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

DOI10.1016/S0378-4754(01)00329-9MaRDI QIDQ5952567zbMATH OpenOpenAlexFDO

Authors S. K. Chan, V. Bharadwaj, D. Ghose

Publication date 1 September 2002

Published in Mathematics and Computers in Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0378-4754(01)00329-9

zbMATH Keywords

bus networkscommunication delaycomputation delaydivisible loadexperimental resultsmatrix-vector productprocessing time minimizationscheduling

Mathematics Subject Classification ID

Complexity and performance of numerical algorithms (65Y20) Network design and communication in computer systems (68M10) Analysis of algorithms and problem complexity (68Q25)

Recommendations

• Load partitioning and trade-off study for large matrix-vector computations in multicast bus networks with communictaion delays
• Divisible task scheduling -- concept and verification: Special issue on task scheduling problems for parallel and distributed systems
• Scheduling divisible loads in bus networks with arbitrary processor release times
• Computing BLAS level-2 operations on workstation clusters using the divisible load paradigm
• Design and analysis of load distribution strategies with start-up costs in scheduling divisible loads on distributed networks

Cites work

• Access time minimization for distributed multimedia applications
• Closed form solutions for bus and tree networks of processors load sharing a divisible job
• scientific article; zbMATH DE number 51132 (Why is no real title available?)
• scientific article; zbMATH DE number 947809 (Why is no real title available?)
• Load partitioning and trade-off study for large matrix-vector computations in multicast bus networks with communictaion delays

Cited in

(3)

• Load partitioning and trade-off study for large matrix-vector computations in multicast bus networks with communictaion delays
• Computing BLAS level-2 operations on workstation clusters using the divisible load paradigm
• An incentive-based distributed mechanism for scheduling divisible loads in tree networks

This page was built for publication: Large matrix-vector products on distributed bus networks with communication delays using the divisible load paradigm: Performance analysis and simulation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5952567)