A series-parallel system was proposed with common bus performance sharing in which the performance and failure rate of the element depended on the load it was carrying. In such a system,the surplus performance of a su...A series-parallel system was proposed with common bus performance sharing in which the performance and failure rate of the element depended on the load it was carrying. In such a system,the surplus performance of a sub-system can be transmitted to other deficient sub-systems. The transmission capacity of the common bus performance sharing mechanism is a random variable. Effects of load on element performance and failure rate were considered in this paper. A reliability evaluation algorithm based on the universal generating function technique was suggested. Numerical experiments were conducted to illustrate the algorithm.展开更多
Large-scale parallelization of molecular dynamics simulations is facing challenges which seriously affect the simula- tion efficiency, among which the load imbalance problem is the most critical. In this paper, we pro...Large-scale parallelization of molecular dynamics simulations is facing challenges which seriously affect the simula- tion efficiency, among which the load imbalance problem is the most critical. In this paper, we propose, a new molecular dynamics static load balancing method (MDSLB). By analyzing the characteristics of the short-range force of molecular dynamics programs running in parallel, we divide the short-range force into three kinds of force models, and then pack- age the computations of each force model into many tiny computational units called "cell loads", which provide the basic data structures for our load balancing method. In MDSLB, the spatial region is separated into sub-regions called "local domains", and the cell loads of each local domain are allocated to every processor in turn. Compared with the dynamic load balancing method, MDSLB can guarantee load balance by executing the algorithm only once at program startup without migrating the loads dynamically. We implement MDSLB in OpenFOAM software and test it on TianHe-lA supercomputer with 16 to 512 processors. Experimental results show that MDSLB can save 34%-64% time for the load imbalanced cases.展开更多
Redundantly actuated parallel manipulators have the advantage of enhancing load-carrying capability over their non-redundant ones, however they also cause the problem of uneven load distribution and need a high requir...Redundantly actuated parallel manipulators have the advantage of enhancing load-carrying capability over their non-redundant ones, however they also cause the problem of uneven load distribution and need a high requirement for the control system. This paper presents a 2-RPR/RP planar redundantly actuated parallel manipulator which can self-coordinate the distribution of external loads. This capability is realized by an appropriate design of the moving platform to make the manipulator stable at equilibrium position. The stability is proved by the theorem of direct Lyapunov method in classical mechanics. The numerical simulations are conducted to validate the stable capability by means of the observation of potential energies and phase planes. This paper offers an alternative way to design a redundantly actuated manipulator with the capability of self-coordinating the load distribution to actuations, such that parts of the controlling work are assigned to the manipulator itself by its own structure and only a little work remains to the control system.展开更多
This paper presented an idea to replace the traditionally expensive parallel machines by heterogeneous cluster of workstations. To emphasise the usability of cluster of workstations platform for parallel and distribut...This paper presented an idea to replace the traditionally expensive parallel machines by heterogeneous cluster of workstations. To emphasise the usability of cluster of workstations platform for parallel and distributed computing, also the paper presented the status report on the effort and experiences for the implementation of a dynamic load balancing for parallel tree computation depth first search(DFS) on the cluster of a workstations project. It compared the speedup performance obtained from our platform with that obtained from the traditional one. The speedup results show that cluster of workstations can be a serious alternative to the expensive parallel machines.展开更多
