EASEA : a generic optimization tool for GPU machines in asynchronous island model

• Autorzy: Baumes L. A. , Kruger F. , Collet P.

Warianty tytułu

PL

Ogólne narzędzie do optymalizacji na maszynach GNU w asynchronicznym modelu wyspowym

• Języki publikacji: EN

Abstrakty

EN

Very recently, we presented an efficient implementation of Evolutionary Algorithms (EAs) using Graphics Processing Units (GPU) for solving microporous crystal structures. Because of both the inherent complexity of zeolitic materials and the constant pressure to accelerate R&D solutions, an asynchronous island model running on clusters of machines equipped with GPU cards, i.e. the current trend for super-computers and cloud computing, is presented. This last improvement of the EASEA platform allows an effortless exploitation of hierarchical massively parallel systems. It is demonstrated that supra-linear speedup over one machine and linear speedup considering clusters of different sizes are obtained. Such an island implementation over several potentially heterogeneous machines opens new horizon for various domains of application where computation time for optimization remains the principal bottleneck.

PL

W swojej poprzedniej pracy Autorzy przedstawili wydajną implementację Algorytmów Ewolucyjnych (ang. Evolutionary Algorithms - EA) z zastosowaniem procesorów graficznych (Graphics Processing Units GPU) do rozwiązywania struktur krystalicznych z mikroporami. Ze względu na skomplikowanie materiałów zeolitycznych oraz ciągłą presję na poprawę efektywności symulacji, w niniejszej pracy zaproponowano asyn-chroniczny model wyspowy na klastrach maszyn wyposażonych w karty GPU. Jest to najnowszy trend w zakresie superkomputerów oraz obliczeń w chmurze (ang. cloud computing). To ostatnie usprawnienie platformy EASEA (ang. EAsy Specification of Evolutionary Algorithms) łatwa specyfikacja algorytmów ewolucyjnych) pozwala na łatwą eksploatację rozbudowanych systemów (komputerów) masowo równoległych. Pokazano, że można osiągnąć ponadliniowe przyspieszenie w stosunku do jednej maszyny oraz liniowe przyspieszenie stosując klastery o różnych rozmiarach. Takie implementacje wyspowe dla kilku potencjalnie heterogenicznych maszyn otwiera nowe perspektywy dla różnych obszarów zastosowań, w których czasy obliczeń odgrywają kluczową rolę.

Słowa kluczowe

EN

GPU; evolutionary algorithms; island model; parallelism; zeolite materials

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Methods in Materials Science
• Rocznik: 2011
• Tom: Vol. 11, No. 3
• Strony: 489--499
• Opis fizyczny: Bibliogr. 30 poz., rys.

Twórcy

autor

Baumes L. A.

autor

Kruger F.

autor

Collet P.

• ITQ, UPV-CSIC, Valencia, Spain,

Bibliografia

• Adamidis, P., 1994, Parallel Evolutionary Algorithms: A Review, 4th Hellenic-European Conference on Computer Math-ematics and its Applications (HERCMA '98), Sept. 1998, Athens.
• Alba, E., J. M. Troya, 1999, An analysis of synchronous and asynchronous parallel distributed genetic algorithms with structured and Panmictic Islands, San Juan PR., Lecture Notes in Computer Science, Springer-Verlag London, UK, 1586: 248-256
• Ausfelder, F., L. A. Baumes, D. Farrusseng, 201 la, Last Devel-opments in Combinatorial Catalysis Research and High-Throughput Technologies, Catalysis Today, 159(1), 1-150.
• Ausfelder, F., L. A. Baumes, D. Farrusseng, 2011b, Preface, Catalysis Today, 159(1), 1.
• Baumes, L. A., A. Blansche, P. Serna, A. Tchougang, N. Lachiche, P. Collet, A. Corma, 2009, Using genetic programming for an advanced performance assessment of industrially relevant heterogeneous catalysts, Materials and Manufacturing Processes, 24(3), 282-292.
• Baumes, L. A., P. , Collet, 2009, Examination of genetic programming paradigm for high-throughput experimenta¬tion and heterogeneous catalysis, Computational Materials Science, 45(1), 27-40.
• Baumes, L. A., S. Jimenez, A., Corma, 2011a, hITeQ: A new workflow-based computing environment for streamlining discovery. Application in materials science, Catalysis Today, 159(1), 126-137.
• Baumes, L. A., F. Kruger, S. Jimenez, P. Collet, A. Corma, 2011b, Boosting theoretical zeolitic framework generation for the determination of new materials structures using GPU programming, Physical Chemistry Chemical Physics, 13,4674-4678.
• Baumes, L. A., M. Moliner, A. Corma, 2007, Prediction of ITQ-21 Zeolite Phase Crystallinity: Parametric Versus Non-parametric Strategies, QSAR & Combinatorial Science, 26(2), 255-272.
• Baumes, L. A., M. Moliner, A. Corma, 2009, Design of a Full-Profile-Matching Solution for High-Throughput Analysis of Multiphase Samples Through Powder X-ray Dif-fraction, Chemistry - A European Journal, 15(17), 4258-4269.
• Baumes, L. A., M. Moliner, N. Nicoloyannis, A. Corma, 2008, A reliable methodology for high throughput iden¬tification of a mixture of crystallographic phases from powder X-ray diffraction data, Cryst. Eng. Comm., 10(10), 1321-1324.
• Branke, J., A. Kamper, H. Schmeck., 2004, Distribution of Evolutionary Algorithms in Heterogeneous Networks -GECCO 2004, Lecture Notes in Computer Science, 3102, 923-934.
• Cantu-Paz, E., 2000, Efficient and Accurate Parallel Genetic Algorithms, Kluwer Academy Publishers.
• Collet, P., E. Lutton, M. Schoenauer, J. Louchet, 2000, Take It EASEA, 6th International Conference on Parallel Problem Solving from Nature, PPSN, 891-901.
• Corma, A., M. Moliner, J. M. Serra, P. Serna, M. J. Diaz-Cabanas, L. A. Baumes, 2006, A New Mapping/Exploration Approach for HT Synthesis of Zeolites, Chem. Mater., 18, 3287- 3296.
• Eldredge, N., S. J. Gloud, 1972, Models in Paleobiology. T. Schopf. San Francisco, Freeman, Cooper and Co., 82-115.
• Farrusseng, D., L. A. Baumes, C. Hayaud, I. Vauthey, P. Denton, C. Mirodatos, 2002, The Combinatorial Approach for Heterogeneous Catalysis: a Challenge for Academic Research, Kluwer Academic Publishers.
• Farrusseng, D., L. A. Baumes, C. Mirodatos, 2003, Data Management for Combinatorial Heterogeneous Catalysis: Methodology and Development of Advanced Tools, Kluwer Academic/Plenum Publishers.
• Gordon, V. S., D. Whitley, A. Bohn, 1992, Dataflow parallelism in genetic algorithms. Parallel Problem Solving from Nature, 2. R. Manner; B. Manderick. Brussels, Elsevier Science, 533-542.
• Jiang, J., J. L. Jorda, J. Yu, L. A. Baumes, E. Mugnaioli, M. J. Diaz-Cabanas, U. Kolb, A. Corma, 2011, Synthesis and Structure Determination of the Hierarchical Meso-Microporous Zeolite ITQ-43, Science, 333, 1131.
• Kruger, F., O. Maitre, S. Jimenez, L. A. Baumes, P. Collet, 2010, Speedups between x70 and xl20 for a generic local search (memetic) algorithm on a single GPGPU chip, EvoApplications 2010, April 7-9, 2010, Istanbul, Turkey, Lecture Notes in Computer Science, Springer.
• Lin, S.-C, W. F. Punch, E. D. Goodman, 1994, Coarse-grain parallel genetic algorithms: categorization and new ap-proach. Parallel and Distributed Processing, 1994. Proceedings. Sixth IEEE Symposium on Dallas, TX, USA, 28-37.
• Luong, T. V., N. Melab, E. Talbi, 2010, GPU-based island Model for Evolutionary Algoritms. GECCO, Portland, Oregon, USA.
• Maitre, O., L. A. Baumes, N. Lachiche, A. Corma, P. Collet, 2009a, Coarse grain parallelization of evolutionary algorithms on GPGPU cards with EASEA, 11th Annual Ge netic and Evolutionary Computation Conference, GECCO-2009, Montreal.
• Maitrc, O., N. Lachiche, P. Clauss, L. A. Baumes, P. Collet, 2009b, Efficient parallel implementation of evolutionary algorithms on GPGPU cards, August 25-28, Euro-Par 2009, Delft, The Netherlands, Lecture Notes in Comput¬er Science, Springer.
• Munetomo, M., Y. Takai, Y. Sato, 1993, An Efficient Migration Scheme for Subpopulation-Based Asynchronously Parallel Genetic Algorithms, Proceedings of the 5th International Conference on Genetic Algorithms, San Francisco, CA, USA, Morgan Kaufmann Publishers, 649.
• Pettey, B., M. Leuze, J. Grefenstette, 1987, A Parallel Genetic Algorithm, 2nd Int. Conf. on Genetic Algorithms, Hills¬dale, N.J., Lawrence Erlbaum Associates.
• Serra, J. M., L. A. Baumes, M. Molincr, P. Serna, A. Corma, 2007, Zeolite Synthesis Modelling with Support Vector Machines: A Combinatorial Approach, Combinatorial Chemistry & High Throughput Screening, 10(1), 13-24.
• Tanese, R., 1987, Parallel genetic algorithms for a hypercubc, 2nd Int. Conf. on Genetic Algorithms, Hillsdale, NJ, Lawrence Erlbaum Associates.
• Whitley, D., S. Rana, R. B. Heckendorn, 1999, The Island Mod¬el Genetic Algorithm: On Separability, Population Size and Convergence, Journal of Computing and Information Technology, 7, 33-48.