Third Workshop on Accelerator Programming using Directives (WACCPD) http://waccpd.org/ In cooperation with ACM SIGHPC Monday, November 14, 2016 co-located with SC16: The International Conference for High Performance Computing, Networking, Storage and Analysis November 13-18, 2016 Call for Papers One of the hard realities is that the hardware continues to evolve very rapidly with diverse memory subsystems or cores with different ISAs or accelerators of varied types. The HPC community is in constant need for sophisticated software tools and techniques to port legacy code to these emerging platforms. Maintaining a single code base yet achieving performance portable solution continues to pose a daunting task. Directive-based programming models such as OpenACC, OpenMP tackle this issue by offering scientists a high-level approach to accelerate scientific applications and develop performance portable solutions. This enables accelerators to be first-class citizens for HPC! To address the rapid pace of hardware evolution, developers continue to explore and add richer features to the various (parallel) programming standards. Domain scientists continue to explore the programming and tools space while preparing themselves for future Exascale systems. This workshop aims to solicit papers that explore innovative language features – their implementations, compilation & runtime scheduling techniques, performance optimization strategies, auto-tuning tools exploring the optimization space and so on. WACCPD has been one of the major forums for bringing together the users, developers and tools community to share their knowledge and experiences of using directives and similar approaches to program emerging complex systems. Topics of interest for workshop submissions include (but are not limited to): Compiler and Runtime support for current and emerging architectures Language-based extensions Memory management using directives Performance evaluation and lessons learnt Auto-tuning and optimization strategies Programming experience porting applications in any domain Extensions to and shortcomings of current accelerator directives APIs Hybrid heterogeneous or many-core programming with accelerator directives with other models (i.e. OpenMP, MPI, OpenSHMEM) Scientific libraries interoperability with accelerator directives Experiences in implementing compilers for accelerator directives on newer architectures Low level communication APIs or runtimes that support accelerator directives Asynchronous execution and scheduling (heterogeneous tasks) Power / energy studies Static analysis and verification tools Modeling and performance analysis tools Benchmarks and validation suites Important Deadlines Submission Deadline: August 22nd, 2016 AoE Author notification: September 30th, 2016 Camera Ready papers due: October 2nd, 2016 AOE Best Paper Award: NVIDIA has generously offered to sponsor the ‘Best Paper Award’ with NVIDIA’s newest Pascal compute capable card. This award will be given to the author(s) of the paper selected by the Technical Program Committee and the Program Chairs. The award will be determined from viewpoints of the technical and scientific merits, impact on the science and engineering of the research work and the clarity of presentation of the research contents in the paper. Paper Submission Guidelines Submissions are limited to 10 pages. They must follow the ACM format (see http://www.acm.org/sigs/publications/proceedings-templates). The 10-page limit includes figures, tables, and appendices, but does not include references, for which there is no page limit. Papers should be submitted electronically via EasyChair: https://easychair.org/conferences/?conf=waccpd2016 Submitted papers should not have appeared in or be under consideration for a different workshop, conference or journal. It is also expected that all accepted papers will be presented at the workshop by one of the authors. Journal Special Issue A Special issue of the International Journal of High Performance Computing and Networking (IJHPCN) titled ‘High Level Programming Approaches for Accelerators’ will feature invited contributions from the workshop. These special issues will be edited by Sunita Chandrasekaran and Guido Juckeland. The submission to this special issue is by invitation only. Steering Committee: Barbara Chapman (StonyBrook University, cOMPunity, USA) Oscar Hernandez (ORNL, USA) Kuan-Ching Li (Providence University, Taiwan) Satoshi Matsuoka (Titech, Japan) Duncan Poole (OpenACC) Thomas Schulthess (ORNL, USA) Jeff Vetter (ORNL, USA) Program Co-Chairs: Guido Juckeland, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany Sunita Chandrasekaran, University of Delaware, Newark, DE, USA Program Committee: Christopher Bergstorm (Pathscale) James Beyer (NVIDIA, USA) Henri Callandra (TOTAL, USA) Robert Dietrich (TU Dresden, Germany) Fernanda Foertter (ORNL, USA) Mark Govette (NOAA, USA) Georg Hager (FAU, Germany) Jeff Hammond (Intel, USA) Christian Iwainsky (TU Darmstadt, Germany) Arpith J. Jacob (IBM, USA) Henri Jin (NASA-Ames, USA) Wayne Joubert (ORNL, USA) Michael Klemm (Intel, Germany) Seyong Lee (ORNL, USA) Antonio J. Pena (BSC, Spain) William Sawyer (CSCS, Switzerland) Thomas Schwinge (MentorGraphics, Germany) Ray Sheppard (Indiana University, USA) Christian Terboven (RWTH Aachen University, Germany) Michael Wolfe (NVIDIA, USA) Keynote Speaker: Jack Wells, the Director of Science for the Oak Ridge Leadership Computing Facility (OLCF), will give the Keynote at the workshop. OLCF is a DOE Office of Science national user facility, and the Titan supercomputer is located at the Oak Ridge National Laboratory (ORNL). Wells is responsible for the scientific outcomes of the OLCF’s user programs. Wells has previously lead both ORNL’s Computational Materials Sciences group in the Computer Science and Mathematics Division and the Nanomaterials Theory Institute in the Center for Nanophase Materials Sciences. Prior to joining ORNL as a Wigner Fellow in 1997, Wells was a postdoctoral fellow within the Institute for Theoretical Atomic and Molecular Physics at the Harvard-Smithsonian Center for Astrophysics. Wells has a Ph.D. in physics from Vanderbilt University, and has authored or co-authored over 80 scientific papers and edited 1 book, spanning nanoscience, materials science and engineering, nuclear and atomic physics computational science, applied mathematics, and text-based data analytics. Contact: Pls email email@example.com for any questions.