Project ASCAR originated from the Storage Systems Research Center (SSRC) at the University of California, Santa Cruz. The project focuses on using machine learning to improve the tuning process of complex computer systems, starting from what we are good at, the storage systems.
Yan Li is the main figure behind this project. After discovering a machine learning method that can increase the performance of some Lustre workloads by 35% automatically, without any need for human input, he decided to put more effort into commercializing this project, as well as other emerging machine learning methods, to improve the practices of today’s performance tuning.
Currently Yan Li is working at SSRC under the supervision of Professor Darrell Long. Many UCSC students are contributing their ideas and code to this project.