针对大数据环境下并行深度森林算法中存在不相关及冗余特征过多、多粒度扫描不平衡、分类性能不足以及并行化效率低等问题,提出了基于互信息和融合加权的并行深度森林算法(parallel deep forest algorithm based on mutual information ...针对大数据环境下并行深度森林算法中存在不相关及冗余特征过多、多粒度扫描不平衡、分类性能不足以及并行化效率低等问题,提出了基于互信息和融合加权的并行深度森林算法(parallel deep forest algorithm based on mutual information and mixed weighting,PDF-MIMW)。首先,在特征降维阶段提出了基于互信息的特征提取策略(feature extraction strategy based on mutual information,FE-MI),结合特征重要性、交互性和冗余性度量过滤原始特征,剔除过多的不相关和冗余特征;接着,在多粒度扫描阶段提出了基于填充的改进多粒度扫描策略(improved multi-granularity scanning strategy based on padding,IMGS-P),对精简后的特征进行填充并对窗口扫描后的子序列进行随机采样,保证多粒度扫描的平衡;其次,在级联森林构建阶段提出了并行子森林构建策略(sub-forest construction strategy based on mixed weighting,SFC-MW),结合Spark框架并行构建加权子森林,提升模型的分类性能;最后,在类向量合并阶段提出基于混合粒子群算法的负载均衡策略(load balancing strategy based on hybrid particle swarm optimization algorithm,LB-HPSO),优化Spark框架中任务节点的负载分配,降低类向量合并时的等待时长,提高模型的并行化效率。实验表明,PDF-MIMW算法的分类效果更佳,同时在大数据环境下的训练效率更高。展开更多
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
排序算法是计算机科学领域的一个基础算法,是大量应用的算法核心。在大数据时代,随着数据量的极速增长,并行排序算法受到广泛关注。现有的并行排序算法普遍存在通信开销过大、负载不均衡等问题,导致算法难以大规模扩展。针对以上问题,...排序算法是计算机科学领域的一个基础算法,是大量应用的算法核心。在大数据时代,随着数据量的极速增长,并行排序算法受到广泛关注。现有的并行排序算法普遍存在通信开销过大、负载不均衡等问题,导致算法难以大规模扩展。针对以上问题,提出一种大规模可扩展的正则采样并行排序(scalable parallel sorting by regular sampling,ScaPSRS)算法,摒弃传统正则采样并行排序(parallel sorting by regular sampling,PSRS)算法中由一个进程负责采样的做法,转而让所有进程参与正则采样,选出p-1个分隔元素,将整个数据集划分成p个不相交的子集,然后实施并行排序,避免了单一进程的采样瓶颈。此外,ScaPSRS采用一种新的迭代更新策略选择p-1个分隔元素,保证划分的p个子集尽可能大小相同,从而确保p个进程对各自的子集进行本地排序时的负载均衡。在天河二号超级计算机上进行的大量实验表明,ScaPSRS算法能够成功地扩展到32000个内核,性能比PSRS算法和Hofmann等人提出的分区算法分别提升了3.7倍和11.7倍。展开更多
基金National Natural Science Foundations of China(Nos.71231001,11001005,71301009)China Postdoctoral Science Foundation(No.2013M530531)+1 种基金the Fundamental Research Funds for the Central Universities of China(Nos.FRF-M P-13-009A,FRF-TP-13-026A)the MOE PhD Supervisor Fund of China(No.20120006110025)
文摘A series-parallel system was proposed with common bus performance sharing in which the performance and failure rate of the element depended on the load it was carrying. In such a system,the surplus performance of a sub-system can be transmitted to other deficient sub-systems. The transmission capacity of the common bus performance sharing mechanism is a random variable. Effects of load on element performance and failure rate were considered in this paper. A reliability evaluation algorithm based on the universal generating function technique was suggested. Numerical experiments were conducted to illustrate the algorithm.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.61303071 and 61120106005)the Natural Science Fund from the Guangzhou Science and Information Technology Bureau (Grant No.134200026)
文摘Large-scale parallelization of molecular dynamics simulations is facing challenges which seriously affect the simula- tion efficiency, among which the load imbalance problem is the most critical. In this paper, we propose, a new molecular dynamics static load balancing method (MDSLB). By analyzing the characteristics of the short-range force of molecular dynamics programs running in parallel, we divide the short-range force into three kinds of force models, and then pack- age the computations of each force model into many tiny computational units called "cell loads", which provide the basic data structures for our load balancing method. In MDSLB, the spatial region is separated into sub-regions called "local domains", and the cell loads of each local domain are allocated to every processor in turn. Compared with the dynamic load balancing method, MDSLB can guarantee load balance by executing the algorithm only once at program startup without migrating the loads dynamically. We implement MDSLB in OpenFOAM software and test it on TianHe-lA supercomputer with 16 to 512 processors. Experimental results show that MDSLB can save 34%-64% time for the load imbalanced cases.
