Device Accelerated solvers with PETSc: current status, future perspectives, and applications

Euler Institute

Date: 30.06.2022 / 16:30 - 17:30

USI Campus EST, room D1.14, Sector D // Online on Zoom

Click here to join
(Meeting ID: 833 9979 6680 - Passcode: 159830)

Speaker: Stefano Zampini, King Abdullah University of Science and Technology, Saudi Arabia

Abstract: In this talk, I will review recent developments towards exploiting Graphical Processing Units (GPUs) from the Portable and Extensible Toolkit for Scientific computing (PETSc). Current status and future perspectives will be discussed. Examples include multi GPU distributed sparse matrix-matrix multiplications, device accelerated linear solvers with the CFD open-source software OpenFOAM, and machine-learning training.

Biography: 
Stefano Zampini is a research scientist in the Extreme Computing Research Center at King Abdullah University of Science and Technology, and a developer of the Portable and Extensible Toolkit for Scientific computing (PETSc). His main interests are numerical methods and high-performance computing, domain decomposition solvers for Partial Differential Equations, and machine learning.

Host: prof. Rolf Krause