Haoxing (Mark) Ren - Director of Design Automation Research - Nvidia
Inspired by the groundbreaking success of AlphaGO, Reinforcement Learning (RL) techniques have, over the past five years, been applied to numerous design optimization challenges, revealing the transformative potential of AI. This talk explores recent advancements in AI applications for chip design that extend beyond RL. First, I will present how RL, in synergy with traditional algorithms, has been harnessed to automate standard cell layout. Next, I will delve into the use of generative models for direct circuit optimization, leveraging pre-trained models and gradient-based methods. Finally, I will discuss how the rise of Large Language Models (LLMs) has expanded the scope of AI in design. I will highlight the role of LLM-based copilots in enhancing productivity through knowledge sharing and coding support, as well as the emergence of LLM-based agents that tackle critical design tasks, including analysis, debugging, and optimization.
About Haoxing (Mark) Ren
Haoxing (Mark) Ren is the Director of Design Automation Research at NVIDIA, focusing on leveraging machine learning and GPU-accelerated tools to enhance chip design quality and productivity. He has over 25 years of industrial EDA research and development experience at IBM and NVIDIA. He holds over thirty patents and has co-authored over 100 papers and books, including a book on ML for EDA and several book chapters in EDA. He received several prestigious awards for his work, including the IBM Corporate Award and best paper awards at ISPD, DAC, TCAD, MLCAD and LAD. He serves in the organization and steering committees of international conferences such as ICCAD and ISPD and as the conference chair at ICLAD. He holds Bachelor's and Master's degrees from Shanghai Jiao Tong University and Rensselaer Polytechnic Institute, respectively, and earned his PhD from the University of Texas at Austin. He is a Fellow of the IEEE.
Nael Abu-Ghazaleh - Professor in the CSE department, UC Riverside
AR/VR devices promise a new era of immersive computing, where our everyday experience is augmented with helpful information (Augmented Reality), or where we are immersed in fully virtual worlds (Virtual Reality). These systems fuse the physical world, and the virtual world, through computing resources to provide these immersive experiences rendered on the user's headset. As a result, it allows new opportunities for attackers to compromise the security and privacy of users, that are not well understood. Towards understanding the security and privacy challenges in these systems, this talk presents a number of recent attacks we developed on AR/VR systems. One threat model exploits the shared computing resources used by multiple applications on a headset to extract information through side channels; we show attacks that spy on user activity or compromise privacy. Another threat model exploits the shared state among multiple users in a multi-user application, allowing malicious users to inject compromised information or to recover information they are not allowed to access. Other threat models include those that interfere with applications and cause the virtual model to become out of sync with the physical world, causing user motion sickness or bypassing safety guardrails. I will conclude with discussion potential defenses and ways to build more security AR/VR experiences.
About Nael Abu-Ghazaleh
Nael Abu-Ghazaleh is a Professor in the Computer Science and Engineering as well as the Electrical and Computer Engineering Departments at the University of California, Riverside. His research is in architecture and system security, high-performance computing, and systems and security for Machine Learning. He has published over 250 papers in these areas, several of which have been recognized with best paper awards or nominations. His offensive security research has resulted in the discovery of several new attacks on CPUs and GPUs that have been disclosed to companies including Intel, AMD, ARM, Apple, Microsoft, Google, and Nvidia, and resulted in patches and modifications to products, and coverage from technical news outlets. He is a member of the Micro Hall of Fame, an ACM distinguished member, and an IEEE distinguished speaker.