Deep Learning in the Age of Zen, Vega, and Beyond

Explore the challenges and advancements in deep learning and machine intelligence in this Stanford Computer Systems Colloquium seminar. Delve into the computational challenges of deep learning and discover how new compute platforms like Zen (x86) and Vega (GPU) provide high-performance solutions for various training and inference applications. Learn about the ROCm software stack and its role in supporting libraries and frameworks for different environments. Gain insights from Allen Rush, an AMD fellow with over 25 years of experience in imaging and computer vision projects, as he discusses the current state of machine learning development activities in hardware, software, and application support. This comprehensive talk covers topics ranging from integrated circuits to operating systems and programming languages, offering valuable knowledge for those interested in the latest developments in computer architecture and deep learning.

Stanford Seminar: Deep Learning in the Age of Zen, Vega, and Beyond