摘要
LogP模型作为一种并行算法设计模型,它的性能参数较好地反映了并行计算的实际问题。讨论了它的特点,分析了轻载条件下的网络延迟、额外开销时间,并对相应参数进行试验测试。提出在网络机群并行计算环境中,依据LogP模型设计并行算法,以粗粒度发送长消息是减少通信开销,提高并行效率的有效方法。
The LogP is a parallel algorithm design one, reflecting the key performance of the parallel computation. The features are discussed and the network delay and overhead time based on the LogP model under the light load is analyzed. The transmission of the long message of big granularity is presented to reduce the communication cost and improve the parallel efficiency.
出处
《成都信息工程学院学报》
2003年第3期275-277,共3页
Journal of Chengdu University of Information Technology
关键词
LOGP模型
网络机群
网络并行计算
网络延迟
额外开销
LogP model
cluster of work station
network parallel computation
network delay
overhead time
