Workshop:PAW-ATM 2020: The 3rd Annual Parallel Applications Workshop, Alternatives To MPI+X
Authors: Karla V. Morris (Sandia National Laboratories), Bradford L. Chamberlain (Hewlett Packard Enterprise), and Rosa M. Badia (Barcelona Supercomputing Center (BSC))
Abstract: Architectural hierarchy and heterogeneity make programming supercomputers challenging. In practice, HPC applications tend to be written using a mix of programming models, such as C++, MPI, CUDA and/or OpenMP; each of which is becoming more complex over time. This negatively impacts the costs of developing, maintaining and porting HPC applications.
Meanwhile, alternative HPC programming models strive to improve things by raising the level of abstraction, incorporating modern features and/or leveraging the respective strengths of programmers, compilers and runtimes. These alternatives take the form of new languages (e.g., Chapel, Regent, XcalableMP), frameworks for large-scale data science (e.g., Arkouda, Dask, Spark), or extensions to existing languages (e.g., Charm++, COMPSs, Fortran, Legion, UPC++).
PAW-ATM is a forum for discussing HPC applications written in alternatives to MPI+X. Its goal is to bring together applications experts and proponents of high-level languages to present concrete example use cases of such alternatives, describing their benefits and challenges.
Website: https://sourceryinstitute.github.io/PAW/