AMD's EPYC Venice CPUs have entered volume production, making them the first HPC product to achieve the milestone on TSMC's 2nm process tech.

AMD & TSMC Enter Volume Production On The Industry's First 2nm HPC Chip, 6th Gen EPYC Venice

The Agentic AI boom is driving the CPU market up, unlike anything that came before. High-Performance CPUs are seeing massive demands, and AMD, being a leader in HPC, has just achieved volume ramp of its next-generation EPYC Venice CPUs based on the Zen 6 core architecture. The volume ramp was achieved on TSMC's cutting-edge 2nm process technology.

Looking ahead, AMD plans to achieve volume ramp for the same EPYC Venice CPUs at TSMC Arizona, further enhancing its manufacturing capacity to fulfill the demands of AI datacenters and Enterprises. AMD will also extend TSMC's 2nm process technology to its next-generation "AI-Focused" CPU called Verano, which is a version of Venice designed specifically for Agentic AI workflows and features the latest memory standards, such as LPDDR, providing the performance, bandwidth, and efficiency advantage for AI.

AMD and TSMC’s partnership spans the technologies needed to scale modern data center computing, from TSMC 2nm process technology for next-generation CPUs to advanced packaging technologies, including TSMC’s SoIC-X and CoWoS-L, used across AMD’s broader AI and data center portfolio. With “Venice” ramping on TSMC 2nm, AMD is advancing the CPU foundation for AI infrastructure while continuing to leverage TSMC’s process and packaging leadership to deliver increasingly integrated compute platforms at scale.

AMD

What We Know About AMD's EPYC Venice CPUs So Far

The 6th Gen AMD EPYC family will be codenamed Venice, and will feature the Zen 6 core architecture. AMD's EPYC Venice CPUs will offer over 70% improvement in performance and efficiency. This is quite massive and shows us what Zen 6 is capable of, even if this lineup only represents the server segment. In addition to the performance and efficiency improvement, AMD's EPYC Venice CPUs will also offer over 30% improvement in thread density.

These CPUs will come in two options: classic 96-core and denser 256-core variant. The 256-core and 512-thread processors mark a 33.3% improvement versus the existing Turin lineup, which maxes out at 192 cores and 384 threads.

We should now roll back to the >70% performance and efficiency improvement. These numbers are solid since a 33.3% increase just from the core count increase is represented, but the rest should come from IPC, clock rate, and other architectural improvements.

The TSMC 2nm process technology transitions from FinFET to Nanosheet transistors (GAA), and offers 10-15% higher performance at the same power, 25-30% lower power consumption at the same performance, and up to 15% higher transistor density.

AMD is set to have a heated battle later this year as other firms also gear up to release their own CPUs to address the growing Agentic AI demands. We have seen NVIDIA claiming to become the leading CPU supplier in 2026 with its Vera CPU, racking in an estimated $20 billion in revenue, the Arm AGI CPU, and Intel doubling down on its own CPU efforts.

Given AMD's close relations with TSMC, and since Lisa Su herself made a surprise visit to Taiwan, ahead of Computex 2026, reported to secure 2nm capacity for its EPYC Venice CPU, followed by the multi-billion dollar investment across various Taiwanese firms, and then the announcement by TSMC itself, AMD is looking very strong as it enters a contested CPU space.

But in all of this, volume and supply matter, and regardless of the chip, whoever provides the most volume is going to be the winner in the Agentic AI race.

Follow Wccftech on Google to get more of our news coverage in your feeds.