Software-Hardware Co-Design for Future AI-driven Complex SystemsSpeaker: Shuaiwen Leon Song – Baltimore, MD, United States
Topic(s): Architecture, Embedded Systems and Electronics, Robotics
AbstractAI-driven system design has become prevalent, from embedded systems (e.g., IoT and edge computing) to large-scale data center and HPC system design. However, the current data-flow driven design has shown significant inefficiency on new deep learning network designs. In this session, I will discuss how to use memory- and data-centric design to help practitioners build their software and hardware layers of the desired deep learning system architectures. I will demonstrate usage cases from some of the emerging networks, including large LSTM training, Bayesian Neural Network Inference and Training, CapsuleNet inference, etc.
About this LectureNumber of Slides: 45
Duration: 50 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.