Intra prediction architecture for H.264/AVC QFHD encoder

Gang He, Dajiang Zhou, Jinjia Zhou, Satoshi Goto

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

6 Citations (Scopus)

Abstract

This paper proposes a high-performance intra prediction architecture that can support H.264/AVC high profile. The proposed MB/block co-reordering can avoid data dependency and improve pipeline utilization. Therefore, the timing constraint of real-time 4kx2k encoding can be achieved with negligible quality loss. 16×16 prediction engine and 8×8 prediction engine work parallel for prediction and coefficients generating. A reordering interlaced reconstruction is also designed for fully pipelined architecture. It takes only 160 cycles to process one macroblock (MB). Hardware utilization of prediction and reconstruction modules is almost 100%. Furthermore, PE-reusable 8×8 intra predictor and hybrid SAD & SATD mode decision are proposed to save hardware cost. The design is implemented by 90nm CMOS technology with 113.2k gates and can encode 4kx2k video sequences at 60 fps with operation frequency of 310MHz.

Original languageEnglish
Title of host publication28th Picture Coding Symposium, PCS 2010
Pages450-453
Number of pages4
DOIs
Publication statusPublished - 2010
Event28th Picture Coding Symposium, PCS 2010 - Nagoya
Duration: 2010 Dec 82010 Dec 10

Other

Other28th Picture Coding Symposium, PCS 2010
CityNagoya
Period10/12/810/12/10

Fingerprint

Engines
Hardware
Pipelines
Costs

Keywords

  • Fukuoka
  • H.264/AVC
  • Hardware architecture 2-7 Hibikino
  • Intra prediction
  • Japan
  • Kitakyushu
  • Wakamatsu-ku

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

He, G., Zhou, D., Zhou, J., & Goto, S. (2010). Intra prediction architecture for H.264/AVC QFHD encoder. In 28th Picture Coding Symposium, PCS 2010 (pp. 450-453). [5702533] https://doi.org/10.1109/PCS.2010.5702533

Intra prediction architecture for H.264/AVC QFHD encoder. / He, Gang; Zhou, Dajiang; Zhou, Jinjia; Goto, Satoshi.

28th Picture Coding Symposium, PCS 2010. 2010. p. 450-453 5702533.

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

He, G, Zhou, D, Zhou, J & Goto, S 2010, Intra prediction architecture for H.264/AVC QFHD encoder. in 28th Picture Coding Symposium, PCS 2010., 5702533, pp. 450-453, 28th Picture Coding Symposium, PCS 2010, Nagoya, 10/12/8. https://doi.org/10.1109/PCS.2010.5702533
He G, Zhou D, Zhou J, Goto S. Intra prediction architecture for H.264/AVC QFHD encoder. In 28th Picture Coding Symposium, PCS 2010. 2010. p. 450-453. 5702533 https://doi.org/10.1109/PCS.2010.5702533
He, Gang ; Zhou, Dajiang ; Zhou, Jinjia ; Goto, Satoshi. / Intra prediction architecture for H.264/AVC QFHD encoder. 28th Picture Coding Symposium, PCS 2010. 2010. pp. 450-453
@inproceedings{63f42a78bf42496bb85c5d1517354c92,
title = "Intra prediction architecture for H.264/AVC QFHD encoder",
abstract = "This paper proposes a high-performance intra prediction architecture that can support H.264/AVC high profile. The proposed MB/block co-reordering can avoid data dependency and improve pipeline utilization. Therefore, the timing constraint of real-time 4kx2k encoding can be achieved with negligible quality loss. 16×16 prediction engine and 8×8 prediction engine work parallel for prediction and coefficients generating. A reordering interlaced reconstruction is also designed for fully pipelined architecture. It takes only 160 cycles to process one macroblock (MB). Hardware utilization of prediction and reconstruction modules is almost 100{\%}. Furthermore, PE-reusable 8×8 intra predictor and hybrid SAD & SATD mode decision are proposed to save hardware cost. The design is implemented by 90nm CMOS technology with 113.2k gates and can encode 4kx2k video sequences at 60 fps with operation frequency of 310MHz.",
keywords = "Fukuoka, H.264/AVC, Hardware architecture 2-7 Hibikino, Intra prediction, Japan, Kitakyushu, Wakamatsu-ku",
author = "Gang He and Dajiang Zhou and Jinjia Zhou and Satoshi Goto",
year = "2010",
doi = "10.1109/PCS.2010.5702533",
language = "English",
isbn = "9781424471348",
pages = "450--453",
booktitle = "28th Picture Coding Symposium, PCS 2010",

}

TY - GEN

T1 - Intra prediction architecture for H.264/AVC QFHD encoder

AU - He, Gang

AU - Zhou, Dajiang

AU - Zhou, Jinjia

AU - Goto, Satoshi

PY - 2010

Y1 - 2010

N2 - This paper proposes a high-performance intra prediction architecture that can support H.264/AVC high profile. The proposed MB/block co-reordering can avoid data dependency and improve pipeline utilization. Therefore, the timing constraint of real-time 4kx2k encoding can be achieved with negligible quality loss. 16×16 prediction engine and 8×8 prediction engine work parallel for prediction and coefficients generating. A reordering interlaced reconstruction is also designed for fully pipelined architecture. It takes only 160 cycles to process one macroblock (MB). Hardware utilization of prediction and reconstruction modules is almost 100%. Furthermore, PE-reusable 8×8 intra predictor and hybrid SAD & SATD mode decision are proposed to save hardware cost. The design is implemented by 90nm CMOS technology with 113.2k gates and can encode 4kx2k video sequences at 60 fps with operation frequency of 310MHz.

AB - This paper proposes a high-performance intra prediction architecture that can support H.264/AVC high profile. The proposed MB/block co-reordering can avoid data dependency and improve pipeline utilization. Therefore, the timing constraint of real-time 4kx2k encoding can be achieved with negligible quality loss. 16×16 prediction engine and 8×8 prediction engine work parallel for prediction and coefficients generating. A reordering interlaced reconstruction is also designed for fully pipelined architecture. It takes only 160 cycles to process one macroblock (MB). Hardware utilization of prediction and reconstruction modules is almost 100%. Furthermore, PE-reusable 8×8 intra predictor and hybrid SAD & SATD mode decision are proposed to save hardware cost. The design is implemented by 90nm CMOS technology with 113.2k gates and can encode 4kx2k video sequences at 60 fps with operation frequency of 310MHz.

KW - Fukuoka

KW - H.264/AVC

KW - Hardware architecture 2-7 Hibikino

KW - Intra prediction

KW - Japan

KW - Kitakyushu

KW - Wakamatsu-ku

UR - http://www.scopus.com/inward/record.url?scp=79951789952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951789952&partnerID=8YFLogxK

U2 - 10.1109/PCS.2010.5702533

DO - 10.1109/PCS.2010.5702533

M3 - Conference contribution

SN - 9781424471348

SP - 450

EP - 453

BT - 28th Picture Coding Symposium, PCS 2010

ER -