GPU Bootcamp at GTC 2019

Fast track the acceleration of your code

CALLS FOR SUBMISSIONS ARE NOW CLOSED


Sunday, March 17, 2019 from 8:30 a.m. to 6:00 p.m.

NVIDIA Corporate Headquarters
2788 San Tomas Expressway, Santa Clara, CA 95050


GPU Bootcamp at GTC Silicon Valley is an exciting and unique way for scientists and researchers to learn the skills needed to start quickly accelerating codes on GPUs. Held at the beginning of NVIDIA’s flagship GPU Technology Conference (GTC), this one-day event will introduce you to available GPU libraries, programming models, and platforms where you will learn the basics of GPU programming through extensive hands-on collaboration based on a real-life code using the OpenACC programming model. GPU Bootcamp is organized collaboratively by OpenACC.org, Amazon Web Services, NVIDIA, and Linux Academy. Registration to GTC is not required.

Agenda

Registration: 8:30-9:00AM
Part 1: Introduction to GPU Programming with OpenACC (9AM - 12PM)

  • Introduction to GPU programming (15 min)
    • What is a GPU and Why Should You care?
    • What is GPU Programming?
    • Available Libraries, Programming Models, Platforms
  • Introduction to OpenACC (55 min)
    • What is OpenACC and Why Should You Care?
    • Profile-driven Development
    • First Steps with OpenACC
    • Lab 1
  • OpenACC Data Management (55 min)
    • CPU and GPU Memories
    • CUDA Unified (Managed) Memory
    • OpenACC Data Management
    • Lab 2
  • Gangs, Workers, and Vectors Demystified (55 min)
    • GPU Profiles
    • Loop Optimizations
    • Lab 3

Lunch: 12:00-1:00PM
Part 2: Mini-application challenge (1PM - 6PM)

  • Overview of the mini-application (15 min)
  • Review steps to acceleration (5 min)
  • The application challenge using AWS and Linux academy infrastructure (the rest of the day)

Moderators

BHARATKUMAR SHARMA
Senior Solution Architect, NVIDIA

Bharatkumar Sharma is a senior solutions architect at NVIDIA in south Asia. He has about 10 years of research and development experience in software architecture and distributed and parallel computing. He has published papers and journal articles in fields of parallel computing and software architecture. He obtained his master's degree in information technology from the Indian Institute of Information Technology, Bangalore.

ANDREAS HERTEN
Researcher, Jülich Supercomputing Centre

Andreas Herten is a scientific researcher at Jülich Supercomputing Centre investigating GPU acceleration capabilities of various scientific applications. He hosts training courses on GPU programming for OpenACC and CUDA and is involved in operating Jülich's POWER-based supercomputer JURON.


Organizers


Frequently Asked Questions (FAQs)

What is GPU Bootcamp?

GPU bootcamps are free, one- or two-day events designed to teach scientists and researchers how to start quickly accelerating codes on GPUs. Participants will be introduced to available libraries, programming models, and platforms and will learn the basics of GPU programming through extensive hands-on collaboration based on real-life codes using the OpenACC programming model.

Who Can Attend?

GPU Bootcamps are open to all—you do not have to be registered for GTC Silicon Valley 2019 to participate. Whether you’re a seasoned researcher or novice programmer, we want you to be here. Be prepared to learn, brainstorm, and build amazing real-world skills. Throughout the Bootcamp, we’ll be holding workshops where participants will learn the foundations of GPU programming and how to use various tools for development.

How Much Does it Cost?

GPU Bootcamp is free for all admitted participants. We’ll have WiFi, food, workshops, and awesome swag during the entire time you’ll be with us.

What if I Don't Have a Team?

The hacker ethos is all about teamwork. If you don’t have a teammate, we’ll assign you to a team where you can meet your new best friends. 3-5 people per team is the limit.

What Do I Bring?

An ID card, laptop, and your enthusiasm to learn new skills and meet new people.