Special issue on parallel architectures and bioinspired algorithm: guest editors message

This special issue includes the extended version of selected papers presented at the fourth Parallel Architectures and Bioinspired Algorithms Workshop held in Galveston Island (TX, USA) on October 14, 2011 in conjunction withParallel Architectures and Compilation Techniques (PACT). This workshop follows the success of the three previous workshops held in conjunction with PACT 2008 in Toronto, Canada 1, PACT 2009 in Raleigh, USA 2, and PACT 2010 in Vienna 3, Austria and the two previous Workshops on Parallel Bioinspired Algorithms 4 held in Oslo, 2005, (together with IEEE International Conference on Parallel Processing (ICPP)) 5 and London, 2007 (together with Association for Computing Machinery (ACM) Genetic and Evolutionary Computation Conference (Gecco) 2007) 6. These series of workshops has shown that knowledge fields such as parallel computer architectures and Parallel and Distributed Computing and Bioinspired Algorithms, which could seem quite different in a first approach, are able to find transversal elements that enrich them. Bioinspired Algorithms comprise a set of heuristics that can help to optimize a wide range of problems, including many tasks faced by parallel architectures designers, such as balancing computer load, fault-tolerance and dependability, thermal-aware design, and NoC design. In addition, Bioinspired Algorithms may help in finding solutions related to compilation and resource sharing issues, which are interesting problems for parallel architectures. Parallel architecture designers may also propose infrastructures that allow the improvement of computing performance of Bioinspired Algorithms, which usually face real-world problems that manage huge amounts of data. Alternatives to the classical sequential solution are needed by this community. Therefore, topics such as P2P, cluster and grid computing, cloud computing, and Graphics Processing Unit (GPUs) implementation of Bioinspired Algorithms are very interesting to this field. We have therefore considered this opportunity to give a broader view on the application of nature inspired computing techniques to hardware design and parallel architectures problem solving. We have also considered the interest of including an overview of the available bioinspired techniques based tools that have been used so far to solve problems related to automatic hardware design. We thus invited Professors Oscar Garnica and Juan Lanchares to work with us with this aim. Therefore, this special issue includes the paper entitled A review of bioinspired CAD tools for parallel architectures and hardware design 7 together with four papers carefully selected for publications, extended versions of Parallel Architectures and Bioinspired Algorithms 2011 workshop's best papers. The first paper selected, GPU-based acceleration of bio-inspired motion estimation model 8, describes the specific and efficient implementation of a gradient-based optical flow model. The proposed model enhances the GPU computing capability when compared with other optical flow gradient family algorithms and has been particularized using a validated neuromorphic motion estimation system for the robust extraction of image velocity. The second paper, entitled Evaluation of asynchronous multi-swarm particle optimization on several topologies 9, evaluates the impact of the topology on multi-swarm systems, considering that swarms are independently interacting only when particle migration occurs. Several topologies and communication strategies have been evaluated within the paper, including broadcast and gossip on fully connected networks, unidirectional and bidirectional rings, hypercubes, and a dynamic topology. The work KLONOS: Similarity-based planning tool support for porting scientific applications 10 proposes a methodology to address planning support, an important aspect of software porting that usually receives little attention. When porting a scientific application, the selection of key subroutines greatly impacts the productivity . The authors propose ad methodology on the basis of the idea that a set of similar subroutines can be ported with similar strategies and result in a similar-quality porting. They apply bioinformatics techniques to conduct the similarity analysis of subroutines, by viewing subroutines as data and operator sequences, analogous to DNA sequences. Finally, the work entitled Boosting the 3D thermal-aware floorplanning problem through a master-worker parallel MOEA 11 deals with the problem of placing the hardware components on a 3D chip to reduce overheating by dissipation. The main contribution of this paper is to present a parallelization of the evaluation phase in a master-worker model to achieve a dramatic speed-up of the thermal-aware floorplanning process. Exhaustive experimentation was carried out over 3D integrated circuits, with 48 and 128 cores, outperforming previous published works. This work has been partially supported by Spanish Government grants Avanza Competitividad I+D+i TSI-020100-2010-962, TIN 2008-00508, MEC Consolider Ingenio CSD00C-07-20811, TIN2011-28627-C04-03, and GRU10029 Gobierno de Extremadura and EDRF, and Municipality of Almendralejo.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.