Data dependency reduction for parallelism enhancement of HEVC decoder

Song Hyun Jo, Yong Ho Song

Research output: Contribution to journalLetter

Abstract

HEVC is a video codec which yields higher coding efficiency compared to its predecessors. This efficiency improvement has been realized by adopting many advanced algorithms to its coding tools which often require a huge amount of computation. Beside, HEVC is designed to be applicable mainly to high resolution videos that necessitate the enormous amount of computation. One common solution to this problem is to execute the algorithms in a parallelized way. However, the data dependency between neighboring coding tree units, the basic decoding unit in HEVC, limits the level of parallelization in Intra Prediction. This paper proposes a dependency reduction technique which identifies virtual dependencies among coding tree units via runtime analysis and eliminates them to enhance potential parallelism. The experimental results show that the performance of Intra Prediction can be significantly improved by lifting such virtual dependencies.

Original languageEnglish
JournalIEICE Electronics Express
Volume11
Issue number7
DOIs
StatePublished - 2014 Mar 14

Fingerprint

decoders
Data reduction
coding
augmentation
Decoding
decoding
predictions
high resolution

Keywords

  • HEVC
  • Intra prediction
  • Parallelism

Cite this

@article{982b17fe5683433ab59353a000a58c65,
title = "Data dependency reduction for parallelism enhancement of HEVC decoder",
abstract = "HEVC is a video codec which yields higher coding efficiency compared to its predecessors. This efficiency improvement has been realized by adopting many advanced algorithms to its coding tools which often require a huge amount of computation. Beside, HEVC is designed to be applicable mainly to high resolution videos that necessitate the enormous amount of computation. One common solution to this problem is to execute the algorithms in a parallelized way. However, the data dependency between neighboring coding tree units, the basic decoding unit in HEVC, limits the level of parallelization in Intra Prediction. This paper proposes a dependency reduction technique which identifies virtual dependencies among coding tree units via runtime analysis and eliminates them to enhance potential parallelism. The experimental results show that the performance of Intra Prediction can be significantly improved by lifting such virtual dependencies.",
keywords = "HEVC, Intra prediction, Parallelism",
author = "Jo, {Song Hyun} and Song, {Yong Ho}",
year = "2014",
month = "3",
day = "14",
doi = "10.1587/elex.11.20140027",
language = "English",
volume = "11",
journal = "IEICE Electronics Express",
issn = "1349-2543",
number = "7",

}

Data dependency reduction for parallelism enhancement of HEVC decoder. / Jo, Song Hyun; Song, Yong Ho.

In: IEICE Electronics Express, Vol. 11, No. 7, 14.03.2014.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Data dependency reduction for parallelism enhancement of HEVC decoder

AU - Jo, Song Hyun

AU - Song, Yong Ho

PY - 2014/3/14

Y1 - 2014/3/14

N2 - HEVC is a video codec which yields higher coding efficiency compared to its predecessors. This efficiency improvement has been realized by adopting many advanced algorithms to its coding tools which often require a huge amount of computation. Beside, HEVC is designed to be applicable mainly to high resolution videos that necessitate the enormous amount of computation. One common solution to this problem is to execute the algorithms in a parallelized way. However, the data dependency between neighboring coding tree units, the basic decoding unit in HEVC, limits the level of parallelization in Intra Prediction. This paper proposes a dependency reduction technique which identifies virtual dependencies among coding tree units via runtime analysis and eliminates them to enhance potential parallelism. The experimental results show that the performance of Intra Prediction can be significantly improved by lifting such virtual dependencies.

AB - HEVC is a video codec which yields higher coding efficiency compared to its predecessors. This efficiency improvement has been realized by adopting many advanced algorithms to its coding tools which often require a huge amount of computation. Beside, HEVC is designed to be applicable mainly to high resolution videos that necessitate the enormous amount of computation. One common solution to this problem is to execute the algorithms in a parallelized way. However, the data dependency between neighboring coding tree units, the basic decoding unit in HEVC, limits the level of parallelization in Intra Prediction. This paper proposes a dependency reduction technique which identifies virtual dependencies among coding tree units via runtime analysis and eliminates them to enhance potential parallelism. The experimental results show that the performance of Intra Prediction can be significantly improved by lifting such virtual dependencies.

KW - HEVC

KW - Intra prediction

KW - Parallelism

UR - http://www.scopus.com/inward/record.url?scp=84898477453&partnerID=8YFLogxK

U2 - 10.1587/elex.11.20140027

DO - 10.1587/elex.11.20140027

M3 - Letter

AN - SCOPUS:84898477453

VL - 11

JO - IEICE Electronics Express

JF - IEICE Electronics Express

SN - 1349-2543

IS - 7

ER -