NVIDIA's AI Supercomputers Get a Massive Upgrade

NVIDIA (NASDAQ: NVDA) announced on Monday that its A100 graphics processing unit (GPU) -- the chip designed specifically for artificial intelligence (AI), high-performance computing (HPC), and analytics use cases -- just got a significant upgrade. The latest version of the A100 now has double the memory of its predecessor, "providing researchers and engineers unprecedented speed and performance to unlock the next wave of AI and scientific breakthroughs."

The newest edition boasts an 80 GB GPU, twice the 40 GB available in the previous version. The high-speed chip powers NVIDIA's HGX AI supercomputing platform -- a turnkey AI processor in a box. The company touts the A100 as "the world's fastest data center GPU." The chip will also be found at the core of NVIDIA DGX A100 and DGX Station A100 systems, the company's other AI supercomputers, both of which launched today and are expected to ship this quarter.

Image source: NVIDIA.

Source Fool.com