January 25, 2013 - ALCHEMY Workshop (Architecture, Languages, Compilation and Hardware support for Emerging ManYcore systems)
ALCHEMY Workshop (Architecture, Languages, Compilation and Hardware support for Emerging ManYcore systems) Held in conjunction with the International Conference on Computational Science (ICCS 2013) Barcelona, Spain, 5-7 June 2013 *Call for papers* Massively parallel processors are becoming one of the key actors for the next embedded and high performance computing architectures. They offer thousands of cores, integrated memory and network on a single chip. They also keep a low power consumption compared to regular chip multiprocessors. As far as today, taking benefit of parallel and distributed architectures such as GPGPU farms, clusters, grids and clouds, has exhibited the complexity of offering tight programmability to the developer, while preserving a high level of performance. Manycores encounter the same challenges, but they rely on paradigms coming from CMP architectures. In this session, we explore the newest academic and industrial works that contribute to the efficient programmability of manycores. These contributions should be from any of the following research fields: programming languages and compilers, runtime generation, architecture support for massive parallelism management and enhanced communications, new operating systems and dedicated operating systems. ICCS is the relevant place to gather researchers that work both on novel architecture concepts and execution support for such architectures. It can also bring useful interactions with the computational science community in order to match the proposal of new architectures and programmability support with the computational needs. *Topics (not limited to)* - Advanced compilers for programming languages targeting massively parallel architectures - Advanced architecture support for massive parallelism management - Advanced architecture support for enhanced communication for CMP/manycores - Shared memory, data consistency models and protocols - New OS, or dedicated OS for massively parallel application - Runtime generation for parallel programing on manycores. *Important dates (subject to modifications)* Full paper submission January 25, 2013 Notification of acceptance February 15, 2013 Camera-ready papers March 5, 2013 *Submission* Papers should be formatted using the ICCS rules (up to 10 page papers, single column). See ALCHEMY workshop page and ICCS page for further details. https://sites.google.com/site/alchemyworkshop/ *Program Committee* David Bader, Georgia Institute of Technology, USA Loïc Cudennec, CEA LIST, France Roberto Di Cosmo, University of Paris-Diderot, France Stephan Diestelhorst, AMD Dresden, Germany Aleksandar Dragojevic, Microsoft Research Cambridge, UK Benoît Dupond de Dinechin, KALRAY, France Daniel Etiemble, University of Paris-Sud, France Stéphane Louise, CEA LIST, France Eric Petit, University of Versailles Saint Quentin-en-Yvelines, France Antoniu Pop, Ecole Normale Superieure (ENS) de Paris, France Erwan Raffin, CAPS entreprise, France Etienne Rivière, University of Neuchâtel, Switzerland Osamu Tatebe, University of Tsukuba, Japan Organizers Loïc Cudennec, CEA LIST, France Stéphane Louise, CEA LIST, France -- Loïc CUDENNEC http://www.cudennec.fr/ CEA LIST, Nano-Innov / Saclay 91191 Gif-sur-Yvette cedex +33 1 69 08 00 58
Document Actions