Efficient selection strategies towards processor reordering techniques for improving data locality in heterogeneous clusters

Grid architecture integrates geographically distributed nodes to manage and provide resources to execute scientific applications. For data locality, applications with different computational phases require data redistribution for realignment. The tradeoff between high efficiency computation and communication cost of data redistribution accompanies. This paper introduces a research model and two methods to derive new lists of processor logical id according to the characteristics of heterogeneous network. Both methods provide choices of more low-cost communication schedules in grid. The simulations show both proposed methods yield outstanding performance in grid.

[1]  Jong Sik Lee.  Data Distribution Management Modeling and Implementation on Computational Grid , 2005, GCC.

[2]  Ian Foster,et al.  The Grid 2 - Blueprint for a New Computing Infrastructure, Second Edition , 1998, The Grid 2, 2nd Edition.

[3]  Minyi Guo,et al.  A Framework for Efficient Data Redistribution on Distributed Memory Multicomputers , 2001, The Journal of Supercomputing.

[4]  Chih-Ping Chu,et al.  An Efficient Communication Scheduling Method for the Processor Mapping Technique Applied Data Redistribution , 2006, The Journal of Supercomputing.

[5]  Ching-Hsien Hsu,et al.  Localized Communications of Data Parallel Programs on Multi-cluster Grid Systems , 2005, EGC.

[6]  Ami Marowka,et al.  The GRID: Blueprint for a New Computing Infrastructure , 2000, Parallel Distributed Comput. Pract..

[7]  Yves Robert,et al.  Scheduling divisible workloads on heterogeneous platforms , 2003, Parallel Comput..

[8]  Francine Berman,et al.  Resource Allocation for Steerable Parallel Parameter Searches , 2002, GRID.

[9]  Ching-Hsien Hsu,et al.  Localization Techniques for Cluster-Based Data Grid , 2005, ICA3PP.

[10]  Viktor K. Prasanna,et al.  Efficient Algorithms for Block-Cyclic Redistribution of Arrays , 1999, Algorithmica.

[11]  Xiao Qin,et al.  Dynamic, reliability-driven scheduling of parallel real-time jobs in heterogeneous systems , 2001, International Conference on Parallel Processing, 2001..

[12]  Ian T. Foster,et al.  Condor-G: A Computation Management Agent for Multi-Institutional Grids , 2004, Cluster Computing.

[13]  Florin Isaila,et al.  Mapping functions and data redistribution for parallel files , 2002, Proceedings 16th International Parallel and Distributed Processing Symposium.

[14]  Mohammad Kazem Akbari,et al.  Performance analysis of heterogeneous multi-cluster systems , 2005, 2005 International Conference on Parallel Processing Workshops (ICPPW'05).

[15]  Lionel M. Ni,et al.  Processor mapping techniques toward efficient data redistribution , 1994, Proceedings of 8th International Parallel Processing Symposium.

[16]  Henri E. Bal,et al.  Optimizing parallel applications for wide-area clusters , 1998, Proceedings of the First Merged International Parallel Processing Symposium and Symposium on Parallel and Distributed Processing.

[17]  Jens Knoop,et al.  Distribution Assignment Placement: Effective Optimization of Redistribution Costs , 2002, IEEE Trans. Parallel Distributed Syst..

[18]  Myong-Soon Park,et al.  Processor reordering algorithms toward efficient GEN_BLOCK redistribution , 2001, SAC.

[19]  Florin Isaila,et al.  Mapping functions and data redistribution for parallel files , 2002, Proceedings 16th International Parallel and Distributed Processing Symposium.

[20]  Yves Robert,et al.  Optimal algorithms for scheduling divisible workloads on heterogeneous systems , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[21]  Subhash Saini,et al.  Local grid scheduling techniques using performance prediction , 2003 .

[22]  Henri E. Bal,et al.  Sensitivity of parallel applications to large differences in bandwidth and latency in two-layer interconnects , 1999, Proceedings Fifth International Symposium on High-Performance Computer Architecture.

[23]  Mohammad Kazem Akbari,et al.  Performance Analysis of Interconnection Networks for Multi-cluster Systems , 2005, International Conference on Computational Science.

[24]  Dharma P. Agrawal,et al.  Scheduling of periodic time critical applications for pipelined execution on heterogeneous systems , 2001, International Conference on Parallel Processing, 2001..

[25]  Peter E. Strazdins,et al.  Optimizing user-level communication patterns on the Fujitsu AP3000 , 1999, ICWC 99. IEEE Computer Society International Workshop on Cluster Computing.