Oversubscribed Round Led by Atreides Management, with Backing from Sutter Hill Ventures, NVIDIA to Advance Production of Flagship Accelerated Compute Fabric (ACF) Devices
Enfabrica’s 8 Terabits/second ACF Switch Systems Now Pre-orderable
Enfabrica Corporation, a fast-growing startup building converged networking and memory fabric silicon and software tailored to the performance and scalability demands of artificial intelligence (AI) and accelerated computing workloads, today announced its successful close of a $125 million Series B financing round. The oversubscribed round, which increases Enfabrica’s valuation more than 5X, was led by Atreides Management, with support from existing investor Sutter Hill Ventures, and includes new investors NVIDIA, IAG Capital Partners, Liberty Global Ventures, Valor Equity Partners, Infinitum Partners and Alumni Ventures.
The new capital will be deployed to advance the production of Enfabrica’s groundbreaking Accelerated Compute Fabric Switch (ACF-S) devices and solutions, which complement GPUs, CPUs and accelerators to solve critical networking, I/O and memory scaling problems in data center AI and high-performance computing clusters. The company will showcase its ACF-S solutions at the AI Hardware and Edge AI Summit 2023 taking place September 12-14 in Santa Clara, California.
News Highlights:
- The oversubscribed $125M Series B round was led by crossover firm Atreides Management, with supporting capital from Series A lead Sutter Hill Ventures, and new capital from IAG Capital, Liberty Global, NVIDIA, Valor Equity Partners, Infinitum and Alumni Ventures.
- The funding will be used by Enfabrica to expand its R&D and operations and advance the production of its flagship ACF-S devices that enable 50 percent lower cost of compute and 50X memory expansion in GPU and accelerated compute clusters in data centers.
- The successful Series B financing round resulted in Enfabrica’s valuation rising to more than 5 times its Series A post-money valuation.
- Pursuant to the Series B financing, Gavin Baker, Managing Partner & CIO of Atreides Management, has joined Enfabrica’s Board of Directors to assist the company’s growth and strategic direction.
- Earlier this year, Enfabrica emerged from stealth mode to announce its revolutionary new class of AI infrastructure interconnect chips called Accelerated Compute Fabric devices. Enfabrica’s ACF devices deliver unmatched scalability, performance and total cost of ownership for distributed AI, extended reality, high-performance computing and in-memory database infrastructure.
- Enfabrica’s 8 Terabit/second ACF switching system, which directly bridges and internetworks GPUs, CPUs and memories at scale with native, multi-port 800-Gigabit-Ethernet networking, is now accessible to customers for pre-order.
“The fundamental challenge with today’s AI boom is the scaling of infrastructure,” said Rochan Sankar, Enfabrica CEO and co-founder. “There’s no denying the transformative value that AI delivers to a multitude of economic sectors. But there is a critical need to bridge the exploding demand to the overall cost, efficiency and ease of scaling AI compute, across all customers seeking to take control of their distributed AI infrastructure and services. Much of the scaling problem lies in the I/O subsystems, memory movement and networking attached to GPU compute, where Enfabrica’s ACF solution shines. Our Series B funding and investors are an endorsement of our team and product thesis, and further enable us to produce high-performance ACF silicon and software that drive up the efficient utilization and scaling of AI compute resources. As an organization, we are hyper-focused to work with the larger ecosystem of partners and customers to solve the AI infrastructure scaling problem.”
Generative AI, Large Language Model (LLM) and Deep Learning Recommendation Model (DLRM) technologies are not only increasing in adoption but are driving a massive infrastructure push in the cloud. As a result, aggregate AI training capacity and user serving scale will continue to grow exponentially. This, in turn, applies the pressure for cost and power efficiency to sustain the workload growth on the lowest possible number of GPUs and processors— which Enfabrica’s ACF solution enables through its high-performance converged memory and network fabric architecture.
The industry’s first, production-grade ACF switching system powered by Enfabrica silicon, produced in collaboration with partners, is an 8 Terabit/second platform enabling direct-attach of any combination of GPUs, CPUs, CXL-attached DDR5 memory and SSD storage to high-performance, multi-port 800-Gigabit-Ethernet networks. ACF switching systems incorporate Enfabrica’s high-performance ACF-S silicon having 100 percent standards-compliant interfaces and host networking software stack components running on standard Linux kernel and userspace interfaces.
Enfabrica was started in 2020 by Silicon Valley veterans Rochan Sankar, Shrijeet Mukherjee and key engineers who built industry-leading silicon and software stacks at Broadcom, Google, Cisco, AWS and Intel. The team has designed its innovative ACF devices to deliver scalable, streaming, multi-Terabit-per-second data movement between GPUs, CPUs, accelerators, memory and networking devices. The solution enables customers to cut their cost of compute by an estimated 50 percent for LLM inferencing and 75 percent for DLRM inferencing at the same performance point.