The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic l...The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic load balancing is a technique for the parallel implementation of problems, which generate unpredictable workloads by migration work units from heavily loaded processor to lightly loaded processors at run time. This paper proposed an efficient load balancing method in which parallel tree computations depth first search (DFS) generates unpredictable, highly imbalance workloads and moves through different phases detectable at run time, where dynamic load balancing strategy is applicable in each phase running under the MPI(message passing interface) and Unix operating system on cluster of workstations parallel platform computing.展开更多
针对大数据环境下DCNN(deep convolutional neural network)算法中存在网络冗余参数过多、参数寻优能力不佳和并行效率低的问题,提出了大数据环境下基于特征图和并行计算熵的深度卷积神经网络算法MR-FPDCNN(deep convolutional neural n...针对大数据环境下DCNN(deep convolutional neural network)算法中存在网络冗余参数过多、参数寻优能力不佳和并行效率低的问题,提出了大数据环境下基于特征图和并行计算熵的深度卷积神经网络算法MR-FPDCNN(deep convolutional neural network algorithm based on feature graph and parallel computing entropy using MapReduce)。该算法设计了基于泰勒损失的特征图剪枝策略FMPTL(feature map pruning based on Taylor loss),预训练网络,获得压缩后的DCNN,有效减少了冗余参数,降低了DCNN训练的计算代价。提出了基于信息共享搜索策略ISS(information sharing strategy)的萤火虫优化算法IFAS(improved firefly algorithm based on ISS),根据“IFAS”算法初始化DCNN参数,实现DCNN的并行化训练,提高网络的寻优能力。在Reduce阶段提出了基于并行计算熵的动态负载均衡策略DLBPCE(dynamic load balancing strategy based on parallel computing entropy),获取全局训练结果,实现了数据的快速均匀分组,从而提高了集群的并行效率。实验结果表明,该算法不仅降低了DCNN在大数据环境下训练的计算代价,而且提高了并行系统的并行化性能。展开更多
基金Natural Science Foundation of China (No.60 173 0 3 1)
文摘The real problem in cluster of workstations is the changes in workstation power or number of workstations or dynmaic changes in the run time behavior of the application hamper the efficient use of resources. Dynamic load balancing is a technique for the parallel implementation of problems, which generate unpredictable workloads by migration work units from heavily loaded processor to lightly loaded processors at run time. This paper proposed an efficient load balancing method in which parallel tree computations depth first search (DFS) generates unpredictable, highly imbalance workloads and moves through different phases detectable at run time, where dynamic load balancing strategy is applicable in each phase running under the MPI(message passing interface) and Unix operating system on cluster of workstations parallel platform computing.
文摘针对大数据环境下DCNN(deep convolutional neural network)算法中存在网络冗余参数过多、参数寻优能力不佳和并行效率低的问题,提出了大数据环境下基于特征图和并行计算熵的深度卷积神经网络算法MR-FPDCNN(deep convolutional neural network algorithm based on feature graph and parallel computing entropy using MapReduce)。该算法设计了基于泰勒损失的特征图剪枝策略FMPTL(feature map pruning based on Taylor loss),预训练网络,获得压缩后的DCNN,有效减少了冗余参数,降低了DCNN训练的计算代价。提出了基于信息共享搜索策略ISS(information sharing strategy)的萤火虫优化算法IFAS(improved firefly algorithm based on ISS),根据“IFAS”算法初始化DCNN参数,实现DCNN的并行化训练,提高网络的寻优能力。在Reduce阶段提出了基于并行计算熵的动态负载均衡策略DLBPCE(dynamic load balancing strategy based on parallel computing entropy),获取全局训练结果,实现了数据的快速均匀分组,从而提高了集群的并行效率。实验结果表明,该算法不仅降低了DCNN在大数据环境下训练的计算代价,而且提高了并行系统的并行化性能。
