The Ultra Ethernet Consortium (UEC) has launched its 1.0 specification.

In a statement, the consortium said the release “marks a critical step forward in redefining ethernet for next-generation, data-intensive infrastructure.”

Ultra Ethernet Consortium
– Ultra Ethernet Consortium

Built on the globally adopted ethernet standard, the 1.0 specification delivers a high-performance and scalable solution across all layers of the networking stack, including NICs, switches, optics, and cables.

It includes a modern RDMA (Remote Direct Memory Access) approach to support low-latency transport for high-throughput environments, open standards, and interoperability to avoid vendor lock-in, and end-to-end scalability.

“The Ultra Ethernet 1.0 Specification is the result of an outstanding collaboration of AI, HPC, and networking experts, system and silicon vendors, and network operators,” said Hugh Holbrook, chair of the technical advisory committee, UEC. “It incorporates a wealth of knowledge, experience, and ideas related to applications, transport protocols, congestion control, direct memory access, Ethernet link and PHY technologies, and network security.”

Dr. J Metz, chair of the steering committee, UEC, added: “This standard is the result of unprecedented collaboration across the industry, and it delivers the low-latency, high-bandwidth, and intelligent transport needed for the most demanding workloads of today and tomorrow. The UEC 1.0 release is just the beginning—Ultra Ethernet is here, and it’s built to scale the future.”

Founded in mid-2023 by founding members AMD, Arista, Broadcom, Cisco, Eviden, HPE, Intel, Meta, and Microsoft, UEC aims to deliver an ethernet based open, interoperable, high performance, full-communications stack architecture to meet the growing network demands of AI and HPC at scale.

Last week, founding member AMD announced Oracle Cloud Infrastructure was deploying what is claims is the first Ultra Ethernet-compliant NIC, the 400GbE Pensando Pollara. Designed to support scale-out environments containing up to one million GPUs, AMD says that its Pollara 400GbE card offers a 10 percent higher RDMA performance compared to Nvidia's CX7 and can improve RDMA performance by 25 percent compared to traditional RoCEv2.

AMD said it was championing an open ecosystem approach to AI innovation, including across its networking division, and said those involved with the open standard project are now able to scale their network 20 times more, when compared to Nvidia’s InfiniBand, and 10 times more when compared to classic ethernet.