Oana Balmauمشاهده پروفایل
استادیار
Oana Balmau is an Assistant Professor in the School of Computer Science at McGill University, leading the Data-Intensive Storage and Computer Systems Laboratory (DISCS Lab). She also holds a status-only appointment at the University of Toronto and chairs the MLPerf Storage working group. Her research focuses on storage systems, persistent memory, machine learning workloads, and edge computing. Balmau earned her PhD in Computer Science from the University of Sydney (2020) under Prof. Willy Zwaenepoel, with earlier degrees from EPFL. She has received notable awards including the SEC 2024 Best Paper Award, MLCommons Hero Award (2023), and the CORE John Makepeace Bennett Award (2021). Education: PhD in Computer Science, University of Sydney (2020) MSc in Computer Science, EPFL BSc in Computer Science, EPFL Research Interests: Her work spans storage infrastructure optimizations for ML and edge computing, including the MLPerf Storage benchmark and frameworks for secure hierarchical edge computing. Key contributions include systems like KeVell , SILK , and FloDB , addressing latency spikes, write amplification, and I/O efficiency in key-value stores. Recent projects explore processing-in-memory virtualization and live reconfiguration for edge stream processing. Awards & Honors: SEC 2024 Best Paper Award MLCommons Hero Award 2023 ACM SIGOPS Dennis M. Ritchie Doctoral Dissertation Award (Honorable Mention, 2021) CORE John Makepeace Bennett Award (2021) USENIX ATC 2019 Best Paper Award Teaching & Service: Teaches advanced courses on computer systems (COMP-513, COMP-604) and OS fundamentals at McGill. Serves on program committees for SOSP, SIGMOD, FAST, and EuroSys. Co-organizes workshops like Dagstuhl’s Resource-efficient ML and DSDS. Active in academic service, including the EuroSys Roger Needham Award committee. Labs & Collaborations: DISCS Lab focuses on scalable storage solutions for data-intensive workloads. Collaborates with institutions like UBC, ETS Montréal, and University of Toronto on edge computing initiatives through the DND IDEaS micro-net. Open-source contributions include the SILK and TRIAD systems.






