The explosion of AI and pervasive intelligence, combined with the demand for exponentially increasing computing power after Moore's Law, has given rise to domain-specific architectures (DSAs). Xilinx technology is ideally suited for DSAs as it can be programmed and tuned to address today's most complex and demanding architectures with impressive results across a wide variety of workloads and applications. The same piece of silicon can be updated and reconfigured to tackle multiple tasks. This movement will be underscored by five talks to be given at the event:

 

Victor Peng, Xilinx CEO, will present his vision for the future in a keynote titled "Adaptable Intelligence: the Next Computing Era," at 11:45 a.m. on Tuesday, Aug. 21.

Juanjo Noguera, engineering director, Xilinx Architecture Group, will present on "HW/SW Programmable Engine: Domain Specific Architecture for Project Everest." This is a first peek at one of the novel heterogeneous components in the forthcoming "Everest" product family, which will provide orders of magnitude performance increase. Everest is part of a new category of computing technology called the Adaptive Compute Acceleration Platform (ACAP). This will be delivered at 9:45 a.m. on Tuesday, Aug. 21.

Rahul Nimaiyar, director of Data Center and IP Solutions at Xilinx, will describe the deep neural network (DNN) processor for Xilinx FPGAs that is currently available for use in Amazon Web Services (AWS) F1 instance. The talk is titled "Xilinx Tensor Processor: An Inference Engine, Network Compiler + Runtime for Xilinx FPGAs." It will be presented at 4 p.m. on Tuesday, Aug. 21.

Song Yao, co-founder and CEO of DeePhi Technologies – now a Xilinx company – will present a session titled "The Evolution of Deep Learning Accelerators Upon the Evolution of Deep Learning Algorithms," at 3:30 p.m., also on Tuesday, Aug. 21.

Michaela Blott, principal engineer for Xilinx CTO, will share insights from the forefront of research in a tutorial on architectures for deep neural nets called "Deep Learning and Computer Architectures." This takes places at 2 p.m. on Sunday, Aug. 19.