FPGAs accelerate machine learning applications in data centres

As rapid growth of emerging applications begins to drive up computational workloads, data centres are turning to application accelerators to keep up with the demands for greater throughput at low latency while retaining practical power levels.

Xilinx FPGAs deliver the power efficiency that makes accelerators practical to deploy throughout the data center and can deliver a 10-20X performance/watt improvement. Baidu-optimised FPGA platforms are tuned for machine learning applications such as image and speech recognition. The platforms will also be leveraged in Baidu’s initiative to develop commercially viable autonomous cars. When deployed in Baidu data centers, a powerful centralised pool of accelerators can be rapidly configured for the most demanding workloads based on user demand.

“Acceleration is essential to keep up with the rapidly increasing data center workloads that support our growth,” said Yang Liu, Executive Director at Baidu.

“Xilinx FPGAs are assisting greatly with this critical task and can provide significant value in the design of autonomous vehicles,” added Junwei Bao, Director in Baidu’s Autonomous Driving Unit.

“The momentum for FPGA-based acceleration continues as shown by this significant implementation with Baidu,” said Victor Peng, Executive Vice President and GM of the Programmable Products Group at Xilinx. “We celebrate Baidu’s innovation, expertise and creativity in bringing advanced applications to market.”