MediaTek, Marvell, Alchip Technologies, Astera Labs, Synopsys, and Cadence Join Forces with NVIDIA NVLink Ecosystem for Custom AI Silicon
In an exciting development at COMPUTEX, NVIDIA has unveiled its new NVIDIA NVLink Fusion. This advanced silicon technology is designed to enable industries to build semi-custom AI infrastructure. Working with a wide array of partners, including MediaTek, Marvell, Alchip Technologies, Astera Labs, Synopsys, and Cadence, this initiative leverages the NVIDIA NVLink, which is recognized as the most sophisticated and widely implemented computing fabric globally.
The introduction of NVLink Fusion represents a significant step forward in the AI sector. It opens the door for these leading companies to develop custom silicon solutions tailored to the demanding needs of AI workloads, such as model training and agentic AI inference. With the power of NVLink Fusion, companies like Fujitsu and Qualcomm Technologies are set to integrate NVIDIA GPUs with their CPUs, paving the way for the creation of high-performance NVIDIA AI factories.
Jensen Huang, the founder and CEO of NVIDIA, emphasized the revolutionary nature of this development, stating, “A tectonic shift is underway: for the first time in decades, data centers must be fundamentally rearchitected — AI is being fused into every computing platform. NVLink Fusion opens NVIDIA’s AI platform and rich ecosystem for partners to build specialized AI infrastructures.”
NVLink Fusion also offers cloud providers a streamlined process for scaling AI factories to accommodate millions of GPUs. This is achievable through the use of any Application-Specific Integrated Circuit (ASIC), NVIDIA’s rack-scale systems, and the NVIDIA end-to-end networking platform. This powerful network platform boasts a throughput of up to 800Gb/s and integrates components like NVIDIA ConnectX®-8 SuperNICs, NVIDIA Spectrum-X Ethernet, and NVIDIA Quantum-X800 InfiniBand switches, with co-packaged optics expected to be available soon.
A Comprehensive Technology Ecosystem
The NVLink Fusion framework empowers hyperscalers to collaborate with the NVIDIA partner ecosystem. This collaboration facilitates the integration of NVIDIA rack-scale solutions for seamless deployment in data center infrastructures. Among the AI chipmaking partners utilizing NVLink Fusion are MediaTek, Marvell, Alchip, Astera Labs, Synopsys, and Cadence.
Rick Tsai, the vice chairman and CEO of MediaTek, remarked on the collaboration with NVIDIA, saying, “By leveraging our world-class ASIC design services and deep expertise in high-speed interconnects, MediaTek is collaborating with NVIDIA to build the next generation of AI infrastructure. Our collaboration, which began in the automotive segment, now extends even further, enabling us to deliver scalable, efficient, and flexible technologies that address the rapidly evolving needs of cloud-scale AI.”
Similarly, Matt Murphy, chairman and CEO of Marvell, shared his insights: “Marvell is collaborating with NVIDIA to redefine what’s possible for AI factory integration. Marvell custom silicon with NVLink Fusion gives customers a flexible, high-performance foundation to build advanced AI infrastructure — delivering the bandwidth, reliability, and agility required for the next generation of trillion-parameter AI models.”
Johnny Shen, CEO of Alchip, highlighted their role in broadening the availability of NVLink Fusion through a design and manufacturing ecosystem. This ecosystem encompasses advanced processes and proven packaging, supported by the ASIC industry’s most flexible engagement. “It’s our contribution to ensuring that the next generation of AI models can be trained and deployed efficiently to meet the demands of tomorrow’s intelligent applications,” Shen added.
Astera Labs is also making significant contributions to the NVLink Fusion ecosystem. Jitendra Mohan, CEO of Astera Labs, expressed enthusiasm about adding purpose-built connectivity solutions, stating, “Low-latency and high-bandwidth scale-up interconnects with native support for memory semantics is critical for maximizing AI server utilization and performance. By expanding our scale-up connectivity portfolio with NVLink solutions, we are providing more optionality with faster time to market for our hyperscaler and enterprise AI customers.”
