CPC Welcomes you to the Hyperion Research HPC/AI Briefing During SC25 Watch the Breakfast Briefing to get the latest updates on the HPC and related AI markets.
The Cool Factor: Rising Above the Heated Innovation Race This panel discussion will focus on how both the legacy and the next gen tech of supercomputing pioneers enables future applications (such as cloud HPC, genAI, etc.)
Introducing UQDv2 : Interoperability & Reliability for the AI Era Watch Elizabeth Langer, Principal Technologist of Thermal at CPC and Travis Gaskill, Thermal Mechanical Engineer at Etched introduce the UQDv2 specification at the Open Compute Project Global Summit 2025. The Universal Quick-Disconnect (UQD) has played a significant role in the cooling ecosystem for GPUs and GenAI. In order to scale, and to further enable the adoption of liquid throughout the ecosystem, a workstream was established at the end of 2024 to develop a UQD Version 2.
The Reliability Roadmap: The Journey to Quality Performance Deploying liquid cooled infrastructure for AI-enabling compute isn’t for the faint of heart. Power and cooling pose some of the greatest risks to overall data center reliability, which makes understanding component level reliability in a liquid cooling system foundational for robust rack infrastructure and efficient data center operation.
Pressure-Proof: The Future of Quick Disconnect Innovations This tech showcase will explore the critical role of quick disconnects in enabling efficient and reliable liquid cooling for next-generation servers and rack architectures. Gain insights into how and where quick disconnects are integrated within liquid cooling systems, and why these components have become foundational in some of the world’s top supercomputers and AI superclusters.
Cool Under Pressure: Quick Disconnect Innovation in Liquid Cooling Listen to CPC's Applications Engineering Manager, Andres Abraham, share liquid cooling considerations for AI data center and hyperscale applications as it relates to quick disconnect innovation.
10 Tips for Specifying QDs -- And Why Liquid Cooling Connections Are So Critical It’s well known that poorly designed thermal management systems can result in suboptimal performance or system failure. What isn’t as well understood are the material properties and myriad calculations that all need to be taken into consideration when developing a high-performing liquid cooling system -- or the role that quick disconnects play in supporting reliability, uptime, ease of maintenance and system performance. It’s complicated but it doesn’t need to be confusing.
It’s Material: Chemical Compatibility in Liquid Cooling There is a growing utilization of liquid cooling to address the high temperature output of electronics and computing systems. And as various types of liquid cooling techniques, systems and components evolve, the focus on materials is paramount to successful implementation. This presentation will provide a summary of how material selection of system components and subcomponents impacts performance and reliability.
Liquid Cooling: When Component Failure is Not an Option When deploying liquid-cooled infrastructure for AI-enabling accelerated compute, failure is not an option. While data center efficiency has been studied, data center reliability with new liquid cooling technologies is a gap. Understanding component level reliability in a liquid cooling system supports robust rack infrastructure and efficient data center operation.
Revolutionizing Liquid Cooling: The Evolution of Quick Disconnects In this episode of the Open Compute Project (OCP) Podcast, Rob Coyle welcomes Beth Langer, Principal Thermal Technologist at CPC (Colder Products Company), to discuss the rapid development of quick disconnects for liquid cooling in data centers.