NVIDIA is entering the CPU market with an Arm-based processor that will be tightly integrated with its next-generation GPUs. The Grace CPU seeks to bring new levels of power and efficiency to massive AI workloads, and offer a high-end alternative to Intel x86 CPUs.
The growing adoption of artificial intelligence (AI) poses challenges for data center design, as high-density racks of GPUs require low-latency access to massive datasets, including some in the cloud.
NVIDIA has unveiled a new generation of its GPU technology designed to further shake up the world of AI computing. Here’s a look at the DGX A100 system, and what it may mean for the data center.
In a sign of strengthening demand for water-cooled racks, high-density hosting specialist Colovore has fully pre-leased a 2 megawatt expansion of its Santa Clara data center.
Avitas Systems’ drone inspection service is bringing AI data-crunching to remote locations with the NVIDIA DGX Station “supercomputer in a box.”
The rise of specialized computing is bringing powerful new server hardware into the data center, a trend seen in new tech from Google, NVIDIA, AMD, ARM, Intel and Microsoft.
The rise of artificial intelligence, and the GPU computing hardware that often supports it, is reshaping the data center industry’s relationship with power density.