Finalists are announced!  Read more on the OpenPOWER Foundation blog and stay tuned for Grand Prize and rankings announcement during the OpenPOWER Foundation Summit in Barcelona, Oct 26-28th

We just launched the Linux on Power Developer Portal – your entry point to a community and resources for developing, migrating and testing your applications on IBM Power hardware in the cloud.  Read more and check it out here.

-- The OpenPOWER Developer Challenge Team

Follow OpenPOWER on Twitter, FacebookGoogle+ , LinkedIn and

Have a need for speed? Performance barriers getting in the way?

We know traditional system architectures aren't keeping up with the performance demands of your data-intensive applications. A faster platform coupling a powerful processor with hardware acceleration technology is out there – but we know that change isn't always easy.

So we're handing you the keys to a totally different car - built for speed and performance on a brand new road. Take it for a test drive and see how fast you can go!

There are three courses for you:

The Open Road Test

  • Port to OpenPOWER
  • Performance optimize & race against your first compile
  • Go faster with accelerators

The Accelerated Spark Rally

Multiple possibilities to choose from:

  • Port an existing GPU accelerated application to Apache Spark
  • Create a new Spark application that uses GPU acceleration, or add GPU acceleration to an existing Spark application.
  • Use GPUs to accelerate Spark itself

The Cognitive Cup

Multiple Deep Learning challenges to choose from:

  • ArtNet: Recognize artwork with Deep Learning
  • TuneNet: Guide Programmer Optimization Using Deep Learning
  • YourNet: Define and solve your own Deep Learning problem

What will you build? How fast will you go?

Get your hands on OpenPOWER! Check out the SuperVessel development environment you'll be accessing. 

Why come to the OpenPOWER Ecosystem?

Familiar Tools

Access a wide range of familiar development tools and a differentiated set of accelerators that will help you unleash innovation that you never thought possible.

Open to the Core

Participate in an ecosystem that truly exemplifies “open”—across not only operating systems, and software, but also hardware.

High Visibility

Showcase your talents across the breadth of the OpenPOWER ecosystem— to the companies, communities, and users who practice the best of machine learning, HPC, and Big Data.


Develop critical skills in the increasingly important area of accelerated computing that can set you apart in the future.

Compete to win a trip to SC 2016 in Salt Lake City, UT in November.


This challenge is open to individuals who are at least 18 years of age as of the time of entry, teams of eligible individuals, and organizations with no more than 50 employees from the following countries: Australia, Canada (excluding Quebec), China (including Hong Kong), France, Germany, India, Israel, Japan, Mexico, Netherlands, South Korea, United Kingdom, and the United States.

See the Official Rules for complete eligibility requirements.

Hackathon Sponsors


$24,000 in prizes

Grand Prizes, for Each Track (4)

One representative from winning individual/team will receive an all-expenses paid trip to Supercomputing 2016.

Members of the winning team (up to 5 people) win an Apple Watch Sport.

Second Prizes, for Each Track

Apple iPad Air 16GB for members of the winning team (max of 5 per winning team).

Third Prizes, for Each Track

Apple Watch Sport for members of the winning team (max of 5 per winning team)

Devpost Achievements

Submitting to this hackathon could earn you:


John Zannos

John Zannos
Chairman, OpenPOWER Foundation Vice President of Cloud Channels and Alliances, Canonical

Randy Swanberg

Randy Swanberg
Distinguished Engineer, Power Systems Software and Solutions, IBM

John Ashley

John Ashley
Senior Enterprise Software Developer Relationship Manager, NVIDIA

Bruce Wile

Bruce Wile
CAPI Chief Engineer and Distinguished Engineer, Power Systems, IBM

Nima Negahban

Nima Negahban

Ashish Sirasao

Ashish Sirasao
Distinguished Engineer, Xilinx

More judges to be announced soon

More judges to be announced soon

Judging Criteria

  • Community Impact 1- The Open Road Test
    Does your contribution add ppc64le support to an existing application or package? How widely used is your solution within the free / open-source community?
  • Community Impact 2- The Open Road Test
    If your solution is open-source, was it successfully contributed back to the original project? If your solution is not open source, what's your path for distribution on OpenPOWER? How will you provide and support a binary?
  • Use of OpenPOWER Technologies - The Open Road Test
    How well does your solution leverage the technologies available in the OpenPOWER ecosystem, like 8-way multithreading on POWER8, or accelerator offload via accelerators?
  • Technical Achievement - The Open Road Test
    Quality of implementation and the extent to which you demonstrate in a verifiable manner performance gain after tuning from a first compile (e.g. verifiable performance gain of 50% from tuning)
  • Demonstrated Ability to Scale - Spark Rally
    Does the solution incorporate Spark as the framework to scale beyond a single node? How well does the solution incorporate Spark to scale?
  • Relative speed-up with GPUs - Spark Rally
    The extent to which the submitter demonstrates in a verifiable manner, performance gain after GPU-enabling your application (2-node Spark non-GPU enabled versus 2-node Spark GPU enabled).
  • Technical Innovation - Spark Rally
    Does the solution: Incorporate any innovative ideas for the Spark Community?
 Incorporate multiple possibilities across “A”, “B”, and/or “C” of the Spark Rally? Address Deep Learning challenges as defined in the “Cognitive Cup”?
  • Demonstrated Ability to Maximize Accuracy - Cognitive Cup
    End-to-end accuracy achieved for the problem.
  • Spark Usage - Cognitive Cup
    Does the solution incorporate Spark as the framework to scale beyond a single node? How well does the solution incorporate Spark to scale?
  • Technical Innovation - Cognitive Cup
    How well is Deep Learning exploited as part of the solution? Does the solution incorporate any new approaches to the Deep Learning problem (e.g. did the submission involve creating new code, algorithms, or leverage emerging frameworks)?

Tell your friends

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.