Speaker: Subhasish Mitra, Stanford University
The Future of AI Compute Chips
3 September 2026, 09:00-10:00
This keynote presents transformative solutions to fundamental barriers facing 21st-century AI compute chips:
- Memory and miniaturization walls: Data movement already dominates AI execution time and energy, and the bottleneck is worsening as conventional 2D scaling slows. N3XT 3D architectures break through these limits via dense 3D integration of high-speed, low-energy logic, heterogeneous memories, and 3D thermal scaffolding, targeting 1,000× system-level Energy-Delay-Product benefits.
- Design productivity wall: Chip design costs are skyrocketing, dominated by design verification. ABCD – AI-Boosted Chip Design – delivers extremely thorough verification, up to 10× design productivity improvement (i.e., days instead of months), and Power, Performance, Area within 4–7% of expert-written RTL at under $50 API cost. ABCD is enabled by G-QED, a new AI-Ready verification technique.
- Reliability wall: Too many defective compute chips are escaping existing manufacturing testing – at least 10× more than industry targets. Silent data corruption by such defective chips threatens the integrity of AI systems. This creates golden opportunities for new “system-driven” approaches – from extremely thorough in-field test and diagnostics, deemed impossible during manufacturing today, all the way to cost-effective tolerance and prediction of failures in hardware during system operation.
Speaker Bio
Subhasish Mitra holds the William E. Ayer Endowed Chair Professorship in the Departments of Electrical Engineering and Computer Science at Stanford University. He directs the Stanford Robust Systems Group, serves on the leadership team of the Microelectronics Commons AI Hardware Hub, leads the Computation Focus Area of the Stanford SystemX Alliance, and is the Associate Chair (Faculty Affairs) of Stanford Computer Science. His research ranges across Robust Computing, NanoSystems, Electronic Design Automation (EDA), and Neurosciences. Prof. Mitra also has consulted for major technology companies including AMD (XIlinx), Anthropic, Cisco, Google, Intel, Samsung, and Sony. He recently cofounded TenX Semi, a startup on AI autopilot for chip design.
Further information about Professor Mitra can be found at: https://profiles.stanford.edu/subhasish-mitra.