Distributed and Parallel Storage - I/O
High-Performance Storage and Exascale I/O.
Director of I/O research at the SCS Lab @Illinois Tech.
"Accelerating I/O Using Data Labels: A Contention-aware, Multi-tiered, Scalable, and Distributed I/O Platform", May 2019.
I/O is now the biggest challenge in modern supercomputers!
Storage systems are called to efficiently support both compute- and data-intensive workloads. As we move towards the exascale era, most of these storage systems face significant challenges in performance, scalability, complexity, and limited metadata services, creating an I/O bottleneck that leads to less scientific productivity.
Website was created with Mobirise site theme