AMD Tapes Out Industry’s First 2nm HPC Silicon in Partnership with TSMC

AMD reveals its upcoming EPYC ´Venice´ as the world´s first HPC processor on TSMC´s cutting-edge 2nm process, reinforcing its leadership in data center tech and U.S. semiconductor manufacturing.

AMD has unveiled a significant technological milestone with the successful tape-out and bring-up of its next-generation EPYC processor, codenamed ´Venice,´ as the first high-performance computing (HPC) product in the industry to utilize the advanced TSMC 2 nm (N2) process technology. This achievement showcases the deep collaborative efforts between AMD and TSMC to co-optimize new processor architectures with the latest fabrication techniques. The ´Venice´ processor’s successful tape-out not only marks a leap forward on AMD’s data center CPU roadmap but also demonstrates both companies’ shared vision for leadership in high-performance and energy-efficient computing solutions.

The partnership between AMD and TSMC has been pivotal for both companies, with TSMC providing the manufacturing backbone for AMD’s most advanced silicon products. AMD’s Chair and CEO, Dr. Lisa Su, emphasized the longstanding collaboration, crediting joint research and development as well as manufacturing initiatives with enabling AMD to consistently achieve breakthrough performance in its product lines. She highlighted the significance of being a flagship customer for TSMC’s N2 process as well as a key client for the newly commissioned TSMC Arizona Fab 21, further cementing AMD’s role at the forefront of next-generation semiconductor innovation.

In addition to the progress with ´Venice,´ AMD announced the successful validation and launch readiness of its 5th Generation EPYC CPUs produced at TSMC’s Arizona manufacturing facility. This move underscores AMD’s ongoing commitment to domestic U.S. silicon production, which is increasingly important for supply chain resilience and strategic technology leadership. With the anticipated launch of ´Venice´ next year, AMD aims to set new industry benchmarks for data center processing power, efficiency, and scalability, reinforcing its long-term commitment to powering the future of computing, including workloads in scientific research, Artificial Intelligence, and enterprise data centers.

78

Impact Score

Ex Parte Desjardins reshapes Artificial Intelligence patent eligibility

A precedential PTAB decision and two USPTO memoranda have clarified how Artificial Intelligence inventions can qualify for patent protection under 35 U.S.C. § 101. The guidance gives applicants a clearer path to showing technical improvements in machine learning systems and computer performance.

Why opinion on Artificial Intelligence is so divided

Stanford’s 2026 Artificial Intelligence Index highlights a sharp disconnect between rapid technical progress and uneven real-world performance. That split is also visible in how experts and the public judge Artificial Intelligence’s impact on jobs, the economy, and daily life.

Stanford report charts the rapid rise of Artificial Intelligence

Stanford’s 2026 index portrays Artificial Intelligence as a fast-improving technology spreading through business, education, and daily life faster than past computing shifts. It also highlights mounting pressure on energy, jobs, benchmarking, and regulation as governments and researchers struggle to keep pace.

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.