Presenter: Galen Arnold, NCSA, University of Illinois

Tuesday, May 4, 2021

Slides: https://uofi.app.box.com/s/8eqlmu26u6nycyqh50z5mkffxe7gr519

Video: https://uofi.app.box.com/s/37bco35ogqixsu196pzvgzhoeh8qgi9p

Abstract

This webinar introduces computing with accelerators and how they can augment traditional multi-core processing from laptop and deskside systems to supercomputers. The topics covered will include:

• Hardware overview, what makes an accelerator
• Graphics Processing Units
• Field Programmable Gate Arrays (FPGA)
• Academic GPU computing started at UIUC, NCSA stood up the first GPU clusters:
• Software overview, how accelerators are utilized
• Simple code walkthroughs to demonstrate programming concepts (OpenACC, CUDA)
• Example applications (fields of science, production libraries, codes)

Prerequisites: No prior HPC experience is needed.

Biography

As a system engineer with NCSA, Galen enjoys helping people get the most out of HPC systems such as: Blue Waters and XSEDE systems with accelerators. He’s part of the Blue Waters applications support team as well as the XSEDE software development and integration testing group. He has a good working knowledge of most things unix/linux/hpc/networking and has a knack for debugging code. He believes k&r-c is the one true language but reluctantly admits the superior numerical performance of fortran codes.