GPU Computing and Programming on Expanse

Thursday, October 26, 2023

11:00 AM - 12:00 PM PDT

This event will be held remotely.

This webinar provides a brief introduction to massively parallel computing with graphics processing units (GPUs) on the SDSC Expanse supercomputer. The use of GPUs is popular across all scientific domains both for traditional simulations and AI applications since GPUs can significantly accelerate time to solution for many data parallel computational tasks. In this webinar, participants will learn how to access Expanse GPU nodes, how to launch GPU jobs on Expanse, and get introduced to GPU programming. The webinar will cover the essential background of GPU chip architectures and the basics of programming GPUs with the NVIDIA CUDA Toolkit and HPC SDK via the use of libraries, OpenACC compiler directives, and the CUDA programming language. We will also briefly discuss performance analysis with NVIDIA Nsight profilers. The participants will thus acquire the foundation to use and develop GPU aware applications.


Andreas Goetz

Director of Computational Chemistry Laboratory, SDSC

Andreas Goetz leads the computational chemistry efforts at SDSC, working at the intersection of chemistry, biophysics, and scientific computing. His research draws on quantum mechanics, statistical mechanics, molecular dynamics, and machine learning approaches to enable simulations of complex molecular systems from atmospheric chemistry to computational drug design on massively parallel computer architectures. He is a contributing author to the ADF and QUICK quantum chemistry software and the AMBER software for biomolecular simulations, which are widely used in academic and industrial research. His research has been supported by NSF, DOE, NIH, Intel, AMD and Nvidia. Andreas also enjoys training the next generation of scientists in software engineering and numerical simulation methods via lectures, workshops and supervision of interns. He is author of over 70 scientific publications and editor of the book 'Electronic structure calculations on GPUs'. Prior to joining SDSC in 2009 Andreas performed postdoctoral research at the VU University in Amsterdam and obtained his undergraduate and Ph.D. degrees in chemistry from the University of Erlangen in Germany.