Accelerating AI and ML: Architectures and Systems for Efficient Computing

Attend a 55-minute colloquium featuring Divya Mahajan from Microsoft, hosted by the Paul G. Allen School. Explore the revolutionary impact of Artificial Intelligence (AI) and Machine Learning (ML) on various industries, and delve into the critical role of high-performance computing in enabling these advancements. Learn about domain-specific accelerators as efficient solutions for meeting AI/ML compute requirements in heterogeneous data centers. Discover Mahajan's contributions to designing and deploying accelerators for AI/ML applications, including TABLA and DaNA, comprehensive full-stack solutions for machine learning accelerators. Examine FAE, a framework leveraging data properties to optimize heterogeneous resources for recommender model training. Gain insights into future research directions for sustainable massive-scale distributed AI/ML, addressing challenges in the data processing pipeline. Hear from Divya Mahajan, a Senior Researcher at Microsoft's Cloud Accelerated Systems & Technologies group, as she shares her expertise in designing novel architectures and building robust systems for emerging applications.