In the light of technology scaling and data explosion trends, the long latency and limited bandwidth of transferring data within a computer and across computers have become a key bottleneck to the improvement of performance and energy efficiency. Tacking this critical challenge, researchers have proposed various near-data processing architectures in the form of in-network and near-memory computing to move computation closer to data. In this talk, first, I introduce a technique that leverages the potentials of in-network processing for efficient power-management of network-connected computers. Then I present Memory Channel Network (MCN), a memory module based, near-memory processing architecture that seamlessly unifies near-memory processing with distributed computing for the acceleration of data-intensive applications.
Mohammad Alian is a Ph.D. candidate at the Electrical and Computer Engineering Department of the University of Illinois Urbana Champaign. His research is at the intersection of computer architecture and networking where he proposed several cross-stack, near-memory, and in-network computing architectures. His work has been published in top computer architecture and systems venues and recognized by several best paper candidacies and one honorable mention in IEEE MICRO Top Picks 2017. Mohammad holds an M.Sc. degree in computer engineering from the University of Wisconsin-Madison.
Faculty Host: Darko Marinov