Cutting-Edge Technology The World's First Photonic AI Computer is Running at the Leibniz Computing Center

From Q.Ant | Translated by AI 1 min Reading Time

Related Vendors

Q.Ant has delivered its Native Processing Server (NPS) to the Leibniz Computing Center (LRZ). It is said to be the world's first co-processor in a high-performance computing (HPC) environment.

What once began after World War II with wardrobe-sized computers is now starting again in these dimensions as the most modern form of computing. At the Leibniz Computing Center (LZR) in Garching, the world's first photonic AI computer was launched ...(Image: Q.Ant)
What once began after World War II with wardrobe-sized computers is now starting again in these dimensions as the most modern form of computing. At the Leibniz Computing Center (LZR) in Garching, the world's first photonic AI computer was launched ...
(Image: Q.Ant)

Calculating with light instead of electricity was long considered science fiction, but it is now becoming reality in Bavaria, Germany. For the first time, a photonic AI server is in use in Garching, which requires around 90% less energy per application while delivering 100 times the performance of other computing systems. According to the deep-tech company Q.Ant, the technically groundbreaking implementation of the NPS allows the Leibniz Supercomputing Center (LZR) to evaluate photonic acceleration for artificial intelligence (AI) and simulations. This paves the way for significantly higher computing power with substantially reduced energy requirements, as the AI era demands a lot of computing power with an increasing trend. The LZR is one of the largest supercomputing centers in Europe and drives cutting-edge research projects with its infrastructure. The collaboration between Q.Ant and the LZR demonstrates how data centers could harmonize performance, space requirements, energy efficiency, and system architecture in the future.

These Features also Characterize Photonic Computers ...

As the partners emphasize, this marks the beginning of a new chapter in data processing, where analog precision powered by light provides solutions to the scaling challenges of today's AI infrastructures. Other compelling features of the photonic Q.Ant computer include 16-bit floating-point precision with nearly 100% accuracy for all computing operations on the chip and seamless integration via PCIe interface, x-86 compatibility, as well as support for Pytorch, Tensorflow, and Keras, as noted further. In the first evaluation phase at the LZR, several units of the latest generation of the Q.Ant NPS will be installed, suitable benchmark workloads will be selected, and real application scenarios will be tested—particularly in the areas of AI inference, computer vision, and physics simulations. In later phases, second- and third-generation NPS units will be deployed for more in-depth evaluations.

Subscribe to the newsletter now

Don't Miss out on Our Best Content

By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

Unfold for details of your consent