Welcome to MSRG_
The Middleware Systems Research Group at the University of Toronto
Traditionally, the “M” in MSRG stood for “middleware”—the Middleware Systems Research Group at the University of Toronto. But don’t worry, “middleware is literally everywhere.” Over the years, that “M” has evolved to mean “mobile,” “microservices,” “machine learning,” and, last but not least, “matter,” as in entangled particles in space-time. What more could you ask for?
We are always looking for interested trainees and students to join our research endeavors. We've summarized some specific points as well as some more general information about engaging with us. For more information, check out our we are hiring in the following areas ...
Our data management and distributed systems research focuses on designing 3H systems—highly scalable, highly reliable, and highly available. We explore transactional and analytical database systems, distributed ledger technologies, and consensus mechanisms to maintain synchronized distributed data.
We are also deeply interested in cloud databases and efficient resource allocation within cloud environments, particularly in containerized clouds supporting serverless computing and microservices architectures.
Our distributed learning systems projects focus on high performance distributed deep learning with the objective of optimizing training costs.
We also extensively engage in federated learning research in resource constrained environments (e.g., edge computing).
Our primary objective is to build new systems that can scale, are energy efficient, and legally compliant with emerging AI legislation.
As an application area, we work on systems for graph neural networks.
Currently, our work centers around foundational research in quantum computer systems.
We explore NISQ-era quantum algorithms, quantum error correction, and overall qubit noise reduction.
Our overall goal is to increase the robustness of modern quantum computing systems and explore scalability characteristics.
...
...
...
...
...
The SustainSys project addresses the growing environmental impact of large-scale ML tasks, which demand complex compute and software infrastructure. To meet these challenges, future data engineers must adopt green, holistic approaches to design energy-efficient data processing platforms.
SustainSys is an NSERC CREATE training network where we partner with Concordia, McGill, and Waterloo to train a new generation of highly skilled computer scientists focused on sustainability.
The PANDORA project advances AI and data engineering to drive industrial innovation and economic growth. It develops AI-driven frameworks for trustworthy datasets, improving AI model accuracy, sustainability, and efficiency in managing IoT data for smarter, more responsive devices in smart ecosystems..
PANDORA is an EU-funded project in which we are participating as an associated partner.
...
...
...