Chemora: A PDE-solving framework for modern high-performance computing architectures
Modern HPC architectures consist of heterogeneous multicore, many-node systems with deep memory hierarchies. Modern applications employ ever more advanced discretization methods to study multiphysics problems. Developing such applications that explore cutting-edge physics on cutting-edge HPC systems has become a complex task that requires significant HPC knowledge and experience. Unfortunately, this combined knowledge is currently out of reach for all but a few groups of application developers. Chemora is a framework for solving systems of partial differential equations (PDEs) that targets modern HPC architectures. Chemora is based on Cactus, which sees prominent usage in the computational relativistic astrophysics community. In Chemora, PDEs are expressed either in high-level LaTeX-like languages or in Mathematica. The authors use Chemora in the Einstein Toolkit to implement the Einstein equations on CPUs and on accelerators, and study astrophysical systems such as black hole binaries, neutron stars, and core-collapse supernovae.
Publication Source (Journal or Book title)
Computing in Science and Engineering
Schnetter, E., Blazewicz, M., Brandt, S., Koppelman, D., & Löffler, F. (2015). Chemora: A PDE-solving framework for modern high-performance computing architectures. Computing in Science and Engineering, 17 (2), 53-64. https://doi.org/10.1109/MCSE.2015.2