The increase in the number of processor cores has opened up new opportunities to take advantage of the parallelism available in modern data-centric applications and workloads. On the other hand, parallelising programs is still an error-prone and challenging task for the typical programmer.
Novel programming/execution models, which ease the job of the programmer while expose the hardware resources to the compiler/runtime/OS stack, are key to unleash the parallelism potential of future applications. In recent years task-based programming models (e.g. OpenMP and OpenSs) have shown to be a scalable and flexible approach to extract task parallelism from applications.
MPP 2016 brings together researchers and practitioners interested in developing novel computational models for parallel programming and architectures. Given the growing interest in task parallelism programming and execution models, MPP 2016 dedicated this edition to such programming model. Nevertheless, authors are also encouraged to submit original works that include but are not limited to:
- Novel Execution models and languages for parallelism exploitation;
- Languages, compilers and parallelism extraction tools;
- Heterogeneous programming models;
- Scheduling and Placement Algorithms for Parallel Programming models;
- Novel Parallel Programming Techniques;
- Novel Parallel Architectures;
- Error Detection/Recovery for Parallel Programming Models;
- Theoretical Analysis of Parallelism.
MPP 2016 will be held in conjunction with the 28th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2016), at Marina del Rey Marriott, Los Angeles, USA.
The proceedings of MPP will be submitted to IEEE Xplore and Computer Society Digital Library.