Topic 11: Multicore and Manycore Programming

Description

Modern multi-core and many-core systems offer impressive performance for various applications. However, achieving this performance is a challenging task. While multi-core processors alleviate several problems that are related to single-core processors -- known as memory wall, power wall, or instruction-level parallelism wall -- they raise the issue of the programmability wall. The multi-core programmability wall calls for new parallel programming methods and tools. Therefore, this topic focuses on novel solutions for efficient programming of multi-core and many-core processors in the context of general-purpose and embedded systems.

Focus

  • programming techniques, models and languages
  • programming embedded systems
  • advances in compilers
  • runtime systems
  • advances in algorithms and data-structures
  • application case studies
  • performance and scalability analysis of real-world systems
  • programming high-performance computing systems
  • hardware support for programmability

Topic Committee

Global chair

Sabri Pllana, University of Vienna, Austria

Local chair

Jean-François Méhaut, University of Grenoble, France

Vice-chairs

Eduard Ayguade, Technical University of Catalunya & Barcelona Supercomputing Center, Spain
Herbert Cornelius, Intel, Germany
Jacob Barhen, Oak Ridge National Laboratory, USA