陈伟伟, 朱惠, 何卫锋, 毛志刚. 一种面向HEVC运动估计的高性能VLSI架构[J]. 微电子学与计算机, 2013, 30(6): 10-14.
引用本文: 陈伟伟, 朱惠, 何卫锋, 毛志刚. 一种面向HEVC运动估计的高性能VLSI架构[J]. 微电子学与计算机, 2013, 30(6): 10-14.
CHEN Wei-wei, ZHU Hui, HE Wei-feng, MAO Zhi-gang. High Performance VLSI Architecture for HEVC Motion Estimation[J]. Microelectronics & Computer, 2013, 30(6): 10-14.
Citation: CHEN Wei-wei, ZHU Hui, HE Wei-feng, MAO Zhi-gang. High Performance VLSI Architecture for HEVC Motion Estimation[J]. Microelectronics & Computer, 2013, 30(6): 10-14.

一种面向HEVC运动估计的高性能VLSI架构

High Performance VLSI Architecture for HEVC Motion Estimation

  • 摘要: HECV是正在开发的下一代视频编码标准.为了进一步提高视频图像的压缩效率,HEVC中引入了不对称划分模式,且最大编码单元达到64×64像素.针对HEVC标准,提出了一种面向超高清视频图像应用的高性能运动估计VLSI架构.该VLSI架构能够支持从4×4到64×64的849种块的划分种类,其中包括168种不对称划分,并可重构支持3种搜索区间.通过层次化数据重用策略和存储访存策略,与传统设计相比将片外数据带宽减少了99.2%.采用TSMC 90nm工艺综合,该电路的最高工作频率可达到330MHz,电路规模86万门,功耗229mW.仿真结果表明,在280.4MHz工作频率下,能够完成超高清视频图像3 840×2 160p,30f/s的实时编码要求.

     

    Abstract: High Efficiency Video Coding(HEVC) is the next generation video coding system under standardization.HEVC employs the Largest Coding Unit(LCU) up to 64×64 pixels with Asymmetric Motion Partitions(AMP),which significantly increases the algorithm complexity of Motion Estimation(ME).In this paper,a novel VLSI architecture compatible to HEVC ME algorithm is proposed for the first time.A quarter of LCU size's Processing Element(PE) array architecture is adopted to conduct full search ME with 849 different block sizes from 4×4 to 64×64 pixels,168 AMPs such as 4×16 and 24×32 pixels,as well as 3 search ranges(SR) including -4,4),-8,8) and -16,16) pixels.Moreover,a hierarchy data reuse scheme and a memory access strategy are adopted to reduce off-chip bandwidth up to 99.2% compared to the traditional method.Using TSMC 90 nm 1P9M technology,the proposed architecture is synthesized at the maximum work frequency of about 330 MHz with 860×103 Gates and 229 mW.Simulation results show that the architecture is able to process 3 840×2 160 p video at 30 f/s at nearly 280.4 MHz.

     

/

返回文章
返回