5th Workshop on
Highly Parallel Processing on a Chip (HPPC 2011)

August 30, 2011, Bordeaux, France

in conjunction with

the 17th International European Conference on Parallel and Distributed Computing (Euro-Par)
August 29 - September 2, 2011, Bordeaux, France.


In response to the stagnant growth in single-processor performance single-chip, multi-core parallelism is the most promising solution to the demands for high performance and power efficiency for general purpose, mainstream computing. While both general-purpose architectures with a moderate number of cores and more specialized architectures with a larger number of cores are already on the market, Moore's law predicts future architectures with a significant amount of on-chip parallelism. How the processing power of such architectures can be leveraged for general-purpose computing is a critical issue, as witnessed by the lack of convergence towards a standard model architecture.  The design of parallel multi-core architectures that can support manageable parallel programming abstractions to allow the mainstream programmer to take advantage of the processing power furthered by the technological developments is a vital and challenging issue.

The 5th HPPC workshop, co-located with the EuroPar conference, is *the* workshop dedicated to the interface between highly parallel multi-core architectures and programming paradigms, models, and languages that can support parallel algorithms and applications development in an efficient and manageable way.  HPPC is intended as a forum for bold, new ideas on architectural organization (general- and special-purpose processors, heterogeneous designs, memory organization, on-chip communication network), parallel programming models, languages, and libraries, multi-core parallel algorithms, and application studies on both existing and envisaged, speculative architectures. Complementary to other multi-core and GPGPU meetings, HPPC stresses programmability and architectural support for more massive levels of parallelism.

Topics of interest include, but are not limited to

° processor core architectures (homogeneous and heterogeneous)
° special purpose processors for general-purpose applications (accelerators, GPUs)
° on-chip memory and cache (or cache-less) organization, and interconnects
° off-chip memory, I/O, and multi-core interconnects
° overall system design (resource allocation and balancing)
° programming models (e.g. PRAM, BSP, data parallel, vector, transactional)
° parallel programming languages and software libraries
° supporting algorithms and implementation techniques (e.g. multi-threading, work-stealing)
° parallel algorithms and applications
° migration of existing codebase
° teaching of parallel computing

for/on highly parallel multi-core systems.

The workshop will be conducted in an informal atmosphere with room for interaction and discussion between presenters and audience. Depending on the number of accepted submissions, this year may, in addition to forward-looking invited talks, include a panel discussion.
June 10, 2011

July 25, 2011

August 30, 2011

Final LNCS paper:
September, 2011

via Euro-Par

Last updated August 16, 2011, MF