Supercomputing for Molecular Dynamics Simulations, 2015 Handling Multi-Trillion Particles in Nanofluidics SpringerBriefs in Computer Science Series
Langue : Anglais
Auteurs : Heinecke Alexander, Eckhardt Wolfgang, Horsch Martin, Bungartz Hans-Joachim
This work presents modern implementations of relevant molecular dynamics algorithms using ls1 mardyn, a simulation program for engineering applications. The text focuses strictly on HPC-related aspects, covering implementation on HPC architectures, taking Intel Xeon and Intel Xeon Phi clusters as representatives of current platforms. The work describes distributed and shared-memory parallelization on these platforms, including load balancing, with a particular focus on the efficient implementation of the compute kernels. The text also discusses the software-architecture of the resulting code.
Introduction
Molecular Dynamics Simulation
Parallelization of MD Algorithms and Load Balancing
Efficient Implementation of the Force Calculation in MD Simulations
Experiments
Conclusion
Describes the state-of-the-art algorithms and implementations essential for molecular simulation in chemical engineering
Includes high-performance implementations of MD algorithms on current HPC systems covering shared-memory, distributed-memory parallelization and vectorization
Presents a special focus on hybrid systems using Intel Xeon processors and Intel Xeon Phi coprocessors
Includes supplementary material: sn.pub/extras
Date de parution : 04-2015
Ouvrage de 76 p.
15.5x23.5 cm
Thèmes de Supercomputing for Molecular Dynamics Simulations :
© 2024 LAVOISIER S.A.S.
