SoftBank Corp., ZutaCore and Hon Hai Expertise Group (Foxconn) have introduced that they carried out ZutaCore’s two-phase Direct Liquid Cooling (DLC) know-how in an Synthetic Intelligence (AI) server utilizing NVIDIA accelerated computing, making it the world’s first implementation, in accordance with ZutaCore analysis, of ZutaCore’s two-phase DLC (Direct Liquid Cooling) know-how utilizing NVIDIA H200 GPUs. As well as, SoftBank designed and developed a rack-integrated resolution that integrates every element of the server, together with cooling tools with two-phase DLC know-how, on a rack scale, and performed an operational demonstration and efficiency analysis at its information centre in February 2025. The demonstration outcomes indicated the answer handed NVIDIA’s temperature check (NVQual), thereby confirming the compatibility, stability and reliability of this rack-integrated resolution. The answer additionally achieved partial Energy Utilization Effectiveness (pPUE) of 1.03 (precise measured worth) per rack for cooling effectivity.
With the unfold and elevated adoption of AI, demand for AI servers and different computing assets is anticipated to develop, additional growing energy consumption at information centres. On the similar time, lowering energy consumption from the angle of lowering carbon dioxide (CO2) emissions has grow to be a urgent subject worldwide, requiring information centres to grow to be extra environment friendly, devour much less energy, and introduce warmth elimination options. Since Could 2024, SoftBank has been collaborating with ZutaCore, a worldwide contributor within the growth and enterprise deployment of two-phase DLC know-how, to develop options optimised for low energy consumption at AI information centres.
SoftBank, ZutaCore and Foxconn will proceed their efforts to attain larger effectivity and decrease energy consumption in AI information centres utilizing NVIDIA accelerated computing, and collaborate on the event of rack-integrated options optimised with two-phase DLC know-how for sensible use and deployment within the world market.
Options of rack-integrated resolution optimised with two-phase DLC know-how
1. “Plug & Play” resolution
By integrating server elements akin to cooling tools geared up with 2-phase DLC know-how, which conventionally needed to be optimised individually, on a rack scale, it’s attainable to offer a “Plug & Play” resolution that can be utilized instantly by merely connecting the tools. This makes it simple and easy to put in in AI information centres.
2. Modern 2-phase DLC cooling system
ZutaCore’s two-phase DLC know-how, which cools the chipsets (CPUs, GPUs, reminiscence, and so on.) which can be the warmth sources within the server by bringing them into contact with a chilly plate, circulates a particular insulating warmth switch (dielectric) fluid with a low boiling level within the chilly plate and makes use of warmth absorption through the section change from liquid to fuel brought on by the warmth supply. Environment friendly cooling is achieved by means of repeated evaporation and condensation. As well as, the water temperature might be maintained at the next temperature than in standard water-cooled services, which improves the warmth transport capability of the water used for cooling and reduces the movement fee of water to attain the required cooling impact. This makes it attainable to scale back the stress of the pump that delivers the water for cooling, contributing to decrease energy consumption. Moreover, using insulating warmth switch fluid prevents critical harm to the server within the occasion of a spill of particular fluid.
3. AI server with assured compatibility, stability and reliability
Foxconn developed an AI server based mostly on NVIDIA H200 GPUs, optimised with ZutaCore’s two-phase DLC know-how. This AI server was capable of exceed goal efficiency figures in NVIDIA’s certification check (NVQual), which determines the compatibility, stability and reliability of server programs.
4. Versatile and scalable rack for high-density placement of AI servers
SoftBank developed a rack designed to maximise cooling effectivity and enhance operational effectivity with its two-phase DLC know-how. Along with being designed to be versatile and scalable for high-density placement of the newest AI servers, the rack has airflow for improved cooling effectivity, and energy provide. As well as, energy provide and wiring are concentrated within the rear of the rack for operational security and robot-friendly operation. The rack can be suitable with 21-inch servers and traditional 19-inch servers compliant with the ORV3 normal, which is a specification set by the Open Compute Mission (OCP), a non-profit organisation that promotes open-source {hardware} specs and designs. The specs are designed to be deployed in accordance with world requirements.
Feedback from every firm
Hironobu Tamba, the vp and the top of the information platform technique division at SoftBank Corp., mentioned: “As we work to develop one of many largest AI infrastructures in Japan and homegrown large-scale language fashions (LLMs), enhancing the power effectivity of information centres is crucial to speed up AI growth and realise a sustainable society. The operational demonstration of this rack-integrated resolution with optimised two-phase DLC know-how has confirmed secure operation and improved power effectivity of high-density GPU servers with liquid cooling. Sooner or later, we are going to work on the sensible utility of this resolution to be used in AI information centres and AI factories to construct a sustainable AI infrastructure and maximise computational effectivity.”
Erez Freibach, the co-founder and CEO at ZutaCore, mentioned: “ZutaCore is honoured to companion with world trade leaders SoftBank and Foxconn to introduce the world’s first 2-phase DLC rack integration resolution utilizing NVIDIA accelerated computing for AI servers. This groundbreaking collaboration highlights the transformative potential of our waterless DLC cooling know-how to ship unmatched effectivity whereas addressing the rising want for sustainable power options. Collectively, we’re not simply assembly at this time’s challenges however setting a brand new normal for energy-efficient innovation in next-generation AI information centres and factories, driving progress whereas safeguarding the planet.”
Foxconn indicated: “Foxconn, because the world’s largest AI server provider, is delighted to affix this collaboration and share our in depth in AI server growth. We look ahead to driving better worth for the worldwide AI trade collectively.”
Future Developments
SoftBank, ZutaCore, and Foxconn will strengthen cooperation with AI server and rack design firms to enhance the effectivity and low energy consumption of AI information centres utilizing NVIDIA accelerated computing, with a view to the commercialisation of this resolution and its deployment within the world market.
Touch upon this text by way of X: @IoTNow_ and go to our homepage IoT Now
