MASS-APP: A High-Performance Collisionless Plasma Simulation Tool
ORAL
Abstract
Modern supercomputers leverage a mix of CPUs and GPUs to maximize available computing power, and this heterogeneity must be specifically accounted for when developing new software. With current exascale computers, such as LLNL's El Capitan and OLCF's Frontier, deriving the majority of their FLOPs from GPUs, and even more tightly-integrated systems such as NVIDIA's Grace Hopper superchip starting to enter the market, this is becoming increasingly important. In this talk, we will present our use of LANL's FleCSI library, an adaptable infrastructure created to facilitate asynchronous multiphysics applications, to develop a novel plasma dynamics simulation tool targeted for deployment on exascale machines. In it, we navigate the heterogeneous computing environment using Kokkos. The impact of performing an asynchronous computation in place of a sequential MPI-based simulation will be discussed, along with realized speedups from offloading work to GPUs. Results from large scale simulations relevant to space weather will demonstrate the capabilities of the new simulation tool.
–
Presenters
-
Robert M Chiodi
Los Alamos National Laboratory
Authors
-
Robert M Chiodi
Los Alamos National Laboratory
-
Peter T Brady
Los Alamos National Laboratory
-
Cale Harnish
Los Alamos National Laboratory
-
Zach Jibben
Los Alamos National Laboratory
-
Oleksandr Koshkarov
Los Alamos National Laboratory
-
Ryan Wollaeger
Los Alamos National Laboratory
-
Svetlana Tokareva
Los Alamos National Laboratory
-
Chris L Fryer
Los Alamos National Laboratory
-
Gian Luca Delzanno
Los Alamos National Laboratory
-
Daniel Livescu
LANL