AMD Highlights LUMI Supercomputer: Europe’s Fastest, Powered by EPYC and Instinct

AMD´s EPYC CPUs and Instinct GPUs drive the LUMI supercomputer in Finland—now Europe´s fastest and advancing global research using sustainable energy.

The LUMI supercomputer, situated in Kajaani, Finland, represents a significant collaborative achievement by European nations in high-performance computing. Funded by the European High-Performance Computing Joint Undertaking (EuroHPC JU) along with resources from multiple consortium countries such as Finland, Belgium, the Netherlands, and others, LUMI serves as a central tool for scientific and technological advancements aimed at addressing major global challenges.

Ranked as the eighth fastest supercomputer in the world and the fastest in Europe on the Top500 list as of November 2024, LUMI delivers sustained computing performance at 380 petaflops—equivalent to the combined power of approximately 1.5 million high-end laptops. Its architecture is built on the HPE Cray EX platform and utilizes AMD´s EPYC CPUs and Instinct MI250X GPUs, enabling unparalleled processing speed crucial for demanding workloads in areas such as climate modeling, molecular research, and Artificial Intelligence.

LUMI is lauded not only for its computational prowess but also its commitment to energy efficiency and sustainability. According to the Green500 list, it ranks as the twenty-fifth most energy-efficient supercomputer globally. The system operates entirely on hydropower, and sophisticated heat recapture technology allows excess thermal output from the facility to provide heating for around 100 homes in Kajaani, contributing to a more sustainable local environment while powering research vital to Europe and the world.

70

Impact Score

Tsmc debuts A13 process technology

Tsmc has introduced its A13 process at its 2026 North America Technology Symposium as a tighter version of A14 aimed at next-generation Artificial Intelligence, high performance computing, and mobile designs. The company positions the node as a more compact and efficient option with backward-compatible design rules for faster migration.

Google unveils eighth-generation tensor processor units

Google introduced its eighth generation of custom tensor processor units with separate designs for training and inference. The new TPU 8t and TPU 8i are aimed at large-scale model training, serving, and agentic workloads.

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.