The paradigm shift in micro-processors production towards multicores demands the use of parallel programming to achieve performance gains. However, it is an arduous and non-trivial task to write parallel applications, which imposes new challenges to the scientific community: the creation of models and alternatives to ease parallelism exploitation by the average programmer. The Goal of MPP is to bring together researchers that are interested in presenting their contributions to the evolution of existing models or in proposing novel ones. MPP will be held in conjunction with the XIII Simpósio em Sistemas Computacionais (WSCAD-SSC), at the Laboratório Nacional de Computação Científica premises ("Scientific Computation National Laboratory"), at Petrópolis.
MPP invites authors to submit unpublished full papers on the subject. Papers written in Portuguese and English will be accepted. Title and abstract for all papers (including the ones written in Portuguese) must be in English. Papers will follow WSCAD format, with a maximum of 8 pages. Topics of interest include (but are not limited to):
MPP invites authors to submit unpublished full papers on the subject. Papers written in Portuguese and English will be accepted. Title and abstract for all papers (including the ones written in Portuguese) must be in English. Papers will follow WSCAD format, with a maximum of 8 pages. Topics of interest include (but are not limited to):
- Dataflow based execution models
- Languages, compilers and parallelism extraction tools
- Heterogeneous programming models
- GPU Programming (CUDA / OpenCL)
- Application and parallelism techniques
- Synchronization mechanisms, such as Transactional Memories
- Load-balancing for multithreading
- Task placement mechanisms
