GTC Silicon Valley-2019: GPU-Accelerated Large Scale Phase Field and Molecular Dynamics Simulations
GTC Silicon Valley-2019 ID:S9851:GPU-Accelerated Large Scale Phase Field and Molecular Dynamics Simulations
Shun Xu(Computer Network Information Center, Chinese Academy of Sciences),Jian Zhang(Computer Network Information Center)
Learn about algorithm design, implementation, and optimization techniques to accelerate large-scale, phase-field molecular dynamics simulations on a GPU platform. Numerical simulations of phase-field equations are conventionally performed by stencil computation with a very small time-step size and low efficiency. We'll describe how we designed an efficient, GPU friendly algorithm that combines a large step-size exponential time integrator with domain decomposition and localization of matrix exponentials. By using this algorithm with optimization techniques on a single GPU and multiple GPU platforms, we achieved a 50X increase in simulation speed over the conventional stencil computing approach. We'll also discuss GPU-Accelerated molecular dynamics simulation, with a focus on parallel strategies of atomic partition and spatial partition. We demonstrated efficiency on dissipative particle dynamics and free-energy calculations on GPU devices for hundreds of millions of particles.