Center for Artificial Intelligence Innovation

Back to Listing

Research Seminar: The Cerebras Wafer-Scale Engine (WSE-2) - A new architecture for Machine Learning (ML) and High Performance Computing (HPC) Workloads

Event Type
Seminar/Symposium
Sponsor
Center for Artificial Intelligence Innovation
Virtual
wifi event
Date
May 2, 2022   11:00 am - 12:00 pm  
Speaker
Cindy Orozco Bohorquez, Cerebras
Views
226

The Center for Artificial Intelligence Innovation will be hosting a Research Seminar on Monday, May 2nd from 11:00am-12:00pm via Zoom. The speaker for this seminar will be Cindy Orozco Bohorquez from Cerebras. Cindy will be presenting on "The Cerebras Wafer-Scale Engine (WSE-2) - A new architecture for Machine Learning (ML) and High Performance Computing (HPC) Workloads." 

Seminar:  https://go.ncsa.illinois.edu/CAIIResearchSeminar  

Abstract:
Cerebras has developed a new hardware architecture for AI acceleration using the largest processor in the industry. The Wafer-Scale Engine (WSE-2) is the largest chip ever built and powers the CS-2 system. The WSE-2 is 56 times larger than the largest GPU, has 123 times more compute cores, and 1000 times more high performance on-chip memory. The only wafer-scale processor ever produced, it contains 2.6 trillion transistors, 850,000 AI-optimized cores, and 40 gigabytes of high performance on-wafer memory. Purpose built for AI, the CS-2 system replaces an entire cluster of graphics processing units (GPUs). Gone are the challenges of parallel programming, distributed training, and cluster management. From chip to system to software – every aspect of the CS-2 is optimized to accelerate and to simplify AI work. This presentation will introduce the Cerebras CS-2 platform and how it can be used for ML and HPC workloads.

 

Speaker Bio:
Cindy Orozco Bohorquez is a member of the Product team’s technical staff at Cerebras. She holds a PhD in Computational and Mathematical Engineering from Stanford University. Cindy is focused on helping Cerebras customers utilize the full potential of the WSE for ML model training and inference. Adam Lavely is also a member of the Product team’s technical staff. He holds a PhD in Aerospace, Aeronautical and Astronautical Engineering from Penn State University. Adam is focused on helping Cerebras customers unlock the HPC potential of the WSE via our SDK.

link for robots only