NVIDIA says its new H100 datacenter GPU is up to six times faster than its last

Partway by final yr, NVIDIA introduced , its first-ever datacenter CPU. On the time, the corporate solely shared a number of tidbits of details about the chip, noting, for example, it might make the most of its to offer knowledge switch speeds of as much as 900 GB/s between elements. Quick ahead to the 2022 GPU Expertise Convention, which kicked off on Tuesday morning. On the occasion, CEO Jensen Huang unveiled the Grace CPU Superchip, the primary discrete CPU NVIDIA plans to launch as a part of its Grace lineup.

Constructed on ARM’s lately launched , the Grace CPU Superchip is definitely two Grace CPUs linked through the corporate’s aforementioned NVLink interconnect expertise. It integrates a staggering 144 ARM cores right into a single socket and consumes roughly 500 watts of energy. Extremely-fast LPDDR5x reminiscence constructed into the chip permits for bandwidth speeds of as much as 1 terabyte per second.

Whereas they’re very totally different chips, a helpful method to conceptualize NVIDIA’s new silicon is to consider Apple’s lately introduced. In the most straightforward phrases, the M1 Extremely is made up of two M1 Max chips linked through Apple’s aptly named UltraFusion expertise.

When NVIDIA begins transport the Grace CPU Superchip to shoppers just like the Division of Vitality within the first half of 2023, it would supply them the choice to configure it both as a standalone CPU system or as a part of a server with as much as eight Hopper-based GPUs (extra on these in only a second). The corporate claims its new chip is twice as quick as conventional servers. NVIDIA estimates it would obtain a rating of roughly 740 factors in SPECrate®2017_int_base benchmarks, placing it within the higher echelon knowledge heart processors.

Alongside the Grace CPU Superchip, NVIDIA introduced its extremely anticipated . Named after pioneering pc scientist, it’s the successor to the corporate’s present (you already know, the one which powers the entire firm’s impossible-to-find RTX 30 sequence GPUs). Now earlier than you get excited, know that NVIDIA did not announce any mainstream GPUs at GTC. As a substitute, we bought to see the . It is an 80 billion transistor behemoth constructed utilizing TSMC’s cutting-edge 4nm course of. On the coronary heart of the H100 is NVIDIA’s new Transformer Engine, which the corporate claims permits it to supply unparalleled efficiency when it must compute transformer fashions. Over the previous few years, transformer fashions have change into broadly fashionable with AI scientists working with techniques like GPT-3 and AlphaFold. NVIDIA claims the H100 can cut back the time it takes to coach massive fashions right down to days and even mere hours. The H100 will probably be out there later this yr.

All merchandise really useful by Engadget are chosen by our editorial group, unbiased of our mother or father firm. A few of our tales embody affiliate hyperlinks. In the event you purchase one thing by certainly one of these hyperlinks, we might earn an affiliate fee.

Sharing Is Caring:

Leave a Comment