Cache based motion compensation architecture for quad-HD H.264/AVC video decoder

Jinjia Zhou, Dajiang Zhou, Gang He, Satoshi Goto

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, we present a cache based motion compensation (MC) architecture for Quad-HD H.264/AVC video decoder. With the significantly increased throughput requirement, VLSI design for MC is greatly challenged by the huge area cost and power consumption. Moreover, the long memory system latency leads to performance drop of the MC pipeline. To solve these problems, three optimization schemes are proposed in this work. Firstly, a high-performance interpolator based on Horizontal-Vertical Expansion and Luma-Chroma Parallelism (HVE-LCP) is proposed to efficiently increase the processing throughput to at least over 4 times as the previous designs. Secondly, an efficient cache memory organization scheme (4S × 4) is adopted to improve the on-chip memory utilization, which contributes to memory area saving of 25% and memory power saving of 39 ∼ 49%. Finally, by employing a Split Task Queue (STQ) architecture, the cache system is capable of tolerating much longer latency of the memory system. Consequently, the cache idle time is saved by 90%, which contributes to reducing the overall processing time by 24 ∼ 40%. When implemented with SMIC 90 nm process, this design costs a logic gate count and on-chip memory of 108.8k and 3.1kB respectively. The proposed MC architecture can support real-time processing of 3840 × 2160@60 fps with less than 166 MHz.

Original languageEnglish
Pages (from-to)439-447
Number of pages9
JournalIEICE Transactions on Electronics
VolumeE94-C
Issue number4
DOIs
Publication statusPublished - 2011 Apr

Fingerprint

Motion compensation
Data storage equipment
Processing
Throughput
Cache memory
Logic gates
Elvitegravir, Cobicistat, Emtricitabine, Tenofovir Disoproxil Fumarate Drug Combination
Costs
Electric power utilization
Pipelines

Keywords

  • 2-D cache
  • H.264/AVC
  • Interpolation
  • Motion compensation
  • Quad-HD
  • Ultra high definition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Cache based motion compensation architecture for quad-HD H.264/AVC video decoder. / Zhou, Jinjia; Zhou, Dajiang; He, Gang; Goto, Satoshi.

In: IEICE Transactions on Electronics, Vol. E94-C, No. 4, 04.2011, p. 439-447.

Research output: Contribution to journalArticle

Zhou, Jinjia ; Zhou, Dajiang ; He, Gang ; Goto, Satoshi. / Cache based motion compensation architecture for quad-HD H.264/AVC video decoder. In: IEICE Transactions on Electronics. 2011 ; Vol. E94-C, No. 4. pp. 439-447.
@article{778e9447d605447b953fca8a8cd9d75e,
title = "Cache based motion compensation architecture for quad-HD H.264/AVC video decoder",
abstract = "In this paper, we present a cache based motion compensation (MC) architecture for Quad-HD H.264/AVC video decoder. With the significantly increased throughput requirement, VLSI design for MC is greatly challenged by the huge area cost and power consumption. Moreover, the long memory system latency leads to performance drop of the MC pipeline. To solve these problems, three optimization schemes are proposed in this work. Firstly, a high-performance interpolator based on Horizontal-Vertical Expansion and Luma-Chroma Parallelism (HVE-LCP) is proposed to efficiently increase the processing throughput to at least over 4 times as the previous designs. Secondly, an efficient cache memory organization scheme (4S × 4) is adopted to improve the on-chip memory utilization, which contributes to memory area saving of 25{\%} and memory power saving of 39 ∼ 49{\%}. Finally, by employing a Split Task Queue (STQ) architecture, the cache system is capable of tolerating much longer latency of the memory system. Consequently, the cache idle time is saved by 90{\%}, which contributes to reducing the overall processing time by 24 ∼ 40{\%}. When implemented with SMIC 90 nm process, this design costs a logic gate count and on-chip memory of 108.8k and 3.1kB respectively. The proposed MC architecture can support real-time processing of 3840 × 2160@60 fps with less than 166 MHz.",
keywords = "2-D cache, H.264/AVC, Interpolation, Motion compensation, Quad-HD, Ultra high definition",
author = "Jinjia Zhou and Dajiang Zhou and Gang He and Satoshi Goto",
year = "2011",
month = "4",
doi = "10.1587/transele.E94.C.439",
language = "English",
volume = "E94-C",
pages = "439--447",
journal = "IEICE Transactions on Electronics",
issn = "0916-8524",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "4",

