LEVIATHAN SYSTEMS
← Back to Glossary

What Is Coolant Distribution Unit (CDU)?_

A CDU is the heat exchanger that sits between the facility water loop and the rack-level liquid cooling system. It transfers heat from the server-side coolant (typically propylene glycol solution) to the facility water, which then rejects heat through cooling towers or dry coolers. CDUs are typically deployed at row-level or rack-level depending on facility design.

Technical Details

CDUs serve as the thermal interface between the clean, controlled server-side coolant loop and the facility water loop. This separation is critical: the server-side loop uses treated propylene glycol/water mixture at precise concentrations, while the facility loop may use different water treatment and operates at different temperatures and pressures. CDUs include pumps for coolant circulation, heat exchangers (plate-and-frame or brazed plate), flow meters and temperature sensors, pressure regulation, and control systems for monitoring and alarming. CDU sizing depends on total heat load: a row of GB200/GB300 NVL72 racks at 120 kW each requires CDU capacity measured in megawatts. CDUs are typically located at end-of-row or in dedicated mechanical spaces.

How Leviathan Systems Works with Coolant Distribution Unit (CDU)

Leviathan Systems installs CDUs and connects them to rack-level manifolds as part of our liquid cooling integration scope, including pressure testing, flow verification, and leak detection system installation.

Appears In

White-Space Planning for Liquid-Cooled GPU HallsWarm-Water Cooling for GPU Clusters: Why Hotter Water WinsTwo-Phase vs Single-Phase Direct Liquid Cooling for GPUsGetting Ready for Rubin / VR200: Deployment-Readiness Planning NowRear-Door Heat Exchangers vs Direct Liquid Cooling: Choosing Your Path to High DensityRaised Floor vs Slab for High-Density GPU HallsScaling from Pilot to Production GPU Cluster: What Breaks and What to PlanMEP Coordination for AI Data Halls: Where Mechanical, Electrical, and IT CollideGPU Data Center Deployment in Ohio: Staffing the Physical BuildGPU Data Center Deployment in Georgia: Who Builds It and How to HireGB200 NVL72 Deployment Deep Dive: Liquid Loop, Busbar, and SpineFacility Water Loop Design for AI Halls: TCS to FWS Done RightCondensation & Dew-Point Control in Liquid-Cooled GPU HallsHow to Size a CDU for a GPU Cluster: Heat Load, Flow, Approach TempB200 / HGX B200 Deployment Guide: Power, Thermal, and Rack DemandsAir-Cooled vs Liquid-Cooled GPU Platforms: Picking the Variant for Your SiteNVIDIA B200 vs GB200: HGX vs Rack-Scale, and What Changes to DeployNVIDIA GB300 NVL72 Explained: Specs, Power, and What It Takes to DeployData Center Migration for AI Infrastructure: A Practical Field GuideNVIDIA H100 vs H200 vs B200: What Changes for DeploymentDirect-to-Chip vs Immersion Liquid Cooling for GPU Data CentersLiquid Cooling vs Air Cooling in the Data Center: When the Crossover HappensHow to Choose a Data Center Liquid Cooling CompanyWho Deploys GB200 / GB300 NVL72 Infrastructure?Site Readiness Before the GPUs Arrive: Power, Cooling, Floor, PathwaysGPU Rack Assembly: What Drives the CostHGX vs DGX: What's Different When You Deploy ThemGB300 NVL72 Deployment: Power, Cooling, and the Cable PlantGB200 vs GB300 NVL72: What Changes for DeploymentGPU Rack Receiving, Staging & Lift Plan: Moving ~1,360 kg Racks Without DamageAir-to-Liquid Cooling Retrofit: The Install SideThermal Burn-In for GPU Clusters: Duration, Watch Items, Pass/FailCoolant Distribution Unit (CDU) Installation & CommissioningLiquid-Cooling Loop Commissioning for GB200 & GB300 NVL72: Flush, Fill, Leak-Test, Accept