All the Nvidia news announced by Jensen Huang at Computex

Featured Sponsor

Store	Link	Sample Product
UK Artful Impressions	Premiere Etsy Store

Jensen Huang wants to bring generative AI to every data center, the nvidia co-founder and CEO said during Computex in Taipei today. During the speech, Huang’s first public address in nearly four years, he said, he made a series of announcements, including release dates for the chip, his DGX GH200 supercomputer and partnerships with major companies. Here’s all the news from the two-hour long keynote.

1. Nvidia’s GForce RTX 4080 Ti GPU for gamers is now in full production and is being produced in “bulk quantities” with partners in Taiwan.

2. Huang announced Nvidia Avatar Cloud Engine (ACE) for Games, a customizable AI model foundry service with pre-trained models for game developers. It will give NPCs more character through AI-driven language interactions.

3. The Nvidia Cuda computing model now serves four million developers and more than 3,000 applications. Cuda saw 40 million downloads, including 25 million last year alone.

4. Full-volume production of the HGX H100 server GPU has begun and is being manufactured by “companies all over Taiwan,” Huang said. He added that it is the world’s first computer to have a transformer engine.

5. Huang referred to Nvidia’s 2019 acquisition of supercomputer chipmaker Mellanox for $6.9 billion as “one of the most important strategic decisions” he has ever made.

6. Production of the next generation Hopper GPU will begin in August 2024, exactly two years after manufacturing of the first generation began.

7. Nvidia’s GH200 Grace Hopper is already in full production. The superchip powers 4 PetaFIOPS TE, 72 Arm CPUs connected by chip-to-chip link, 96 GB HBM3, and 576 GPUs of memory. Huang described it as the world’s first accelerated computer processor that also has giant memory: “this is a computer, not a chip.” It is designed for highly resilient data center applications.

8. If Grace Hopper’s memory isn’t enough, Nvidia has the solution: the DGX GH200. It is done by first connecting eight Grace Hoppers together with three NVLINK switches, then connecting the pods together at 900GB together. Then finally 32 are joined together, with another layer of switches, to connect a total of 256 Grace Hopper chips. The resulting ExaFLOPS Transformer Engine has 144TB GPU memory and performs like a giant GPU. Huang said that Grace Hopper is so fast that it can run the 5G stack in software. Google Cloud, Meta and Microsoft will be the first companies to have access to the DGX GH200 and will conduct research on its capabilities.

9. Nvidia and SoftBank partnered to introduce the Grace Hopper superchip into SoftBank’s new distributed data centers in Japan. They will be able to host wireless and generative AI applications on a common multi-tenant server platform, reducing costs and energy.

10. The SoftBank-Nvidia partnership will be based on the Nvidia MGX reference architecture, which is currently used in partnership with companies in Taiwan. It provides system builders with a modular reference architecture to help them build more than 100 server variations for AI, accelerated computing, and omniverse uses. Companies in the association include ASRock Rack, Asus, Gigabyte, Pegatron, QCT, and Supermicro.

11. Huang announced the Spectrum-X accelerated network platform to increase the speed of Ethernet-based clouds. It includes the Spectrum 4 switch, which has 128 ports of 400GB per second and 51.2T per second. The switch is designed to enable a new type of Ethernet, Huang said, and was designed end-to-end to perform adaptive routing, isolate performance and perform computation on the fabric. It also includes the Bluefield 3 Smart Nic, which connects to the Spectrum 4 switch to perform congestion control.

12. WPP, the world’s largest advertising agency, partnered with Nvidia to develop a content engine based on Nvidia Omniverse. It will be able to produce photo and video content to be used in advertising.

13. The Nvidia Isaac ARM robotics platform is now available to anyone who wants to build robots, and it’s a complete stack, from chips to sensors. Isaac ARM starts with a chip called Nova Orin and is the first complete robotics reference stack, Huang said.

Thanks largely to its prominence in AI computing, Nvidia’s stock has skyrocketed over the past year and it currently has a market valuation of around $960 billion, making it one of the most valuable companies in the world. world (only Apple, Microsoft, Saudi Aramco, Alphabet and Amazon are ranked higher).

Business in China in limbo

China’s AI companies are no doubt taking a close look at the next-generation silicon that Nvidia is bringing to the table. In the meantime, they probably fear another round of US chip bans that threaten to undermine their advancement in generative AI, which requires far more computing power and data than previous generations of AI.

The United States government last year restricted Nvidia to sell its A100 and H100 graphics processing units to China. Both chips are used to train large language models like OpenAI’s GPT-4. H100, its next-generation chip based on the Nvidia Hopper GPU computing architecture with its built-in transformer engine, is experiencing particularly strong demand. Compared to A100H100 can deliver 9x faster AI training and up to 30x faster AI inference in LLM.

Obviously, China is too big a market to miss out on. The chip export ban would cost Nvidia an estimated $400 million in potential sales in the third quarter of last year alone. nvidia like this resorted to selling China a slower chip that it complies with US export control rules. But in the long run, China will likely look to stronger alternatives, and the ban serves as a poignant reminder for China to achieve self-sufficiency in key technology sectors.

As Huang recently said in a interview with the Financial Times: “Yes [China] You can’t buy it from…the US, they’ll just build it themselves. So the United States has to be careful. China is a very important market for the technology industry.”