A Novel Computational Model for Non-Linear Divisible Loads on a Linear Network

This work investigates the problem of a non-linear divisible load distribution on a homogeneous linear network. A novel computational model of non-linear loads that includes complete steps for processing them, is proposed. This model solves the problem of the classical model, whose performance degrades by separating the load. This work also presents an algorithm S (Single-installment) that uses single-installment processing to distribute a non-linear divisible load on a homogeneous linear network. An algorithm M (Multi-installment) that applies multi-installment processing to reduce the initial distribution time for load is also proposed. Closed-form expressions for the parallel processing time and speed-up of the proposed algorithms are derived. The speed-up of algorithm S is much better than that of the classical algorithm that is based on the classical model. Algorithm M outperforms algorithm S in terms of speed-up when the load to be processed is very large or when the start-up costs are small.

[1]  Naga K. Govindaraju,et al.  Mars: A MapReduce Framework on graphics processors , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[2]  Laxmi N. Bhuyan,et al.  An efficient packet scheduling algorithm in network processors , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[3]  Robert C. Ward,et al.  Parallel block tridiagonalization of real symmetric matrices , 2008, J. Parallel Distributed Comput..

[4]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[5]  Chih-Ping Chu,et al.  Improved Methods for Divisible Load Distribution on k-Dimensional Meshes Using Multi-Installment , 2007, IEEE Transactions on Parallel and Distributed Systems.

[6]  B. Veeravalli.  Design and Performance Analysis of Heuristic Load-Balancing Strategies for Processing Divisible Loads on Ethernet Clusters , 2005 .

[7]  Hisham Othman,et al.  A Separable Low Complexity 2D HMM with Application to Face Recognition , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Henri Casanova,et al.  Multiround algorithms for scheduling divisible loads , 2005, IEEE Transactions on Parallel and Distributed Systems.

[9]  Thomas G. Robertazzi,et al.  Scheduling nonlinear divisible loads in a single level tree network , 2011, The Journal of Supercomputing.

[10]  N. Ahmed,et al.  Discrete Cosine Transform , 1996 .

[11]  Thomas G. Robertazzi,et al.  Distributed Scheduling of Nonlinear Computational Loads , 2003 .

[12]  Claudia Rosas,et al.  Improving Performance on Data-Intensive Applications Using a Load Balancing Methodology Based on Divisible Load Theory , 2012, International Journal of Parallel Programming.

[13]  Bharadwaj Veeravalli,et al.  Requirement-aware strategies for scheduling real-time divisible loads on clusters , 2013, J. Parallel Distributed Comput..

[14]  F. Harris.  On the use of windows for harmonic analysis with the discrete Fourier transform , 1978, Proceedings of the IEEE.

[15]  Debasish Ghose,et al.  Scheduling Divisible Loads in Parallel and Distributed Systems , 1996 .

[16]  Chih-Ping Chu,et al.  Improved methods for divisible load distribution on d‐dimensional hypercube using multi‐installment , 2008 .

[17]  Sundaram Suresh,et al.  Parallel implementation of back-propagation algorithm in networks of workstations , 2005, IEEE Transactions on Parallel and Distributed Systems.

[18]  T.G. Robertazzi,et al.  Signature search time evaluation in flat file databases , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[19]  Keqin Li.  New Divisible Load Distribution Methods using Pipelined Communication Techniques on Tree and Pyramid Networks , 2011, IEEE Transactions on Aerospace and Electronic Systems.

[20]  Young-Il Kim,et al.  Scheduling Second-Order Computational Load in Master-Slave Paradigm , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[21]  Olivier Beaumont,et al.  Non Linear Divisible Loads: There is No Free Lunch , 2013, 2013 IEEE 27th International Symposium on Parallel and Distributed Processing.

[22]  Sameer M. Bataineh,et al.  Toward an analytical solution to task allocation, processor assignment, and performance evaluation of network processors , 2005, J. Parallel Distributed Comput..

[23]  H. V. Jagadish,et al.  Partitioning Techniques for Large-Grained Parallelism , 1988, IEEE Trans. Computers.

[24]  Jin-Soo Kim,et al.  HAMA: An Efficient Matrix Computation with the MapReduce Framework , 2010, 2010 IEEE Second International Conference on Cloud Computing Technology and Science.

[25]  K. Ming Leung,et al.  Learning Vector Quantization , 2017, Encyclopedia of Machine Learning and Data Mining.

[26]  Bharadwaj Veeravalli,et al.  Distributed scheduling strategy for divisible loads on arbitrarily configured distributed networks using load balancing via virtual routing , 2006, J. Parallel Distributed Comput..

[27]  Joanna Berlinska,et al.  Scheduling divisible MapReduce computations , 2011, J. Parallel Distributed Comput..

[28]  T.G. Robertazzi,et al.  Scheduling nonlinear computational loads , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[29]  Julio Villalba,et al.  A fast Hough transform for segment detection , 1995, IEEE Trans. Image Process..

[30]  Judy Qiu,et al.  Mammoth Data in the Cloud: Clustering Social Images , 2012, High Performance Computing Workshop.

[31]  Thomas G. Robertazzi,et al.  Distributed computation with communication delay (distributed intelligent sensor networks) , 1988 .

[32]  Pawel Wolniewicz,et al.  Out-of-Core Divisible Load Processing , 2003, IEEE Trans. Parallel Distributed Syst..

[33]  Thomas G. Robertazzi,et al.  Scheduling data intensive parallel processing in distributed and networked environments , 2000 .

[34]  Subramaniam Shamala,et al.  New method for scheduling heterogeneous multi-installment systems , 2012, Future Gener. Comput. Syst..

[35]  Bharadwaj Veeravalli,et al.  Scheduling divisible loads on heterogeneous linear daisy chain networks with arbitrary processor release times , 2004, IEEE Transactions on Parallel and Distributed Systems.

[36]  Daniel Grosu,et al.  An incentive-based distributed mechanism for scheduling divisible loads in tree networks , 2012, J. Parallel Distributed Comput..

[37]  Maciej Drozdowski,et al.  Performance limits of divisible load processing in systems with limited communication buffers , 2004, J. Parallel Distributed Comput..

[38]  Ping Li,et al.  Design and implementation of parallel video encoding strategies using divisible load analysis , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[39]  Thomas G. Robertazzi,et al.  Ten Reasons to Use Divisible Load Theory , 2003, Computer.

[40]  Bharadwaj Veeravalli,et al.  Aligning biological sequences on distributed bus networks: a divisible load scheduling approach , 2005, IEEE Transactions on Information Technology in Biomedicine.

[41]  Bharadwaj Veeravalli,et al.  Resource-Aware Distributed Scheduling Strategies for Large-Scale Computational Cluster/Grid Systems , 2007, IEEE Transactions on Parallel and Distributed Systems.

[42]  Debasish Ghose,et al.  Computing BLAS level-2 operations on workstation clusters using the divisible load paradigm, , 2005, Math. Comput. Model..

[43]  William J. Dally,et al.  Sequoia: Programming the Memory Hierarchy , 2006, International Conference on Software Composition.