Description

Modern homogeneous and heterogeneous multi-core and many-core architectures are now part of the high-end and mainstream computing scene and can offer impressive performance for various applications.
This architecture trend has been driven by the need to reduce power consumption, increase processor utilization, and deal with the memory-processor speed gap. However, the complexity of these new architectures created several programming challenges and achieving performance on these systems is a difficult task. This topic seeks to explore productive programming of Multi-Core (MC), Many Integrated Cores (MIC), and hybrid systems with accelerators (GPUs). It focus on novel research and solutions in the form of programming models, languages, compilers, analysis tools, runtime, and libraries, to increase the programmability of multicore, manycore, and hybrid systems, in the context of general-purpose parallel computing, including HPC.

Focus

Topics of interest, of both theoretical and practical significance, include but are not limited to

• Programming Framework for MC, MIC, and GPUs
• Programming techniques, models and languages
• Compiler optimizations and techniques for MC, MIC, and GPUs
• Libraries and runtime systems
• Tools for discovering and understanding parallelism
• Advances in algorithms and data-structures for MC, MIC, and GPUs
• Innovative application and case studies for MC, MIC, and GPUs
• Performance and scalability analysis on MC, MIC, and GPUs
• Hardware support for programming models and runtime systems

Topic Committee

Global chair
Luiz DeRose, Cray Inc., USA

Local chair
Jan Treibig, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

Further members
David Abramson, Monash University, Australia
Alastair Donaldson, Imperial College London, UK
William Jalby, University of Versailles Saint-Quentin-en-Yvelines, France
Tomàs Margalef, Universitat Autònoma de Barcelona, Spain
Alba Cristina M. A. de Melo, University of Brasilia, Brazil