AMD confirms Zen 6 (2 nm) and Zen 7 with efficiency and Artificial Intelligence upgrades

AMD's updated roadmap reveals Zen 6 will arrive next year on TSMC's 2 nm node with performance and efficiency variants and expanded Artificial Intelligence support, while Zen 7 is listed for the first time as a next-generation design with a new matrix engine.

AMD updated its CPU core roadmap at Financial Analyst Day 2025, confirming Zen 6 as the next major architecture and listing Zen 7 as a future generation. Zen 6 is slated to launch next year and will be manufactured on TSMC’s 2 nm process node. The lineup will include both Zen 6 and Zen 6C variants, with the former optimized for high performance and the latter tuned for power efficiency.

According to AMD chief technology officer Mark Papermaster, Zen 6 will deliver higher instructions per clock, improved power efficiency, and expanded Artificial Intelligence data type support with additional Artificial Intelligence pipelines. Early information about Zen 6 also notes initial instruction set architecture changes that introduce new instruction sets and broaden compute capabilities. AMD plans to deploy Zen 6 across multiple platforms, including EPYC “Venice,” Ryzen desktop “Olympic Ridge,” and Ryzen mobile “Medusa Point.”

For the first time AMD also listed Zen 7 on the roadmap as a “Future Node” and “Next-Generation” design. Zen 7 is described as introducing a new matrix engine and broadening Artificial Intelligence data format handling, signaling deeper Artificial Intelligence integration within standard CPU cores. AMD did not disclose a specific process node or exact launch window for Zen 7, though the architecture is expected to follow Zen 6 and appear around 2027 in next-generation EPYC “Verano” processors. No further details were provided on cache layout, core counts, or power targets, leaving those specifics to future announcements.

58

Impact Score

RenderFormer: how neural networks are reshaping 3D rendering

RenderFormer, from Microsoft Research, is the first model to show that a neural network can learn a complete graphics rendering pipeline. It is designed to support full-featured 3D rendering using only machine learning and no traditional graphics computation.

Artificial Intelligence improves diagnosis of invisible airway blockages

Researchers at the University of Southampton developed an Artificial Intelligence tool that detects radiolucent foreign bodies on chest CT scans more reliably than experienced radiologists. The model combines an airway mapping technique with a neural network and was validated against bronchoscopy-confirmed cases.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.