Large matrix-vector products on distributed bus networks with communication delays using the divisible load paradigm: performance analysis and simulation

We present a performance analysis and experimental simulation results on the problem of scheduling a divisible load on a bus network. In general, the computing requirement of a divisible load is CPU intensive and demands multiple processing nodes for efficient processing. We consider the problem of scheduling a very large matrix–vector product computation on a bus network consisting of a homogeneous set of processors. The experiment was conducted on a PC-based networking environment consisting of Pentium II machines arranged in a bus topology. We present a theoretical analysis and verify these findings on the experimental test-bed. We also developed a software support system with flexibility in terms of scalability of the network and the load size. We present a detailed discussion on the experimental results providing directions for possible future extensions of this work.

[1]  Debasish Ghose,et al.  Optimal Sequencing and Arrangement in Distributed Single-Level Tree Networks with Communication Delays , 1994, IEEE Trans. Parallel Distributed Syst..

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

[3]  T.G. Robertazzi,et al.  Optimal divisible job load sharing for bus networks , 1996, IEEE Transactions on Aerospace and Electronic Systems.

[4]  Debasish Ghose,et al.  Load Partitioning and Trade-Off Study for Large Matrix-Vector Computations in Multicast Bus Networks with Communication Delays , 1998, J. Parallel Distributed Comput..

[5]  Thomas G. Robertazzi Processor equivalence for a linear daisy chain of load sharing processors , 1992 .

[6]  Keqin Li Managing Divisible Load on Partitionable Networks , 1998 .

[7]  Gerassimos D. Barlas Collection-Aware Optimum Sequencing of Operations and Closed-Form Solutions for the Distribution of a Divisible Load on Arbitrary Processor Trees , 1998, IEEE Trans. Parallel Distributed Syst..

[8]  Bharadwaj Veeravalli,et al.  On the Influence of Start-Up Costs in Scheduling Divisible Loads on Bus Networks , 2000, IEEE Trans. Parallel Distributed Syst..

[9]  Thomas G. Robertazzi,et al.  Closed Form Solutions for Bus and Tree Networks of Processors Load Sharing A Divisible Job , 1993, 1993 International Conference on Parallel Processing - ICPP'93.

[10]  E. Haddad Real-time optimization of distributed load balancing , 1994, Second Workshop on Parallel and Distributed Real-Time Systems.

[11]  Bharadwaj Veeravalli,et al.  Efficient partitioning and scheduling of computer vision and image processing data on bus networks using divisible load analysis , 2000, Image Vis. Comput..

[12]  Debasish Ghose,et al.  Distributed Computation with Communication Delays: Asymptotic Performance Analysis , 1994, J. Parallel Distributed Comput..

[13]  Thomas G. Robertazzi Processor equivalence for daisy chain load sharing processors , 1993 .

[14]  Thomas G. Robertazzi,et al.  A Multi-Job Load Sharing Strategy for Divisible Jobs on Bus Networks , 1993 .

[15]  Sartaj Sahni,et al.  Performance metrics: keeping the focus on runtime , 1996, IEEE Parallel Distributed Technol. Syst. Appl..

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