HPF parallelization of a molecular dynamics code: Strategies and performances

The High Performance Fortran (HPF) environment has been used to efficiently parallelize a Molecular Dynamics (MD) code. The MD code is a Tight-Binding code, properly specialized for semiconductor materials and characterized by inhomogeneous data distribution. Furthermore, the electronic properties are taken into account during the atomic dynamics: for this reason a large sparse matrix is built and diagonalized to compute the whole body of its eigenvalues and eigenvectors at each time step. For the diagonalization task, a parallel mathematical routine implemented. The strategy of parallelization, the integration of the mathematical routine in the HPF code are described and discussed. hll the benchmark are performed on IBM SP architecture.