Filters








4,351 Hits in 8.3 sec

Message Clustering Technique towards Efficient Irregular Data Redistribution in Clusters and Grids [chapter]

Shih-Chang Chen, Tai-Lung Chen, Ching-Hsien Hsu
2010 Lecture Notes in Computer Science  
It is important for schedulers to keep an eye on load balance and low communication cost while distributing different size of data segment on various processors.  ...  Efficient scheduling algorithms are essential to irregular data redistribution in cluster grid. Cluster grid is an environment with heterogeneous computing nodes and complex network.  ...  An efficient communication scheduling method [9] was proposed for processor mapping technique.  ... 
doi:10.1007/978-3-642-13119-6_25 fatcat:b5n2tsk73ffl3cnqyemu3o6kxa

Processor reordering algorithms toward efficient GEN_BLOCK redistribution

Saeri Lee, Hyun-Gyoo Yook, Mi-Soo Koo, Myong-Soon Park
2001 Proceedings of the 2001 ACM symposium on Applied computing - SAC '01  
The use of data redistribution represents a performance tradeoff between the expected higher efficiency of a new distribution for subsequent computation and the communication cost of redistributing the  ...  This paper focuses on reducing the communication cost in GEN_BLOCK redistribution using a logical processor reordering method.  ...  In this case, if the processor is to apply the processor mapping techniques in order to minimize the amount of data exchanged among processor memories, an undesired side effect is incurred.  ... 
doi:10.1145/372202.372457 dblp:conf/sac/LeeYKP01 fatcat:xsqxtlemtvcgbgsyftiugefl7u

Optimizing Scheduling Stability for Runtime Data Alignment [chapter]

Ching-Hsien Hsu, Chao-Yang Lan, Shih-Chang Chen
2006 Lecture Notes in Computer Science  
In this paper, we present an algorithm independent technique for optimizing scheduling stability of different scheduling heuristics.  ...  The experimental results show that the proposed technique is effective in terms of scheduling stability, communication efficiency and easy to implement.  ...  In [3] , Guo et al. also presented an approach for scheduling all-to-many communications in redistribution. Hsu et al. [5] discussed processor mapping techniques for array redistribution.  ... 
doi:10.1007/11807964_83 fatcat:xbehlj5l6naezda4lqos4zkey4

Irregular Redistribution Scheduling by Partitioning Messages [chapter]

Chang Wu Yu, Ching-Hsien Hsu, Kun-Ming Yu, C. -K. Liang, Chun-I Chen
2005 Lecture Notes in Computer Science  
This work presents an efficient algorithm to partition large messages into multiple small ones and schedules them by using the minimum number of steps without communication contention and, in doing so,  ...  Therefore, the largest sized messages in the same communication step dominate the data transfer time required for this communication step.  ...  Examples are the processor mapping techniques [10, 12, 4] for minimizing data transmission overheads, the multiphase redistribution strategy [11] for reducing message startup cost, the communication  ... 
doi:10.1007/11572961_24 fatcat:2lpuebmb2vd7zgkcpns2sstaje

Efficient Multidimensional Data Redistribution for Resizable Parallel Computations [article]

Rajesh Sudarsan, Calvin J. Ribbens
2007 arXiv   pre-print
The algorithm ensures a contention-free communication schedule for data redistribution if P_r ≤ Q_r and P_c ≤ Q_c.  ...  The resizing library in ReSHAPE includes support for releasing and acquiring processors and efficiently redistributing application state to a new set of processors.  ...  We are currently evaluating ReSHAPE framework with different scheduling strategies for processor reallocation, quality-of-service and advanced reservation services.  ... 
arXiv:0706.2146v1 fatcat:m7jr5z3tl5abzbpg5hhjncns2i

Efficient Multidimensional Data Redistribution for Resizable Parallel Computations [chapter]

Rajesh Sudarsan, Calvin J. Ribbens
2007 Lecture Notes in Computer Science  
The algorithm ensures a contention-free communication schedule for data redistribution if Pr ≤ Qr and Pc ≤ Qc.  ...  The resizing library in ReSHAPE includes support for releasing and acquiring processors and efficiently redistributing application state to a new set of processors.  ...  We are currently evaluating ReSHAPE framework with different scheduling strategies for processor reallocation, quality-of-service and advanced reservation services.  ... 
doi:10.1007/978-3-540-74742-0_19 fatcat:6ionkagmcvav7gtpzy4ctjcjn4

A generalized processor mapping technique for array redistribution

Ching-Hsien Hsu, Yeh-Ching Chung, Don-Lin Yang, Chyi-Ren Dow
2001 IEEE Transactions on Parallel and Distributed Systems  
Since the redistribution is performed at runtime, there is a performance trade-off between the efficiency of the new data decomposition for a subsequent phase of an algorithm and the cost of redistributing  ...  The generalized processor mapping technique can handle array redistribution with arbitrary source and destination processor sets and can be applied to multidimensional array redistribution.  ...  ACKNOWLEDGMENTS The work of this paper was partially supported by NSC of ROC under contract NSC-88-2213-E-035-002.  ... 
doi:10.1109/71.940748 fatcat:jds6uxiu5jeq7czeaap6pn4anu

Improving communication scheduling for array redistribution

Minyi Guo, Yi Pan
2005 Journal of Parallel and Distributed Computing  
It is essential to use efficient algorithms for redistribution, otherwise the performance of the programs will degrade considerably.  ...  In order to solve this problem, in this paper, we propose an efficient scheduling scheme that not only minimizes the number of communication steps and eliminates node contention, but also minimizes the  ...  The authors thank the four anonymous reviewers for their careful reading of the manuscript and many insightful comments and suggestions.  ... 
doi:10.1016/j.jpdc.2004.12.001 fatcat:csvulniqdbhqbej6n7tkzzxwoy

