Nvidia Unveils ‘Grace’ ARM-based CPU
During the Nvidia GTC 2021 event, company CEO Jensen Huang showed off the new magic machine that does magic things. Huang then pointed up at a graph which proved that their magic thing is much better than corporation B’s magic thing. I walked away from the event moved, starstruck and determined. My wallet pangs for magic machine. I must have magic machine!
Am I calm? Okay, let’s jump back into the products. We do love those “products,” am I right, people? Huang actually showed off Nvidia’s newest ARM-based CPU. This sleek hunk won’t fit into your PC’s motherboard though. ARM-based machines are used for training and perfecting AI systems.
The CPU is called Grace, and Grace is used for training AI models and running ARM cores as efficiently as possible. “Grace is a breakthrough CPU. It’s purpose-built for accelerated computing applications of giant scale for AI and HPC,” said Senior Director of Product (product!!) management Paresh Kharya
Huang later confirmed that Grace is the first CPU capable of terabyte scale computing. “Leading-edge AI and data science are pushing today’s computer architecture beyond its limits — processing unthinkable amounts of data,” he said in his keynote. “Using licensed ARM IP, Nvidia has designed Grace as a CPU specifically for giant-scale AI and HPC. Coupled with the GPU and DPU, Grace gives us the third foundational technology for computing and the ability to re-architect the data-center to advance AI. Nvidia is now a three-chip company.”
I don’t know about you people, but me? I am hungry for some products.