We bring latest research in performance tuning to production.

Machine learning-based performance optimization does it faster and better.


Performance tuning used to be a tedious task. Project ASCAR seeks to do automated performance tuning using machine learning.

The Pilot Framework

Pilot is a framework that is designed for collecting precise benchmark results in the shortest possible time. This is useful when a designer or administrator needs to evaluate many candidate parameters. Pilot analyzes time series data in real time and tells you when the desired width of confidence interval is reached. Pilot can also automate many benchmark chores, such as measuring the overhead, detecting warm-up and tear-down phases, discovering bottleneck of the system, and comparing very close benchmark results. It comes with an easy-to-use scriptable interface with C/C++/Python bindings.

We will begin a closed alpha test in late June, 2016, and plan to make the first public release in or before September, 2016. Join the mailing list to receive future release announcements:

If you don’t mind spending time testing bleeding edge code and giving us feedback in the Pilot alpha test, please let me (yanli AT ascar.io, or Twitter) know and join us on Slack.

Read more about the Pilot Framework.

Call for Collaboration

We are highly interested in partnerships with:
  • Companies who are interested in using machine learning to accelerate the tuning process of their products
  • Engineers who are interested in transforming research ideas into products that can benefit real world projects
  • Researchers from both machine learning and systems research areas that are interested in applying more machine learning methods to systems research
Want to know more? Leave us a message, or email yanli AT ascar.io, or join us on Slack.