From gfursin at gmail.com Mon Nov 3 07:31:49 2008 From: gfursin at gmail.com (Grigori Fursin) Date: Mon Nov 3 07:31:51 2008 Subject: CFP: SMART'09 - submission deadline extended until Nov 21 - 3rd workshop on statistical and machine learning approaches to architecture and compilation Message-ID: Apologies if you receive multiple copies of this call. ******* DEADLINE EXTENDED UNTIL NOVEMBER 21, 2008 ******* ******************************************************************************** CALL FOR PAPERS 3rd Workshop on Statistical and Machine learning approaches to ARchitecture and compilaTion (SMART'09) http://www.hipeac.net/smart-workshop.html January 25, 2009, Paphos, Cyprus (co-located with HiPEAC 2009 Conference) **** NEW PANEL INFORMATION **** Can machine learning help to solve the multicore code generation issues? **** NEW PUBLICATION INFORMATION **** Selected papers will be considered for publication in a special issue of the International Journal of Parallel Programming. ******************************************************************************** The rapid rate of architectural change and the large diversity of architecture features has made it increasingly difficult for compiler writers to keep pace with microprocessor evolution. This problem has been compounded by the introduction of multicores. Thus, compiler writers have an intractably complex problem to solve. A similar situation arises in processor design where new approaches are needed to help computer architects make the best use of new underlying technologies and to design systems well adapted to futureapplication domains. Recent studies have shown the great potential of statistical machine learning and search strategies for compilation and machine design. The purpose of this workshop is to help consolidate and advance the state of the art in this emerging area of research. The workshop is a forum for the presentation of recent developments in compiler techniques and machine design methodologies based on space exploration and statistical machine learning approaches with the objective of improving performance, parallelism, scalability, and adaptability. Topics of interest include (but are not limited to): Machine Learning, Statistical Approaches, or Search applied to * Feedback-Directed Compilation * Auto-tuning Programs + Language Extensions * Library Generators * Iterative Compilation * Dynamic Compilation/Adaptive Execution * Parallel Compiler Optimizations * Low-power Optimizations * Simulation * Performance Models * Adaptive Processor and System Architecture * Design Space Exploration * Other Topics relevant to Intelligent and Adaptive Compilers/ Architectures **** Paper Submission Guidelines **** Paper length - maximum 15 pages. Papers must be submitted in the PDF (preferably) or postscript formats using the workshop submission website: http://unidapt.org/dissemination/workshops/smart09 We suggest to use LNCS LaTeX templates that can be found at http://www.springeronline.com/lncs (go to "For Authors" and then "Information for LNCS Editors/Authors"). An informal collection of the papers to be presented will be distributed at the workshop. All accepted papers will appear on the workshop website. **** Important Dates **** Final deadline for submission: November 21, 2008 Decision notification: December 19, 2008 Workshop: January 25, 2009 Program Chair: David Padua, University of Illinois at Urbana-Champaign, USA Organizers: Grigori Fursin, INRIA Saclay, France John Cavazos, University of Delaware, USA Program Committee: Saman Amarasinghe, MIT, USA Francois Bodin, CAPS Enterprise, France Calin Cascaval, IBM T.J. Watson Research Center, USA John Cavazos, University of Delaware, USA Franz Franchetti, Carnegie Mellon University, USA Ari Freund, IBM Haifa Research Lab, Israel Grigori Fursin, INRIA Saclay, France Mary Hall, USC/ISI, USA Robert Hundt, Google, USA Michael O'Boyle, University of Edinburgh, UK David Padua, University of Illinois at Urbana-Champaign, USA Richard Vuduc, Georgia Institute of Technology, USA David Whalley, Florida State University, USA Panel: Can machine learning help to solve the multicore code generation issues? Chair: Francois Bodin, CAPS-Enterprise, France Participants: Marcelo Cintra, University of Edinburgh, UK Bilha Mendelson, IBM, Israel Lawrence Rauchwerger, Texas A&M University, USA Per Stenstrom, Chalmers University of Technology, Sweden ==================================================== Grigori Fursin, PhD INRIA, France http://unidapt.org From newsdesk at wolfram.com Tue Nov 18 21:22:07 2008 From: newsdesk at wolfram.com (Wolfram Research) Date: Tue Nov 18 21:22:09 2008 Subject: Mathematica 7 is now available Message-ID: Wolfram Research announced Mathematica 7, a major release that accelerates the drive to integrate and automate functionality as core Mathematica capabilities, adding image processing, parallel high-performance computing (HPC), new on-demand curated data, and other recently developed computational innovations--in total over 500 new functions and 12 application areas. The fully integrated image processing environment of Mathematica 7 was designed from the ground up to become