基金Supported by National Basic Research Program of China(973 Program,Grant No.2014CB046600)National Natural Science Foundation of China(Grant No.11472172)+1 种基金National Science Foundation for the Youth(Grant No.51305256)Specialized Research Fund for the Doctoral Program of Higher Education,China(Grant No.20130073110039)
文摘Redundantly actuated parallel manipulators have the advantage of enhancing load-carrying capability over their non-redundant ones, however they also cause the problem of uneven load distribution and need a high requirement for the control system. This paper presents a 2-RPR/RP planar redundantly actuated parallel manipulator which can self-coordinate the distribution of external loads. This capability is realized by an appropriate design of the moving platform to make the manipulator stable at equilibrium position. The stability is proved by the theorem of direct Lyapunov method in classical mechanics. The numerical simulations are conducted to validate the stable capability by means of the observation of potential energies and phase planes. This paper offers an alternative way to design a redundantly actuated manipulator with the capability of self-coordinating the load distribution to actuations, such that parts of the controlling work are assigned to the manipulator itself by its own structure and only a little work remains to the control system.
基金National Science Foundation of China(No.60 173 0 3 1)
文摘This paper presented an idea to replace the traditionally expensive parallel machines by heterogeneous cluster of workstations. To emphasise the usability of cluster of workstations platform for parallel and distributed computing, also the paper presented the status report on the effort and experiences for the implementation of a dynamic load balancing for parallel tree computation depth first search(DFS) on the cluster of a workstations project. It compared the speedup performance obtained from our platform with that obtained from the traditional one. The speedup results show that cluster of workstations can be a serious alternative to the expensive parallel machines.
文摘针对大数据环境下并行深度森林算法中存在不相关及冗余特征过多、多粒度扫描不平衡、分类性能不足以及并行化效率低等问题,提出了基于互信息和融合加权的并行深度森林算法(parallel deep forest algorithm based on mutual information and mixed weighting,PDF-MIMW)。首先,在特征降维阶段提出了基于互信息的特征提取策略(feature extraction strategy based on mutual information,FE-MI),结合特征重要性、交互性和冗余性度量过滤原始特征,剔除过多的不相关和冗余特征;接着,在多粒度扫描阶段提出了基于填充的改进多粒度扫描策略(improved multi-granularity scanning strategy based on padding,IMGS-P),对精简后的特征进行填充并对窗口扫描后的子序列进行随机采样,保证多粒度扫描的平衡;其次,在级联森林构建阶段提出了并行子森林构建策略(sub-forest construction strategy based on mixed weighting,SFC-MW),结合Spark框架并行构建加权子森林,提升模型的分类性能;最后,在类向量合并阶段提出基于混合粒子群算法的负载均衡策略(load balancing strategy based on hybrid particle swarm optimization algorithm,LB-HPSO),优化Spark框架中任务节点的负载分配,降低类向量合并时的等待时长,提高模型的并行化效率。实验表明,PDF-MIMW算法的分类效果更佳,同时在大数据环境下的训练效率更高。
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.
文摘排序算法是计算机科学领域的一个基础算法,是大量应用的算法核心。在大数据时代,随着数据量的极速增长,并行排序算法受到广泛关注。现有的并行排序算法普遍存在通信开销过大、负载不均衡等问题,导致算法难以大规模扩展。针对以上问题,提出一种大规模可扩展的正则采样并行排序(scalable parallel sorting by regular sampling,ScaPSRS)算法,摒弃传统正则采样并行排序(parallel sorting by regular sampling,PSRS)算法中由一个进程负责采样的做法,转而让所有进程参与正则采样,选出p-1个分隔元素,将整个数据集划分成p个不相交的子集,然后实施并行排序,避免了单一进程的采样瓶颈。此外,ScaPSRS采用一种新的迭代更新策略选择p-1个分隔元素,保证划分的p个子集尽可能大小相同,从而确保p个进程对各自的子集进行本地排序时的负载均衡。在天河二号超级计算机上进行的大量实验表明,ScaPSRS算法能够成功地扩展到32000个内核,性能比PSRS算法和Hofmann等人提出的分区算法分别提升了3.7倍和11.7倍。