-

Baya Systems Collaborates with Tenstorrent to Demonstrate Optimized Subsystem for TT-Ascalon Processors, Joins OCA Ecosystem

Published joint white papers and demos showcase customizable compute systems, highlighting a shared vision for agile, software-driven design of next-generation compute

SANTA CLARA, Calif.--(BUSINESS WIRE)--Baya Systems, a leader in software-driven, chiplet-ready fabric IP for scalable AI and high-performance computing, today announced two key milestones: successful interoperability between Baya’s WeaveIP™ fabric and Tenstorrent’s TT- Ascalon™ processor portfolio and becoming one of the first members of Tenstorrent’s Open Chiplet Atlas (OCA). Both companies are actively working on leveraging the unique advantages of Baya’s fabric interoperability within OCA. Together, these milestones underscore their shared vision and commitment to enabling flexible, scalable, and customizable compute systems designed for the next generation of AI and other high-performance applications.

Tenstorrent is redefining processor architectures for the AI age, and Baya is redefining system interconnects and system design paradigms. Together, we are enabling customers to weave scalable compute systems from proven, interoperable building blocks.

Share

By integrating Baya’s chiplet-ready interconnect IP with Tenstorrent’s RISC-V-based Ascalon cores, system architects can now design and deploy compute platforms that are optimized end-to-end, from core to chiplet to system level. The collaboration brings to life a common vision: agile, software-driven development, optimization, and deployment of state-of-the-art systems.

Joint Technical Showcase

Tenstorrent and Baya have jointly published a white paper with results that illustrate the performance, configurability, and scalability of this combined scalable compute solution. Building on the white paper on AI fabrics that the companies published in June, the two companies demonstrate how the WeaveIP fabric extends its technical leadership and versatility. Ascalon cores deliver best-in-class performance, both peak and per watt, while Baya’s WeaveIP fabric enables a data-driven system optimization to meet customer needs and dynamically adapt to Tenstorrent’s application requirements, ensuring future-proof scalability. The interoperability demos highlight how customers can design customized compute systems with faster time-to-market and reduced risk. Request a demo to explore how this solution can accelerate your designs.

Executive Perspectives

“We believe in a chiplet future, and interoperability across ecosystems is the only way to get there,” said Keith Witek, COO of Tenstorrent. “Baya’s WeaveIP is an elegant fabric that connects our market-beating Ascalon processors in powerful and flexible ways. This is exactly the kind of collaboration that will accelerate innovation in AI and beyond.”

Tenstorrent is a leader in driving the RISC-V and AI processing ecosystems and has collaborated with Baya Systems on enabling designers to rapidly innovate and bring ground-breaking silicon platforms to market.

“Tenstorrent is redefining processor architectures for the AI age, and Baya is redefining system interconnects and system design paradigms. Together, we are enabling customers to weave scalable compute systems from proven, interoperable building blocks,” said Dr. Sailesh Kumar, CEO of Baya Systems. “This is a major step toward our mission of democratizing hyper-efficient, data-centric SoC and multi-chiplet design.”

Commitment to the OCAA Ecosystem

As part of the collaboration, Baya Systems will support Tenstorrent’s Open Chiplet Atlas Architecture (OCAA) ecosystem, ensuring seamless interoperability for customers adopting heterogeneous chiplet solutions. Baya’s WeaverPro™ design platform was built to help system designers analyze workloads at speed, partition and organize intelligent compute systems that scale across entire compute platforms, from SOCs through chiplets and beyond, while WeaveIP has been designed from the ground up to be chiplet-ready. Together, they provide a foundation for interoperable, scalable, and future-proof multi-die systems. This joint work paves the way for a broader ecosystem of co-optimized IP and compute chiplets, giving system developers more choice and control in crafting differentiated platforms.

About Open Chiplet Atlas

The Open Chiplet Atlas Architecture is an open specification developed by Tenstorrent intended to accelerate the development of chiplet-based systems by standardizing interfaces, behaviors, and interconnects across chiplets. OCAA enables “plug-and-play” composability, so that compute, memory, analog, and I/O chiplets can be mixed and matched from multiple vendors without redesigning core interconnect or boot and management infrastructure. Key goals include improving modularity, reducing development time and cost, easing integration of heterogeneous components, and supporting scalable AI and HPC systems.

About Baya Systems

Baya Systems is leading the next wave of foundational, high-performance, and modular semiconductor systems technologies that are chiplet-ready and accelerate intelligent compute everywhere. Inspired by the baya bird’s nest-weaving ability, Baya integrates best-in-class compute, communication, and I/O components into seamless, energy-efficient solutions. Its software-based design and exploration platform enhances performance, yield and reusability, enabling cutting-edge, cost-effective innovation across multiple industries. A member of the EE Times 2025 Silicon 100 and recipient of Frost & Sullivan’s 2025 Technology Innovation Leader award in semiconductor IP interconnect, Baya is backed by leading investors including Matrix Partners, Maverick Silicon, Synopsys Inc., and Intel Capital. For more information, visit https://bayasystems.com or follow us on LinkedIn.

About Tenstorrent

At Tenstorrent, we build computers for AI, and the developers that are shaping its future.

Our high-performance RiscV based CPUs and AI, modular chiplets, and scalable compute systems give developers full control, at any scale from a single-node experimentation to data center-scale deployment.

We believe in an open future. Our architecture and software are designed to be edited, forked, and owned. Our team of engineers, dreamers, and first-principle thinkers is redefining how hardware and software converge to accelerate innovation.

Contacts

Media Contact
Crackle PR for Baya Systems
Baya@cracklepr.com

Baya Systems


Release Versions

Contacts

Media Contact
Crackle PR for Baya Systems
Baya@cracklepr.com

Social Media Profiles
More News From Baya Systems

Baya Systems Awarded Globally Recognized ISO 9001:2015 Certification for Quality Management by TÜV Rheinland

SAN JOSE, Calif. & COLOGNE, Germany--(BUSINESS WIRE)--Baya Systems, a leader in high-performance semiconductor system technologies, today confirmed it has achieved ISO 9001:2015 certification....

Baya Systems Celebrates First Year of Hypergrowth After Emerging from Stealth

SAN JOSE, Calif.--(BUSINESS WIRE)--Baya Systems, a leader in high-performance semiconductor system technologies, today celebrated its return to the Design Automation Conference (DAC) and the anniversary of its emerging from stealth. In this transformative year, Baya has achieved strong customer traction, significant team growth and key technology breakthroughs– solidifying its role in enabling the next-generation of AI compute innovations, through modular, scalable, high-performance and future-...

Baya Systems, Imagination Technologies and Andes Technology to Present on Heterogeneous Compute Architectures at Andes RISC-V CON Silicon Valley

SANTA CLARA, Calif.--(BUSINESS WIRE)--Baya Systems, a leader in high-performance system architecture and design tools, today announced it will participate in Andes RISC-V CON Silicon Valley. In a joint developer track session with Imagination Technologies and Andes Technology, Baya chief software architect Dr. Eric Norige and Imagination director of product management Pallavi Sharma will present on heterogeneous system-on-chip (SoC) strategies designed to optimize performance for AI, machine le...
Back to Newsroom