In order to address the significant scaling and data movement challenges in AI infrastructure that are propelling advanced SoCs and innovative 3D chiplet-based designs, Baya Systems unveiled its new NeuraScale switch fabric technology.
Because AI applications require unprecedented levels of efficiency, performance, and throughput, standard crossbar switching designs are finding it difficult to stay up. With its non-blocking performance, NeuraScale offers a radical and novel solution that will significantly outperform current platforms and allow for a 100x increase in node density and scale.
A Breakthrough in AI Infrastructure Scaling
Despite the sophisticated connection technology of NVLink, UALink, and Ultra Ethernet, the industry still confronts significant challenges in terms of scaling density and performance.
Next-generation AI systems can now attain previously unheard-of levels of efficiency, speed, and scalability thanks to Baya Systems’ patent-pending NeuraScale switch fabric, which presents a fundamentally novel methodology that goes beyond the limitations of traditional switching architectures.
- Radical Scalability:Supports 256 ports per chiplet with 1 Tb/s throughput, enabling next-generation AI infrastructure.
- Unprecedented Performance:Achieves 2 GHz+ operation in 4 nm technology with less than 20 ns maximum latency and 2048-bit data width for efficient data transfer.
- Modularity for chiplets:A fully modular architecture that simplifies physical implementation for each SoC, while enabling seamless scaling across multiple chiplets.
- Protocol-Ready for Industry Standards:Supports AMBA protocols and is designed for future UALink, UCIe and Ultra Ethernet compliance.
NeuraScale greatly speeds up development cycles when paired with Baya Systems’ WeaverPro, a software-driven platform that simplifies design, analysis, and KPI-driven optimization.
In addition to providing flexible, multi-protocol compatibility to guarantee interoperability and adaptability for AI-driven data centers, it streamlines the design of large-scale interconnects, removing major bottlenecks in conventional crossbar topologies.
Leadership Comments
“NVIDIA has demonstrated the benefits of high-performance networking for scaling AI with its NVLink™ proprietary interconnect,” said Karl Freund, founder of Cambrian-AI Research. “Now the industry is developing the UALink™ standard, which could democratize scaling, but it needs rapid innovation in SoC and chiplet-ready switching technologies creating opportunities for companies like Baya Systems and their fabric solutions.”
“The Ultra Accelerator Link™ Consortium (UALink™) was formed with a vision of creating an open ecosystem that boosts innovation and collaboration in scale-up, and our first specification will support up to 1K accelerators in an AI pod,” said Peter Onufryk, President of the UALink Consortium. “We welcome Baya Systems, which joins a rapidly growing set of game changers meeting the challenges of AI scaling.”
“AI workload demands have outpaced what traditional crossbar interconnects can provide for the next generation of scale-up,” said Dr. Sailesh Kumar, Baya Systems’ CEO. “NeuraScale empowers a radical growth in node density, with highly energy-efficient and area-efficient switching solutions for next-gen AI – the key challenges to scale. With our platform, we enable unprecedented performance and scale, while substantially reducing the implementation challenges and time to market, which are serious challenges for traditional switching solutions.”
NeuraScale is being used by Baya Systems’ lead partners to develop cutting-edge next-generation scale-up and scale-out switching solutions. In Q2 2025, the technology will be accessible to a wider ecosystem, affirms its official release.
For further info on NeuraScale and Baya Systems Innovations in High-Performance Computing Fabrics: CLICK HERE
