Skip to Main content Skip to Navigation

Équilibrage dynamique de charge sur supercalculateur exaflopique appliqué à la dynamique moléculaire

Abstract : In the context of classical molecular dynamics applied to condensed matter physics, CEA researchers are studying complex phenomena at the atomic scale. To do this, it is essential to continuously optimize the molecular dynamics codes of recent massively parallel supercomputers to enable physicists to exploit their capacity to numerically reproduce more and more complex physical phenomena. Nevertheless, simulation codes must be adapted to balance the load between the cores of supercomputers.To do this, in this thesis we propose to incorporate the Adaptive Mesh Refinement method into the ExaSTAMP molecular dynamics code. The main objective is to optimize the computation loop performing the calculation of particle interactions using multi-threaded and vectorizable data structures. The structure also reduces the memory footprint of the simulation. The design of the AMR is guided by the need for load balancing and adaptability raised by sets of particles moving dynamically over time.The results of this thesis show that using an AMR structure in ExaSTAMP improves its performance. In particular, the AMR makes it possible to execute 1.31 times faster than before the simulation of a violent shock causing a tin microjet of 1 billion 249 million atoms on 256 KNLs. In addition, simulations that were not conceivable so far can be carried out thanks to AMR, such as the impact of a tin nanodroplet on a solid surface with more than 500 million atoms.
Document type :
Complete list of metadatas
Contributor : Abes Star :  Contact
Submitted on : Monday, December 16, 2019 - 10:48:26 AM
Last modification on : Saturday, July 25, 2020 - 3:08:28 AM
Long-term archiving on: : Tuesday, March 17, 2020 - 2:20:56 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02413331, version 1



Raphaël Prat. Équilibrage dynamique de charge sur supercalculateur exaflopique appliqué à la dynamique moléculaire. Analyse numérique [cs.NA]. Université de Bordeaux, 2019. Français. ⟨NNT : 2019BORD0174⟩. ⟨tel-02413331⟩



Record views


Files downloads