Presenter
Vasily Tarasov
Biography
Vasily Tarasov is a principal research scientist at IBM Research. His broad research interests revolve
around data storage, focusing on high-performance storage systems for hybrid clouds and AI. At IBM, Vasily has led projects on making IBM Spectrum Scale container-native (https://www.ibm.com/products/storage-scale), building storage acceleration tiers for AI workloads and high-performance object stores for data lakehouses. Most recently, he has worked on building and operating high-performance storage solutions for IBM’s Vela supercomputer for AI (https://research.ibm.com/blog/AI-supercomputer-Vela-GPU-cluster).
Vasily holds a PhD in computer science from Stony Brook University and has studied data deduplication, storage performance and workload analysis, user-space file systems, and storage for containers. He has published dozens of papers in systems conferences, and regularly serves on conference planning committees.
around data storage, focusing on high-performance storage systems for hybrid clouds and AI. At IBM, Vasily has led projects on making IBM Spectrum Scale container-native (https://www.ibm.com/products/storage-scale), building storage acceleration tiers for AI workloads and high-performance object stores for data lakehouses. Most recently, he has worked on building and operating high-performance storage solutions for IBM’s Vela supercomputer for AI (https://research.ibm.com/blog/AI-supercomputer-Vela-GPU-cluster).
Vasily holds a PhD in computer science from Stony Brook University and has studied data deduplication, storage performance and workload analysis, user-space file systems, and storage for containers. He has published dozens of papers in systems conferences, and regularly serves on conference planning committees.
Presentations