This tutorial is open to those outside of the ATLAS collaboration.
This introductory GPU training session will focus on understanding the basics of GPU programming. It will cover GPU architectures, and how they differ from CPUs, how to write CUDA programs, and how to program and run on GPUs using python. If time permits, it will also examine using GPUs directly from C++ using std::par.
It will feature interactive exercises, and will be run by Scot Halverson and Robert Searles from NVIDIA and cover the basics of CUDA in C++.
Participants will be given access to Perlmutter training accounts to run their code. You can also use another machine with an NVIDIA GPU if you prefer. Instructions will be provided on how to setup a jupyter notebook and runtime environment (see the links below).
The tutorial is remote only, and broadcast via zoom. A recording will be made of the sessions.
Each session will run from 15:00 to 19:00 CET
contact: CGLeggett@lbl.gov
