AMD unveils world's first 2nm GPU, the Instinct MI455X
AMD launches the world's first 2nm MI455X GPU and Helios AI rack, outperforming NVIDIA Vera Rubin with superior throughput and cost efficiency.
“AI Disruption” Publication 10,300 Subscriptions 20% Discount Offer Link.
Frontally challenging NVIDIA, Intel, and Arm.
Just now, at the annual AMD Advancing AI event, AMD Board Chair and CEO Dr. Lisa Su unleashed a series of major announcements, launching AMD’s most powerful AI chip—the Instinct MI455X GPU, the “most powerful agentic CPU” Venice, the “most powerful rack-scale AI infrastructure” Helios, and a Ryzen chip specially designed for robots.
Overall, AMD announced seven major releases today:
Rack-scale AI platform Helios
Server CPU “Venice”
Instinct MI400 series GPUs (including MI455X and MI430X)
Air-cooled PCIe GPU MI350P
AI software stack ROCm.ai
Local AI developer platform “Gorgon Halo”
Kria AI robotics system modules & developer platform
At the same time, Lisa Su unveiled the latest roadmaps for AMD’s GPUs, CPUs, and rack-scale AI infrastructure.
Among GPU products, the MI500 series is expected to launch next year, using next-generation HBM, supporting larger scale-up networks, and introducing new copper interconnect and optical interconnect technologies. The MI600 series is under development and scheduled for release in 2028.
The inference throughput of the next-generation MI500 will soar to more than 2,000 times that of the MI300X.
In server CPUs, the sixth-generation “Venice” released today is AMD’s first 2nm server CPU, the first to feature 512 threads and PCIe 6.0. The seventh-generation server CPU “Florence” will use a new process node and memory, with shipments expected in 2028. The eighth-generation “Ravenna” is under development, with shipments planned for 2030.
