Upgraded Springdale facility now delivers multi-megawatt power for full-scale, warm-water testing of two-phase, direct-to-chip cooling at megawatt-class rack densities, with an 18,000-square-foot expansion set to open in January.
AUSTIN, Texas–(BUSINESS WIRE)–Accelsius, a leader in two-phase, direct-to-chip liquid cooling for AI and high-performance computing, today announced that it has upgraded its Springdale lab and facility in Austin, Texas, to multi-megawatt power for two-phase liquid cooling testing. The upgraded environment allows Accelsius to validate its NeuCool® platform at the rack densities and facility water temperatures that next-generation AI infrastructure is expected to demand. The company will also grow its lease footprint at the location with an additional 18,000 square feet in January 2027. The announcement comes as Accelsius exhibits at the Open Compute Project (OCP) Global Summit 2026 in San Jose.
Publicly disclosed GPU roadmaps already point to 600kW racks in 2027, with megawatt-class rack and pod designs. With multi-megawatt capacity at Springdale, Accelsius will be able to power a single rack at megawatt-plus loads, or multiple racks at today’s highest densities, and characterize complete two-phase systems, from cold plate to coolant distribution unit (CDU) to facility loop, under real-world conditions.
“Two-phase cooling has moved from proving the physics to scaling the product, and that means testing at the power levels our customers are actually planning for,” said John Hewitt, CEO of Accelsius. “With multi-megawatt capacity at Springdale, we can run full racks at megawatt-class loads on warm facility water and show operators exactly how NeuCool performs under the conditions we expect their next AI factories will face. This expansion is about growing in step with our customers’ roadmaps.”
Because the lab sits in Central Texas, where summer temperatures routinely exceed 100°F, it is also a real-world proving ground for warm-water cooling in a warm climate. Independent benchmark results published in July showed NeuCool delivering 9°C lower NVIDIA B200 junction temperatures than single-phase direct-to-chip cooling in warm-water conditions, and matching single-phase performance at NVIDIA’s 45°C facility water benchmark with inlet water as warm as 54°C. With every 1°C increase in facility water temperature worth approximately 4 percent in annual energy savings, the Springdale upgrade enables Accelsius to demonstrate two-phase efficiency gains with rack- and row-level deployments.
The upgraded lab also strengthens Accelsius’ support for hyperscale customers through the NeuCool HyperStart program, which gives hyperscale operators, high performance compute providers and key partners a structured path to validate two-phase, direct-to-chip cooling and bring it into their data center reference designs and product roadmaps. Several hyperscalers are already engaged under the program and customers are taking advantage of the expanded Springdale capability to validate two-phase cooling at full rack and row scale for their next-generation AI infrastructure.
Accelsius is also expanding its NeuCool multi-rack family with a 375kW-capable unit, the next step beyond the MR250 in a roadmap built to evolve alongside successive generations of AI rack and pod designs. Additional details will be published in the coming months.
See Accelsius at the OCP Global Summit 2026
Accelsius will showcase the NeuCool platform at the OCP Global Summit, October 12–15 at the San Jose McEnery Convention Center, Booth D7.
About Accelsius
Founded by Innventure, Inc. (NASDAQ:INV), Accelsius empowers high performance compute and AI data centers to achieve their business, financial and sustainability goals through advanced cooling solutions. The proprietary NeuCool® platform provides advanced thermal efficiencies through a safe, two-phase, direct-to-chip liquid cooling system that scales from single racks to entire data centers. For more information, visit accelsius.com or follow us on LinkedIn.
Contacts