	978-3-319-25914-7
DOIs	https://doi.org/10.1007/978-3-319-25915-4_21
Publication status	Published - Dec 2015

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
ISSN (Print)	1865-0929

Keywords

High Efficiency Video Coding (HEVC)
Wavefront Parallel Processing (WPP)
Heterogeneous WPP (HWPP)
Graphics Processing Unit (GPU)
Motion Estimation (ME)
Massively parallel computing

Access to Document

10.1007/978-3-319-25915-4_21

Cite this

Radicke, S., Hahn, J.-U., Wang, Q., & Grecos, C. (2015). Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation. In M. Obaidat , A. Holzinger , & J. Filipe (Eds.), E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers (Vol. 554, pp. 393-417). (Communications in Computer and Information Science). Springer. https://doi.org/10.1007/978-3-319-25915-4_21

Radicke, Stefan ; Hahn, Jens-Uwe ; Wang, Qi et al. / Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation. E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers. editor / M. Obaidat ; A. Holzinger ; J. Filipe . Vol. 554 Springer, 2015. pp. 393-417 (Communications in Computer and Information Science).

@inproceedings{6204b535a77d48519910596bcec87746,

title = "Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation",

abstract = "The High Efficiency Video Coding (HEVC) standard provides an outstanding compression performance and is thus ideally suited for Ultra High Definition (UHD) content. However, the complexity of the encoder is substantial and therefore highly optimized implementations are required to achieve reasonable speeds. For this purpose, high-level parallelization mechanisms like Wavefront Parallel Processing (WPP), can be used to leverage modern multi-core hardware. In this work, the WPP mechanism is theoretically analyzed and a non-intrusive implementation of it based on the reference test model HM-13.0 is presented. Furthermore, a novel extension for heterogeneous computing platforms called Heterogeneous WPP (HWPP) is proposed which largely increases the achievable speedups. To demonstrate the power of HWPP, a Graphics Processing Unit (GPU) accelerated Motion Estimation (ME) algorithm is integrated. Based on a large amount of experimental data, it is shown that the speedups achieved with WPP and HWPP reach up to 8.9 and 17.9 times, respectively.",

keywords = "High Efficiency Video Coding (HEVC) , Wavefront Parallel Processing (WPP), Heterogeneous WPP (HWPP), Graphics Processing Unit (GPU), Motion Estimation (ME) , Massively parallel computing",

author = "Stefan Radicke and Jens-Uwe Hahn and Qi Wang and Christos Grecos",

year = "2015",

month = dec,

doi = "10.1007/978-3-319-25915-4_21",

language = "English",

isbn = "978-3-319-25914-7",

volume = "554",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "393--417",

editor = "{Obaidat }, M. and {Holzinger }, A. and {Filipe }, J.",

booktitle = "E-Business and Telecommunications",

address = "United States",

}

Radicke, S, Hahn, J-U, Wang, Q & Grecos, C 2015, Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation. in M Obaidat , A Holzinger & J Filipe (eds), E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers. vol. 554, Communications in Computer and Information Science, Springer, pp. 393-417. https://doi.org/10.1007/978-3-319-25915-4_21

Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation. / Radicke, Stefan ; Hahn, Jens-Uwe ; Wang, Qi et al.
E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers. ed. / M. Obaidat ; A. Holzinger ; J. Filipe . Vol. 554 Springer, 2015. p. 393-417 (Communications in Computer and Information Science).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation

AU - Radicke, Stefan

AU - Hahn, Jens-Uwe

AU - Wang, Qi

AU - Grecos, Christos

PY - 2015/12

Y1 - 2015/12

N2 - The High Efficiency Video Coding (HEVC) standard provides an outstanding compression performance and is thus ideally suited for Ultra High Definition (UHD) content. However, the complexity of the encoder is substantial and therefore highly optimized implementations are required to achieve reasonable speeds. For this purpose, high-level parallelization mechanisms like Wavefront Parallel Processing (WPP), can be used to leverage modern multi-core hardware. In this work, the WPP mechanism is theoretically analyzed and a non-intrusive implementation of it based on the reference test model HM-13.0 is presented. Furthermore, a novel extension for heterogeneous computing platforms called Heterogeneous WPP (HWPP) is proposed which largely increases the achievable speedups. To demonstrate the power of HWPP, a Graphics Processing Unit (GPU) accelerated Motion Estimation (ME) algorithm is integrated. Based on a large amount of experimental data, it is shown that the speedups achieved with WPP and HWPP reach up to 8.9 and 17.9 times, respectively.

AB - The High Efficiency Video Coding (HEVC) standard provides an outstanding compression performance and is thus ideally suited for Ultra High Definition (UHD) content. However, the complexity of the encoder is substantial and therefore highly optimized implementations are required to achieve reasonable speeds. For this purpose, high-level parallelization mechanisms like Wavefront Parallel Processing (WPP), can be used to leverage modern multi-core hardware. In this work, the WPP mechanism is theoretically analyzed and a non-intrusive implementation of it based on the reference test model HM-13.0 is presented. Furthermore, a novel extension for heterogeneous computing platforms called Heterogeneous WPP (HWPP) is proposed which largely increases the achievable speedups. To demonstrate the power of HWPP, a Graphics Processing Unit (GPU) accelerated Motion Estimation (ME) algorithm is integrated. Based on a large amount of experimental data, it is shown that the speedups achieved with WPP and HWPP reach up to 8.9 and 17.9 times, respectively.

KW - High Efficiency Video Coding (HEVC)

KW - Wavefront Parallel Processing (WPP)

KW - Heterogeneous WPP (HWPP)

KW - Graphics Processing Unit (GPU)

KW - Motion Estimation (ME)

KW - Massively parallel computing

U2 - 10.1007/978-3-319-25915-4_21

DO - 10.1007/978-3-319-25915-4_21

M3 - Conference contribution

SN - 978-3-319-25914-7

VL - 554

T3 - Communications in Computer and Information Science

SP - 393

EP - 417

BT - E-Business and Telecommunications

A2 - Obaidat , M.

A2 - Holzinger , A.

A2 - Filipe , J.

PB - Springer

ER -

Radicke S, Hahn JU, Wang Q, Grecos C. Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation. In Obaidat M, Holzinger A, Filipe J, editors, E-Business and Telecommunications: 11th International Joint Conference, ICETE 2014, Vienna, Austria, August 28-30, 2014, Revised Selected Papers. Vol. 554. Springer. 2015. p. 393-417. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-25915-4_21

Many-core HEVC encoding based on wavefront parallel processing and GPU-accelerated motion estimation

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this