UPDATED 17:36 EST / NOVEMBER 17 2026.
AI factories are growing so dense that storage, not just compute, now decides how rapidly they turn data into tokens. For Dell Technologies Inc., the answer starts with turning its PowerEdge servers into flexible, software-defined storage nodes that can change roles as workloads shift.
It has been revealed that the move from training toward inference and agents has put latest pressure on time to value. Dell has spent the year extending its AI Data Platform with a semantic layer for agentic workloads. Its AI factory pitch now reaches well beyond compute and graphics processing units, according to George Papadopoulos (pictured), senior vice president of product and engineering at Dell.
“We look at our AI factory not just as a set of CPUs and GPUs, but networking becoming more and more key, particularly around speed, reliability of storage and the ability to take your raw data and generate context and knowledge from it,” he noted.
Papadopoulos spoke with theCUBE Research’s John Furrier and Rebecca Knight at SC26, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how Dell is adapting its storage and cooling to keep AI factories running at scale. (* Disclosure below.).
Customers want storage they can buy for today’s needs and repurpose later. For instance, a customer might start with file and move to object or parallel file as workloads evolve. Agentic workloads lean on small input/output operations rather than streaming, so the right storage type can shift quickly, Papadopoulos explained. Dell’s answer is Dell Exascale Storage, which runs as licensed software on Dell servers.
“It’s our really purpose-built software-defined solution for allowing us to take a PowerEdge-based node and … with flexible licensing, allow you to deploy a file persona, a block persona, an object persona or a parallel file persona, and allow that flexibility to change over time as your needs change,” he remarked.
Industry observers note that density is also forcing a rethink of cooling. The power envelope of today’s AI systems is so large that customers are planning for 100% liquid-cooled data centers, according to Papadopoulos. That requirement now extends to storage.
“The conversations have really gotten down to how can we most effectively provide a direct liquid-cooled solution — and the storage, that means even liquid cooling the drives, which is something that hasn’t been done as of yet,” he said.
At SC26, Dell unveiled a 2U, 32-drive node with 100% liquid cooling, which it bills as the first direct liquid-cooled storage for rack-scale AI. The node deploys as an Exascale system with any persona. Separating the software from an appliance also lets Dell bring new PowerEdge generations to market faster. That flexibility matters for neocloud operators, who need an off-ramp for every purchase, Papadopoulos noted.
“That allows them to make an upfront purchase and know that they won’t be locked into one particular storage type,” he remarked, “or have a set of data silos that they can’t leverage as they go forward.”.
Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of SC26:.
In a recent development, (* Disclosure: Dell Technologies Inc. sponsored this segment of theCUBE. Neither Dell Technologies Inc. nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.).
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
Sources indicate that founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our latest proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
Quantum computing drops its decade-away tag as error rates fall 200-fold in two years.
Reson8 releases Rumble-2-Flash speech model as a free open-weights download.
Tesorai raises $5.3M to feed starving AI models with biological data and accelerate drug discovery.
OneTrust's Fall '26 Release expands AI visibility, privacy and third-party risk tools.
AI and supercomputing merge as universities build GPU clusters at cloud-provider scale.
Starburst adds context support to give AI agents consistent access to business data definitions.
Quantum computing drops its decade-away tag as error rates fall 200-fold in two years.
AI - BY RYAN STEVENS . 5 MINUTES AGO.
Reson8 releases Rumble-2-Flash speech model as a free open-weights download.
AI - BY DUNCAN RILEY . 32 MINUTES AGO.
Tesorai raises $5.3M to feed starving AI models with biological data and accelerate drug discovery.
BIG DATA - BY MIKE WHEATLEY . 32 MINUTES AGO.
OneTrust's Fall '26 Release expands AI visibility, privacy and third-party risk tools.
According to recent reports, AI - BY DUNCAN RILEY . 32 MINUTES AGO.
AI and supercomputing merge as universities build GPU clusters at cloud-provider scale.
It has been revealed that AI - BY RYAN STEVENS . 36 MINUTES AGO.
Starburst adds context support to give AI agents consistent access to business data definitions.
AI - BY PAUL GILLIN . 2 HOURS AGO.