Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Call for Applications: NCSA GPU Hackathon in September

NCSA is now accepting team applications for the Blue Waters GPU Hackathon. This event will take place September 10-14, 2018 in Illinois.

General-purpose Graphics Processing Units (GPGPUs) potentially offer exceptionally high memory bandwidth and performance for a wide range of applications. A challenge in utilizing such accelerators has been learning how to program them. These hackathons are intended to help overcome this challenge for new GPU programmers and also to help existing GPU programmers to further optimize their applications – a great opportunity for graduate students and postdocs. Any and all GPU programming paradigms are welcome.

There will be pre-workshop training opportunities as well as intensive mentoring during this five-day hands-on workshop to ensure that the teams leave with applications running on GPUs, or at least with a clear roadmap of how to get there. Each team will be assigned mentors who have extensive experience in programming GPUs, many of whom are from NVIDIA and Dr. Wen-mei Hwu’s lab and are knowledgeable in developing GPU-capable compilers and helping define standards such as OpenACC. Programming experience with OpenACC or CUDA is not a requirement.

We are looking for teams of 3-8 developers, ideally graduate students and/or postdocs, with a scalable application to port to (or optimize on) the GPU accelerators available at the University of Illinois, including the Blue Waters system at NCSA and systems supported by the IBM-Illinois Center for Cognitive Computing Systems Research. Collectively, the team should know the application intimately. If the application is to address a suite of applications, no more than two applications per team is allowed and a minimum of two people per application must attend.

Applications are due by June 18, 2018.

Check out our insideHPC Events Calendar

 

Leave a Comment

*

Resource Links: