Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264

Liu Zhenyu, Satoshi Goto, Takeshi Ikenaga

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

10 Citations (Scopus)

Abstract

Variable block size motion estimation algorithm is the efficient approach to reduce the temporal redundancies and it has been adopted by the latest video coding standard H.264/AVC. The computational complexity augment coming from the variable block size technique makes the hardwired accelerator essential, especially for real-time applications. In this paper, the authors apply the architecture level and the circuits level approaches to improve the performance of Propagate Partial SAD and SAD Tree hardwired engines, which outperform other counterparts when considering the impact of supporting the variable block size technique. Experiments demonstrate that by using the proposed approaches, compared with the original architectures, 14.7% and 18.0% hardware cost can be saved for Propagate Partial SAD architecture and SAD Tree architecture, respectively. With TSMC 0.18 mm 1P6M CMOS technology, the proposed Propagate Partial SAD architecture attains 231.6MHz operating frequency at a cost of 84.1k gates. Correspondingly, the execution speed of the optimized SAD Tree architecture is improved to 204.8MHz with 88.5k gate hardware overhead.

Original languageEnglish
Title of host publication26th IEEE International Conference on Computer Design 2008, ICCD
Pages328-333
Number of pages6
DOIs
Publication statusPublished - 2008
Event26th IEEE International Conference on Computer Design 2008, ICCD - Lake Tahoe, CA
Duration: 2008 Oct 122008 Oct 15

Other

Other26th IEEE International Conference on Computer Design 2008, ICCD
CityLake Tahoe, CA
Period08/10/1208/10/15

Fingerprint

Motion estimation
Engines
Hardware
Image coding
Particle accelerators
Redundancy
Costs
Computational complexity
Networks (circuits)
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Zhenyu, L., Goto, S., & Ikenaga, T. (2008). Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264. In 26th IEEE International Conference on Computer Design 2008, ICCD (pp. 328-333). [4751881] https://doi.org/10.1109/ICCD.2008.4751881

Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264. / Zhenyu, Liu; Goto, Satoshi; Ikenaga, Takeshi.

26th IEEE International Conference on Computer Design 2008, ICCD. 2008. p. 328-333 4751881.

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

Zhenyu, L, Goto, S & Ikenaga, T 2008, Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264. in 26th IEEE International Conference on Computer Design 2008, ICCD., 4751881, pp. 328-333, 26th IEEE International Conference on Computer Design 2008, ICCD, Lake Tahoe, CA, 08/10/12. https://doi.org/10.1109/ICCD.2008.4751881
Zhenyu L, Goto S, Ikenaga T. Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264. In 26th IEEE International Conference on Computer Design 2008, ICCD. 2008. p. 328-333. 4751881 https://doi.org/10.1109/ICCD.2008.4751881
Zhenyu, Liu ; Goto, Satoshi ; Ikenaga, Takeshi. / Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264. 26th IEEE International Conference on Computer Design 2008, ICCD. 2008. pp. 328-333
@inproceedings{005396fae6b44a6b9ea7c35eb3c659e2,
title = "Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264",
abstract = "Variable block size motion estimation algorithm is the efficient approach to reduce the temporal redundancies and it has been adopted by the latest video coding standard H.264/AVC. The computational complexity augment coming from the variable block size technique makes the hardwired accelerator essential, especially for real-time applications. In this paper, the authors apply the architecture level and the circuits level approaches to improve the performance of Propagate Partial SAD and SAD Tree hardwired engines, which outperform other counterparts when considering the impact of supporting the variable block size technique. Experiments demonstrate that by using the proposed approaches, compared with the original architectures, 14.7{\%} and 18.0{\%} hardware cost can be saved for Propagate Partial SAD architecture and SAD Tree architecture, respectively. With TSMC 0.18 mm 1P6M CMOS technology, the proposed Propagate Partial SAD architecture attains 231.6MHz operating frequency at a cost of 84.1k gates. Correspondingly, the execution speed of the optimized SAD Tree architecture is improved to 204.8MHz with 88.5k gate hardware overhead.",
author = "Liu Zhenyu and Satoshi Goto and Takeshi Ikenaga",
year = "2008",
doi = "10.1109/ICCD.2008.4751881",
language = "English",
isbn = "9781424426584",
pages = "328--333",
booktitle = "26th IEEE International Conference on Computer Design 2008, ICCD",

}

TY - GEN

T1 - Optimization of propagate partial SAD and SAD tree motion estimation hardwired engine for H.264

AU - Zhenyu, Liu

AU - Goto, Satoshi

AU - Ikenaga, Takeshi

PY - 2008

Y1 - 2008

N2 - Variable block size motion estimation algorithm is the efficient approach to reduce the temporal redundancies and it has been adopted by the latest video coding standard H.264/AVC. The computational complexity augment coming from the variable block size technique makes the hardwired accelerator essential, especially for real-time applications. In this paper, the authors apply the architecture level and the circuits level approaches to improve the performance of Propagate Partial SAD and SAD Tree hardwired engines, which outperform other counterparts when considering the impact of supporting the variable block size technique. Experiments demonstrate that by using the proposed approaches, compared with the original architectures, 14.7% and 18.0% hardware cost can be saved for Propagate Partial SAD architecture and SAD Tree architecture, respectively. With TSMC 0.18 mm 1P6M CMOS technology, the proposed Propagate Partial SAD architecture attains 231.6MHz operating frequency at a cost of 84.1k gates. Correspondingly, the execution speed of the optimized SAD Tree architecture is improved to 204.8MHz with 88.5k gate hardware overhead.

AB - Variable block size motion estimation algorithm is the efficient approach to reduce the temporal redundancies and it has been adopted by the latest video coding standard H.264/AVC. The computational complexity augment coming from the variable block size technique makes the hardwired accelerator essential, especially for real-time applications. In this paper, the authors apply the architecture level and the circuits level approaches to improve the performance of Propagate Partial SAD and SAD Tree hardwired engines, which outperform other counterparts when considering the impact of supporting the variable block size technique. Experiments demonstrate that by using the proposed approaches, compared with the original architectures, 14.7% and 18.0% hardware cost can be saved for Propagate Partial SAD architecture and SAD Tree architecture, respectively. With TSMC 0.18 mm 1P6M CMOS technology, the proposed Propagate Partial SAD architecture attains 231.6MHz operating frequency at a cost of 84.1k gates. Correspondingly, the execution speed of the optimized SAD Tree architecture is improved to 204.8MHz with 88.5k gate hardware overhead.

UR - http://www.scopus.com/inward/record.url?scp=62349134012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62349134012&partnerID=8YFLogxK

U2 - 10.1109/ICCD.2008.4751881

DO - 10.1109/ICCD.2008.4751881

M3 - Conference contribution

SN - 9781424426584

SP - 328

EP - 333

BT - 26th IEEE International Conference on Computer Design 2008, ICCD

ER -