摘要
首先探讨AVS视频编码的可并行性,然后给出一种基于集群服务器的AVS并行编码器设计和实现方法.该方法通过消息循环调度和在图像序列一级上的粗粒度数据划分,有效地降低了通讯代价,极大地提高了系统的并行度.实验结果表明:该系统在16节点(32个CPU)集群服务器上的加速比最高可达30.
This paper first discusses the parallelizability of AVS video encoding, then describes a method for implementing parallel AVS video encoding on cluster. A message - loop scheduling policy and picture sequence level data partition are used to reduce communication cost and guarantee high parallelity. Experimental results show that in this scheme the AVS video encoding time can be significantly reduced. On a 16 nodes cluster with 32 CPUs, the implementation speedup ratio can reach 30.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2007年第1期106-109,共4页
Journal of Harbin Institute of Technology
关键词
AVS
视频编码
并行处理
图像序列
AVS
video encoding
parallel processing
picture sequence
