Parallelizing CPAIMD Using Charm++
Authors:
Ramkumar Venkat Vadali
Parallel Programming Laboratory, Department of Computer Science, University
of Illinois at Urbana-Champaign
Master's Thesis, Dept. of Computer Science, University of Illinois 2003
Many important problems in material science, chemistry, solid-state physics, and biophysics require a modeling approach based on fundamental quantum mechanical principles. A particular approach that has proved to be relatively efficient and useful is Car-Parrinello ab initio molecular dynamics (CPAIMD). Parallelization of this approach beyond a few hundred processors is challenging, due to the complex dependencies among various subcomputations, which lead to complex communication optimization and load balancing problems. This thesis presents a scalable parallelization of CPAIMD using Charm++. The computation is modeled using a large number of virtual processors, which are mapped flexibly to available processors with assistance from the Charm++ runtime system. Charm++ allows the use of ``parallel'' libraries to facilitate common operations such as parallel 3-D FFTs. We present results for a benchmark (based on PINY MD) with 32 water molecules (128 states) scaling to more than 1000 processors, setting a precedent for this problem.