Pervasive and Sustainable AI with Adaptive Computing
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
In the context of AI, we face a plethora of challenges that extend beyond the widely discussed performance scalability required to meet the growing demands of compute and storage in the latest models. These challenges encompass sustainability, pervasiveness, agility, and diversity, all of which are needed to cater to a constantly evolving range of applications and algorithms from endpoint to edge and cloud. In this talk, we explore how adaptive devices such as FPGAs paired with agile compiler stacks can provide solutions by delivering post-production hardware specialization and co-designed algorithms. This results in highly optimized AI systems which not only provide the necessary performance scalability but also bring a reduction in carbon footprint while addressing the needs of a broad range of diverse applications with the necessary agility.