Fungible wins Innovative Storage and Best Startup of the Year Awards! See awards.

The Fungible Data Center

Reclaim Fungibility of Your Data Centers

Watch Video

Product Features


Effortlessly compose Fungible DPU-powered servers into right-sized configurations for varied workloads


Efficiently pool disaggregated resources at high performance and massive scale to maximize utilization


Significantly shorten infrastructure deployment time by spinning up resources in just minutes

Fungible Storage Cluster

Introducing the Fungible Storage Cluster – the world’s fastest secure, scale-out and All-Flash NVMe-oF disaggregated storage platform. The Fungible Storage Cluster delivers best-in-class performance characteristics for IOPS, latency, and throughput, in the smallest footprint and lowest power envelope.

Learn More

Foundational Technology

Fungible Data Processing Unit™

The Fungible DPU™ is recognized as the third socket in data centers alongside the CPU and GPU. It efficiently executes data-centric computations inside server nodes and the interchange of data among nodes.

The Fungible DPU serves as the data-path hub in each server node, connecting all servers via a technology called TrueFabric™. Benefits include improved reliability, security and infrastructure composability at no additional cost.

Watch Video

Featured Resources

The Case for Disaggregated Storage

NVMe-oF has enabled a new thinking around high-performance and large scale disaggregation. The Fungible DPU™ allows data center infrastructure to break free from the limitations of HCI, enabling high performance and reliable disaggregated storage at all scales.

Read Whitepaper 4 pages

The Case for Disaggregated Storage

Modern workloads are exposing the inherent limitations of Direct-Attached Storage architecture. The shift to a disaggregated storage architecture brings many benefits. Find out more about the role the Data Processing Unit will play to enable this transition.

Watch Video 5:25 min

Fungible DPU™: A New Category of Microprocessor

The Data Processing Unit (DPU) has gained recognition as the coveted third socket in data center servers. Find out more about what drives the need for this new class of microprocessors and the key innovations in the Fungible DPU that enables it to tackle the biggest data-centric computing challenges in scale-out data center infrastructure.

Read Whitepaper 9 pages


IBM Spectrum Scale is the industry-leading file system for data management at scale, supporting the most stringent requirements of high-performance computing and data-intensive workloads. These workloads demand high performance, scalable, secure storage. The Fungible Storage Cluster is a compelling storage solution for use with IBM Spectrum Scale, especially for workloads with small random I/Os. We welcome Fungible to the Scale family of high performance storage.

— Wayne A. Sawdon, Chief Technology Officer and Strategy Architect Spectrum Scale and Elastic Storage System (ESS) IBM Systems Group

With the continuous advancements in NVMe SSD media and protocols, the time is ripe to capitalize on the benefits of disaggregated storage, The Fungible Storage Cluster comes at an opportune time to serve an industry clamoring not just to maximize performance, but to turn performance density into much better footprint and cost efficiencies.

— Ashok Ganesan, Chief Product Office at Stackpath

We are excited about the expansion of the Spectrum Scale ecosystem with Fungible and the joint validation we have completed.

— Bina Hallman, Vice President of Strategy at IBM Storage

At Tech Data, our goal is to bring compelling technology solutions and value to end customers through our massive network of channel partners, the Fungible Storage Cluster represents the type of high-value technology that will energize the channel, supporting end-customers with extremely stringent performance and efficiency requirements.

— Sergio Farache, Executive VP of Strategy, Innovation, Cloud and M & A at Tech Data

Today’s technology leaders are continuously challenged to drive efficiencies, optimize for lean deployments, maximize hardware investments, yet be adequately agile to keep up with the dynamic rate of change of modern workloads, Fungible has addressed this market in a very innovative way with their disaggregated technology. The high-performance Fungible Storage Cluster enables next-gen workloads to solve today’s demands solidifying the path for what is coming next.

— Jay Chappell, Senior Director of Platform Architecture at Trace3

Innovations in data center infrastructure have occurred largely within the silos of compute, storage and networking, Fungible has broken down these silos delivering end-to-end value with Fungible DPU enabled servers interconnected by TrueFabric, a truly ground-breaking networking technology, and software composable for on-demand provisioning. This approach will serve as a blueprint for future data centers from core to edge.

— Raj Yavatkar, CTO at Juniper Networks

As enterprises move towards more data-driven business models, they will look to modernized IT infrastructure to deliver performance at scale for analytics workloads and the agility to rapidly adapt to evolving market conditions, Powered by the innovative new Fungible Data Processing Unit, Fungible’s new Storage Cluster delivers eye-popping throughput of hundreds of millions of IOPS with a composable, software-defined architecture that enables on-the-fly adaptability to meet the dynamically changing requirements of the new digital era.

— Eric Burgener, research VP, Infrastructure Systems, Platforms and Technologies Group at IDC

The Fungible DPU™, which is optimized for data-centric compute, enables line rate storage and security data services, unleashing the full capabilities and blazing fast performance of NVMe SSDs over the network.

— Young Sohn, President and CSO for Samsung Electronics and Chairman, HARMAN

We are excited to be working with Fungible to address large-scale network challenges in data centers and beyond. Fungible’s TrueFabric technology has demonstrated game-changing performance and latency characteristics that allow efficient disaggregation of all resources at data center scale.

— Rami Rahim, CEO of Juniper Networks

Current compute technologies fall short in the vendor’s ability to create an ultra-low latency and ultra-scalable solution for high bandwidth data movement. The industry needs a holistic and end-to-end solution that can disaggregate and compose infrastructure resources at cloud scale.

— Ashish Nadkarni, Group VP of Worldwide Infrastructure at IDC