Runtime and language support for compiling adaptive irregular programs on distributed-memory machines

Yuan-Shin Hwang, Bongki Moon, Shamik D. Sharma, Ravi Ponnusamy, Raja Das, Joel H. Saltz
1995 Software, Practice & Experience  
The CHAOS library provides efficient runtime primitives for distributing data and computation over processors; it supports efficient index translation mechanisms and provides users high-level mechanisms  ...  for optimizing communication.  ...  ACKNOWLEDGMENTS The authors thank Richard Wilmoth at NASA Langley for his help with the parallelization of direct simulation Monte Carlo methods.  ... 
doi:10.1002/spe.4380250603 fatcat:zbzluzrtt5futjpv4m3bbumdjy

A basic-cycle calculation technique for efficient dynamic data redistribution

Yeh-Ching Chung, Ching-Hsien Hsu, Sheng-Wen Bai
1998 IEEE Transactions on Parallel and Distributed Systems  
Since it is performed at run-time, there is a performance trade-off between the efficiency of the new data decomposition for a subsequent phase of an algorithm and the cost of redistributing data among  ...  Index Terms-Data redistribution, the basic-cycle calculation technique, the PITFALLS method, the multiphase method, distributed memory multicomputers.  ...  ACKNOWLEDGMENTS The work of this paper was partially supported by the National Science Council of the Republic of China under contract NSC-87-2213-E035-011.  ... 
doi:10.1109/71.667897 fatcat:fvwxevakebdzzjn56gzkowrskm

A Compressed Diagonals Remapping Technique for Dynamic Data Redistribution on Banded Sparse Matrix

Ching-Hsien Hsu, Kun-Ming Yu
2004 Journal of Supercomputing  
Examples are the processor mapping technique [14], the multiphase redistribution technique [15], communication scheduling approach [6] and the strip mining approach [28].  ...  The CDR technique uses an efficient one-dimensional indexing scheme to perform data redistribution on banded sparse matrix.  ...  The other term for evaluating the efficiency of a redistribution algorithm is transiting cost, which is defined as time complexity of an algorithm to perform data packing and unpacking.  ... 
doi:10.1023/b:supe.0000026846.74050.18 fatcat:omizx2ectbgkzhpikiwsioredi

A Compressed Diagonals Remapping Technique for Dynamic Data Redistribution on Banded Sparse Matrix [chapter]

Ching-Hsien Hsu, Kun-Ming Yu
2003 Lecture Notes in Computer Science  
Examples are the processor mapping technique [14], the multiphase redistribution technique [15], communication scheduling approach [6] and the strip mining approach [28].  ...  The CDR technique uses an efficient one-dimensional indexing scheme to perform data redistribution on banded sparse matrix.  ...  The other term for evaluating the efficiency of a redistribution algorithm is transiting cost, which is defined as time complexity of an algorithm to perform data packing and unpacking.  ... 
doi:10.1007/3-540-37619-4_8 fatcat:chcwbycbnzd3pdijtb42mibvta

Operators for Data Redistribution: Applications to the STL Library and RayTracing Algorithm

Ana Moreton-Fernandez, Yuri Torres De La Sierra, Arturo Gonzalez-Escribano, Diego R. Llanos
2021 IEEE Access  
They abstract to the programmer the data-redistribution implementation details, such as the new mapping, relocation, and communication of the selected data.  ...  In this paper, we present a method based on four combinable operators to redistribute partial domains selected by the programmer at runtime in an efficient and simple way.  ...  ACKNOWLEDGMENT The authors have used the computing facilities of Extremadura Research Centre for Advanced Technologies (CETA-CIEMAT), funded by the European Regional Development Fund (ERDF).  ... 
doi:10.1109/access.2021.3063628 fatcat:huew4kmt3fcdrgqjfn53azamlu

Redistribution aware two-step scheduling for mixed-parallel applications

Sascha Hunold, Thomas Rauber, Frederic Suter
2008 2008 IEEE International Conference on Cluster Computing  
This separation can induce unnecessary or costly data redistributions that have an impact on the overall performance. This is particularly true for data intensive applications.  ...  Two redistribution aware mapping strategies are detailed and a study of their impact on the schedule length is proposed through a comparison with an efficient two step algorithm over a broad range of experimental  ...  accounting for data communication and data redistribution costs.  ... 
doi:10.1109/clustr.2008.4663755 dblp:conf/cluster/HunoldRS08 fatcat:mbw45agfmzc6bemece2fwlqipq

The Paradigm compiler for distributed-memory multicomputers

P. Banerjee, J.A. Chandy, M. Gupta, E.W. Hodges, J.G. Holm, A. Lain, D.J. Palermo, S. Ramaswamy, E. Su
1995 Computer  
The programmer must manually distribute computations and data across processors and explicitly manage communication.  ...  The Paradigm (Parallelizing Compiler for Distributed-Memory, General-Purpose Multicomputers) project at the University of Illinois addresses this problem by developing automatic methods for efficient parallelization  ...  We are also grateful to the National Center for Supercomputing Applications, the San Diego Supercomputing Center, and the Argonne National Laboratory for providing access to their machines.  ... 
doi:10.1109/2.467577 fatcat:ghmtervcfzehzlelvf2ealwgyu
« Previous Showing results 1 — 15 out of 4,351 results