Faster Simulations with LAMMPS - Advancing Performance on Intel(r) Xeon(r) and Xeon Phi(tm) Processors

This talk will present some of the challenges in continuing to advance simulation rates in molecular dynamics. I will present hardware and software advances that allow for substantial performance improvements with reduced programmer effort. I will show performance results for standard LAMMPS benchmarks and production science simulations on Intel(r) architecture. Finally, I will discuss ongoing efforts to continue to advance simulation capabilities to drive advanced computational science.