EPISODE · Apr 22, 2026 · 25 MIN
Innovation & Impact Podcast: Designing the Future of AI and the Next Era of Computing
from Innovation & Impact
Hosted by Vijay Kumar, Nemirovsky Family Dean of Penn Engineering and Professor in Mechanical Engineering and Applied Mechanics, episode 11 of Penn Engineering’s Innovation & Impact podcast features Jason Cong, Distinguished Professor in Computer Science and Electrical and Computer Engineering at UCLA’s Samueli’s School of Engineering. A pioneer in customizable computing whose work has helped redefine how modern computing systems are designed and optimized, Cong reflects on the technological shifts that have reshaped the field over the past two decades, from the end of Dennard scaling to the growing importance of energy efficiency in an AI-driven world.As artificial intelligence models grow larger and more complex, the traditional “one-size-fits-all” approach to computing is no longer sustainable. Instead, Cong highlights the rise of specialized hardware architectures tailored to specific workloads, enabling dramatic improvements in performance and efficiency. His insights shed light on how customizable computing has become foundational to advances in deep learning and large-scale AI systems. The conversation also explores the evolution of tools like FPGAs and high-level synthesis, which are transforming how engineers design and deploy hardware. For everyday users, this shift matters because it directly impacts how fast, affordable and energy-efficient the technologies we rely on — like smartphones, voice assistants and AI-powered tools — can become. The innovations discussed in this episode are helping shape a future where AI is not only more powerful, but also more accessible and sustainable in daily life.Listen to Episode 11 of Penn Engineering’s Innovation & Impact podcast on Apple Music, Spotify or your favorite listening platforms, or find all the episodes on our Penn Engineering YouTube channel. Hosted on Acast. See acast.com/privacy for more information.
What this episode covers
Hosted by Vijay Kumar, Nemirovsky Family Dean of Penn Engineering and Professor in Mechanical Engineering and Applied Mechanics, episode 11 of Penn Engineering’s Innovation & Impact podcast features Jason Cong, Distinguished Professor in Computer Science and Electrical and Computer Engineering at UCLA’s Samueli’s School of Engineering. A pioneer in customizable computing whose work has helped redefine how modern computing systems are designed and optimized, Cong reflects on the technological shifts that have reshaped the field over the past two decades, from the end of Dennard scaling to the growing importance of energy efficiency in an AI-driven world.As artificial intelligence models grow larger and more complex, the traditional “one-size-fits-all” approach to computing is no longer sustainable. Instead, Cong highlights the rise of specialized hardware architectures tailored to specific workloads, enabling dramatic improvements in performance and efficiency. His insights shed light on how customizable computing has become foundational to advances in deep learning and large-scale AI systems. The conversation also explores the evolution of tools like FPGAs and high-level synthesis, which are transforming how engineers design and deploy hardware. For everyday users, this shift matters because it directly impacts how fast, affordable and energy-efficient the technologies we rely on — like smartphones, voice assistants and AI-powered tools — can become. The innovations discussed in this episode are helping shape a future where AI is not only more powerful, but also more accessible and sustainable in daily life.Listen to Episode 11 of Penn Engineering’s Innovation & Impact podcast on Apple Music, Spotify or your favorite listening platforms, or find all the episodes on our Penn Engineering YouTube channel. Hosted on Acast. See acast.com/privacy for more information.
NOW PLAYING
Innovation & Impact Podcast: Designing the Future of AI and the Next Era of Computing
No transcript for this episode yet
Similar Episodes
Apr 29, 2026 ·48m
Apr 29, 2026 ·106m
Apr 29, 2026 ·55m
Apr 29, 2026 ·74m