Baidu, the Chinese Internet giant that is partnering with NVIDIA to use artificial intelligence (AI) in the creation of a cloud-to-car autonomous car platform for local Chinese and global car makers (earlier post), is incorporating Pascal architecture-based NVIDIA Tesla P40 GPUs and NVIDIA deep learning software in the new Baidu cloud.
The NVIDIA Tesla P40 is purpose-built to deliver maximum throughput for deep learning deployment. With 47 TOPS (Tera-Operations Per Second) of inference performance and INT8 operations per GPU, a single server with 8 Tesla P40s delivers the performance of more than 140 CPU servers. The Tesla P40 delivers more than 30X lower latency than a CPU for real-time responsiveness in even the most complex models.
Our partnership with NVIDIA has long provided Baidu with a competitive advantage.—Shiming Yin, vice president and general manager of Baidu Cloud Computing
Baidu’s Autonomous Driving Unit (ADU) is working to commercialize autonomous driving by 2018 and achieve mass production by 2020. ADU is developing autonomous driving technologies at Level 4 automation, per the NHTSA definition. ADU leverages Baidu’s capabilities in the areas of artificial intelligence, deep learning, big data, advanced hardware, and high definition maps.