Department of Computer Science, Yale University
Title: Computer Architectures for Mind-Machine Teaming
Direct brain-computer communication promises to help treat neurological disorders, explain brain function, and augment human cognition and decision-making. The promise of mind-machine teaming hinges on computer systems that delicately balance the tight power, latency, and bandwidth trade-offs needed to decode brain activity, stimulate biological neurons, and control assistive devices most effectively.
This talk presents the design of two systems that unlock several brain-computer interactions while navigating the power and performance trade-offs posed by brain interfacing. The first system, HALO, is an accelerator-rich processing fabric that enables flexible single-brain-site interfacing at high data rates using only tens of milliwatts of power. The second system, Hull, realizes multi-brain-site interfacing using a distributed system of networked accelerator-rich processing fabrics built atop HALO. Driven by important brain-computer interface applications (e.g., epilepsy, movement disorders, paralysis), we explore systems research questions pertaining to the design and integration of hardware accelerators, co-design of hardware accelerators with networking & storage stacks, and clean interfaces/abstractions for programmability. Key insights are undergirded via chip tape-outs in a 12nm CMOS process.