20 Nov 2024
...and Fraunhofer IAF orders “first in Europe” quantum accelerator from Quantum Brilliance.
Q.ANT, a startup developing technologies for photonic computing, has announced the launch of its first commercial product – a photonics-based Native Processing Unit (NPU) based on the company’s compute architecture LENA; light-empowered native arithmetics.The product is fully compatible with today’s existing computing ecosystem as it comes on the industry-standard PCIExpress. The Q.ANT NPU can execute complex, non-linear mathematics natively using photons instead of electrons, and specified to deliver at least 30 times greater energy efficiency and significant computational speed improvements over traditional CMOS technology.
Designed for compute-intensive applications such as AI Inference, machine learning, and physics simulation, the NPU can solve real-world challenges, Q.ANT asserts, “including number recognition for deep neural network inference.”
Dr. Michael Förtsch, CEO of Q.ANT, commented, “With our photonic chip technology now available on the standard PCIe interface, we’re bringing the incredible power of photonics directly into real-world applications. For the first time, developers can create AI applications and explore the capabilities of photonic computing, particularly for complex, nonlinear calculations. For example, experts calculated that one GPT-4 query today uses 10 times more electricity than a regular internet search request. Our photonic computing chips offer the potential to reduce the energy consumption for that query by a factor of 30.”
Q.ANT’s achievement relies on its proprietary LENA platform, which includes thin-film lithium niobate on insulator chips. The company has been developing this photonic material since its foundation in 2018. This platform enables precise light control at the chip level. By controlling the entire value chain from wafer to finished processors and leveraging its deep understanding of light, Q.ANT achieves mathematical and algorithmic density surpassing conventional CMOS technology. For instance, a Fourier transform that requires millions of transistors in traditional computing can be accomplished with a single optical element.
“Q.ANT’s novel approach to photonic processing is a groundbreaking step towards addressing the escalating energy demands of the AI era,” said Eric Mounier, PhD. Chief Analyst, Photonics & Sensing at Yole Group. “This new processor generation finally gives access to superior mathematical operations, which have been too energy-demanding on traditional GPUs. The first impact is expected in AI inference and training performance, paving the way for high efficiency, sustainable AI computing.”
First Quantum Brilliance quantum accelerator ordered in EuropeQuantum Brilliance (QB), a developer of diamond-based quantum technology, has announced the first purchase of a room temperature quantum accelerator in the European market by Fraunhofer Institute for Applied Solid State Physics (IAF) following the company’s participation in a public tender.
QB says its quantum accelerators differ from other quantum mainframe computers “by leveraging synthetic diamonds to run at room temperature in any environment without the need for large, expensive and energy-intensive refrigeration units to keep qubits stable.”
The purchase of its second-generation Quantum Development Kit (QB-QDK2.0) — a 19 in rack-mountable quantum accelerator featuring nitrogen-vacancy centres in diamond—enhances QB’s existing software suite at Fraunhofer IAF. This includes the Qristal SDK (open-source) and Qristal Emulator, which allow users to simulate quantum computing back-ends with realistic noise models powered by NVidia’s CUDA-Q platform.
The IAF, a leading research institute for synthetic diamonds and their potential for quantum computing applications, has been collaborating with QB on multiple projects, including DE BRILL, which focuses on advancing quantum computing technologies using diamond-based qubits. The nitrogen vacancy-based system, together with the corresponding high-performance computing integrated virtual emulation system, is intended to advance IAF’s research infrastructure as part of a comprehensive quantum computing ecosystem.
“Our long-standing collaboration with Fraunhofer IAF highlights the development of room-temperature quantum accelerators and continues to push the boundaries of scalable, energy-efficient quantum computing solutions,” said QB’s CRO Mark Mattingley-Scott. “We look forward to delivering impactful quantum solutions to the IAF.”
© 2024 SPIE Europe |
|