HIGH-PERFORMANCE COMPUTING IN 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. Usi ng self-consistent field Density Functional Theory (DFT) as a prototyp ical application, we describe the development, implementation and perf ormance of the NWChem computational chemistry package that is targetin g 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 structur es. 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 shar ed-memory machines. The impact of these developments is illustrated th rough a performance analysis of the DFT module of NWChem on a variety of MPP systems.