Baidu is using Xilinx FPGAs to accelerate machine learning applications in their data centres in China.

The two companies are collaborating to further expand volume deployment of FPGA-based accelerated platforms.

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

FPGAs deliver the power efficiency that makes accelerators practical to deploy throughout the data centre and can deliver a 10-20X performance/watt improvement.

Baidu-optimized 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 centres, a powerful centralized 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,” says Baidu’s Yang Liu.

By: DocMemory
Copyright © 2023 CST, Inc. All Rights Reserved