}

TY - JOUR

T1 - Cache based motion compensation architecture for quad-HD H.264/AVC video decoder

AU - Zhou, Jinjia

AU - Zhou, Dajiang

AU - He, Gang

AU - Goto, Satoshi

PY - 2011/4

Y1 - 2011/4

N2 - In this paper, we present a cache based motion compensation (MC) architecture for Quad-HD H.264/AVC video decoder. With the significantly increased throughput requirement, VLSI design for MC is greatly challenged by the huge area cost and power consumption. Moreover, the long memory system latency leads to performance drop of the MC pipeline. To solve these problems, three optimization schemes are proposed in this work. Firstly, a high-performance interpolator based on Horizontal-Vertical Expansion and Luma-Chroma Parallelism (HVE-LCP) is proposed to efficiently increase the processing throughput to at least over 4 times as the previous designs. Secondly, an efficient cache memory organization scheme (4S × 4) is adopted to improve the on-chip memory utilization, which contributes to memory area saving of 25% and memory power saving of 39 ∼ 49%. Finally, by employing a Split Task Queue (STQ) architecture, the cache system is capable of tolerating much longer latency of the memory system. Consequently, the cache idle time is saved by 90%, which contributes to reducing the overall processing time by 24 ∼ 40%. When implemented with SMIC 90 nm process, this design costs a logic gate count and on-chip memory of 108.8k and 3.1kB respectively. The proposed MC architecture can support real-time processing of 3840 × 2160@60 fps with less than 166 MHz.

AB - In this paper, we present a cache based motion compensation (MC) architecture for Quad-HD H.264/AVC video decoder. With the significantly increased throughput requirement, VLSI design for MC is greatly challenged by the huge area cost and power consumption. Moreover, the long memory system latency leads to performance drop of the MC pipeline. To solve these problems, three optimization schemes are proposed in this work. Firstly, a high-performance interpolator based on Horizontal-Vertical Expansion and Luma-Chroma Parallelism (HVE-LCP) is proposed to efficiently increase the processing throughput to at least over 4 times as the previous designs. Secondly, an efficient cache memory organization scheme (4S × 4) is adopted to improve the on-chip memory utilization, which contributes to memory area saving of 25% and memory power saving of 39 ∼ 49%. Finally, by employing a Split Task Queue (STQ) architecture, the cache system is capable of tolerating much longer latency of the memory system. Consequently, the cache idle time is saved by 90%, which contributes to reducing the overall processing time by 24 ∼ 40%. When implemented with SMIC 90 nm process, this design costs a logic gate count and on-chip memory of 108.8k and 3.1kB respectively. The proposed MC architecture can support real-time processing of 3840 × 2160@60 fps with less than 166 MHz.

KW - 2-D cache

KW - H.264/AVC

KW - Interpolation

KW - Motion compensation

KW - Quad-HD

KW - Ultra high definition

UR - http://www.scopus.com/inward/record.url?scp=79953300707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953300707&partnerID=8YFLogxK

U2 - 10.1587/transele.E94.C.439

DO - 10.1587/transele.E94.C.439

M3 - Article

AN - SCOPUS:79953300707

VL - E94-C

SP - 439

EP - 447

JO - IEICE Transactions on Electronics

JF - IEICE Transactions on Electronics

SN - 0916-8524

IS - 4

ER -