- AMD positions MI450 as its no asterisk generation aimed at AI leadership
- Company compares future GPU launch to 2021 Milan CPUs breaking Intel’s dominance
- Nvidia remains overwhelmingly ahead with Rubin set to challenge MI450 in 2026
AMD has made a startlingly confident claim regarding its upcoming Instinct MI450 GPUs.
Speaking at a recent investor conference, data center chief Forrest Norrod declared the firm’s new chips will outperform any rival hardware, including Nvidia’s Rubin Ultra.
He described the product as the company’s “no asterisk generation,” aimed at delivering leadership in both AI training and inference.
Milan moment
Norrod compared the launch to AMD’s 2021 “Milan moment,” when its EPYC server CPUs helped the company break Intel’s dominance in the server market.
“MI450 is perhaps akin to our Milan moment for people that are familiar with our EPYC roadmap,” he said. “It will be, we believe, and we are planning for it to be the best training, inference, distributed inference, reinforcement learning solution available on the market.”
The MI450 will follow the current MI355, which is intended to strengthen training capabilities after earlier models were primarily optimized for inference.
AMD says that the new generation has been designed with both silicon and software improvements in mind, alongside full system-level support.
Norrod stressed that the hardware and software roadmap had been carefully staged to deliver competitiveness at every step.
At present, Nvidia utterly dominates the AI accelerator market, with estimates placing its share between 70 and 95 percent.
AMD’s most advanced GPU today, the MI355X, still lags behind Nvidia’s Blackwell Ultra, although it shows clear progress over its predecessor.
The MI450 is expected to launch in 2026, arriving as Nvidia readies Rubin, which is forecast to deliver up to triple the performance of Blackwell Ultra. That will set up a direct test of AMD’s claims.
Although the chip giant is describing the future launch as a turning point, history suggests customer adoption will depend not just on raw speed but also on software ecosystem maturity and data center integration.
This is something AMD is preparing for, as it has already said that the MI450 will ship with rack-level solutions designed for compatibility with existing infrastructure.
Acknowledging Nvidia’s current dominance, Norrod said, “Nvidia is a fantastic company. They’ve done a fantastic job, and they were well ahead. We had to catch up.”
He added, “We decided, with this multigenerational roadmap, to put the objective in place of, okay, when we get to 450, we’re going to be there the same time as when Vera Rubin was intended to be there, and we’re going to be there with that part that’s fully performant, the software stack that’s fully there, at least for the 80% of the market that’s constituted by the top 20% or so customers. We’ve focused on getting there in the 450 so that for training, there’s no excuses, and there’s no impediment, there’s no hesitation of, hey, if I’m training, I’ll be behind in this generation if I go with AMD. That’s been the learning for us, and that’s been the realization.”
