In his first live keynote since the pandemic, NVIDIA founder and CEO Jensen Huang today kicked off the COMPUTEX conference in Taipei, announcing platforms that companies can use to ride a historic wave of generative AI that's transforming industries from advertising to manufacturing to telecom.We're back, Huang roared as he took the stage after years of virtual keynotes, some from his home kitchen. I haven't given a public speech in almost four years - wish me luck!
Speaking for nearly two hours to a packed house of some 3,500, he described accelerated computing services, software and systems that are enabling new business models and making current ones more efficient.
Accelerated computing and AI mark a reinvention of computing, said Huang, whose travels in his hometown over the past week have been tracked daily by local media.
In a demonstration of its power, he used the massive 8K wall he spoke in front of to show a text prompt generating a theme song for his keynote, singable as any karaoke tune. Huang, who occasionally bantered with the crowd in his native Taiwanese, briefly led the audience in singing the new anthem.
We're now at the tipping point of a new computing era with accelerated computing and AI that's been embraced by almost every computing and cloud company in the world, he said, noting 40,000 large companies and 15,000 startups now use NVIDIA technologies with 25 million downloads of CUDA software last year alone.
Top News Announcements From the Keynote
Grace Hopper powers big-memory supercomputers for gen AI.
Modular reference architecture enables 100+ accelerated server variations.
WPP, NVIDIA create digital ad content engine in Omniverse.
SoftBank, NVIDIA build 5G, gen AI data centers in Japan.
Networking technology accelerates Ethernet-based AI clouds.
NVIDIA ACE for Games breathes life into characters with gen AI.
Electronics manufacturers worldwide embrace NVIDIA AI.
A New Engine for Enterprise AI For enterprises that need the ultimate in AI performance, he unveiled DGX GH200, a large-memory AI supercomputer. It uses NVIDIA NVLink to combine up to 256 NVIDIA GH200 Grace Hopper Superchips into a single data-center-sized GPU.
The GH200 Superchip, which Huang said is now in full production, combines an energy-efficient NVIDIA Grace CPU with a high-performance NVIDIA H100 Tensor Core GPU in one superchip.
The DGX GH200 packs an exaflop of performance and 144 terabytes of shared memory, nearly 500x more than in a single NVIDIA DGX A100 320GB system. That lets developers build large language models for generative AI chatbots, complex algorithms for recommender systems, and graph neural networks used for fraud detection and data analytics.
Google Cloud, Meta and Microsoft are among the first expected to gain access to the DGX GH200, which can be used as a blueprint for future hyperscale generative AI infrastructure.
NVIDIA's DGX GH200 AI supercomputer delivers 1 exaflop of performance for generative AI. DGX GH200 AI supercomputers integrate NVIDIA's most advanced accelerated computing and networking technologies to expand the frontier of AI, Huang told the audience in Taipei, many of whom had lined up outside the hall for hours before the doors opened.
NVIDIA is building its own massive AI supercomputer, NVIDIA Helios, coming online this year. It will use four DGX GH200 systems linked with NVIDIA Quantum-2 InfiniBand networking to supercharge data throughput for training large AI models.
The DGX GH200 forms the pinnacle of hundreds of systems announced at the event. Together, they're bringing generative AI and accelerated computing to millions of users.
Zooming out to the big picture, Huang announced more than 400 system configurations are coming to market powered by NVIDIA's latest Hopper, Grace, Ada Lovelace and BlueField architectures. They aim to tackle the most complex challenges in AI, data science and high performance computing.
Acceleration in Every Size To fit the needs of data centers of every size, Huang announced NVIDIA MGX, a modular reference architecture for creating accelerated servers. System makers will use it to quickly and cost-effectively build more than a hundred different server configurations to suit a wide range of AI, HPC and NVIDIA Omniverse applications.
MGX lets manufacturers build CPU and accelerated servers using a common architecture and modular components. It supports NVIDIA's full line of GPUs, CPUs, data processing units (DPUs) and network adapters as well as x86 and Arm processors across a variety of air- and liquid-cooled chassis.
QCT and Supermicro will be the first to market with MGX designs appearing in August. Supermicro's ARS-221GL-NR system announced at COMPUTEX will use the Grace CPU, while QCT's S74G-2U system, also announced at the event, uses Grace Hopper.
ASRock Rack, ASUS, GIGABYTE and Pegatron will also use MGX to create next-generation accelerated computers.
5G/6G Calls for Grace Hopper Separately, Huang said NVIDIA is helping shape future 5G and 6G wireless and video communications. A demo showed how AI running on Grace Hopper will transform today's 2D video calls into more lifelike 3D experiences, providing an amazing sense of presence.
Laying the groundwork for new kinds of services, Huang announced NVIDIA is working with telecom giant SoftBank to build a distributed network of data centers in Japan. It will deliver 5G services and generative AI applications on a common cloud platform.
The data centers will use NVIDIA GH200 Superchips and NVIDIA BlueField-3 DPUs in modular MGX systems as well as NVIDIA Spectrum Ethernet switches to deliver the highly precise timing the 5G protocol requires. The platform will reduce cost by increasing spectral efficiency while reducing energy consumption.
The systems will help SoftBank explore 5G
