Photonic Processor for energy-efficient High-Performance Computing and real-time AI Applications available as industry-standard PCI Express Card
The Q.ANT Native Processing Unit NPU, the first commercially available photonic processor, sets a new era, going beyond traditional computing. With the promise to deliver up to 30 times the energy efficiency of conventional CMOS technologies, the system reduces operational costs and the environmental impact of data centers significantly. The product is fully compatible with the computing ecosystem as it comes on the industry-standard PCI Express card. Experience the platform powered by light instead of electrons, where complex mathematical models for AI training and inference, machine learning, physics simulations and time-series analysis can be executed with exceptional performance. Q.ANT tackles complex functions at their core by using native operations of light. That’s why we call it Native Computing.
30x Energy Efficiency
Seize the exclusive opportunity to experience Q.ANT’s first commercial Photonic AI Accelerator, promising to set new standards in energy efficiency and computational speed. Test, innovate, and get hands-on with a technology that promises a sustainable and powerful future. Redefine the possibilities of AI processing – where cutting-edge efficiency meets the brilliance of light.
The Native Processing Server NPS as 19″ rack-mountable server with our photonic NPU PCIe card is designed specifically for AI inference and advanced data processing. Its Plug & Play system design makes it ready to be integrated in datacenters and HPCs for immediate access to photonic computing. The NPS is upgradable with additional NPU PCIe cards for even more processing power in the future.
| System / Subsystem | Feature |
| System node | x86 processor architecture; based 19” 4U commercially available rack system |
| Operating System | Linux Debian/Ubuntu with Kernel Version 5 |
| Network interface | Ethernet with up to 10 Gbit speed |
| Software interface | Python library functions; upgradable to HPC job submission |
| API to subsystem | Linux device driver |
| Native Processing Unit NPU |
|
| Power consumption of NPU | 30 W |
| Photonic integrated circuit (PIC) | Ultrafast photonic core based on z-cut Lithium Niobate on Insulator (LNoI) |
| Throughput of NPU | 100 MOps |
| Cooling of NPU | Passive |
| Operating temperature range | 15 to 35°C |
As an analog computing unit, the NPU enables the solution of complex, non-linear mathematical functions that would be too energy-intensive to calculate on conventional processors. Initial applications are in the field of AI inference and AI training, paving the way for efficient and sustainable AI computing. Start programming the Q.ANT NPU using our custom Software Development Kit, called the Q.ANT Toolkit. This interface enables users to operate directly at the chip level or to leverage higher level optimized neural network operations, such as fully connected layers or convolutional layers to build your AI model. The Toolkit offers a comprehensive collection of example applications that illustrate how AI models can be programmed. These examples can be used directly or as a foundation for creating own implementations.
| Name | Description | Programming Language |
| Digit Recognition | Determination of the number shown in a picture (based on the MNIST data set) | Python (Jupyter) |
| Matrix Multiplication | Multiplication of a matrix and a vector | Python / C++ |
| Speech Recognition (coming soon) | Recognition of spoken English words (based on LibriSpeech data set) | Python (Jupyter) |
| Semantic Segmentation (coming soon) | Segmentation of an image (based on the KITTI data set) | Python (Jupyter) |
Run ever larger generative models at fraction of the cost, pushing the bounderies of computer’s ability to understand natural language, and create content like text, images and videos by leveraging advanced machine learning models.
Enhance healthcare by improving diagnosis of diseases and aiding discovery of completely new classes of medicine as well as personalized medicine using more complex photonic AI models.
Improve quality of life using low power AI-driven automation in smart factories and self-driving cars by performing mundane tasks, optimizing workflows and enhancing efficiency.
We provide complimentary access to the Gartner® Hype Cycle™ for Compute 2024 report. Learn how Photonic Computing can transform future business and society.
Thin Film Lithium Niobate on Insulator TFLNoI – The Optimal Material Choice for Photonic Integrated Circuits PIC. Q.ANT relies on our proprietary material platform for making the photonic chips inside the NPU. The central components in the PIC are optical waveguides, modulators and various other building blocks, which enable high-speed and precise control of light, all integrated in a single chip at nanoscopic level. In this chip, a very thin layer of lithium niobate is bonded on a silicon wafer, on which the photonic components are fabricated. We believe that TFLNoI is the key to the future of photonic computing.
PICs based on TFLNoI show several main advantages:
At the heart of photonic processors are photonic chips that perform calculations. In this process, photons deliver huge computing power.
These guide tiny particles of light (photons) through conductive paths.
This beams classical light waves into the waveguide.
The photons are manipulated through the building blocks on the chip, as i.e. modulators or resonators.
This occurs on the waveguide at the narrow points, also called beam splitters. It means that photons can pass into the other waveguide.
This is used to read out the information that the photons carry.
These control the interaction of photons and calculate previously unsolvable tasks.
SVP Native Computing
I look forward to discussing the potentials of Photonic Computing with you.
We look forward to explore and discuss the potential of our Native Processing Server NPS for your application. Please fill in this contact form and we will contact you shortly.
Q.ANT is in the German experts consortium lead of the LichtBriQ project, funded by the Bundesministerium für Bildung und Forschung BMBF. The project has been [...]
Available Now: Q.ANT’s first Native Processing Unit is poised to provide at least 30x energy efficiency improvements and substantial performance boost bringing Data Center sustainability [...]
Research cooperation between federal company and Stuttgart-based high-tech start-up Stuttgart, 27. June 2023 – Quantum chips working with light may play a central role on [...]
Q.ANT GmbH
Handwerkstr. 29
70565 Stuttgart
Germany
We provide exclusive access to the Gartner® Hype Cycle™ for Compute 2024 report. Learn how Photonic Computing can transform future business and society.
