SANTA CLARA, Calif., May 15, 2025 /PRNewswire/ — Ampere® today announced two key developments in its strategy to deliver open, efficient and scalable infrastructure for AI and cloud workloads: the launch of the Ampere Systems Builders program and the availability of additional 12 memory channel platforms based on AmpereOne® M processors. Together, these milestones mark a step forward in the effort to scale AI inference infrastructure through innovation, openness and ecosystem collaboration.
Ampere Systems Builders: Accelerating Open, Modular Platform Innovation
The newly launched Ampere Systems Builders program brings together industry leaders to accelerate the development and delivery of modular, standards-based platforms optimized for AI and Cloud Native computing. The program is built on openness and flexibility, with shared architectures such as the DC-MHS standard driving interoperability, customization and faster time to market.
Joint collaborators — including Broadcom, Supermicro, Giga Computing, ASRock Rack, Jabil and Rebellions — are working collaboratively with Ampere to co-develop solutions using shared engineering resources, open specifications and coordinated platform validation. Members can also package turnkey solutions that integrate hardware, software and services tailored to the demands of AI inference.
“As the industry accelerates the build-out of AI Compute, it’s critical that we maintain the efficient, scalable and open principles that have driven decades of innovation,” said Jeff Wittich, Chief Product Officer at Ampere. “With Ampere Systems Builders, we’re enabling the ecosystem to deliver high-performance infrastructure that’s open, interoperable and ready for the future of AI.”
AI inference solutions of the future will require many ingredients, from accelerators for AI to connectivity and storage ingredients for systems built at scale. With strong experience in ingredients such as high-performance networking, storage and internal PCIe switching, Broadcom joins Ampere Systems Builders to assist in the critical development, characterization and validation of systems built with these foundational computing components, including systems built on AmpereOne M.
Several platforms are already in development through the program from system providers such as Jabil, Supermicro, Giga Computing and ASRock Rack. This also includes platforms with dense AI inference acceleration technology from accelerator supplier Rebellions. More add-in options, systems and members are expected in the coming months.
Additional AmpereOne M 12-Channel Platforms Coming to Market
In parallel, Ampere is announcing the delivery of new 12-channel platforms based on AmpereOne M processors, representing the next step in the evolution of high-efficiency platforms for data- intensive AI workloads. This builds on availability following the release of AmpereOne M in December 2024, scaling it to an even broader market. These platforms offer strong performance- per-watt and high memory bandwidth for AI, making them ideal for modern inference infrastructure.
New platforms include:
- Giga Computing has developed a 12-channel platform based on AmpereOne M through its participation in Ampere Systems Builders. Available for purchase, the system delivers high- performance and efficiency for AI inference and Cloud Native workloads, offering customers a new option for scalable, high-density compute.
- Jabil’s DC-MHS host processing module based on AmpereOne M will be ready to sample by Q3 2025, spanning edge to hyperscale deployments. This platform is coming to market through Jabil’s participation in Ampere Systems Builders.
- ASRock Rack, through its participation in Ampere Systems Builders, has developed a 12- channel platform based on AmpereOne M.
Laying the Foundation for an Open AI Future
Together, the launch of Ampere Systems Builders and the broader rollout of AmpereOne M platforms underscore Ampere’s commitment to building the next generation of AI infrastructure— one that is open, scalable and ready to meet the rising demand for AI Compute.
Many of these systems will be showcased at Computex 2025. To learn more about Ampere Systems Builders, contact Ampere. More information on Ampere processors and AmpereOne M is available here.
Supporting Quotes
“Our collaboration with Ampere and participation in Ampere Systems Builders is an exciting opportunity to explore new possibilities for scalable, efficient AI infrastructure,” said Weishi Sa, President at ASRock Rack. “The development of our 12-channel AmpereOne M platform is just one example of the potential of this collaboration, and we look forward to continuing to innovate together to support the evolving needs of AI inference workloads.”
“As AI workloads continue to grow in complexity and scale, open and modular system design is more important than ever,” said Jas Tremblay, vice president and general manager, Data Center Solutions Group, Broadcom. “Our collaboration with Ampere, through Ampere Systems Builders, brings Broadcom’s leadership in high-performance connectivity and system solutions to a new generation of platforms optimized for AI inference.”
“Collaborating with Ampere through Ampere Systems Builders is enabling Giga Computing to bring new, efficient AI Compute solutions to market,” said Vincent Wang, Sales VP at Giga Computing. “Our new 2U GIGABYTE server features a unique design. We can stack two motherboards, each having an AmpereOne M socket for a total of 24 DIMMs. This results in a memory dense server that has an incredible amount of total system memory, which is ideal for large language models, such as LLaMa.”
“The Ampere Systems Builders program aligns perfectly with Jabil’s mission to deliver agile, scalable infrastructure for a rapidly evolving AI landscape,” said Ed Bailey, CTO and SVP of Jabil’s Intelligent Infrastructure segment. “By supporting open standards like DC-MHS and collaborating with Ampere on AmpereOne M-based platforms, we’re enabling a new class of modular solutions designed for performance, efficiency, and speed to market.”
“Through the Ampere Systems Builders program, Supermicro will support customers with MegaDC modular systems integrating DC-MHS-based Ampere motherboards, supporting both CPU-only and CPU-plus-accelerator configurations,” said Michael Clegg, VP & GM, Edge at Supermicro. “These systems are specifically designed to meet the needs of high-volume AI inference deployments across cloud and enterprise markets, where flexibility, performance and efficiency are critical.”
About Ampere
Ampere is a modern semiconductor company designing the future of cloud computing with the world’s first Cloud Native Processors. Built for the sustainable Cloud with the highest performance and best performance per watt, Ampere processors accelerate the delivery of all cloud computing applications. Ampere Cloud Native Processors provide industry-leading cloud performance, power efficiency and scalability. For more information visit Ampere Computing.
Press Contact:
Alexa Korkos
Ampere Computing
press@amperecomputing.com
SOURCE Ampere