SDSC GPU Hackathon
 

News & Updates for March 18, 2020:

Due to the impact of COVID-19 this event will be offered remotely. We are working on the details and will continue to update as decisions are made. Our notification date of March 25 remains intact at this time. Thank you for your continued interest. Stay safe and well!

More News

 

New Remote Schedule

Monday, April 27: Prep Day - Navigate Zoom, access systems, develop plan with mentor and profile code

Monday – Wednesday, May 11-13: Hackathon

 

Hackathon Overview

 

If you have an application that you are thinking about porting to GPUs, or an application already using GPUs that could use a helping hand getting to that next level of performance, you should consider submitting to the San Diego GPU Hackathon.

 

What is a GPU hackathon?

This GPU hackathon is designed as a 5-day intensive coding event. Given the current impact of COVID-19 this event has been adjusted to be held remotely starting with a single preparation day 2 weeks prior to a 3-day coding event. This event pairs application teams with experts in programming and performance. The goal of the event is to port and optimize codes on GPU technologies in a focused, highly collaborative environment. GPU hackathons are part of an international program organized by NVIDIA to help train scientists and researchers to accelerate and optimize their applications on GPUs.

 

What is the format?

Each code team should consist of 4-6 code developers that together are intimately knowledgeable of the code. If a team proposal consists of a suite of applications, no more than two applications should be sent to the hackathon. For each individual code, at least 2 people must attend. Teams will be complimented by mentors that will be assigned based on expert knowledge that matches the needs of the code. Expertise in GPU computing is not required. Selected teams will have access to large-scale GPU clusters for the duration of the event, including preparation and follow-up testing.

 

Who should attend?

Anyone developing or using HPC scientific codes seeking performance improvements, or porting to GPU systems in a cooperative, hands-on environment should apply. Codes should primarily be written in a GPU compatible language, such as C++, Fortran and/or Python. Codes can use/want any standard method of offloading work to the GPUs, including CUDA, RAPIDS, CUDA Fortran, OpenACC, OpenCL or OpenMP. The SDSC GPU hackathon is interested in teams who are working with “long-tail” computational science applications that run well on the Comet (or future Expanse) architectures. However, all coding teams looking to use GPU technologies are encouraged to apply. A broad range of code types and GPU experience levels are sought for this event.

 

Participant Costs:

There is no registration fee to attend the event. Breakfast, lunch, coffee and snacks will be provided during the hackathon. Participants are responsible for all other expenses, including their transportation to and from the event, lodgings and other meals. Participants will also be expected to arrive with a laptop that is capable of wireless internet to work on for the duration of the event.

 

Acceptance Timeline and Notification:

  • Applications Deadline was: Wednesday, March 11, 2020
  • Accepted applicants will be notified by: March 25, 2020
  • Accepted teams should:
    • Register all team members for the event.
    • Review the attendee guide.
    • Mentor introductions and computational resource access instructions will be forthcoming.

For a full list of GPU Hackathons, see https://gpuhackathons.org for more information.