Metaheuristics and Parallelism

Alba, Enrique; Talbi, El-Ghazali; Luque, Gabriel; Melab, Nouredine

doi:10.1002/0471739383.ch4

Cited by 25 publications

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GRID5000 is promoted by CNRS, INRIA and several universities 4 -please refer to [6] for details. At this time the GRID is gathering more than 2600 processors with around 2.5 Tb of cumulated memory and 100 Tb of non-volatile storage capacity.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Evolutionary algorithms are stochastic search iterative techniques, with a large area of appliance -epistatic, multimodal, multicriterion and highly constrained problems [4]. Stochastic operators are applied for evolving the initial randomly generated population, in an iterative manner.…”

Section: Genetic Algorithmmentioning

confidence: 99%

Section: Genetic Algorithmmentioning

confidence: 99%

“…First, several GAs cooperate by exchanging their genetic material (parallel island model [4]). Second, as the fitness function of each GA is time-intensive the fitness evaluation phase of the GA is parallelized (parallel evaluation of the population model [4]). These two models are provided in a transparent way through the ParadisEO-G4 framework [1][2], dedicated to the reusable design of parallel hybrid metaheuristics on computational grids.…”

Section: Genetic Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

A Comparative Study of Parallel Metaheuristics for Protein Structure Prediction on the Computational Grid

Tantar

Melab

Talbi

2007

2007 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

I. INTRODUCTIONWith the evolution of high-performance and highthroughput distributed computing and with the proliferation of nuclear magnetic resonance (NMR) data, we are at the dawns of a new era in molecular research and pharmaceutical drug design. A focus is set by current research on molecular structure prediction, molecular folding and molecular docking. Computational modeling and prediction offer an alternative to laboratory experimentation, unfeasible for large size molecules. A viable approach for addressing the implied complexity matters is grid computing, nowadays admitted as a powerful way for achieving high performance on computational-intensive applications.The protein structure prediction problem, further referred to as PSP, is one of the particularly interesting challenges of

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Genetic Algorithmmentioning

confidence: 99%

Section: Genetic Algorithmmentioning

confidence: 99%

Section: Genetic Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Parallel Metaheuristics for Protein Structure Prediction on the Computational Grid

Tantar

Melab

Talbi

2007

2007 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…Due to this, the performance of LS algorithms is particularly improved when running in parallel. Parallel design and implementation of metaheuristics have been studied as well on different architectures [6][7][8].…”

Section: Parallel Models Of Ls Algorithmsmentioning

confidence: 99%

GPU-Based Multi-start Local Search Algorithms

Melab

Talbi

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In practice, combinatorial optimization problems are complex and computationally time-intensive. Local search algorithms are powerful heuristics which allow to significantly reduce the computation time cost of the solution exploration space. In these algorithms, the multistart model may improve the quality and the robustness of the obtained solutions. However, solving large size and time-intensive optimization problems with this model requires a large amount of computational resources. GPU computing is recently revealed as a powerful way to harness these resources. In this paper, the focus is on the multi-start model for local search algorithms on GPU. We address its re-design, implementation and associated issues related to the GPU execution context. The preliminary results demonstrate the effectiveness of the proposed approaches and their capabilities to exploit the GPU architecture.

show abstract