Lipschitzian optimization without the Lipschitz constant
Journal of Optimization Theory and Applications
Performance bounds for distributed systems with workload variabilities and uncertainties
Parallel Computing - Special issue: distributed and parallel systems: environments and tools
A parallel adaptive tabu search approach
Parallel Computing
Introduction to Algorithms: A Creative Approach
Introduction to Algorithms: A Creative Approach
A Locally-Biased form of the DIRECT Algorithm
Journal of Global Optimization
CCGRID '03 Proceedings of the 3st International Symposium on Cluster Computing and the Grid
Modifications of the direct algorithm
Modifications of the direct algorithm
Scheduling Strategies for Master-Slave Tasking on Heterogeneous Processor Platforms
IEEE Transactions on Parallel and Distributed Systems
Global Search Based on Efficient Diagonal Partitions and a Set of Lipschitz Constants
SIAM Journal on Optimization
Deterministic parallel global parameter estimation for a model of the budding yeast cell cycle
Journal of Global Optimization
Design and implementation of a massively parallel version of DIRECT
Computational Optimization and Applications
A power aware study for VTDIRECT95 using DVFS
SpringSim '09 Proceedings of the 2009 Spring Simulation Multiconference
Direct search versus simulated annealing on two high dimensional problems
Proceedings of the 19th High Performance Computing Symposia
Direct search and stochastic optimization applied to two nonconvex nonsmooth problems
Proceedings of the 2012 Symposium on High Performance Computing
Adjusting process count on demand for petascale global optimization
Parallel Computing
Parallel deterministic and stochastic global minimization of functions with very many minima
Computational Optimization and Applications
Hi-index | 0.00 |
Modeling and analysis techniques are used to investigate the performance of a massively parallel version of DIRECT, a global search algorithm widely used in multidisciplinary design optimization applications. Several high-dimensional benchmark functions and real world problems are used to test the design effectiveness under various problem structures. Theoretical and experimental results are compared for two parallel clusters with different system scales and network connectivities. The present work aims at studying the performance sensitivity to important parameters for problem configurations, parallel schemes, and system settings. The performance metrics include the memory usage, load balancing, parallel efficiency, and scalability. An analytical bounding model is constructed to measure the load balancing performance under different schemes. Additionally, linear regression models are used to characterize two major overhead sources, interprocessor communication and processor idleness, and also applied to the isoefficiency functions in scalability analysis. For a variety of high-dimensional problems and large-scale systems, the massively parallel design has achieved reasonable performance. The results of the performance study provide guidance for efficient problem and scheme configuration. More importantly, the generalized design considerations and analysis techniques are beneficial for transforming many global search algorithms into effective large-scale parallel optimization tools.