Nvidia lays out its three-chip data center roadmap
In his GTC keynote, CEO Jensen Huang previewed what's to come from Nvidia's growing data center business, as well as its new Arm partnerships
In his GTC keynote, CEO Jensen Huang previewed what's to come from Nvidia's growing data center business, as well as its new Arm partnerships
Code-named "Ice Lake," the 10 nanometer-based CPU delivers up to 40 cores per processor.
The GPU maker beat Q4 market expectations with record sales in its two key areas of business.
With leadership performance, all-day battery life, and a modern approach to security, AMD Ryzen PRO 4000 processors are setting a new standard for business PCs.
AMD CEO Lisa Su announced the Vega-based processor as "the most powerful gaming GPU we have ever built."
The chipmaker already dominates the market for training deep neural networks. At its annual GPU Technology Conference, Nvidia made the case for using GPUs not only to train ever bigger models, but also to run these neural networks in data centers to revolutionize industries.
A recent tour of the company's remarkable fab in upstate New York illustrated both how far the foundry has come and how challenging the future will be for advanced chipmakers.
The private preview is slated for NXP's i.MX 6 and i.MX 7 processors.
The semiconductor giant posted revenue of $2.23 billion, with datacenter revenue up year-over-year by more than two and a half times.
At Hot Chips this week, Nvidia announced details of its next-gen Tegra processor, known as "Parker," while others argued that digital signal processors can do the job better. All of them are vying to power emerging applications such as self-driving cars, drones, VR and augmented reality, and smart cameras.