HPC (High Performance Computing) analytics project is focusing on Machine Learning techniques in the domain of HPC resource allocation. This project is based on the log file Beocat which is HPC cluster at Kansas State University, and using Machine Learning techniques, such as supervised learning and reinforcement learning, to aim three purposes:
Predicting the sufficiency of resource requested in HPC system during job submission time,making HPC resource allocation more efficient and building decision support for HPC users
This specific repository uses python and neo4j to create a property graph database which will be used to run varied ML algorithms.
Data can be found: http://people.cs.ksu.edu/~happystep/HPC/
Project Site: http://www.kddresearch.com/page/70/