2013 Barcelona
ALCHEMY Workshop
Held in conjunction with the International Conference on Computational Science (ICCS 2013)
Barcelona, Spain, 5-7 June 2013
Proceedings
Wed, 5 June, 13:50 - 15:30
Session W33a, room 214
Slides of presentations are available at the bottom of this page.
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)
Check out the ICCS important dates.
Submission
Papers should be formatted using the ICCS rules.
The submitted paper must be camera-ready and formatted according to the rules of Procedia Computer Science. Please use this file for a Latex template plus instructions and click here for an MS word template file). Submission implies the willingness of at least one of the authors to register and present the paper. PostScript and source versions of your paper must be submitted electronically through the paper submission system.
Please, note that papers must not exceed ten pages in length, when typeset using the Procedia format.
Program Committee
David Bader, Georgia Institute of Technology, USA
Loïc Cudennec, CEA LIST, France
Roberto Di Cosmo, University of Paris-Diderot, France
Aleksandar Dragojevic, Microsoft Research Cambridge, UK
Daniel Etiemble, University of Paris-Sud, France
Stéphane Louise, CEA LIST, France
Eric Petit, University of Versailles Saint Quentin-en-Yvelines, France
Erwan Piriou, CEA LIST, 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
Theo Ungerer, University of Augsburg, Germany
Organizers
Loïc Cudennec, CEA LIST, France
Stéphane Louise, CEA LIST, France
