Engineering High Density – Building the future of HPC for research NOW
Tuesday, June 23, 2026 4:00 PM to 4:20 PM · 20 min. (Europe/Berlin)
Hall H, Booth L01 - Ground Floor
HPC Solutions Forum
AI Applications powered by HPC TechnologiesData Center Infrastructure and CoolingEnergy Efficiency and SustainabilityIndustrial Use Cases of HPC, ML and QCOptimizing for Energy and Performance
Information
As high‑performance computing (HPC) and AI workloads continue to redefine the boundaries of enterprise and scientific computing, the infrastructure that supports them is undergoing rapid change. This session brings together industry and operational perspectives to explore how next‑generation compute is reshaping data centre design—and why liquid cooling is moving from niche innovation to mainstream necessity.
We open by setting the broader IT and HPC context, examining the forces driving unprecedented increases in compute density. From accelerated AI adoption to more latency‑sensitive workloads, traditional data centre architectures are being stretched beyond their original design limits. Air cooling, once the default standard, is no longer sufficient to support the thermal, power and performance demands of modern processors. At the same time, connectivity and latency are becoming just as critical as raw compute, influencing where and how high‑density infrastructure can be deployed at scale.
The session then demystifies liquid cooling, addressing the misconceptions that have historically slowed its adoption. Concerns around operational complexity, risk, cost and retrofitting are explored head‑on, with a clear narrative on how liquid cooling technologies—particularly Direct Liquid Cooling (DLC)—have matured. Today’s solutions are repeatable, reliable and operationally manageable, enabling organisations to deploy liquid‑cooled infrastructure with confidence rather than treating each implementation as a bespoke project.
A key focus of the discussion is the accelerating role of sustainability and energy efficiency. Liquid cooling is not just a response to higher rack densities—it is a strategic enabler for meeting carbon reduction targets, energy accountability requirements and broader regulatory commitments. This session challenges the perception of data centres as sustainability liabilities, demonstrating how advanced cooling approaches can significantly improve performance per watt, enable higher utilisation, and positively impact the economics of large‑scale AI and HPC environments. Sustainability and performance are no longer opposing forces; they are increasingly interdependent.
Theory is brought to life through a real‑world case study from Woking, hosted at Digital Realty’s AI‑ready data centre. Attendees will gain insight into the applications and workloads deployed, the bespoke Lenovo DLC platform used, and how the solution delivers substantially higher compute performance per rack. The speakers will share what worked, what surprised them, and how the deployment supported ambitious sustainability objectives—providing practical takeaways for organisations planning their own liquid‑cooled HPC or AI projects.
Finally, the session looks ahead to scaling liquid cooling across Europe. With 4MW of high‑density colocation already pre‑provisioned, the conversation highlights why standardisation and pre‑deployment are critical to reducing risk, accelerating time to value, and enabling repeatable outcomes. The discussion concludes by showing how liquid‑cooling‑ready, well‑connected sites can support both AI‑led innovation and traditional HPC workloads—at scale, and starting today.
Visit our stand to learn more.
We open by setting the broader IT and HPC context, examining the forces driving unprecedented increases in compute density. From accelerated AI adoption to more latency‑sensitive workloads, traditional data centre architectures are being stretched beyond their original design limits. Air cooling, once the default standard, is no longer sufficient to support the thermal, power and performance demands of modern processors. At the same time, connectivity and latency are becoming just as critical as raw compute, influencing where and how high‑density infrastructure can be deployed at scale.
The session then demystifies liquid cooling, addressing the misconceptions that have historically slowed its adoption. Concerns around operational complexity, risk, cost and retrofitting are explored head‑on, with a clear narrative on how liquid cooling technologies—particularly Direct Liquid Cooling (DLC)—have matured. Today’s solutions are repeatable, reliable and operationally manageable, enabling organisations to deploy liquid‑cooled infrastructure with confidence rather than treating each implementation as a bespoke project.
A key focus of the discussion is the accelerating role of sustainability and energy efficiency. Liquid cooling is not just a response to higher rack densities—it is a strategic enabler for meeting carbon reduction targets, energy accountability requirements and broader regulatory commitments. This session challenges the perception of data centres as sustainability liabilities, demonstrating how advanced cooling approaches can significantly improve performance per watt, enable higher utilisation, and positively impact the economics of large‑scale AI and HPC environments. Sustainability and performance are no longer opposing forces; they are increasingly interdependent.
Theory is brought to life through a real‑world case study from Woking, hosted at Digital Realty’s AI‑ready data centre. Attendees will gain insight into the applications and workloads deployed, the bespoke Lenovo DLC platform used, and how the solution delivers substantially higher compute performance per rack. The speakers will share what worked, what surprised them, and how the deployment supported ambitious sustainability objectives—providing practical takeaways for organisations planning their own liquid‑cooled HPC or AI projects.
Finally, the session looks ahead to scaling liquid cooling across Europe. With 4MW of high‑density colocation already pre‑provisioned, the conversation highlights why standardisation and pre‑deployment are critical to reducing risk, accelerating time to value, and enabling repeatable outcomes. The discussion concludes by showing how liquid‑cooling‑ready, well‑connected sites can support both AI‑led innovation and traditional HPC workloads—at scale, and starting today.
Visit our stand to learn more.
HPC Solutions Forum Questions
What is the best way to keep advancing HPC in an AI-driven world?What is most important: maximizing performance in a given power envelope, minimizing power costs, or being green? Do you have to choose?Discuss your solution in terms of benefits for specific use cases, rather than general horizontal terms like HPC, AI, performance, or scalability.
Format
on-site
