Second is the GX350a Accelerated Blade, designed for customers who desire a universal compute engine for mixed-precision ...

Promised for 2027 racks, mixing Nvidia and AMD silicon in one liquid-cooled box HPE's next-gen Cray supercomputing platform ...

Supermicro showcased advanced AI infrastructure at NVIDIA GTC, highlighting systems tailored to meet the requirements of federal customers.

Nvidia has reportedly confirmed it will use Samsung Electronics' fifth-generation high-bandwidth memory (HBM3E) in its latest AI accelerator, the GB300. Additionally, Samsung plans to purchase 50,000 ...

The big picture: The growing popularity of generative AI technology underscores a critical challenge for today's hardware platforms. Powerful AI models often need to move massive amounts of data, ...

The deal between the chipmakers, whose fortunes have diverged sharply, includes plans to collaborate on technology to power artificial intelligence. By Adam Satariano and Tripp Mickle Nvidia, the ...

Nvidia Corp. shares fell Wednesday, reflecting investor concerns over a report saying that China had banned technology companies in the country from buying the company’s artificial-intelligence chips.

Nvidia has unveiled the full specifications of its flagship professional AI accelerator, the Blackwell Ultra GB300. Set to replace the existing GB200, it has more cores, a lot more memory, faster I/O, ...

Jensen Huang, the chipmaker’s chief executive, is trying to balance his company’s interests as the United States and China compete for supremacy in artificial intelligence. By Keith Bradsher and ...

What would you like to be added: The HAMi scheduler logs contain information about multiple GPU device vendors, even though my environment only uses NVIDIA GPUs. For example, the following log entries ...

Data Flows: Nvidia developed NVLink in 2014 as an alternative technology for connecting GPUs and other computing elements in servers and data centers. Unlike PCI Express, NVLink-connected devices use ...

Nvidia Corp. Chief Executive Officer Jensen Huang outlined plans to let customers deploy rival chips in data centers built around its technology, a move that acknowledges the growth of in-house ...