With current investors Matrix Partners and Intel Capital reinvesting in the company, Baya Systems announced that it has secured more than $36 million in a Series B round headed by Maverick Silicon and supported by a strategic investment from Synopsys.
For system-on-chip (SoC) designs and the developing chiplet economy, the company’s software-driven system IP technology portfolio will be developed and deployed more quickly with these funds, alongside focusing on operational expansion.
SoCs are evolving into “system-of-chips” models as a result of the growing demands of intelligent computing for AI capabilities, more effective data transportation, and compute density.
This new method, which uses chiplets, offers scalable performance, optimized power, and lower costs without depending entirely on conventional methods, where improvements have been slow to come by and are becoming more costly.
In addition to meeting new standards like Ultra Accelerator Link (UALink) die-to-die interconnect for even faster AI scaling, Baya offers modular solutions that are made to be flexible and capitalize on these advantages for next-generation AI, automotive, and data center infrastructure designs.
Baya provides a comprehensive method for designing, analyzing, and constructing intricate, highly effective multi-die systems that get around the scalability and data flow limitations of conventional semiconductors in order to better serve AI and other compute-heavy and data-intensive applications.
With integrated simulation and workload analysis that guarantees the design meets KPIs, Baya’s core WeaverPro software facilitates ongoing improvement of data-driven architecture and micro-architecture development from original specification to post-silicon tweaking.
With its distinctive transport, the extensive WeaveIP advanced system IP portfolio supports both standard and custom protocols, optimizes performance and throughput, and reduces power, latency, and silicon footprint to quickly deliver complex solutions.
Baya provides a comprehensive method for designing, analyzing, and constructing intricate, highly effective multi-die systems that get around the scalability and data flow limitations of conventional semiconductors in order to better serve AI and other compute-heavy and data-intensive applications.
With integrated simulation and workload analysis that guarantees the design meets KPIs, Baya’s core WeaverPro software facilitates ongoing improvement of data-driven architecture and micro-architecture development from original specification to post-silicon tweaking.
With its distinctive transport, the extensive WeaveIP advanced system IP portfolio supports both standard and custom protocols, optimizes performance and throughput, and reduces power, latency, and silicon footprint to quickly deliver complex solutions.
With the legendary microprocessor architect Jim Keller as the Chairman of the Board and a powerful group of engineers and entrepreneurial leaders from firms like Apple, AMD, Arm, Intel, and Qualcomm, Baya has quickly come out of stealth, brought its flagship product to market, and is now in a position to increase its market share.
Tenstorrent, which has licensed Baya technology for its AI and RISC-V chiplet solutions, is one of the early Baya clients and collaborators. Other unannounced agreements also demonstrate Baya’s increasing popularity and global reach.
Key Comments
“Generative AI and multimodal compute have clearly shown that the real challenge has transitioned from compute engines to data movement and connectivity to truly deliver on the performance and efficiency needs of AI acceleration and scale compute infrastructure and communications,” said Andrew Homan, Managing Director at Maverick Silicon. “The team at Baya Systems is uniquely positioned to fill this critical gap in the industry with its WeaverPro, WeaveIP and other solutions.”
“Baya Systems has executed ahead of schedule on building the team, the technology and the products that deliver on its vision to solve the high-performance system design challenge for the semiconductor industry,” said Stan Reiss, general partner, Matrix Partners. “This has uncovered a much larger scope for the company, and in our view, this new infusion of capital is necessary to extend leadership and capitalize on that opportunity.”
“Designing increasingly complex combinations of CPUs, GPUs, neural network accelerators and other processors is a brute-force solution that the industry cannot rely on forever. It simply comes with too many risks: high re-engineering costs, difficulty scaling and potentially hitting the market with sub-par metrics,” said Dr. Sailesh Kumar, founder and CEO, Baya Systems. “Baya’s performance-focused, software-based approach, coupled with our unique transport and modular fabric IP, is designed from the ground up to produce complex multi-die solutions that are correct by construction with a simplified design process.”