GPU Bootcamp is an exciting and unique way for scientists and researchers to learn the skills needed to start quickly accelerating codes on GPUs. Held as a virtual event across two days in October, 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 OpenACC, stdpar, Fortran Do-Concurrent and CUDA, and provides hands-on opportunities to learn how to analyse GPU-enabled applications using NVIDIA® Nsight™ Systems. The bootcamp will also cover the PINN approach using NVIDIA SimNet.

Presented by the National Atmospheric Research Laboratory (NARL), this event is specifically designed for current NARL cluster users.

Event Format

This two-day online Bootcamp will be hosted in the India Standard Time (IST) zone. All communication will be done through Zoom, Slack, and email. 

Prerequisites

  • Basic experience with C/C++ or Fortran. No GPU programming knowledge is required.
  • Presented by the National Atmospheric Research Laboratory (NARL), this event is specifically designed for current NARL cluster users.

Compute Resources

Attendees will be given access to NARL cluster for the duration of this event.

Agenda 

Day 1 October 20, 2021: 2PM - 5PM IST

  • Introduction to GPU Computing ( CPU vs GPU ) (30 mins )
  • Programming in Standard Language ( C++ STL, Fortran Do-Concurrent ) (30 Mins)
  • OpenACC : Directive based Programming  (30 Mins)
  • CUDA Language Extension ( C++/Fortran ) (60 Mins)
  • Q&A ( 30 mins )

Day 2 October 21, 2021: 2PM - 5PM IST

  • Latest GPU Architecture Deep Dive ( V100, A100 )
  • HPC SDK
  • NVIDIA CUDA Python
  • AI for Science
    • Data Driven vs PINN
    • SimNet
    • DeepMD
Event Focus
HPC

Important Event Dates

  • NARL N-Ways GPU Bootcamp Application Deadline
  • NARL N-Ways GPU Bootcamp Day 1
  • NARL N-Ways GPU Bootcamp Day 2