@article{GU2011, 
author = {Junli GU and Yihe SUN},
title = {Optimizing a Parallel Video Encoder with Message Passing and a Shared Memory Architecture},
year = {2011},
journal = {Tsinghua Science and Technology},
volume = {16},
number = {4},
pages = {393-398},
keywords = {parallel video encoder, speed improvement, message passing, shared memory},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(11)70057-8},
doi = {10.1016/S1007-0214(11)70057-8},
abstract = {Implementing video applications on emerging multi-core processors is a promising technique for personal, real-time multi-media applications. However, when porting the legacy parallel video encoders developed for clusters to shared-memory multi-cores, the existing parallel algorithms result in workload imbalances on different cores and communication inefficiencies. This paper describes a strip-wise parallel scheme to balance workloads and a hybrid communication mechanism to reduce communication overhead. The implementation of the H.264 parallel encoder on an eight CPU Intel Xeon system achieves 5x to 6x speed-up over a single thread encoder and achieves a 29% performance improvement over the commonly used master-slave schemes on clusters. The paper also gives further analysis on scalability, parallel efficiency, workload balance, and communication overhead as the number of cores varies.}
}