On Sunday, Nvidia CEO Jensen Huang reached past Blackwell and revealed the corporate’s next-generation AI-accelerating GPU platform throughout his keynote at Computex 2024 in Taiwan. Huang additionally detailed plans for an annual tick-tock-style improve cycle of its AI acceleration platforms, mentioning an upcoming Blackwell Extremely chip slated for 2025 and a subsequent platform referred to as “Rubin” set for 2026.
Nvidia’s knowledge heart GPUs at the moment energy a big majority of cloud-based AI fashions, corresponding to ChatGPT, in each improvement (coaching) and deployment (inference) phases, and buyers are protecting a detailed watch on the corporate, with expectations to maintain that run going.
In the course of the keynote, Huang appeared considerably hesitant to make the Rubin announcement, maybe cautious of invoking the so-called Osborne impact, whereby an organization’s untimely announcement of the following iteration of a tech product eats into the present iteration’s gross sales. “That is the very first time that this subsequent click on as been made,” Huang mentioned, holding up his presentation distant simply earlier than the Rubin announcement. “And I am undecided but whether or not I’ll remorse this or not.”
Nvidia Keynote at Computex 2023.
The Rubin AI platform, anticipated in 2026, will use HBM4 (a brand new type of high-bandwidth reminiscence) and NVLink 6 Swap, working at 3,600GBps. Following that launch, Nvidia will launch a tick-tock iteration referred to as “Rubin Extremely.” Whereas Huang didn’t present in depth specs for the upcoming merchandise, he promised price and vitality financial savings associated to the brand new chipsets.
In the course of the keynote, Huang additionally launched a brand new ARM-based CPU referred to as “Vera,” which can be featured on a brand new accelerator board referred to as “Vera Rubin,” alongside one of many Rubin GPUs.
Very like Nvidia’s Grace Hopper structure, which mixes a “Grace” CPU and a “Hopper” GPU to pay tribute to the pioneering laptop scientist of the identical title, Vera Rubin refers to Vera Florence Cooper Rubin (1928–2016), an American astronomer who made discoveries within the subject of deep area astronomy. She is finest identified for her pioneering work on galaxy rotation charges, which supplied robust proof for the existence of darkish matter.
A calculated threat
Nvidia’s reveal of Rubin will not be a shock within the sense that the majority huge tech corporations are constantly engaged on follow-up merchandise properly prematurely of launch, however it’s notable as a result of it comes simply three months after the corporate revealed Blackwell, which is barely out of the gate and never but extensively delivery.
In the meanwhile, the corporate appears to be comfy leapfrogging itself with new bulletins and catching up later; Nvidia simply introduced that its GH200 Grace Hopper “Superchip,” unveiled one 12 months in the past at Computex 2023, is now in full manufacturing.
With Nvidia inventory rising and the corporate possessing an estimated 70–95 p.c of the info heart GPU market share, the Rubin reveal is a calculated threat that appears to come back from a spot of confidence. That confidence may turn into misplaced if a so-called “AI bubble” pops or if Nvidia misjudges the capabilities of its rivals. The announcement may additionally stem from stress to proceed Nvidia’s astronomical progress in market cap with nonstop guarantees of bettering know-how.
Accordingly, Huang has been desperate to showcase the corporate’s plans to proceed pushing silicon fabrication tech to its limits and extensively broadcast that Nvidia plans to maintain releasing new AI chips at a gradual cadence.
“Our firm has a one-year rhythm. Our primary philosophy could be very easy: construct all the knowledge heart scale, disaggregate and promote to you elements on a one-year rhythm, and we push the whole lot to know-how limits,” Huang mentioned throughout Sunday’s Computex keynote.
Regardless of Nvidia’s latest market efficiency, the corporate’s run might not proceed indefinitely. With ample cash pouring into the info heart AI area, Nvidia is not alone in creating accelerator chips. Rivals like AMD (with the Intuition collection) and Intel (with Gaudi 3) additionally wish to win a slice of the info heart GPU market away from Nvidia’s present command of the AI-accelerator area. And OpenAI’s Sam Altman is attempting to encourage diversified manufacturing of GPU {hardware} that can energy the corporate’s subsequent era of AI fashions within the years forward.
