ncnn Porting and Optimization

Index:S2310
Award:15000Chinese Yuan

Challenge Description

ncnn is a high-performance neural network compute framework with good RISC-V support. This challenge assesses the participant’s ability to maximise ncnn performance on a Duo, as benchmarked by its internal performance testsuites.

Rubrics

  1. Does not produce new failures in regression testing.
  2. Makes use of RVV0.7, the TPU, and other compute components available on the Duo.
  3. Runs as many benchmark models as possible, noting time elapsed for each.

Submission

  • Please submit your completed project at https://github.com/plctlab/rvspoc-s2310-ncnn as a pull request.
  • Please outline the software environment needed to run your submission in your pull request body.
  • During the competition, all optimised artifacts may be submitted as the following:
    1. Binary files.
    2. Encrypted code (please send decryption details to rvspoc@cyberlimes.cn).
    3. Source code.
  • After the results are announced, you will need to publish source code for all submissions.
  • The committee will close pull request submissions after the challenge’s run time (on February 16February 29, 2024) and commence assessment of submissions.

Assessment

  1. The assessment platform for this challenge is Duo (64MB model).
    • We will use a specific microSD (TF) card for assessment.
    • Swap usage is not recommended.
    • No overclocking will be applied.
    • No additional cooling will be provided.
  2. If you have a specific operating system configuration, please note it in the pull request body.
  3. The ncnn repository used for assessment will be https://github.com/Tencent/ncnn.
  4. The committee will run ncnnbench as assessment, the weighted rubric for optimization items will be announced soon.
  5. The benchmark results must not be worse than that observed with the Milk-V’s official image with 55MB of RAM.
  6. Some benchmark results may not run on 55MB of RAM without swap space. We will announce instructions on these items soon.
  7. The details of the challenges may change during the competition as we optimise and clarify the rubrics and instructions. Please keep an eye out for updates. The assessment committee reserves the right to final interpretation of all rubrics and instructions.

Notice on Intellectual Properties and Open Source Licenses

All challenge submissions must be open source and committed to a specified repository. The participant(s) (author) holds rights to their work. The host encourages contributing any changes made to the upstream.

Resources