首页> 外文会议>2013 IEEE International Conference on Electronics, Circuits, and Systems >An energy-efficient hardware design for lossless reference frame compression in video coders
【24h】

An energy-efficient hardware design for lossless reference frame compression in video coders

机译:用于视频编码器中无损参考帧压缩的节能硬件设计

获取原文
获取原文并翻译 | 示例

摘要

In current video coders many modules that compose the encoder need to write and to read a large amount of data from external memory. It requires a large memory bandwidth, with significant impact on energy consumption. In this context, this paper presents the hardware architectures of the Reference Frame Context Adaptive Variable-Length Compressor with 4 coding tables (RFCAVLC), which is a standard-free lossless solution for reducing external memory bandwidth. RFCAVLC reaches an average compression rate higher than 24% for the evaluated video sequences. The RFCAVLC hardware (Coder and Decoder) was described in VHDL and synthesized targeting ASIC for 45nm, 65nm, and 90nm TSMC standard cell libraries. The results show that with 45nm, 65nm, and 90nm, the RFCAVLC is able to process up to 83, 69, and 42 QFHD frames per second, respectively. To attend real-time processing for QFHD@30 frames per second our design consumes 23.4 pJ/sample for 90 nm, 15.6 pJ/sample for 65 nm, and 7.1 pJ/sample for 45 nm.
机译:在当前的视频编码器中,组成编码器的许多模块需要写入和读取外部存储器中的大量数据。它需要很大的内存带宽,这对能耗有很大影响。在这种情况下,本文介绍了具有4个编码表(RFCAVLC)的参考帧上下文自适应可变长度压缩器的硬件体系结构,这是减少外部存储器带宽的无标准无损解决方案。对于评估的视频序列,RFCAVLC的平均压缩率高于24%。 RFCAVLC硬件(编码器和解码器)在VHDL中进行了描述,并针对45nm,65nm和90nm TSMC标准单元库针对ASIC进行了合成。结果表明,使用45nm,65nm和90nm的RFCAVLC能够分别每秒处理多达83、69和42个QFHD帧。为了参加每秒QFHD @ 30帧的实时处理,我们的设计消耗90 nm的23.4 pJ /样本,65 nm的15.6 pJ /样本和45 nm的7.1 pJ /样本。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号