the system of choice for imaging research and applications in science, engineering, medicine, and education. Industrial-strength, high-performance functions for image composition, transformation, enhancement, and segmentation combine with the existing Mathematica infrastructure of high-level language, automated interface construction, interactive notebook documents, and computational power to make a uniquely versatile image processing solution. Another key new area of integration in Mathematica 7 (and a first across technical computing) is built-in parallel computing. For the first time, every copy of Mathematica comes standard with the technology to parallelize computations over multiple cores or over networks of Mathematica deployed across a grid. Every copy of Mathematica 7 comes with four computation processes included. More processes as well as network capabilities can be added easily. Integrating parallel computing with Mathematica means that millions of users worldwide can now start to use and build parallel solutions for their technical computing problems. The immediate interactive parallel computing technology of Mathematica 7 is platform independent and needs zero configuration--making it an all-encompassing tool that accelerates Wolfram's tradition of offering HPC solutions. Computable data sources, introduced in Mathematica 6, are unique and popular innovations because of the ease with which data can be utilized in Mathematica. Mathematica 7 builds on this with major additions including the complete human genome, weather, astronomical, GIS, and geodesy data. Example uses include finding, analyzing, and visualizing gene sequences--making use of Mathematica's powerful string capabilities (including new string alignment functionality), pattern matching, and statistics. Similarly, both real-time and historical weather data from 16,000 weather stations is included in Mathematica 7, giving everyone from climatologists to economists curated information to use in their analyses or applications. Other areas of innovation in Mathematica 7 include: * Charting and information visualization * Vector field visualization * Comprehensive spline support, including NURBS * Industrial-strength Boolean computation * Statistical model analysis * Integrated geodesy and GIS data * Many symbolic computation breakthroughs, including discrete calculus, sequence recognition, and transcendental roots Mathematica 7 is available for Windows 2000/XP/Vista, Mac OS X, Linux x86, Solaris UltraSPARC/x86, and compatible systems. To learn more about the enhancements available in Mathematica 7 and to see the full list of new features, visit: http://www.wolfram.com/mathematica/newin7 From lgj at usenix.org Thu Nov 20 13:12:58 2008 From: lgj at usenix.org (Lionel Garth Jones) Date: Thu Nov 20 13:13:00 2008 Subject: Registration for Workshops Co-Located with USENIX OSDI '08 Message-ID: Don't miss the workshops co-located with OSDI '08. Taking place between December 7 and December 11, 2008, in San Diego, CA, the workshops cover a variety of topics--analysis of system logs, power aware computing and systems, I/O virtualization, and more. * HotDep '08: Fourth Workshop on Hot Topics in System Dependability December 7, 2008 The HotDep Workshop brings forth cutting-edge research ideas spanning the domains of fault tolerance/reliability and systems. Check out the Web site for more information: http://www.usenix.org/hotdep08/mem * WASL '08: First USENIX Workshop on the Analysis of System Logs December 7, 2008 WASL '08 will focus on novel techniques for extracting more information from existing logs and on methods to improve the information content of future logs. See the registration page for information on how to participate: http://www.usenix.org/wasl08/mem * HotPower '08: Workshop on Power Aware Computing and Systems December 7, 2008 This workshop hopes to provide a forum in which to present the latest research and to debate directions, challenges, and novel ideas about building energy-efficient computing systems. Find out more at http://www.usenix.org/hotpower08/mem * Diversity '08: Workshop on Supporting Diversity in Systems Research December 7, 2008 The Workshop on Supporting Diversity is a community-building event, serving both to educate women and under-represented minorities about the opportunities in systems research and to support researchers who are already working in the field. To get more information, see http://www.usenix.org/diversity08/mem * WIOV '08: First Workshop on I/O Virtualization December 10-11, 2008 This workshop is meant to provide a forum to discuss challenges of I/O virtualization that span the virtual machine monitor, guest operating system, processor, memory subsystem, and I/O subsystem. Find out more at http://www.usenix.org/wiov08/mem * SysML08: Third Workshop on Tackling Computer Systems Problems with Machine Learning Techniques December 11, 2008 The SysML workshop brings together researchers working at the intersection of machine learning and systems to discuss ideas and techniques that will benefit the future of both fields. For more information, check out http://www.usenix.org/sysml08/mem