Improving the parallel scaling of ABINIT

This work presents the results of a three week stay of T.H. at the High Performance Systems Department of the CINECA Institute in Bologna, Italy. The main goals of the short project to understand and parallelize the core functions of the application ABINIT have been achieved. A huge share of the time consuming part of the code has been parallelized efficiently and scales well on modern supercomputers. We demonstrate parallel scaling on the IBM SP5 in CINECA and a small Opteron PC cluster.