In the world of performance optimization, speedup is a critical metric that helps quantify the improvement in system performance. Speedup refers to the ratio of execution time for a task when using an ...

The graph theory is an old subject and nowadays it has become a method widely used in various fields of mathematics, computer science, engineering, chemistry, among others. Its application ranges from ...

Abstract: An efficient data-flow-graph (DFG) optimized parallelization scheme is proposed for the discontinuous Galerkin time-domain and finite-difference time-domain (DGTD-FDTD) hybrid method. In the ...

Abstract: DeepMD-kit enables deep learning-based molecular dynamics (MD) simulations that require efficient parallelization to leverage modern HPC architectures. In this work, we optimize DeepMD-kit ...