Verge.io adds GPU virtualization to its HCI software

0

Verge.io, formerly known as Yottabyte, has added GPU virtualization to its virtual data center software, allowing GPU-based processing tasks to be partitioned the same way a hypervisor partitions a CPU.

Hyperconverged infrastructure (HCI) creates a tightly integrated computing data center setup configured from standard servers, storage, and network servers with everything virtualized. Verge.io’s software, called Verge-OS, takes it a step further by partitioning pooled resources into what it calls virtual data centers (VDCs). A large pool can come from many VDCs made up of different hardware and software configurations.

Once Verge-OS is installed, it pools hardware resources, “liquefies” them as CEO Yan Ness puts it. This pool of CPUs, memory, storage, and now GPUs can be distributed across individual virtual data centers. These VDCs are independent of each other and can be moved around physical hardware or physical data center locations.

VDCs can run one or more applications and can be saved as blueprints for immediate loading of configurations, VDCs can be switched on the fly. So, for example, a corporate data center might be set up to run business applications during the workday, then at night when no one is using the network, a VDC for high-performance computing tasks might take over. .

With GPU support in Verge-OS, customers are already using GPUs for remote desktops during the day and night, running ML and AI workloads there. “[GPUs] are just another liquefied resource that you can assign to a virtual machine or virtual datacenter anywhere in the stack,” Ness said.

Back in the days of Yottabyte, the company focused on software-defined storage and software-defined networking. It has expanded its offerings to include a hypervisor, backup and restore, system management and integration tools. The main selling point of Verge-OS was that a customer could get all of this software from one source rather than many. The vGPU is just the last piece of hardware it supports in the VDC.

Verge.io does not require the most salient hardware to run its virtualization software. “Give us some basic material. We have demos that work on laptops,” Ness said.

To use Nvidia GPUs with Verge-OS, you need something called a vGPU License from Nvidia, which allows you to use their GPUs in a cloud or virtual environment.

And Ness said the software is a self-monitoring, self-repairing and self-optimizing technology. “So you don’t need all those storage engineers and such to make sure your settings are right for the workloads you have,” he said.

Ness said that Verge-OS will support AMD Instinct cards in the future, it’s just that Nvidia is so dominant that Verge chose it first. But AMD will eventually be supported in VDC software partitioning. “We want to do a little more testing,” he said.

Verge-OS with vGPU support is now available on Verge.io.

Join the Network World communities on Facebook and LinkedIn to comment on topics that matter to you.

Copyright © 2022 IDG Communications, Inc.

Share.

Comments are closed.