A high parallel way for processing IQ/IT part of HEVC decoder based on GPU

Lang Ping He; Satoshi Goto

doi:10.1109/ISPACS.2014.7024454

A high parallel way for processing IQ/IT part of HEVC decoder based on GPU

Lang Ping He, Satoshi Goto

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

5 Citations (Scopus)

Abstract

HEVC (High Efficiency Video Coding) is the newest video compression standard. Compared with the previous standards, the Coding efficiency is greatly improved at the cost of much higher codec complexity. So, many people improve the HEVC algorithm from the hardware level and software level. For the IQ/IT (inverse quantization/inverse transform) part, HEVC just processes one TU block one by one. And TU block size can be 4×4, 8×8, 16×16 and 32×32. So, it costs much decoding time by using this processing. In this paper, we present a parallel way for processing IQ/IT part based on GPU. In HEVC decoder, CABAC decoder only decodes one 64×64 size CTU block's parameters and some syntax elements. So, for now, we can process one 64×64 size Luma block and two 32×32 size Chroma block parallelly by using GPU. And from the experiment results, we can see the computation speed of computing the IQ/IT is about 33 times faster than the HM 12.0's. And finally, we can reduce about 40.7% decoding time compared with HM 12.0's.

Original language	English
Title of host publication	2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	211-215
Number of pages	5
ISBN (Print)	9781479961207
DOIs	https://doi.org/10.1109/ISPACS.2014.7024454
Publication status	Published - 2015 Jan 27
Event	2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014 - Kuching, Sarawak Duration: 2014 Dec 1 → 2014 Dec 4

Other

Other	2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014
City	Kuching, Sarawak
Period	14/12/1 → 14/12/4

Keywords

CU
GPU
HEVC
HM 12.0
IQ/IT
TU

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Signal Processing

Access to Document

10.1109/ISPACS.2014.7024454

Cite this

A high parallel way for processing IQ/IT part of HEVC decoder based on GPU. / He, Lang Ping; Goto, Satoshi.

2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014. Institute of Electrical and Electronics Engineers Inc., 2015. p. 211-215 7024454.

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

He, LP & Goto, S 2015, A high parallel way for processing IQ/IT part of HEVC decoder based on GPU. in 2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014., 7024454, Institute of Electrical and Electronics Engineers Inc., pp. 211-215, 2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014, Kuching, Sarawak, 14/12/1. https://doi.org/10.1109/ISPACS.2014.7024454

@inproceedings{2ec77d72ebb940508c4c6addbcb10c1a,

title = "A high parallel way for processing IQ/IT part of HEVC decoder based on GPU",

abstract = "HEVC (High Efficiency Video Coding) is the newest video compression standard. Compared with the previous standards, the Coding efficiency is greatly improved at the cost of much higher codec complexity. So, many people improve the HEVC algorithm from the hardware level and software level. For the IQ/IT (inverse quantization/inverse transform) part, HEVC just processes one TU block one by one. And TU block size can be 4×4, 8×8, 16×16 and 32×32. So, it costs much decoding time by using this processing. In this paper, we present a parallel way for processing IQ/IT part based on GPU. In HEVC decoder, CABAC decoder only decodes one 64×64 size CTU block's parameters and some syntax elements. So, for now, we can process one 64×64 size Luma block and two 32×32 size Chroma block parallelly by using GPU. And from the experiment results, we can see the computation speed of computing the IQ/IT is about 33 times faster than the HM 12.0's. And finally, we can reduce about 40.7% decoding time compared with HM 12.0's.",

keywords = "CU, GPU, HEVC, HM 12.0, IQ/IT, TU",

author = "He, {Lang Ping} and Satoshi Goto",

year = "2015",

month = jan,

day = "27",

doi = "10.1109/ISPACS.2014.7024454",

language = "English",

isbn = "9781479961207",

pages = "211--215",

booktitle = "2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014 ; Conference date: 01-12-2014 Through 04-12-2014",

}

TY - GEN

T1 - A high parallel way for processing IQ/IT part of HEVC decoder based on GPU

AU - He, Lang Ping

AU - Goto, Satoshi

PY - 2015/1/27

Y1 - 2015/1/27

N2 - HEVC (High Efficiency Video Coding) is the newest video compression standard. Compared with the previous standards, the Coding efficiency is greatly improved at the cost of much higher codec complexity. So, many people improve the HEVC algorithm from the hardware level and software level. For the IQ/IT (inverse quantization/inverse transform) part, HEVC just processes one TU block one by one. And TU block size can be 4×4, 8×8, 16×16 and 32×32. So, it costs much decoding time by using this processing. In this paper, we present a parallel way for processing IQ/IT part based on GPU. In HEVC decoder, CABAC decoder only decodes one 64×64 size CTU block's parameters and some syntax elements. So, for now, we can process one 64×64 size Luma block and two 32×32 size Chroma block parallelly by using GPU. And from the experiment results, we can see the computation speed of computing the IQ/IT is about 33 times faster than the HM 12.0's. And finally, we can reduce about 40.7% decoding time compared with HM 12.0's.

AB - HEVC (High Efficiency Video Coding) is the newest video compression standard. Compared with the previous standards, the Coding efficiency is greatly improved at the cost of much higher codec complexity. So, many people improve the HEVC algorithm from the hardware level and software level. For the IQ/IT (inverse quantization/inverse transform) part, HEVC just processes one TU block one by one. And TU block size can be 4×4, 8×8, 16×16 and 32×32. So, it costs much decoding time by using this processing. In this paper, we present a parallel way for processing IQ/IT part based on GPU. In HEVC decoder, CABAC decoder only decodes one 64×64 size CTU block's parameters and some syntax elements. So, for now, we can process one 64×64 size Luma block and two 32×32 size Chroma block parallelly by using GPU. And from the experiment results, we can see the computation speed of computing the IQ/IT is about 33 times faster than the HM 12.0's. And finally, we can reduce about 40.7% decoding time compared with HM 12.0's.

KW - CU

KW - GPU

KW - HEVC

KW - HM 12.0

KW - IQ/IT

KW - TU

UR - http://www.scopus.com/inward/record.url?scp=84923561787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923561787&partnerID=8YFLogxK

U2 - 10.1109/ISPACS.2014.7024454

DO - 10.1109/ISPACS.2014.7024454

M3 - Conference contribution

SN - 9781479961207

SP - 211

EP - 215

BT - 2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2014

Y2 - 1 December 2014 through 4 December 2014

ER -

A high parallel way for processing IQ/IT part of HEVC decoder based on GPU

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this