Home / Press Releases / Baya Systems & Tenstorrent Showcase Optimized Subsystem for TT-Ascalon™ Processors

September 25, 2025

Press Releases

Baya Systems & Tenstorrent Showcase Optimized Subsystem for TT-Ascalon™ Processors

Joint solution reduces risk and accelerates time-to-silicon for advanced semiconductor platforms

Share this article

Joint solution reduces risk and accelerates time-to-silicon for advanced semiconductor platforms

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. – September 25, 2025 — 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™ Architecture(OCAA). 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.

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 OCA Ecosystem

As part of the collaboration, Baya Systems will support Tenstorrent’s Open Chiplet Atlas (OCA) 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. Baya is backed by leading investors including Matrix Partners, Maverick Silicon, Synopsys Inc., and Intel Capital. For more information, visit 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.

Media Contact

Crackle PR for Baya Systems

Baya@cracklepr.com

Share this article

White paper

Developing RISC-V Compute Subsystems with Tenstorrent and Baya Systems

As demand grows for scalable, efficient, and customized compute, more companies are turning to RISC-V as the preferred architecture for high-performance computing. Tenstorrent and Baya Systems have designed a compute subsystem combining IP from both companies designed to enable AI and HPC use cases. The solution leverages Tenstorrent’s Ascalon™ processor and Baya’s advanced interconnect technology. This paper showcases a compute subsystem that has been designed to deliver strong performance, power efficiency, flexibility and scalability, making it suitable for cloud, server, data center, and edge computing applications to be used in SoCs and chiplets. This collaboration also enables rapid customization and extension of well-tested compute subsystems.

White paper

Baya Systems Elevates Tenstorrent’s AI Fabric to New Heights

This whitepaper covers how Tenstorrent is elevating their already industry-leading AI fabric to new heights of performance, efficiency, and productivity through a collaboration with Baya Systems. Tenstorrent’s in-house fabric has set a new standard for efficiency and performance in AI compute in their current generation products and is proactively addressing the needs of the next generation. By combining Tenstorrent’s proven AI system architecture with Baya Systems’ WeaveIP™ fabrics and WeaverPro™ software platform, the new AI fabric is able to deliver significant improvements across all key performance metrics while also reducing the total fabric silicon footprint and power consumption. Such results are unmatched by any in-house or off-the-shelf fabric solution and is propelling the next Tenstorrent AI products to a stratospheric level of efficiency and scaling.

Equally transformative is the shift in the development process to improve Tenstorrent’s time to market (TTM), enhance customer total cost of ownership (TCO) and establish a future-proof, chiplet-ready fabric architecture that can scale seamlessly with the demands of large AI models and new workloads.

Dot Wave Push — Final