Nvidia CEO Jensen Huang describes the company’s plans to accelerate AI processing and networking. (Source: Nvidia)

Nvidia Touts AI Chips for Improving Processing Time

At first glance, Nvidia CEO Jensen Huang seems like the kind of guy you would want to run for public office. He’s hard-driving, optimistic and dialed-in to the big tech that is running the world. Last week he gave the keynote address at Nvidia’s GPU Technology Conference (GTC) which is the must-attend digital event for developers, researchers, engineers, and innovators looking to enhance their skills, exchange ideas, and gain a deeper understanding of how AI will transform their work.

Huang made major announcements in data centers, AI, collaboration tools, and healthcare in a talk simultaneously released in nine episodes, each under 10 minutes.

“AI requires a whole reinvention of computing – full-stack rethinking – from chips, to systems, algorithms, tools, the ecosystem,” Huang said, standing in front of the stove of his Silicon Valley home.

Huang’s did his presentation from his kitchen in front of an incredibly ornate stove:

“NVIDIA is a full stack computing company – we love working on extremely hard computing problems that have great impact on the world – this is right in our wheelhouse,” Huang said. “We are all-in, to advance and democratize this new form of computing – for the age of AI.”

Last week’s GTC is one of the biggest yet. It featured more than 1,000 sessions—400 more than the last GTC—in 40 topic areas. And it was the first to run across the world’s time zones, with sessions in English, Chinese, Korean, Japanese and Hebrew. Huang has made a name for himself in the GPU business after four years of focusing on the AI market.

Improved Processing

Brian Caulfield, who an article for the in-house web blog of Nvidia, reports that Huang introduced something he calls the DPU, or Data Processing Unit. The DPU consists of accelerators for networking, storage, security and programmable Arm CPUs to offload the hypervisor, Huang said.

The new Nvidia BlueField 2 DPU is a programmable processor with powerful Arm cores and acceleration engines for at-line-speed processing for networking, storage and security. It was part of the April acquisition of high-speed interconnect provider Mellanox Technologies.

Huang said NVIDIA’s DPU roadmap shows advancements coming fast. BlueField-2 is sampling now, BlueField-3 is finishing and BlueField-4 is in high gear, Huang reported.

“We are going to bring a ton of technology to networking,” Huang said. “In just a couple of years, we’ll span nearly 1,000 times in compute throughput” on the DPU.

Huang spoke on a new supercomputer being designed for the health care industry and NVIDIA also announced a partnership with GSK to build the world’s first AI drug discovery lab.

Caulfield filled the article with several other Huang announcements of the latest tech to become part of Nvidia’s future.

read more at blogs.nvidia.com