YSU hosts national GPU computing workshop

GPU computing is the topic of a national workshop that will be broadcast 11 a.m. to 5 p.m. Nov. 6 in the Computer Science and Information Systems Lab in Room 352 of Meshel Hall on the campus of Youngstown State University.

YSU students, faculty and staff are invited to attend. Registration is free and required. Registration deadline is Nov. 2.

“This workshop covers the fundamental knowledge of GPU computing and demonstrates programming techniques using CUDA and OpenACC,” said Feng “George” Yu, assistant professor of CSIS at YSU.

“Besides live lecturing, the workshop emphasizes the hands-on training on the remote supercomputer. Anyone with basic knowledge of C or Fortran will experience real-world programming on powerful GPUs.”

GPU stands for “Graphics Processing Unit” and has been traditionally employed for computer graphics and video gaming. Using GPU for high-performance computing has become a game-changing technology widely applied in engineering design, simulation, machine learning and image processing, where large-scale computing used to take weeks can now be reduced to hours, Yu said. OpenACC is a high-level programming model designed to significantly reduce programming efforts on GPUs.

The workshop covers the fundamental knowledge of GPU computing and demonstrates programming techniques using CUDA and OpenACC. Besides live lecturing, this workshop emphasizes the hands-on training on the remote supercomputer. Anyone with basic knowledge of C or Fortran will experience real-world programming on powerful GPUs.

YSU CSIS is collaborating with the National Science Foundation’s XSEDE to broadcast the workshop. YSU is among 20 national institutes collaborating in the event. Others include the Pittsburgh Supercomputing Center, Stanford University, Georgia Institute of Technology, University of Notre Dame, Pennsylvania State University, the National Center for Supercomputing Applications and the Lawrence Berkeley National Laboratory

XSEDE, the Extreme Science and Engineering Discovery Environment, is the most advanced, powerful and robust collection of integrated digital resources and services in the world. It is a single virtual system that scientists and researchers can use to interactively share computing resources, data and expertise.