Current popular systems, Hadoop and Spark, cannot achieve satisfied performance because of the inefficient overlapping of computation and communication when running iterative big data applications. The pipeline of com...Current popular systems, Hadoop and Spark, cannot achieve satisfied performance because of the inefficient overlapping of computation and communication when running iterative big data applications. The pipeline of computing, data movement, and data management plays a key role for current distributed data computing systems. In this paper, we first analyze the overhead of shuffle operation in Hadoop and Spark when running PageRank workload, and then propose an event-driven pipeline and in-memory shuffle design with better overlapping of computation and communication as DataMPI- Iteration, an MPI-based library, for iterative big data computing. Our performance evaluation shows DataMPI-Iteration can achieve 9X-21X speedup over Apache Hadoop, and 2X-3X speedup over Apache Spark for PageRank and K-means.展开更多
Delta-based accumulative iterative computation (DAIC) model is currently proposed to support iterative algorithms in a synchronous or an asynchronous way. However, both the synchronous DAIC model and the asynchronou...Delta-based accumulative iterative computation (DAIC) model is currently proposed to support iterative algorithms in a synchronous or an asynchronous way. However, both the synchronous DAIC model and the asynchronous DAIC model only satisfy some given conditions, respectively, and perform poorly under other conditions either for high synchronization cost or for many redundant activations. As a result, the whole performance of both DAIC models suffers from the serious network jitter and load jitter caused by multi- tenancy in the cloud. In this paper, we develop a system, namely Hyblter, to guarantee the performance of iterative algorithms under different conditions. Through an adaptive execution model selection scheme, it can efficiently switch between synchronous and asynchronous DAIC model in order to be adapted to different conditions, always getting the best performance in the cloud. Experimental results show that our approach can improve the performance of current solutions up to 39.0%.展开更多
This paper presents the implicit method of streamline iteration on the bases of the method of streamline itera- tion for computing two-dimensional viscous incompressible steady flow in a channel with arbitrary shape. ...This paper presents the implicit method of streamline iteration on the bases of the method of streamline itera- tion for computing two-dimensional viscous incompressible steady flow in a channel with arbitrary shape. A new total pressure equation of viscous incompressible flow is introduced in this paper and the equation is numerically computed by the implicit method. It is shown from the computational results of examples that the implicit method of streamline iteration can speed up the convergence and decrease the computational time.展开更多
Although many graph processing systems have been proposed, graphs in the real-world are often dynamic. It is important to keep the results of graph computation up-todate. Incremental computation is demonstrated to be ...Although many graph processing systems have been proposed, graphs in the real-world are often dynamic. It is important to keep the results of graph computation up-todate. Incremental computation is demonstrated to be an efficient solution to update calculated results. Recently, many incremental graph processing systems have been proposed to handle dynamic graphs in an asynchronous way and are able to achieve better performance than those processed in a synchronous way. However, these solutions still suffer from sub-optimal convergence speed due to their slow propagation of important vertex state (important to convergence speed) and poor locality. In order to solve these problems, we propose a novel graph processing framework. It introduces a dynamic partition method to gather the important vertices for high locality, and then uses a priority-based scheduling algorithm to assign them with a higher priority for an effective processing order. By such means, it is able to reduce the number of updates and increase the locality, thereby reducing the convergence time. Experimental results show that our method reduces the number of updates by 30%, and reduces the total execution time by 35%, compared with state-of-the-art systems.展开更多
文摘Current popular systems, Hadoop and Spark, cannot achieve satisfied performance because of the inefficient overlapping of computation and communication when running iterative big data applications. The pipeline of computing, data movement, and data management plays a key role for current distributed data computing systems. In this paper, we first analyze the overhead of shuffle operation in Hadoop and Spark when running PageRank workload, and then propose an event-driven pipeline and in-memory shuffle design with better overlapping of computation and communication as DataMPI- Iteration, an MPI-based library, for iterative big data computing. Our performance evaluation shows DataMPI-Iteration can achieve 9X-21X speedup over Apache Hadoop, and 2X-3X speedup over Apache Spark for PageRank and K-means.
基金Acknowledgements This paper was supported by the National Natural Science Foundation of China (Grant Nos. 61272408, 61322210), National High-tech Research and Development Program of China (863 Program) (2012AA010905), CCCPC Youngth Talent Plan, Doctoral Fund of Ministry of Education of China (20130142110048).
文摘Delta-based accumulative iterative computation (DAIC) model is currently proposed to support iterative algorithms in a synchronous or an asynchronous way. However, both the synchronous DAIC model and the asynchronous DAIC model only satisfy some given conditions, respectively, and perform poorly under other conditions either for high synchronization cost or for many redundant activations. As a result, the whole performance of both DAIC models suffers from the serious network jitter and load jitter caused by multi- tenancy in the cloud. In this paper, we develop a system, namely Hyblter, to guarantee the performance of iterative algorithms under different conditions. Through an adaptive execution model selection scheme, it can efficiently switch between synchronous and asynchronous DAIC model in order to be adapted to different conditions, always getting the best performance in the cloud. Experimental results show that our approach can improve the performance of current solutions up to 39.0%.
文摘This paper presents the implicit method of streamline iteration on the bases of the method of streamline itera- tion for computing two-dimensional viscous incompressible steady flow in a channel with arbitrary shape. A new total pressure equation of viscous incompressible flow is introduced in this paper and the equation is numerically computed by the implicit method. It is shown from the computational results of examples that the implicit method of streamline iteration can speed up the convergence and decrease the computational time.
基金the National Natural Science Foundation of China (Grant No. 61702202)China Postdoctoral Science Foundation Funded Project (2017M610477 and 2017T100555).
文摘Although many graph processing systems have been proposed, graphs in the real-world are often dynamic. It is important to keep the results of graph computation up-todate. Incremental computation is demonstrated to be an efficient solution to update calculated results. Recently, many incremental graph processing systems have been proposed to handle dynamic graphs in an asynchronous way and are able to achieve better performance than those processed in a synchronous way. However, these solutions still suffer from sub-optimal convergence speed due to their slow propagation of important vertex state (important to convergence speed) and poor locality. In order to solve these problems, we propose a novel graph processing framework. It introduces a dynamic partition method to gather the important vertices for high locality, and then uses a priority-based scheduling algorithm to assign them with a higher priority for an effective processing order. By such means, it is able to reduce the number of updates and increase the locality, thereby reducing the convergence time. Experimental results show that our method reduces the number of updates by 30%, and reduces the total execution time by 35%, compared with state-of-the-art systems.