Back to all updates

7 months ago

1 Week Left! Get to know the submission requirements.

Howdy Challengers!

We've reached the final week of the submission period - all Submissions will be due by Thursday, September 1st at 11:45 PM US EST!

Now's a great time to familiarize yourself with the submission requirements (see below; they're also available on the rules page).  The requirements are different for each track (see A, B, or C below as well as the General Requirements for all tracks under D), so take a look and let us know if you have any questions on Slack.

The Judges are waiting!  Good luck!

-- The OpenPOWER Developer Challenge Team

Questions?

We're here to help. If you have any questions about the hackathon, post on the discussion forum or email support@devpost.com and we'll respond as soon as we can.

------ OpenPOWER Develpoper Challenge SUBMISSION REQUIREMENTS: ------

A. Submission Requirements for The Open Road Test Track

(i) General Requirement:

  • Port to or create a new application for OpenPOWER
  • Performance tune and optimize - race against your first compile

(ii) Technical Requirements:

  • The application or package must be ported and demonstrated to function on the ppc64le platform.
  • If the application or package was previously supported on ppc64le, you must show a substantive performance gain from the original compile (ex: verifiable performance gain of 50% or more from tuning/optimization).
  • Each Submission must be functional on OpenPOWER compliant hardware.

(iii) Required Submission Materials Specific to The Open Road Test Track:

  • A Maker may submit more than one Submission, however, each Submission must be unique and substantially different from the others, as determined by the Poster and/or the Administrator.
  • Makers must either:
    • Upload application binaries to Devpost/provide a URL where the binaries are located on a hosting service (be sure to provide pre-and post-optimization binaries)
    • Provide a source code repository URL for their application, assuring to provide pre-and post-optimization examples

B. Submission Requirements for The Accelerated Spark Rally

(i) General Requirements:

  • Access Spark Instances with GPUs in SuperVessel
  • Complete any of the three (3) defined tasks (“A”, “B”, and/or “C”):

A. Port an existing GPU-enabled application to OpenPOWER and demonstrate scaling to 2 GPU-enabled instances running on two (2) nodes under Spark

B. Port or create a new Spark application on OpenPOWER and demonstrate scaling to two (2) nodes under Spark. Then, enable the application with GPU acceleration and demonstrate gains when scaling to two (2) GPU-enabled instances under Spark versus the non-GPU enabled application under 2-node Spark.

C. Modify Spark to enable GPU acceleration, for example GPU-enable a Spark MLlib algorithm, a Spark GraphX algorithm, Spark SQL queries, or any other core function of Spark that you wish to try accelerating with a GPU. Demonstrate the speed-up provided transparently to a Spark application using the Spark functions you GPU-accelerated (with before and after results), scaling across 2-nodes

(ii) Technical Requirements:

  • The solution must be run on SuperVessel
  • The implementation must leverage Spark as a framework for its scaling design
  • The implementation must leverage GPU-accelerators
  • Submissions must be scaled beyond a single instance through Spark

(iii) Required Submission Materials Specific to The Accelerated Spark Rally Track:

  • Makers must provide application binaries and anything needed to reproduce your results to a URL on a hosting service or as an archived file submitted with the Submission Form, including:
    • Application binaries including pre and post-optimization
    • (optional but strongly encouraged) Application source code including pre and post-optimization
      • For Challenge “C” this will include your modified Spark code
    • Written testing instructions sufficiently detailed to reproduce their results
    • Note: your submission video must capture needed evidence to demonstrate accomplishments against the Challenge goals (judging criteria) – for example: Spark User Interface output – job status, statistics, tasks, DAGs, etc. 