Synopsys and Cadence, two other key players in the AI chip design space, are also supporting the NVIDIA NVLink Fusion initiative. Sassine Ghazi, president and CEO of Synopsys, noted, “Data centers are transforming into AI factories, and Synopsys’ industry-leading AI chip design solutions and standards-based interface IP are mission-critical enablers. Our support for NVIDIA NVLink Fusion reflects our commitment to fostering an open and scalable ecosystem for next-generation AI and high-performance computing.”
Boyd Phelps, senior vice president and general manager of the Silicon Solutions Group at Cadence, echoed this sentiment, highlighting Cadence’s role in delivering enabling technology from data centers to the edge. “Our comprehensive IP portfolio, including design IP, chiplet infrastructure, subsystems, and other critical IP, complements the NVIDIA NVLink ecosystem, accelerating the delivery of AI factories that are powerful, energy-efficient, and production-ready at scale.”
Fujitsu and Qualcomm Technologies: Harnessing NVLink Fusion for Enhanced AI Performance
NVLink Fusion is also enabling AI innovators like Fujitsu and Qualcomm Technologies to couple their custom CPUs with NVIDIA GPUs in a rack-scale architecture, significantly boosting AI performance. Vivek Mahajan, CTO at Fujitsu, emphasized the advantages of combining their advanced CPU technology with NVIDIA’s full-stack AI infrastructure. “Fujitsu’s next-generation processor, FUJITSU-MONAKA, is a 2-nanometer, Arm-based CPU aiming to achieve extreme power efficiency. Directly connecting our technologies to NVIDIA’s architecture marks a monumental step forward in our vision to drive the evolution of AI through world-leading computing technology — paving the way for a new class of scalable, sovereign, and sustainable AI systems.”
Cristiano Amon, president and CEO of Qualcomm Technologies, added, “Qualcomm Technologies’ advanced custom CPU technology with NVIDIA’s full-stack AI platform brings powerful, efficient intelligence to data center infrastructure. With the ability to connect our custom processors to NVIDIA’s rack-scale architecture, we’re advancing our vision of high-performance, energy-efficient computing to the data center.”
NVIDIA NVLink: A Proven Leader in AI Scale
To maximize AI factory throughput and performance in a power-efficient manner, the fifth-generation NVIDIA NVLink platform includes the NVIDIA GB200 NVL72 and GB300 NVL72. These compute-dense racks offer a total bandwidth of 1.8 TB/s per GPU, which is 14 times faster than PCIe Gen5. Leading hyperscalers are already deploying NVIDIA NVLink full-rack solutions, enabling them to speed up availability by standardizing their heterogeneous silicon data centers on the NVIDIA rack architecture with NVLink Fusion.
Software Tailored for AI Factories
AI factories connected with NVIDIA NVLink Fusion are powered by NVIDIA Mission Control, a unified operations and orchestration software platform. This platform automates the complex management of AI data centers and workloads, enhancing every aspect of AI factory operations. From configuring deployments to validating infrastructure and orchestrating mission-critical workloads, NVIDIA Mission Control helps enterprises get cutting-edge models up and running faster.
Availability and Further Information
NVIDIA NVLink Fusion silicon design services and solutions are currently available from partners such as MediaTek, Marvell, Alchip, Astera Labs, Synopsys, and Cadence. For those interested in learning more, NVIDIA invites you to watch the COMPUTEX keynote by Jensen Huang and explore more at NVIDIA GTC Taipei.
About NVIDIA
NVIDIA is a global leader in accelerated computing, driving innovation across various sectors with its advanced technologies and products. For more details, visit NVIDIA’s official website.
In conclusion, the introduction of NVIDIA NVLink Fusion marks a pivotal moment in the AI industry, promising enhanced performance and scalability. This development reflects the ongoing evolution of data centers into AI factories, setting the stage for the next generation of AI computing.
For more Information, Refer to this article.
