NVIDIA and the world’s premier computer manufacturers have unveiled advanced systems powered by NVIDIA’s Blackwell architecture, featuring Grace CPUs and NVIDIA networking, to support enterprises in constructing AI factories and data centers. This initiative aims to propel the next wave of generative AI breakthroughs, according to NVIDIA Newsroom.
COMPUTEX Keynote Highlights
During his COMPUTEX keynote, NVIDIA founder and CEO Jensen Huang announced collaborations with prominent industry players. Companies such as ASRock Rack, ASUS, GIGABYTE, Ingrasys, Inventec, Pegatron, QCT, Supermicro, Wistron, and Wiwynn are set to deliver cloud, on-premises, embedded, and edge AI systems utilizing NVIDIA GPUs and networking infrastructure.
Huang emphasized the dawn of the next industrial revolution, where companies and nations are partnering with NVIDIA to transform traditional data centers into accelerated computing hubs known as AI factories. These AI factories are set to produce artificial intelligence on a large scale.
Comprehensive Offerings
To cater to diverse application needs, the offerings range from single to multi-GPUs, x86 to Grace-based processors, and air to liquid cooling technologies. The NVIDIA MGX modular reference design platform now supports Blackwell products, including the new NVIDIA GB200 NVL2 platform, which is designed for mainstream large language model inference, retrieval-augmented generation, and data processing.
The GB200 NVL2 platform is particularly suitable for emerging markets such as data analytics, where companies invest billions annually. Leveraging high-bandwidth memory performance through NVLink®-C2C interconnects and dedicated decompression engines, Blackwell architecture enhances data processing speed by up to 18 times and improves energy efficiency by 8 times compared to x86 CPUs.
Modular Reference Architecture for Accelerated Computing
NVIDIA MGX provides a reference architecture for manufacturers to build over 100 system design configurations quickly and cost-effectively. This flexibility allows manufacturers to choose their GPU, DPU, and CPU to address various workloads. More than 90 systems from over 25 partners have been released or are in development, significantly up from 14 systems from six partners last year. Utilizing MGX can reduce development costs by up to three-quarters and shorten development time to just six months.
AMD and Intel are also supporting the MGX architecture, with plans to deliver their own CPU host processor module designs. These include the next-generation AMD Turin platform and the Intel® Xeon® 6 processor with P-cores (formerly codenamed Granite Rapids). These reference designs aim to save development time while ensuring design and performance consistency.
Ecosystem and Partner Contributions
NVIDIA’s comprehensive partner ecosystem includes TSMC, the world’s leading semiconductor manufacturer, and global electronics makers providing key components for AI factories. These components include server racks, power delivery, cooling solutions, and more from companies such as Amphenol, Asia Vital Components (AVC), Cooler Master, Colder Products Company (CPC), Danfoss, Delta Electronics, and LITEON.
This collaborative effort ensures that new data center infrastructure can be rapidly developed and deployed to meet global enterprise needs. Blackwell technology, along with NVIDIA Quantum-2, Quantum-X800 InfiniBand networking, NVIDIA Spectrum-X Ethernet networking, and NVIDIA BlueField®-3 DPUs, further accelerates this development.
Enterprises can also access the NVIDIA AI Enterprise software platform, which includes NVIDIA NIM inference microservices, to create and run production-grade generative AI applications.
Adoption in Taiwan
During his keynote, Huang highlighted that Taiwan’s leading companies are swiftly adopting Blackwell to integrate AI into their businesses. Chang Gung Memorial Hospital plans to use the NVIDIA Blackwell computing platform to advance biomedical research and enhance clinical workflows. Foxconn intends to develop smart solutions for AI-powered electric vehicles and robotics platforms, as well as generative AI services.
Image source: Shutterstock
. . .
Tags
Credit: Source link
