Friday, 15 August 2025
27.6 C
Singapore
28.1 C
Thailand
19 C
Indonesia
26.7 C
Philippines

Western Digital and Ingrasys collaborate on advanced fabric-attached storage for AI workloads

Western Digital and Ingrasys team up to develop a TOR switch with embedded storage, targeting AI-ready disaggregated data centre solutions.

Western Digital and Ingrasys, a subsidiary of Foxconn Technology Group, have announced a long-term partnership to develop a next-generation Top-of-Rack (TOR) switch with embedded storage. The collaboration aims to address the growing demands of artificial intelligence (AI) workloads by introducing high-performance, fabric-attached disaggregated storage solutions.

The new TOR Ethernet Bunch of Flash (EBOF) switch is designed to deliver distributed storage at the network edge, reducing latency by avoiding the need for centralised storage arrays. It removes the dependency on separate storage networks and brings data closer to compute resources. Ingrasys will handle manufacturing, while Western Digital will lead the architecture and market strategy using its RapidFlex NVMe-oF (Non-Volatile Memory Express over Fabrics) bridge technology.

Enabling flexible disaggregated infrastructure

This partnership marks a key milestone in the AI infrastructure space, with both companies aiming to promote a scalable and efficient storage architecture for data centres. Ingrasys brings extensive experience in building GPU servers, while Western Digital contributes its expertise in fabric-attached storage.

The TOR EBOF switch is set for release in 2027 and will feature Western Digital’s next-generation RapidFlex Fabric bridge device. The solution supports 100G Ethernet connectivity and NVMe/PCIe Gen6 interfaces for E3.S/L solid-state drives (SSDs), enabling seamless integration of flash storage into the networking layer. The system will be powered by the NVIDIA Spectrum-4 switch ASIC, providing high-performance switching with flexible support for 400 and 800GbE cabling to meet future data centre demands.

Western Digital’s RapidFlex NVMe-oF bridge technology stands out for its hardware-accelerated design, which removes firmware from the performance path. This approach allows I/O read and write payloads to pass directly through the adapter, reducing latency while maintaining direct Ethernet connectivity. As a result, the system allows data centres to scale storage independently from compute resources, improving flexibility and efficiency.

A shared vision for next-generation AI data centres

Executives from all three companies involved have expressed optimism about the strategic impact of this collaboration. Kurt Chan, vice president and general manager of Western Digital’s Platforms Business, stated, “Together with Ingrasys, we continue to accelerate the shift toward disaggregated infrastructure by co-developing cutting-edge, fabric-attached solutions designed for the data demands of AI and modern workloads. This collaboration brings together two leaders in storage infrastructure modernisation to deliver flexible, scalable architectures that unlock new levels of efficiency and performance for our customers.”

Benjamin Ting, president of Ingrasys, echoed the sentiment, adding, “Our collaboration with Western Digital reflects a shared commitment to long-term innovation and customer-centric design. By combining our expertise in scalable system integration with Western Digital’s leadership in storage technologies, we’re building a foundation for future-ready, fabric-attached solutions that will meet the evolving demands of AI and disaggregated infrastructure.”

Gilad Shainer, senior vice president of networking at NVIDIA, also commented on the partnership’s significance: “The collaboration between Western Digital and Ingrasys brings together the high-performance storage and scalable system transformation needed to fully unlock the potential of accelerated computing. As AI and data-intensive workloads push infrastructure limits, this joint effort is set to deliver the performance, low latency, and disaggregated scalability that next-generation data centres require.”

This development underscores the importance of close industry collaboration in addressing the infrastructure needs of AI and advanced computing environments.

Hot this week

CreateAI develops Heroes of Jin Yong as China’s next AAA video game

CreateAI is developing Heroes of Jin Yong, a massive open-world RPG based on Louis Cha’s novels, aiming for a 2028 release.

NTT DATA and The GEAR by Kajima launch smart building project in Singapore

NTT DATA and The GEAR by Kajima launch a smart building in Singapore, using 8,700 data points to boost efficiency, sustainability, and security.

Antler invests US$7.4 million in Southeast Asia startups with focus on AI

Antler invests US$7.4M in Southeast Asia startups, with US$2.8M supporting AI firms through its new AI Disrupt residency in Singapore.

Samsung launches first Micro RGB TV with enhanced colour accuracy

Samsung debuts its first Micro RGB TV, offering 100% colour reproduction, advanced gaming features, and a lower price than MicroLED.

Fortnite set to return to iOS in Australia after court ruling against Apple and Google

Fortnite will return to iOS in Australia after a court ruled Apple and Google abused their app store dominance to limit competition.

Okta report finds automation and AI agents leading workplace transformation

Okta’s AI at Work 2025 report finds automation and AI agents leading workplace change, but governance and security remain challenges.

Docusign unveils AI-powered contract tools at Singapore Momentum event

Docusign launches AI-powered agreement tools at Momentum Singapore to speed up contracts and strengthen compliance in Asia-Pacific.

Fortnite set to return to iOS in Australia after court ruling against Apple and Google

Fortnite will return to iOS in Australia after a court ruled Apple and Google abused their app store dominance to limit competition.

Tenable claims GPT-5 jailbreak within a day of launch

Tenable bypasses GPT-5 safety protocols within 24 hours of launch, highlighting urgent need for stronger AI oversight and governance.

Related Articles

Popular Categories