Fungible introduced a means by which data centers could centralize their existing GPU assets into a single resource pool to be attached to servers on demand.
The Fungible GPU-Connect (FGC) solution leverages the company's DPU to dynamically compose GPU and CPU resources across an Ethernet network.
Instead of dedicated GPUs sitting idle most of the time, data centers can provide new users with access to the GPU pool, making greater use of existing assets. This disaggregated solution also removes the constraints of having GPUs and CPUs physically co-located. They can be located anywhere within the same data center, eliminating the stranding of expensive GPU resources.
“Fungible GPU-Connect empowers service providers to combine all their GPUs into one central resource pool serving all their clients. Service providers can now onboard new data-analysis intensive clients quickly without adding expensive servers and GPUs,“ explains Toby Owen, VP of Product at Fungible. “By leveraging FGC, data centers can benefit from the collective computing power of all their GPUs and substantially lower their TCO with the reduction of GPU resources, cooling and physical footprint needed.”
The Fungible DPU creates a secure, virtual PCIe connection between the GPU and the server that is transparent to the server and to applications – no special software or drivers are needed. This connection is managed in hardware by the DPU, ensuring a high-performance and low latency connection. This transparency means FGC can be easily retrofitted into existing environments, and can scale with growing demand, ensuring GPUs are always available when they are needed.
Fungible enhances its Storage Cluster for NVMe over TCP
Fungible unveils its multi-tenant data center platform for pooled resources
Fungible Data Centers - a deep dive discussion