C. Submission Requirements for The Cognitive Cup

(i) General Requirements:

  • Access the deep learning frameworks available via software image in SuperVessel or bring your own code to these environments
  • Complete any of the Deep Learning Challenges (“ArtNet”, “TuneNet”, and/or “YourNet”) using Deep Learning Instances with GPUs and/or FPGAs
    • ArtNet – Use Deep Learning to train Neural Networks to analyze paintings. Create a Neural Network that recognizes the painter, painting style, period, and painting technique for paintings presented to it. The paintings at Wikiart make a good starting point for a training corpus, as they contain paintings labeled with key characteristics, but many more online resources for training a neural network exist online.
    • TuneNet – Guide programmer optimization using Deep Learning. Recognize hot spots and bottlenecks in application code and advise the programmer on how to improve the program. Label source programs with performance events and train a network to predict similar events in application source to guide programmer coding.
    • YourNet – define and solve your own Deep Learning problem. Find an interesting problem and data set that is relevant to you life, and show how to use Deep Learning to solve it. From Log Analytics to recognizing Whales and Birds using Deep Learning, the problem field is wide open to your imagination.
  • Optionally, demonstrate that your code can also leverage Spark to scale

(ii) Technical Requirements:

  • The solution must run on SuperVessel
  • If multi-node scaling is demonstrated (optionally), the implementation must leverage Spark as a framework for its scaling design
  • The implementation must leverage either GPU-accelerators or FPGAs

(iii) Required Submission Materials Specific to The Cognitive Cup:

  • Makers must provide corpus (curated, fit-for-purpose input data set), training script, and anything needed to reproduce your results to a URL on a hosting service or as an archived file submitted with the Submission Form, including but not limited to:
    • Corpus (input data set)
    • training script
    • application binaries
    • Written testing instructions sufficiently detailed to reproduce their results
    • Note: your submission video must capture needed evidence to demonstrate accomplishments against the Challenge goals (judging criteria)

D. General Submission Requirements (Applicable to The Open Road Test, The Accelerated Spark Rally and The Cognitive Cup)

(i) Language Requirements: All Submission materials must be in English or, if not in English, the Maker must provide an English translation of the demonstration video, text description, and testing instructions as well as all other materials submitted. 

(ii) Text Description: The text description should explain your solution, including an optional single paragraph description of any innovative problem approaches to what you built, what tools were used, and any other relevant experiences with the tools.

(iii) Images: The image(s) should be photographs or screenshots of your working solution.

(iv) Video: All Submissions must include a demonstration video screen capture of the solution. The video portion of the Submission: 

a. should be less than ten (10) minutes;

b. must include footage that clearly explains the solution’s features and functionality through a comprehensive demonstration;

c. must be uploaded to YouTube, Vimeo, or Youku and a link to the video must be provided on the Enter a Submission form on the Hackathon Website; and

d. must not include third party trademarks, or copyrighted music or other material unless the Maker has permission to use such material.

(v) Functionality:  Solutions must function as depicted in the video and/or expressed in the text description.

(vi) Testing: The Maker must make the Submission available free of charge and without any restriction, for testing, evaluation and use by the Poster, Administrator and judges during the Hackathon and until the Judging Period ends. 

(vii) SDKs, APIs, & Data: Submissions may, but are not require to, integrate other APIs, SDKs, datasets, and custom code as long as the developer is authorized to use them

(viii) Intellectual Property: Your Submission must: (a) be your (or your team or Organization’s) original work product; (b) be solely owned by you, your team, or your Organization with no other person or entity having any right or interest in it; and (c) not violate the intellectual property rights or other rights including but not limited to copyright, trademark, patent, contract, and/or privacy rights, of any other person or entity. A Maker may contract with a third party for technical assistance to create the Submission provided the Submission components are solely the Maker’s work product and the result of the Maker’s ideas and creativity, and the Maker owns all rights to them. A Maker may submit a Submission that includes the use of open source software or hardware, provided the Maker complies with applicable open source licenses and, as part of the Submission, creates software that enhances and builds upon the features and functionality included in the underlying open source product. By entering the Hackathon you represent, warrant, and agree that your Submission meets these requirements.

(ix) Financial or Preferential Support: A Submission must not have been developed, or derived from a solution developed, with financial or preferential support from the Poster or Administrator. Such solutions include, but are not limited to, those that received funding or investment for their development, were developed under contract, or received a commercial license, from the Poster or Administrator any time prior to the end of the Hackathon Submission Period. The Poster, at their sole discretion, may disqualify an Submission, if awarding a prize to the Submission would create a real or apparent conflict of interest.