Enfabrica 3.2 Tbps ACF SuperNIC Chip: Boosting AI ...

At Supercomputing 2024 (SC24), Enfabrica Company unveiled a milestone in AI information middle networking: the Accelerated Compute Cloth (ACF) SuperNIC chip. This 3.2 Terabit-per-second (Tbps) Community Interface Card (NIC) SoC redefines large-scale AI and machine studying (ML) operations by enabling large scalability, supporting clusters of over 500,000 GPUs. Enfabrica additionally raised $115 million in funding and is predicted to launch its (ACF) SuperNIC chip in Q1 2025.

Addressing AI Networking Challenges

As AI fashions develop more and more giant and complicated, information facilities face mounting pressures to attach giant numbers of specialised processing models, reminiscent of GPUs. These GPUs are essential for high-speed computation in coaching and inference however are sometimes left idle attributable to inefficient information motion throughout present community architectures. The problem lies in successfully interconnecting 1000’s of GPUs to make sure optimum information switch with out bottlenecks or efficiency degradation.

Conventional networking approaches can hyperlink roughly 100,000 AI computing chips in a knowledge middle earlier than inefficiencies and slowdowns turn into vital. Based on Enfabrica’s CEO, Rochan Sankar, the corporate’s new know-how helps as much as 500,000 chips in a single AI/ML system, enabling bigger and extra dependable AI mannequin computations. By overcoming the constraints of typical NIC designs, Enfabrica’s ACF SuperNIC maximizes GPU utilization and minimizes downtime.

Key Improvements within the ACF SuperNIC

The ACF SuperNIC boasts a number of industry-first options tailor-made to trendy AI information middle wants:

1. Excessive-Bandwidth, Multi-Port Connectivity: The ACF SuperNIC delivers multi-port 800-Gigabit Ethernet to GPU servers, quadrupling the bandwidth in comparison with different GPU-attached NICs. This setup offers unprecedented throughput and enhances multipath resiliency, making certain sturdy communication throughout AI clusters.
2. Environment friendly Two-Tier Community Design: With a high-radix configuration of 32 community ports and as much as 160 PCIe lanes, the ACF SuperNIC simplifies the general structure of AI information facilities. This effectivity permits operators to assemble large clusters utilizing fewer tiers, lowering latency and enhancing information switch effectivity throughout GPUs.
3. Scaling Up and Scaling Out: The Enfabrica ACF SuperNIC, with its high-radix, high-bandwidth, and concurrent PCIe/Ethernet multipathing and information mover capabilities, can uniquely scale up and scale out 4 to eight latest-generation GPUs per server system. This considerably will increase AI clusters’ efficiency, scale, and resiliency, making certain optimum useful resource utilization and community effectivity.
4. Built-in PCIe Interface: The chip helps 128 to 160 PCIe lanes, delivering speeds over 5 Tbps. This design permits a number of GPUs to hook up with a single CPU whereas sustaining high-speed communication with information middle backbone switches. The result’s a extra environment friendly and versatile format that helps large-scale AI workloads.
5. Resilient Message Multipathing (RMM): Enfabrica’s proprietary RMM know-how boosts the reliability of AI clusters. By mitigating the affect of community hyperlink failures or flaps, RMM prevents job stalls, making certain smoother and extra environment friendly AI coaching processes. Sankar notes the significance of this function, particularly in giant setups the place hyperlinks to switches failures turn into frequent.
6. Software program-Outlined RDMA Networking: This distinctive function empowers information middle operators with full-stack programmability and debuggability, bringing the advantages of software-defined networking (SDN) into Distant Direct Reminiscence Entry (RDMA) setups. It permits customization of the transport layer, which might optimize cloud-scale community topologies with out sacrificing efficiency.

Enhanced Resiliency and Effectivity

Conventional techniques usually require one-to-one connections between GPUs and numerous parts, reminiscent of PCIe switches and RDMA NICs. Nevertheless, because the variety of GPUs in a system will increase, the chance of hyperlinks to switches failures grows, with potential disruptions occurring as usually as each 23 minutes in setups with over 100,000 GPUs, based on Shankar. 

The ACF SuperNIC addresses this problem by enabling a number of connections from GPUs to switches. This redundancy minimizes the affect of particular person element failures, boosting system uptime and reliability.

The SuperNIC additionally introduces the Collective Reminiscence Zoning function, which helps zero-copy information transfers and optimizes host memory management. By lowering latency and enhancing reminiscence effectivity, this know-how maximizes the floating-point operations per second (FLOPs) utilization of GPU server fleets.

Scalability and Operational Advantages

The ACF SuperNIC’s design is just not solely about scale but in addition about operational effectivity. It offers a software program stack that integrates with customary communication, present interfaces, and RDMA networking operations. This compatibility ensures environment friendly deployment throughout various AI compute environments composed of GPUs and accelerators (AI chips) from totally different distributors. Knowledge middle operators profit from streamlined networking infrastructure, lowering complexity and enhancing the flexibleness of their AI information facilities.

Availability and Future Prospects

Enfabrica’s ACF SuperNIC might be out there in restricted portions in Q1 2025, with each the chips and pilot techniques now open for orders via Enfabrica and chosen companions. As AI fashions demand larger efficiency and bigger scales, Enfabrica’s revolutionary method might play a pivotal function in shaping the following technology of AI information facilities designed to assist Frontier AI models.

Filed in Computers. Learn extra about AI (Artificial Intelligence), Chip, generative AI, Semiconductors, Server, SoC and Supercomputer.