Welcome to the MGHPCC Virtual Booth

Boston University

Machine Learning-Based Performance Analytics on High-Performance Computing Systems

Thursday, November 19 10:30 am EST
Passcode: 759941
As the size and complexity of HPC systems increase, manual analysis methods relying on human experts have become increasingly limited in identifying root causes of performance problems (e.g., slowdowns) or improving resource management decisions. This talk introduces a set of novel machine learning frameworks that diagnose performance anomalies and identify applications running on supercomputers. We evaluate our frameworks on an HPC system and demonstrate that our approach outperforms current state-of-the-art techniques in detecting anomalies and applications, reaching an F-score over 0.97.
Boston University
Computer Engineering
Burak Aksar
PhD Student
Chat with us @
Attend Consortium Talks @


Featured projects

Air Force Arcade
Airborne Optical Systems Test Bed (AOSTB)
Black Hole Initiative
Center for Scientific Computing and Visualization Research (CSCVR)
Data Centric Low Emission Mobility
Fast Accurate NURBS Optimization (FANO)
Fusarium Pathogenomics: Understanding Fungal Pathogenicity through Genomics
GLEAM: Global Epidemic and Mobility project
Lichtman Lab - Center for Brain Science
Lincoln Laboratory Supercomputing Center (LLSC)
LLSC Articles and Publications
MIT Initiative on the Digital Economy
MIT Laboratory for Financial Engineering
Northeast Cyberteam
Northeastern University and Williams College SC20 Student Cluster Competition Team
Quantum Architectures at Goodwill Computing Lab
Simulating Large Biomolecular Assemblies
The Center for Information and Systems Engineering (CISE)
The Mass Open Cloud and Open Cloud Initiative
Video and Imagery Dataset to Drive Public Safety
Visibility Estimation through Image Analytics (VEIA)
linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram