TMCnet News
Networking Chip Startup Enfabrica Emerges from Stealth Mode to Solve Scalability and Price-Performance Challenges for AI Growth in CloudEnfabrica Corporation, a startup building leading-edge networking silicon and software tailored to the needs of fast-evolving Artificial Intelligence (AI) and accelerated computing workloads, today emerged from stealth mode to announce a revolutionary new class of chips- called Accelerated Compute Fabric (ACF) devices. ACF devices deliver unmatched scalability, performance and total cost of ownership (TCO) for distributed AI, machine learning, extended reality, high-performance computing and in-memory database infrastructure. Enfabrica will showcase its ACF solution and its ability to solve the most critical I/O and memory scaling problems for data center AI and accelerated compute at this year's inaugural MemCon Conference, taking place March 28-29 in Mountain View, Calif. Enfabrica Launch Highlights:
More about the Accelerated Compute Fabric solution Enfabrica's first chip, the Accelerated Compute Fabric Switch (ACF-S), developed clean-sheet by the company since 2020, employs entirely standards-based hardware and software interfaces, including multi-port 800 Gigabit Ethernet networking and high-radix PCIe Gen5 and CXL 2.0+ interfaces. ACF-S devices deliver scalable, composable, high-bandwidth data movement between any combination of GPU, CPU, accelerator ASIC, memory, flash storage and networking elements participating in an AI or accelerated computing workload. Without changing physical interfaces, protocols or software layers above device drivers, the ACF-S delivers multi-Terabit switching and bridging between heterogeneous compute and memory resources in a single silicon die, while dramatically reducing the number of devices, I/O latency hops, and device power in today's AI clusters consumed by top-of-rack network switches, RDMA-over-Ethernet NICs, Infiniband HCAs, PCIe/CXL switches, and CPU-attached DRAM. By incorporating unique CXL memory bridging capabilities, Enfabrica's ACF-S is the first data center silicon product in the industry to deliver headless memory scaling to any accelerator, enabling a single GPU rack to have direct, low-latency, uncontended access to local CXL.mem DDR5 DRAM at more than 50 times greater memory capacity versus GPU-native High-Bandwidth Memory (HBM). Addressing Critical Scaling and TCO Challenges of AI Infrastructure Generative AI and Large Language Models (LLMs) are now driving the largest infrastructure push in cloud computing. This forces the largest pressure for cost and power efficiency on being able to sustain growth of user interactions (i.e. inference serving) on the lowest possible number of GPUs and processors. Applying Enfabrica's Accelerated Compute Fabric solution with CXL memory to generative AI workloads enables massively parallel dynamic dispatch of user contexts to GPUs. Simulation results show the ACF-enabled system achieves the same target inference performance using only half the number of GPUs and CPU hosts compared to the latest "bigiron" GPU servers in the market. Enfabrica's ACF-S similarly slashes the cost of compute for large-scale AI recommendation engines. On an exemplary hyperscale DLRM inference load, the solution's memory tiering is shown to cut down the required number of GPUs and CPUs by 75%-- a disruptive TCO and power advantage. "Scaling memory bandwidth and capacity is a critical need for accelerated computing in the cloud," said Bob Wheeler, principal analyst at Wheeler's Network. "In this light, we see CXL and RDMA as complementary technologies, with hyperscalers having already deployed high-bandwidth RDMA networks for GPUs. Enfabrica's unique blending of CXL switching and RDMA networking functions in a single Accelerated Compute Fabric device promises a disruptive way to build scalable memory hierarchies for AI, and importantly the solution doesn't have to rely on advanced CXL 3.x capabilities that are years away from being implemented or proven at scale." Wheeler's Network and Enfabrica have jointly released a white paper, "The Evolution of Memory Tiering at Scale" by Bob Wheeler, which provides a detailed view of CXL technologies, memory expansion, pooling and tiering, and the role of RDMA networking in advanced data centers. An online version of the white paper is published here. About Enfabrica Enfabrica is an emerging silicon and software company building the foundational fabric technologies for the age of AI. Its groundbreaking chips, software and enabled systems are designed to solve critical I/O bottlenecks in accelerated computing infrastructure, at any scale. Enfabrica is unleashing the revolution in next-gen computing with the world's most advanced, performant, and efficient solutions interconnecting compute, memory, and network. Because the fabric is the computer. To learn more, follow us on LinkedIn or visit enfabrica.net. Third-party trademarks mentioned are the property of their respective owners.
View source version on businesswire.com: https://www.businesswire.com/news/home/20230328005830/en/ |