High-performance computing chemistry: NW Chem

The impact of high-performance computing in computational chemistry is considered in the light of increasing demands for both the number and complexity of chemical systems amenable to theoretical treatment. Using self-consistent field Density Functional Theory (DFT) as a prototypical application, we describe the development, implementation and performance of the NWChem computational chemistry package that is targeting both present and future generations of massively parallel processors (MPP). The emphasis throughout this development is on scalability and the distribution, as opposed to the replication, of key data structures. To facilitate such capabilities, we describe a shared non-uniform memory access model which simplifies parallel programming while at the same time providing for portability across both distributed- and shared-memory machines. The impact of these developments is illustrated through a performance analysis of the DFT module of NWChem on a variety of MPP systems.