GPU Bootcamps/Hackathons provide exciting opportunities for scientists to accelerate their AI research or HPC codes under the guidance of expert mentors from National Labs, Universities and Industry leaders in a collaborative environment.

The CCNU bootcamp is a two-day hands-on training session. In this hands-on training, participants will learn about multiple GPU programming models and can choose the one that best fits their needs to run their scientific codes on GPUs. This bootcamp will cover, an introduction to GPU programming using C++ Parallel Constructs, parallel programming frameworks like OpenACC, OpenMP as well as programming models like CUDA C and Kokkos.

GPU Compute Resource

Teams attending the event will be given access to a GPU cluster for the duration of the bootcamp.

Event Format

CCNU Bootcamp will be hosted online, with all times in China Standard Time (CST). All communication will be done through Zoom, Slack and email.

Prerequisites

Basic experience with C/C++ programming is needed. No GPU programming knowledge is required. This event has limited capacity, so please make sure that prerequisites are met before applying. Selected participants will be receiving an acceptance email with details on how to participate. Participants will be selected based on the details provided in the application form.

Agenda

Day 1: April 1st

•    Welcome (Moderator): 1:30 PM
•    Connecting to a cluster:  1:45 PM – 2:00 PM
•    Introduction to GPU computing:  02:00 PM- 02:30 PM (Lecture)
•    Accelerating Standard C++ with GPUs using stdpar: 02:30 PM-03:00 PM (Lecture and Lab)
•    Directive Based Programming with OpenMP and OpenACC on GPU: 03:15-04:30 (Lecture and Lab)

Day 2: April 2nd

•    CUDA C Programming 01:30 PM -03:30 PM (Lecture + Lab)
•    Break 03:30 PM - 5:00 PM (Challenge)

Event Focus
HPC

Important Event Dates

  • Application Deadline
  • CCNU Bootcamp Day 1
  • CCNU Bootcamp Day 2