Gennady Pekhimenko
About
Appointed Canada CIFAR AI Chair – 2019
Gennady Pekhimenko is a Canada CIFAR AI Chair at the Vector Institute and an Associate Professor at the Department of Computer Science and the lead of the Ecosystem research group at the University of Toronto. He is also the CEO and Co-Founder at CentML, the Toronto-based startup that focuses on optimizing ML workloads by making them both faster and cheaper to run.
Pekhimenko’s research focuses on efficient memory hierarchy designs, systems for machine learning, approximate computing, compilers, and hardware acceleration.
Awards
- Ontario Early Research Award, 2024
- Distinguished Artifact Award, ACM, 2023
- Early Career Faculty Award, VMware, 2022
- Google Research Scholar, 2022
- ISCA Hall of Fame, 2021
- IEEE MICRO Top Picks, 2020-2021
- HiPEAC Paper Award, 2020
- Amazon AWS Machine Learning Research Award, 2020-2021
- Facebook Faculty Research Award, 2020-2021
Relevant Publications
- Mu, B., et al. (2024). Sylva: Sparse Embedded Adapters via Hierarchical Approximate Second-Order Information (pp. 485-497). ICS.
- Gao, Y., et al. (2024). Proteus: Preserving Model Confidentiality during Graph Optimizations. MLSys.
- Karargyris, A., et al, (2023). Federated benchmarking of medical artificial intelligence with MedPerf. Nature Machine Intelligence. 5(7) (pp. 799-810).
- Andoorveedu, M., et al. (2022). Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction. NeurIPS.
- Zheng, B., et al. (2022). DietCode: Automatic optimization for dynamic tensor programs. Proceedings of Machine Learning and Systems. 4 (pp. 848-863).