Maryam Mehri Dehnavi

Maryam Mehri Dehnavi is an Associate Professor in the Department of Computer Science at the University of Toronto. Her research interests include systems, scientific and high-performance computing, machine learning, programming languages, high-performance computing, parallel algorithms, compilers, systems for machine learning, cloud computing, computer architecture, numerical analysis and optimization, and graph theory. She is also a Principal Research Scientist at NVIDIA Canada and holds the Canada Research Chair in Parallel and Distributed Computing. Her work focuses on developing scalable numerical methods, high-performance libraries, and domain-specific languages and compilers for high-performance and cloud computing platforms.

Maryam Mehri Dehnavi is a researcher in Computer Science with a focus on optimizing sparse matrix operations and parallel computing. Her work explores efficient algorithms for sparse tensor computations, GPU-based conjugate gradient solvers, and sparse approximate inverse preconditioning. She has contributed to the development of tools like Sympiler and ParSy, which enhance sparse matrix code transformation for parallelism. Her research also extends to distributed platforms for large-scale sparse tensor factorizations and communication-avoiding Krylov techniques. Mehri Dehnavi's publications highlight advancements in sparse computation, data dependence analysis, and high-performance computing for multi-core and many-core architectures.