Gennady Pekhimenko

Gennady Pekhimenko is a researcher in the field of computer architecture, with a focus on memory systems, data compression, and energy efficiency. He has made significant contributions to the design and optimization of memory technologies, including DRAM and GPU systems. His work has been published in top-tier conferences and journals, including ISCA, HPCA, and IEEE Transactions. Pekhimenko has also been recognized for his research, including winning first place in the ACM Student Research Competition. He is currently affiliated with the University of Texas at Austin, where he leads research efforts in memory systems and data compression.

Gennady Pekhimenko is a researcher at the University of Toronto, focusing on Computer Architecture, Systems, and Systems for ML. His work explores optimizing hardware for machine learning, with an emphasis on improving performance and energy efficiency in memory systems. Key areas include DRAM latency reduction, data compression for on-chip caches, and benchmarking frameworks for deep learning. His research addresses challenges in ML training and inference, such as latency variation in DRAM, efficient data encoding, and scalable distributed training. Pekhimenko's contributions span both theoretical and practical advancements, with publications in major conferences like ISCA and MLPerf benchmarking.