| Page 1298 | Kisaco Research

TRACK A: Hardware & Systems: RISC-V, from Edge AI to Data Center

RISC-V adoption has increased dramatically throughout 2022, due to the architecture's simple intruction set, the ability to better pre-process NNs for acceleration and its open source nature. The advent of the RISC-V vector extension allows AI processor builders to develop on top of instructions that other companies are using and then innovate in whatever domain they want to specialize in.

Chip Design

Edge AI

ML at Scale

Novel

Systems Design

Hardware Engineering

Strategy

Systems Engineering

Author:

Bing Yu

Senior Technical Director

Andes Technology

Bing Yu is a Sr. Technical Director at Andes Technology. He has over 30 years of experience in technical leadership and management, specializing in machine learning hardware, high performance CPUs and system architecture. In his current role, he is responsible for processor roadmap, architecture, and product design. Bing received his BS degree in Electrical Engineering from San Jose State University and completed the Stanford Executive Program (SEP) at the Stanford Graduate School of Business.

Read more about TRACK A: Hardware & Systems: RISC-V, from Edge AI to Data Center

Massive Natural Language Model Processing

Cerebras Systems builds the fastest AI accelerators in the industry. In this talk we will review how the size and scope of massive natural language processing (NLP) presents fundamental challenges to legacy compute and to traditional cloud providers. We will explore the importance of guaranteed node to node latency in large clusters, how that can’t be achieved in the cloud, and how it prevents linear and even deterministic scaling. We will examine the complexity of distributing NLP models over hundreds or thousands of GPUs and show how quickly and easily a cluster of Cerebras CS-2s is set up, and how linear scaling can be achieved over millions of compute cores with Cerebras technology. And finally, we will show how innovative customers are using clusters of Cerebras CS-2s to train large language models in order to solve both basic and applied scientific challenges, including understanding the COVID-19 replication mechanism, epigenetic language modelling for drug discovery, and in the development of clean energy. This enables researchers to test ideas that may otherwise languish for lack of resources and, ultimately, reduces the cost of curiosity.

Chip Design

Enterprise AI

ML at Scale

Novel AI Hardware

Systems Design

Data Science

Hardware Engineering

Software Engineering

Strategy

Systems Engineering

Author:

Andy Hock

VP, Product Management

Cerebras

Dr. Andy Hock is VP of Product Management at Cerebras Systems with responsibility for product strategy. His organization drives engagement with engineering and our customers to inform the hardware, software, and machine learning technical requirements and accelerate world-leading AI with Cerebras’ products. Prior to Cerebras, Andy has held senior leadership positions with Arete Associates, Skybox Imaging (acquired by Google), and Google. He holds a PhD in Geophysics and Space Physics from UCLA.