The National Center for Supercomputing Applications (NCSA) at Illinois has announced that team applications for the NCSA Blue Waters GPU Hackathon are now open. The event will take place September 10-14, 2018 at NCSA with a deadline to apply by June 18, 2018.
This event offers a chance to develop GPU skills for graduate students and postdoctoral researchers who can work on optimising their own applications on GPUs. Prior experience with GPUs is not required, as those selected will be paired with experienced mentors who will teach them how to leverage accelerated computing in their own applications or further optimise their codes. The teams will also get the opportunity to run there codes on NCSA GPU resources including potentially using the Blue Waters supercomputer.
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.
The organisers are looking for teams of 3-8 developers, ideally graduate students and/or postdocs, with a scalable application to port to (or optimise 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.
Those interested may apply by June 18, 2018. Selected teams will be notified within two weeks after the deadline closes.
Blue Waters is supported by the National Science Foundation through awards ACI-0725070 and ACI-1238993.
